feautre(workshops): add workshop 6

ML/aufgaben/comparison/compare.txt

@@ -0,0 +1,148 @@
+
+============================================================
+ IRIS
+============================================================
+
+--- Decision Tree ---
+Accuracy: 1.000
+Adj. Rand: 1.000
+              precision    recall  f1-score   support
+
+      setosa       1.00      1.00      1.00        19
+  versicolor       1.00      1.00      1.00        13
+   virginica       1.00      1.00      1.00        13
+
+    accuracy                           1.00        45
+   macro avg       1.00      1.00      1.00        45
+weighted avg       1.00      1.00      1.00        45
+
+
+--- Naive Bayes ---
+Accuracy: 0.978
+Adj. Rand: 0.943
+              precision    recall  f1-score   support
+
+      setosa       1.00      1.00      1.00        19
+  versicolor       1.00      0.92      0.96        13
+   virginica       0.93      1.00      0.96        13
+
+    accuracy                           0.98        45
+   macro avg       0.98      0.97      0.97        45
+weighted avg       0.98      0.98      0.98        45
+
+
+--- Random Forest ---
+Accuracy: 1.000
+Adj. Rand: 1.000
+              precision    recall  f1-score   support
+
+      setosa       1.00      1.00      1.00        19
+  versicolor       1.00      1.00      1.00        13
+   virginica       1.00      1.00      1.00        13
+
+    accuracy                           1.00        45
+   macro avg       1.00      1.00      1.00        45
+weighted avg       1.00      1.00      1.00        45
+
+
+--- K-Means (mapped) ---
+Accuracy: 0.893
+Adj. Rand: 0.730
+              precision    recall  f1-score   support
+
+      setosa       1.00      1.00      1.00        50
+  versicolor       0.77      0.96      0.86        50
+   virginica       0.95      0.72      0.82        50
+
+    accuracy                           0.89       150
+   macro avg       0.91      0.89      0.89       150
+weighted avg       0.91      0.89      0.89       150
+
+
+============================================================
+ DIGITS
+============================================================
+
+--- Decision Tree ---
+Accuracy: 0.843
+Adj. Rand: 0.685
+              precision    recall  f1-score   support
+
+           0       0.92      0.91      0.91        53
+           1       0.74      0.78      0.76        50
+           2       0.83      0.74      0.79        47
+           3       0.78      0.85      0.81        54
+           4       0.81      0.85      0.83        60
+           5       0.92      0.86      0.89        66
+           6       0.93      0.94      0.93        53
+           7       0.85      0.84      0.84        55
+           8       0.89      0.77      0.82        43
+           9       0.78      0.85      0.81        59
+
+    accuracy                           0.84       540
+   macro avg       0.85      0.84      0.84       540
+weighted avg       0.85      0.84      0.84       540
+
+
+--- Naive Bayes ---
+Accuracy: 0.852
+Adj. Rand: 0.710
+              precision    recall  f1-score   support
+
+           0       1.00      0.98      0.99        53
+           1       0.86      0.74      0.80        50
+           2       0.86      0.66      0.75        47
+           3       0.95      0.76      0.85        54
+           4       0.98      0.85      0.91        60
+           5       0.94      0.94      0.94        66
+           6       0.89      0.96      0.93        53
+           7       0.72      0.98      0.83        55
+           8       0.57      0.91      0.70        43
+           9       0.89      0.71      0.79        59
+
+    accuracy                           0.85       540
+   macro avg       0.87      0.85      0.85       540
+weighted avg       0.88      0.85      0.85       540
+
+
+--- Random Forest ---
+Accuracy: 0.976
+Adj. Rand: 0.946
+              precision    recall  f1-score   support
+
+           0       1.00      0.98      0.99        53
+           1       0.96      1.00      0.98        50
+           2       1.00      1.00      1.00        47
+           3       0.98      0.96      0.97        54
+           4       0.97      1.00      0.98        60
+           5       0.97      0.95      0.96        66
+           6       0.98      0.98      0.98        53
+           7       0.98      0.98      0.98        55
+           8       0.95      0.95      0.95        43
+           9       0.97      0.95      0.96        59
+
+    accuracy                           0.98       540
+   macro avg       0.98      0.98      0.98       540
+weighted avg       0.98      0.98      0.98       540
+
+
+--- K-Means (mapped) ---
+Accuracy: 0.794
+Adj. Rand: 0.667
+              precision    recall  f1-score   support
+
+           0       0.99      0.99      0.99       178
+           1       0.62      0.30      0.41       182
+           2       0.84      0.84      0.84       177
+           3       0.86      0.85      0.85       183
+           4       0.99      0.92      0.95       181
+           5       0.87      0.75      0.81       182
+           6       0.97      0.98      0.98       181
+           7       0.86      0.95      0.90       179
+           8       0.45      0.59      0.51       174
+           9       0.58      0.77      0.66       180
+
+    accuracy                           0.79      1797
+   macro avg       0.80      0.79      0.79      1797
+weighted avg       0.80      0.79      0.79      1797
+

ML/aufgaben/comparison/compare_ml_algorihms.py

@@ -0,0 +1,96 @@
+"""
+Compare different ML algorithms against iris & digits dataset.
+
+Supervised:
+    - Decision Tree
+    - Naive Bayes (GaussianNB)
+Unsuprvised:
+    - K-Means
+
+Use metrics (classification_report) to try to evaluate the algorithms.
+"""
+
+from sklearn import datasets
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.naive_bayes import GaussianNB
+from sklearn.cluster import KMeans
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, classification_report, adjusted_rand_score
+
+import numpy as np
+
+
+def kmeans_true_labels(X, y, n_classes):
+    """
+    Since k-means is unsupervised it comes up with its own classes, that
+    do not reflect the classes from the gold standard.
+    This function maps each cluster to its majority true label, to help compute accuracy.
+
+    Each cluster gets assigned the most common true label in it.
+    """
+    # train classifier and do a fit, set the rng seed to a fixed value
+    kmeans = KMeans(n_clusters=n_classes, init="k-means++", n_init=10, random_state=42)
+    kmeans.fit(X)
+
+    # creates an empty array the same shape as the cluster assignments
+    labels = np.zeros_like(kmeans.labels_)
+    # for each cluster i ...
+    for i in range(n_classes):
+        # boolean array, true for every sample that K-Means put in cluster i
+        mask = kmeans.labels_ == i
+        # just skip empty clusters
+        if mask.sum() == 0:
+            continue
+        # set true label as the label most prominent in this cluster
+        # e.g: if cluster 2 contains a mix of digits 7, 7, 7, 3, 7 this gives you 7
+        labels[mask] = np.bincount(y[mask]).argmax()
+    return labels, kmeans
+
+
+def evaluate(name, dataset, target_names):
+    """
+    Evaluate unsupervised and supervised ML algorithms on the same dataset, split with the train_test_split function.
+    Use the classification_report to evaluate the function.
+    """
+    print(f"\n{'=' * 60}")
+    print(f" {name}")
+    print(f"{'=' * 60}")
+
+    # split the dataset into train and test data and use a fixed rng seed
+    X_train, X_test, y_train, y_test = train_test_split(
+        dataset.data, dataset.target, test_size=0.3, random_state=42
+    )
+
+    # all the supervised leanring algorithms to test
+    algorithms = [
+        ("Decision Tree", DecisionTreeClassifier(random_state=42)),
+        ("Naive Bayes", GaussianNB()),
+        ("Random Forest", RandomForestClassifier(n_estimators=100, random_state=42)),
+    ]
+
+    #  do the test on the supervised learning algorithms
+    for classifier_name, classifier in algorithms:
+        classifier.fit(X_train, y_train)
+        y_pred = classifier.predict(X_test)
+        print(f"\n--- {classifier_name} ---")
+        print(f"Accuracy: {accuracy_score(y_test, y_pred):.3f}")
+        print(f"Adj. Rand: {adjusted_rand_score(y_test, y_pred):.3f}")
+        print(classification_report(y_test, y_pred, target_names=target_names))
+
+    # tdo the test on the unsupervised learning algorithm (evaluated on full dataset)
+    n_classes = len(target_names)
+    mapped_labels, kmeans = kmeans_true_labels(dataset.data, dataset.target, n_classes)
+    print(f"\n--- K-Means (mapped) ---")
+    print(f"Accuracy: {accuracy_score(dataset.target, mapped_labels):.3f}")
+    print(f"Adj. Rand: {adjusted_rand_score(dataset.target, kmeans.labels_):.3f}")
+    print(classification_report(dataset.target, mapped_labels, target_names=target_names))
+
+
+# evaluate all ML algorithms on iris
+iris = datasets.load_iris()
+evaluate("IRIS", iris, list(iris.target_names))
+
+# evaluate all ML algorithms on digits
+digits = datasets.load_digits()
+evaluate("DIGITS", digits, [str(n) for n in digits.target_names])

ML/aufgaben/decisiontree/decisiontree_digits.py

@@ -0,0 +1,44 @@
+"""
+Use a decisiontree classifier to predict handwritten digits
+
+- This is an example of a supervised ML algorithm
+    - it has labels on the training data
+    - you tell the model: this is class X during training
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn import datasets
+from sklearn.tree import DecisionTreeClassifier
+from sklearn import tree
+
+# load the digits dataset
+digits = datasets.load_digits()
+# get a feel for it
+print(digits.data.size)
+print(digits.target.size)
+print(digits.feature_names)
+print(digits.target_names)
+
+# use a decision tree classifier
+# set max_depth to 5 otherwise the tree will get huge
+classifier = DecisionTreeClassifier(max_depth=5)
+# use all but the last sample for training
+classifier.fit(digits.data[:-1], digits.target[:-1])
+
+# use the model to predict the last data sample
+last_sample = digits.data[-1:]
+last_target = digits.target[-1:]
+print(f"predicted: {classifier.predict(last_sample)} vs real: {last_target}")
+
+# print the tree for visual inspection
+fig, ax = plt.subplots(figsize=(20, 10))
+tree.plot_tree(
+    classifier,
+    feature_names=digits.feature_names,
+    class_names=[str(i) for i in digits.target_names],
+    filled=True,
+    rounded=True,
+    ax=ax,
+)
+fig.savefig("decisiontree_digits.png", dpi=500, bbox_inches="tight")

ML/aufgaben/decisiontree/decisiontree_iris.py

@@ -0,0 +1,42 @@
+"""
+Use a decisiontree classifier to predict flowers based on sepal and petal features
+
+- This is an example of a supervised ML algorithm
+    - it has labels on the training data
+    - you tell the model: this is class X during training
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn import datasets
+from sklearn.tree import DecisionTreeClassifier
+from sklearn import tree
+
+# load the iris data set and look at its dimensions
+iris = datasets.load_iris()
+print(iris.data.size)
+print(iris.target.size)
+print(iris.feature_names)
+print(iris.target_names)
+
+# use a decision tree classifier
+classifier = DecisionTreeClassifier()
+# use all but the last sample for training
+classifier.fit(iris.data[:-1], iris.target[:-1])
+
+# use the model to predict the last data sample
+last_sample = iris.data[-1:]
+last_target = iris.target[-1:]
+print(f"predicted: {last_sample} vs real: {last_target}")
+
+# print the tree for visual inspection
+fig, ax = plt.subplots(figsize=(20, 10))
+tree.plot_tree(
+    classifier,
+    feature_names=iris.feature_names,
+    class_names=iris.target_names,
+    filled=True,
+    rounded=True,
+    ax=ax,
+)
+fig.savefig("decisiontree_iris.png", dpi=150, bbox_inches="tight")

ML/aufgaben/devenv.lock

@@ -3,11 +3,11 @@
     "devenv": {
       "locked": {
         "dir": "src/modules",
-        "lastModified": 1777372895,
+        "lastModified": 1777498918,
-        "narHash": "sha256-PGesjpeDbEPigEP7tdRw8Sm0mmOmonUdOOthBY+nhJA=",
+        "narHash": "sha256-SBx9JMs4OGrhADeU6qlfTZzJ7Dp/RuVgXErECF0adUo=",
         "owner": "cachix",
         "repo": "devenv",
-        "rev": "cb344e4a5ab9241ae49739352c24268d5f8be13b",
+        "rev": "28668b6851e4e649aadd329527059344d14561cf",
         "type": "github"
       },
       "original": {
@@ -17,6 +17,22 @@
         "type": "github"
       }
     },
+    "flake-compat": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1767039857,
+        "narHash": "sha256-vNpUSpF5Nuw8xvDLj2KCwwksIbjua2LZCqhV1LNRDns=",
+        "owner": "edolstra",
+        "repo": "flake-compat",
+        "rev": "5edf11c44bc78a0d334f6334cdaf7d60d732daab",
+        "type": "github"
+      },
+      "original": {
+        "owner": "edolstra",
+        "repo": "flake-compat",
+        "type": "github"
+      }
+    },
     "nixpkgs": {
       "inputs": {
         "nixpkgs-src": "nixpkgs-src"
@@ -36,6 +52,27 @@
         "type": "github"
       }
     },
+    "nixpkgs-python": {
+      "inputs": {
+        "flake-compat": "flake-compat",
+        "nixpkgs": [
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1777318902,
+        "narHash": "sha256-gb9ZqzELCkn6pcRZkC4A8mIm3KQxjoheTRyfodOwMeo=",
+        "owner": "cachix",
+        "repo": "nixpkgs-python",
+        "rev": "0a64f05ab0bc39dd83f544c3f00c2b32dab4ab85",
+        "type": "github"
+      },
+      "original": {
+        "owner": "cachix",
+        "repo": "nixpkgs-python",
+        "type": "github"
+      }
+    },
     "nixpkgs-src": {
       "flake": false,
       "locked": {
@@ -56,7 +93,8 @@
     "root": {
       "inputs": {
         "devenv": "devenv",
-        "nixpkgs": "nixpkgs"
+        "nixpkgs": "nixpkgs",
+        "nixpkgs-python": "nixpkgs-python"
       }
     }
   },

ML/aufgaben/devenv.nix

@@ -3,6 +3,7 @@
 {
   languages.python = {
     enable = true;
+    version = "3.14.4";
     venv.enable = true;
     venv.requirements = ''
       ipython

ML/aufgaben/devenv.yaml

@@ -0,0 +1,6 @@
+inputs:
+  nixpkgs-python:
+    url: github:cachix/nixpkgs-python
+    inputs:
+      nixpkgs:
+        follows: nixpkgs

ML/aufgaben/kmeans/kmeans_digits.py

@@ -0,0 +1,69 @@
+"""
+Use k-means to try to match handwritten digits and see if changing the parameters
+results in better recognition.
+
+- This is an example of an unsupervised ML algorithm
+    - it has no labels in the training data
+    - it discovers the structure on its own
+    - thus the cluster numbers are arbitrary and do not correspond to the class labels
+
+Takaway:
+- Hier ist k-means nicht der beste algorithmus, weil die Daten nicht in schön kugelförmig
+  verteilten Clustern angeordnet sind und k-means Mühe hat die Centroiden sauber zu bestimmen.
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn import datasets
+from sklearn import metrics
+from sklearn.cluster import KMeans
+from sklearn.decomposition import PCA
+
+# get the digits dataset
+digits = datasets.load_digits()
+
+# 100 samples pro ziffer
+# 64 pixel pro zahl
+print(digits.data.shape)
+
+# ausprobieren verschiedener parameter
+# kmeans = KMeans(n_clusters=10, init="random", n_init=1)
+# kmeans = KMeans(n_clusters=10)
+kmeans = KMeans(n_clusters=10, init="k-means++", n_init=10)
+kmeans.fit(digits.data)
+
+print(list(zip(digits.target, kmeans.labels_)))
+print(metrics.homogeneity_score(digits.target, kmeans.labels_))
+print(metrics.completeness_score(digits.target, kmeans.labels_))
+print(metrics.adjusted_rand_score(digits.target, kmeans.labels_))
+print(metrics.silhouette_score(digits.data, kmeans.labels_))
+
+# Wikipedia:
+# PCA (Principal Component Analysis) finds the directions in your data with
+# the most variance and projects everything onto those axes.
+#
+# Irgendwas mit Eigenvektoren und Kovarianz Matrix, TODO: Anschauen
+# Transformiert 64 dimensionalen Vektor möglichst gut in eine 2D Projektion
+pca = PCA(n_components=2)
+X2d = pca.fit_transform(digits.data)
+centroids2d = pca.transform(kmeans.cluster_centers_)
+
+# Punktewolke plotten und Centroiden einzeichnen, tab10 gibt 10 versch. Farben für die Legende
+# Hier sieht man grosse überlappung zwischen den Clustern -> ein Hinweis, das K-Means nicht optimal ist?
+plt.figure(figsize=(10, 8))
+scatter = plt.scatter(X2d[:, 0], X2d[:, 1], c=kmeans.labels_, cmap='tab10', s=10, alpha=0.6)
+plt.scatter(centroids2d[:, 0], centroids2d[:, 1], c='red', marker='X', s=200, edgecolors='black')
+plt.xlabel(f'PC1 ({pca.explained_variance_ratio_[0]:.1%} var)')
+plt.ylabel(f'PC2 ({pca.explained_variance_ratio_[1]:.1%} var)')
+plt.title('K-Means on Digits (PCA projection)')
+plt.colorbar(scatter, label='Cluster')
+plt.savefig('kmeans_digits.png', dpi=150, bbox_inches='tight')
+
+# Centroiden als 8x8 Bild darstellen, indem man das "durchschnittliche zeichen" um das Zentrum plottet
+# Dieser plot zeigt was die K-Means "gelernt" hat, man sieht die Zuweisung von Cluster zu Zahl sofort
+fig, axes = plt.subplots(2, 5, figsize=(10, 4))
+for i, ax in enumerate(axes.flat):
+    ax.imshow(kmeans.cluster_centers_[i].reshape(8, 8), cmap='gray_r')
+    ax.set_title(f'Cluster {i}')
+    ax.axis('off')
+fig.savefig('kmeans_digits_centroids.png', dpi=150, bbox_inches='tight')

ML/aufgaben/kmeans/kmeans_iris.py

@@ -0,0 +1,59 @@
+"""
+Aufgabe: k-means classifier verwenden um cluster im iris datenset zu finden und aufgrund von features Klassen von Samples predicten
+
+Erkenntnis aus dieser Aufgabe
+ - der k-means Algorithmus ist nicht perfekt für diese Art von Daten geeignet
+ - wahrscheinlich weil die Cluster geometrisch zu wenig kugelförmig sind
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn.decomposition import PCA
+from sklearn import datasets
+from sklearn.cluster import KMeans
+from sklearn import metrics
+
+# iris datenset laden
+iris = datasets.load_iris()
+
+# print 150 samples
+print(iris.target)
+
+"""
+Egal wie die parameter gewählt werden, die metriken sind nicht sehr gut.
+"""
+# kmeans = KMeans(n_clusters=3, init="random", n_init=1)
+# kmeans = KMeans(n_clusters=3, init='random', n_init=50)
+# kmeans = KMeans(n_clusters=3, init='k-means++', n_init=10)
+kmeans = KMeans(n_clusters=3)
+
+# fit auf daten
+kmeans.fit(iris.data)
+
+# Gegenüberstellung gold standard vs prediction
+print("gold standard vs. prediction")
+for target_label, predicted_label in zip(iris.target, kmeans.labels_):
+    print(f"{target_label} -> {predicted_label}")
+
+# ausgeben aller relevanten metriken
+print(metrics.homogeneity_score(iris.target, kmeans.labels_))
+print(metrics.completeness_score(iris.target, kmeans.labels_))
+print(metrics.adjusted_rand_score(iris.target, kmeans.labels_))
+print(metrics.silhouette_score(iris.data, kmeans.labels_))
+
+# plot vorbereiten (Idee von kmeans digits)
+# Transformation 4D nach 2D via Projektionsfit
+pca = PCA(n_components=2)
+X2d = pca.fit_transform(iris.data)
+centroids2d = pca.transform(kmeans.cluster_centers_)
+
+# plotten der Punktewolke und einzeichnen der Centroiden
+plt.scatter(X2d[:, 0], X2d[:, 1], c=kmeans.labels_, cmap="viridis", s=30, alpha=0.7)
+plt.scatter(
+    centroids2d[:, 0], centroids2d[:, 1], c="red", marker="X", s=200, edgecolors="black"
+)
+plt.xlabel(f"PC1 ({pca.explained_variance_ratio_[0]:.1%} var)")
+plt.ylabel(f"PC2 ({pca.explained_variance_ratio_[1]:.1%} var)")
+plt.title("K-Means on Iris (PCA projection)")
+plt.colorbar(label="Cluster")
+plt.savefig("kmeans_iris.png", dpi=150)

ML/aufgaben/naivebayes/naivebayes_digits.py

@@ -0,0 +1,58 @@
+"""
+Use the naive bayes classifier to classify the digits data set.
+
+- This is an example of a supervised ML algorithm
+    - it has labels on the training data                                                    
+    - you tell the model: this is class X during training
+"""
+import matplotlib.pyplot as plt
+import numpy as np
+
+from sklearn import datasets
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import GaussianNB
+
+digits = datasets.load_digits()
+print(digits.data.shape)
+
+# split into training and test data
+x_train, x_test, y_train, y_test = train_test_split(
+    digits.data, digits.target, test_size=0.2, random_state=0
+)
+
+# use a gaussian NB classifier
+classifier = GaussianNB()
+# train on the split data
+classifier.fit(x_train, y_train)
+# test the model and print it's accurecy
+score = classifier.score(x_test, y_test)
+print(score)
+
+# visualizing the learned means as 8x8 images
+fig, axes = plt.subplots(2, 5, figsize=(12, 5))
+for i, ax in enumerate(axes.flat):
+    ax.imshow(classifier.theta_[i].reshape(8, 8), cmap='gray_r')
+    ax.set_title(f'Class {i}')
+    ax.axis('off')
+fig.suptitle('NB: Mean pixel intensity per class')
+fig.savefig('naivebayes_digits_means.png', dpi=150, bbox_inches='tight')
+
+# The variance plot shows where pixels vary most within a class: 
+# - high variance (bright) means that pixel isn't reliable for classification
+# - low variance (dark) means it's consistent.
+fig, axes = plt.subplots(2, 5, figsize=(12, 5))
+for i, ax in enumerate(axes.flat):
+    ax.imshow(classifier.var_[i].reshape(8, 8), cmap='hot')
+    ax.set_title(f'Class {i}')
+    ax.axis('off')
+fig.suptitle('NB: Pixel variance per class')
+fig.savefig('naivebayes_digits_variance.png', dpi=150, bbox_inches='tight')
+
+# plot the variance difference between two commonly confused digits like 3 and 8 to see
+# on which pixels nb relies to tell them apart
+plt.figure()
+diff = abs(classifier.var_[3] - classifier.var_[8])
+plt.imshow(diff.reshape(8, 8), cmap='hot')
+plt.title('Variance difference: 3 vs 8')
+plt.colorbar()
+plt.savefig('naivebayes_3v8_variance.png', dpi=150, bbox_inches='tight')

ML/aufgaben/naivebayes/naivebayes_iris.py

@@ -0,0 +1,42 @@
+"""
+Use the naive bayes classifier to classify the iris data set.
+
+- This is an example of a supervised ML algorithm
+    - it has labels on the training data                                                
+    - you tell the model: this is class X during training
+"""
+import matplotlib.pyplot as plt
+import numpy as np
+
+from sklearn import datasets
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import GaussianNB
+
+iris = datasets.load_iris()
+print(iris.data.shape)
+
+# split into training and test data
+x_train, x_test, y_train, y_test = train_test_split(
+    iris.data, iris.target, test_size=0.2, random_state=0
+)
+
+# use a gaussian NB classifier
+classifier = GaussianNB()
+# train on the split data
+classifier.fit(x_train, y_train)
+# test the model and print it's accurecy
+score = classifier.score(x_test, y_test)
+print(score)
+
+# plot the distributions (bell curves) for each feature and each flower
+fig, axes = plt.subplots(2, 2, figsize=(12, 10))
+for idx, ax in enumerate(axes.flat):
+    x_range = np.linspace(iris.data[:, idx].min() - 1, iris.data[:, idx].max() + 1, 200)
+    for class_idx, class_name in enumerate(iris.target_names):
+        mean = classifier.theta_[class_idx, idx]
+        var = classifier.var_[class_idx, idx]
+        gaussian = np.exp(-0.5 * (x_range - mean) ** 2 / var) / np.sqrt(2 * np.pi * var)
+        ax.plot(x_range, gaussian, label=class_name)
+    ax.set_title(iris.feature_names[idx])
+    ax.legend()
+fig.savefig('naivebayes_iris_distributions.png', dpi=150, bbox_inches='tight')

ML/aufgaben/randomforest/randomforest_digits.py

@@ -0,0 +1,50 @@
+"""
+Use the random forest classifier to classify the digits data set.
+
+- This is an example of a supervised ML algorithm
+    - it has labels on the training data
+    - you tell the model: this is class X during training
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn import datasets
+from sklearn import tree
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+
+digits = datasets.load_digits()
+print(digits.data.shape)
+
+# split into training and test data
+x_train, x_test, y_train, y_test = train_test_split(
+    digits.data, digits.target, test_size=0.2, random_state=0
+)
+
+# use a random forest classifier
+classifier = RandomForestClassifier(n_estimators=100, random_state=42)
+# train on the split data
+classifier.fit(x_train, y_train)
+# test the model and print it's accurecy
+score = classifier.score(x_test, y_test)
+print(score)
+
+# get the first tree and turn it into an image
+fig, ax = plt.subplots(figsize=(20, 10))
+tree.plot_tree(
+    classifier.estimators_[0],
+    feature_names=digits.feature_names,
+    class_names=[str(n) for n in digits.target_names],
+    filled=True,
+    rounded=True,
+    ax=ax,
+)
+fig.savefig("randomforest_digits_tree_0.png", dpi=150, bbox_inches="tight")
+
+# for digits, plot feature importance as 8x8 heatmap
+importances = classifier.feature_importances_
+plt.figure()
+plt.imshow(importances.reshape(8, 8), cmap='hot')
+plt.title('Random Forest: Feature Importance')
+plt.colorbar()
+plt.savefig('randomforest_digits_feature_importance.png', dpi=150, bbox_inches='tight')

ML/aufgaben/randomforest/randomforest_iris.py

@@ -0,0 +1,49 @@
+"""
+Use the random forest classifier to classify the iris data set.
+
+- This is an example of a supervised ML algorithm
+    - it has labels on the training data
+    - you tell the model: this is class X during training
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn import datasets
+from sklearn import tree
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+
+iris = datasets.load_iris()
+print(iris.data.shape)
+
+# split into training and test data
+x_train, x_test, y_train, y_test = train_test_split(
+    iris.data, iris.target, test_size=0.2, random_state=0
+)
+
+# use a random forest classifier
+classifier = RandomForestClassifier(n_estimators=100, random_state=42)
+# train on the split data
+classifier.fit(x_train, y_train)
+# test the model and print it's accurecy
+score = classifier.score(x_test, y_test)
+print(score)
+
+# get the first tree and turn it into an image
+fig, ax = plt.subplots(figsize=(20, 10))
+tree.plot_tree(
+    classifier.estimators_[0],
+    feature_names=iris.feature_names,
+    class_names=list(iris.target_names),
+    filled=True,
+    rounded=True,
+    ax=ax,
+)
+fig.savefig("randomforest_iris_tree_0.png", dpi=150, bbox_inches="tight")
+
+# plot a bar chart with the importance of all features
+plt.figure()
+plt.barh(iris.feature_names, classifier.feature_importances_)
+plt.xlabel('Importance')
+plt.title('Random Forest: Feature Importance (Iris)')
+plt.savefig('randomforest_iris_feature_importance.png', dpi=150, bbox_inches='tight')

SL/aufgaben/data/DecisionTreeRegressor_melb.pmml

@@ -0,0 +1,47 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PMML xmlns="http://www.dmg.org/PMML-4_4" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.4">
+	<Header>
+		<Application name="SkLearn2PMML package" version="0.119.1"/>
+		<Timestamp>2025-06-21T20:20:46Z</Timestamp>
+	</Header>
+	<MiningBuildTask>
+		<Extension name="repr">PMMLPipeline(steps=[('regressor', DecisionTreeRegressor(max_depth=2, random_state=1234))])</Extension>
+	</MiningBuildTask>
+	<DataDictionary>
+		<DataField name="Price" optype="continuous" dataType="double"/>
+		<DataField name="Rooms" optype="continuous" dataType="float"/>
+		<DataField name="Type" optype="continuous" dataType="float"/>
+		<DataField name="Regionname_Southern_Metropolitan" optype="continuous" dataType="float"/>
+	</DataDictionary>
+	<TreeModel functionName="regression" algorithmName="sklearn.tree._classes.DecisionTreeRegressor" missingValueStrategy="nullPrediction" noTrueChildStrategy="returnLastPrediction">
+		<MiningSchema>
+			<MiningField name="Price" usageType="target"/>
+			<MiningField name="Rooms"/>
+			<MiningField name="Type"/>
+			<MiningField name="Regionname_Southern_Metropolitan"/>
+		</MiningSchema>
+		<LocalTransformations>
+			<DerivedField name="double(Rooms)" optype="continuous" dataType="double">
+				<FieldRef field="Rooms"/>
+			</DerivedField>
+			<DerivedField name="double(Type)" optype="continuous" dataType="double">
+				<FieldRef field="Type"/>
+			</DerivedField>
+			<DerivedField name="double(Regionname_Southern_Metropolitan)" optype="continuous" dataType="double">
+				<FieldRef field="Regionname_Southern_Metropolitan"/>
+			</DerivedField>
+		</LocalTransformations>
+		<Node score="2113002.898989899">
+			<True/>
+			<Node score="682863.3751581077">
+				<SimplePredicate field="double(Rooms)" operator="lessOrEqual" value="3.5"/>
+				<Node score="1077045.4976463942">
+					<SimplePredicate field="double(Type)" operator="lessOrEqual" value="1.5"/>
+				</Node>
+			</Node>
+			<Node score="1163850.4992142483">
+				<SimplePredicate field="double(Regionname_Southern_Metropolitan)" operator="lessOrEqual" value="0.5"/>
+			</Node>
+		</Node>
+	</TreeModel>
+</PMML>

SL/aufgaben/data/LinearRegression_melb.pmml

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PMML xmlns="http://www.dmg.org/PMML-4_4" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.4">
+	<Header>
+		<Application name="SkLearn2PMML package" version="0.119.1"/>
+		<Timestamp>2025-06-21T20:20:46Z</Timestamp>
+	</Header>
+	<MiningBuildTask>
+		<Extension name="repr">PMMLPipeline(steps=[('regressor', LinearRegression())])</Extension>
+	</MiningBuildTask>
+	<DataDictionary>
+		<DataField name="Price" optype="continuous" dataType="double"/>
+		<DataField name="Rooms" optype="continuous" dataType="double"/>
+		<DataField name="Type" optype="continuous" dataType="double"/>
+		<DataField name="Distance" optype="continuous" dataType="double"/>
+		<DataField name="Bathroom" optype="continuous" dataType="double"/>
+		<DataField name="Car" optype="continuous" dataType="double"/>
+		<DataField name="logLandsize" optype="continuous" dataType="double"/>
+		<DataField name="logBuildingArea" optype="continuous" dataType="double"/>
+		<DataField name="YearBuilt" optype="continuous" dataType="double"/>
+		<DataField name="CouncilArea" optype="continuous" dataType="double"/>
+		<DataField name="Lattitude" optype="continuous" dataType="double"/>
+		<DataField name="Longtitude" optype="continuous" dataType="double"/>
+		<DataField name="Propertycount" optype="continuous" dataType="double"/>
+		<DataField name="Method_S" optype="continuous" dataType="double"/>
+		<DataField name="Method_SP" optype="continuous" dataType="double"/>
+		<DataField name="Method_VB" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Northern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_South_Eastern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Southern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Victoria" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Western_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="month" optype="continuous" dataType="double"/>
+		<DataField name="year" optype="continuous" dataType="double"/>
+		<DataField name="day_of_week" optype="continuous" dataType="double"/>
+	</DataDictionary>
+	<RegressionModel functionName="regression" algorithmName="sklearn.linear_model._base.LinearRegression">
+		<MiningSchema>
+			<MiningField name="Price" usageType="target"/>
+			<MiningField name="Rooms"/>
+			<MiningField name="Type"/>
+			<MiningField name="Distance"/>
+			<MiningField name="Bathroom"/>
+			<MiningField name="Car"/>
+			<MiningField name="logLandsize"/>
+			<MiningField name="logBuildingArea"/>
+			<MiningField name="YearBuilt"/>
+			<MiningField name="CouncilArea"/>
+			<MiningField name="Lattitude"/>
+			<MiningField name="Longtitude"/>
+			<MiningField name="Propertycount"/>
+			<MiningField name="Method_S"/>
+			<MiningField name="Method_SP"/>
+			<MiningField name="Method_VB"/>
+			<MiningField name="Regionname_Northern_Metropolitan"/>
+			<MiningField name="Regionname_South_Eastern_Metropolitan"/>
+			<MiningField name="Regionname_Southern_Metropolitan"/>
+			<MiningField name="Regionname_Victoria"/>
+			<MiningField name="Regionname_Western_Metropolitan"/>
+			<MiningField name="month"/>
+			<MiningField name="year"/>
+			<MiningField name="day_of_week"/>
+		</MiningSchema>
+		<RegressionTable intercept="-1.486001530644718E8">
+			<NumericPredictor name="Rooms" coefficient="238730.9316843776"/>
+			<NumericPredictor name="Type" coefficient="-144127.0462703874"/>
+			<NumericPredictor name="Distance" coefficient="-41158.74149442419"/>
+			<NumericPredictor name="Bathroom" coefficient="155233.18486695606"/>
+			<NumericPredictor name="Car" coefficient="41608.24584805156"/>
+			<NumericPredictor name="logLandsize" coefficient="82294.47642306813"/>
+			<NumericPredictor name="logBuildingArea" coefficient="297716.9070603722"/>
+			<NumericPredictor name="YearBuilt" coefficient="-2767.549042441214"/>
+			<NumericPredictor name="CouncilArea" coefficient="-4929.3735515952385"/>
+			<NumericPredictor name="Lattitude" coefficient="-511115.932452351"/>
+			<NumericPredictor name="Longtitude" coefficient="179228.15909129355"/>
+			<NumericPredictor name="Propertycount" coefficient="-1.5874021046959097"/>
+			<NumericPredictor name="Method_S" coefficient="70775.86711001841"/>
+			<NumericPredictor name="Method_SP" coefficient="7998.548503785693"/>
+			<NumericPredictor name="Method_VB" coefficient="33895.327337749855"/>
+			<NumericPredictor name="Regionname_Northern_Metropolitan" coefficient="-173563.80389381657"/>
+			<NumericPredictor name="Regionname_South_Eastern_Metropolitan" coefficient="107806.72896395726"/>
+			<NumericPredictor name="Regionname_Southern_Metropolitan" coefficient="239261.2304157773"/>
+			<NumericPredictor name="Regionname_Victoria" coefficient="281825.04678020324"/>
+			<NumericPredictor name="Regionname_Western_Metropolitan" coefficient="-226744.90218339747"/>
+			<NumericPredictor name="month" coefficient="1272.5340782417852"/>
+			<NumericPredictor name="year" coefficient="53847.63382995822"/>
+			<NumericPredictor name="day_of_week" coefficient="3833.1129349071543"/>
+		</RegressionTable>
+	</RegressionModel>
+</PMML>

SL/aufgaben/data/StandardScaler_melb.pmml

@@ -0,0 +1,244 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PMML xmlns="http://www.dmg.org/PMML-4_4" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.4">
+	<Header>
+		<Application name="SkLearn2PMML package" version="0.119.1"/>
+		<Timestamp>2025-06-21T20:20:45Z</Timestamp>
+	</Header>
+	<MiningBuildTask>
+		<Extension name="repr">PMMLPipeline(steps=[('scaler', StandardScaler())])</Extension>
+	</MiningBuildTask>
+	<DataDictionary>
+		<DataField name="Rooms" optype="continuous" dataType="double"/>
+		<DataField name="Type" optype="continuous" dataType="double"/>
+		<DataField name="Distance" optype="continuous" dataType="double"/>
+		<DataField name="Bathroom" optype="continuous" dataType="double"/>
+		<DataField name="Car" optype="continuous" dataType="double"/>
+		<DataField name="logLandsize" optype="continuous" dataType="double"/>
+		<DataField name="logBuildingArea" optype="continuous" dataType="double"/>
+		<DataField name="YearBuilt" optype="continuous" dataType="double"/>
+		<DataField name="CouncilArea" optype="continuous" dataType="double"/>
+		<DataField name="Lattitude" optype="continuous" dataType="double"/>
+		<DataField name="Longtitude" optype="continuous" dataType="double"/>
+		<DataField name="Propertycount" optype="continuous" dataType="double"/>
+		<DataField name="Method_S" optype="continuous" dataType="double"/>
+		<DataField name="Method_SP" optype="continuous" dataType="double"/>
+		<DataField name="Method_VB" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Northern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_South_Eastern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Southern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Victoria" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Western_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="month" optype="continuous" dataType="double"/>
+		<DataField name="year" optype="continuous" dataType="double"/>
+		<DataField name="day_of_week" optype="continuous" dataType="double"/>
+	</DataDictionary>
+	<TransformationDictionary>
+		<DerivedField name="standardScaler(Rooms)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Rooms"/>
+					<Constant dataType="double">2.9317403359973904</Constant>
+				</Apply>
+				<Constant dataType="double">0.9533169121486135</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Type)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Type"/>
+					<Constant dataType="double">1.4526178437449029</Constant>
+				</Apply>
+				<Constant dataType="double">0.6844243657125287</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Distance)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Distance"/>
+					<Constant dataType="double">10.426749306801499</Constant>
+				</Apply>
+				<Constant dataType="double">6.066336425774425</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Bathroom)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Bathroom"/>
+					<Constant dataType="double">1.434757788289023</Constant>
+				</Apply>
+				<Constant dataType="double">0.6519175028229948</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Car)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Car"/>
+					<Constant dataType="double">1.6821073234382646</Constant>
+				</Apply>
+				<Constant dataType="double">0.8558116035647958</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(logLandsize)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="logLandsize"/>
+					<Constant dataType="double">2.3661529658260885</Constant>
+				</Apply>
+				<Constant dataType="double">0.84368444941179</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(logBuildingArea)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="logBuildingArea"/>
+					<Constant dataType="double">2.0990197773631265</Constant>
+				</Apply>
+				<Constant dataType="double">0.18284993213113399</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(YearBuilt)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="YearBuilt"/>
+					<Constant dataType="double">1968.0455879954332</Constant>
+				</Apply>
+				<Constant dataType="double">25.406461747131278</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(CouncilArea)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="CouncilArea"/>
+					<Constant dataType="double">5.748246615560268</Constant>
+				</Apply>
+				<Constant dataType="double">6.170746654990085</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Lattitude)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Lattitude"/>
+					<Constant dataType="double">-37.80912136193117</Constant>
+				</Apply>
+				<Constant dataType="double">0.07441963519407027</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Longtitude)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Longtitude"/>
+					<Constant dataType="double">144.99747812591744</Constant>
+				</Apply>
+				<Constant dataType="double">0.09633550128190778</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Propertycount)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Propertycount"/>
+					<Constant dataType="double">7520.394470722557</Constant>
+				</Apply>
+				<Constant dataType="double">4504.100770431253</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Method_S)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Method_S"/>
+					<Constant dataType="double">0.657396835752732</Constant>
+				</Apply>
+				<Constant dataType="double">0.4745800628924771</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Method_SP)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Method_SP"/>
+					<Constant dataType="double">0.12909802642309573</Constant>
+				</Apply>
+				<Constant dataType="double">0.3353084043037952</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Method_VB)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Method_VB"/>
+					<Constant dataType="double">0.09182841298320013</Constant>
+				</Apply>
+				<Constant dataType="double">0.2887835790902713</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Northern_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Northern_Metropolitan"/>
+					<Constant dataType="double">0.2894307617028217</Constant>
+				</Apply>
+				<Constant dataType="double">0.4534981762730101</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_South_Eastern_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_South_Eastern_Metropolitan"/>
+					<Constant dataType="double">0.03735116620453433</Constant>
+				</Apply>
+				<Constant dataType="double">0.18962082319116638</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Southern_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Southern_Metropolitan"/>
+					<Constant dataType="double">0.3430109280704616</Constant>
+				</Apply>
+				<Constant dataType="double">0.4747151053997568</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Victoria)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Victoria"/>
+					<Constant dataType="double">0.010112542815201435</Constant>
+				</Apply>
+				<Constant dataType="double">0.10005138326386172</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Western_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Western_Metropolitan"/>
+					<Constant dataType="double">0.210650791061817</Constant>
+				</Apply>
+				<Constant dataType="double">0.40777081220564054</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(month)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="month"/>
+					<Constant dataType="double">7.152748328168325</Constant>
+				</Apply>
+				<Constant dataType="double">2.493359348369748</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(year)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="year"/>
+					<Constant dataType="double">2016.5621432066548</Constant>
+				</Apply>
+				<Constant dataType="double">0.49612319222817086</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(day_of_week)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="day_of_week"/>
+					<Constant dataType="double">4.8392595008970805</Constant>
+				</Apply>
+				<Constant dataType="double">1.1094918421491333</Constant>
+			</Apply>
+		</DerivedField>
+	</TransformationDictionary>
+</PMML>

SL/aufgaben/data/catboost_info/learn_error.tsv

@@ -0,0 +1,845 @@
+iter	Logloss
+0	0.6715355719
+1	0.6500104902	2	0.628337545333	0.60966944	044	0.59078205	055	0.57752576	0.6	0.55778077	077	0.54203558	8	8	0.52958589	9	9	0.51714610	1110	0.50423311	11	0.4929307812	12	0.4814072133
+13	0.4713296171
+14	0.4618167061
+15	0.452625197
+16	0.4442922771717	0.4361589191818	0.4279240561919	0.4218459572020	0.4151507422121	0.409436976222	0.4037422555223	0.3976515008224	0.3923734357225	25	0.389420826	026	0.383436327	027	0.378636828	0.3794535398
+29	0.3757155885
+30	0.3717786395
+31	0.3691171784
+32	0.3657305059
+33	0.3632016139
+34	0.3602285367
+35	0.3563286411
+36	0.3536211155
+37	0.3504242069
+38	0.3484263966
+39	0.3458929487
+40	0.3438820826
+41	0.3420411561
+42	0.3396861143
+43	0.3381319584
+44	0.3363482476
+45	0.3345493897
+46	0.3330299771
+47	0.3318525724
+48	0.3309013752
+49	0.3298096059
+50	0.3284301698
+51	0.3269025361
+52	0.3248681668
+53	0.3235173677
+54	0.32236862
+55	0.3215182991
+56	0.3204347043
+57	0.318931893
+58	0.3175421302
+59	0.3165771979
+60	0.3156489037
+61	0.3144519398
+62	0.3136613844
+63	0.3128673057
+64	0.312212034
+65	0.3114018298
+66	0.3106629251
+67	0.310034156
+68	0.3092989124
+69	0.3088944431
+70	0.3081516939
+71	0.3075363379
+72	0.3067525669
+73	0.3056937007
+74	0.3046441095
+75	0.3034415851
+76	076	0.295545077	077	0.29487978	0.78	0.29434479	0.79	0.2939280	0.380	0.293281	0.2981	0.292782	0.2982	0.29283	0.29883	0.29184	0.2976595593
+85	0.29785	0.2986	0.2967502188
+87	0.2962570112
+88	0.2958939803
+89	0.2955636397
+90	0.2949822244
+91	0.29491	0.28792	0.29492	0.28793	0.2933773115
+94	0.2929786319
+95	0.2927127209
+96	0.2923617196
+97	0.2920127162
+98	0.2917110356
+99	0.2913174166
+100	0.2909765376
+101	0.2906426256
+102	0.2902903937
+103	0.289738585
+104	0.2893907106
+105	0.2890596207
+106	0.288792732
+107	0.288534817
+108	0.2882073116
+109	0.2876705255
+110	0.2873647727
+111	0.2871375052
+112	0.2867474887
+113	0.2864232213
+114	0.2860121057
+115	0.2856438106
+116	0.2854464634
+117	0.2851231367
+118	0.2847282285
+119	0.2844702651
+120	0.2842679116
+121	0.2839106114
+122	0.2837456336
+123	0.2834910124
+124	0.2832364481
+125	0.2831050547
+126	0.2828182024
+127	0.2825989469
+128	0.2823589042
+129	0.2820757526
+130	0.2816758823
+131	0.2814171024
+132	0.2809784086
+133	0.2807750643
+134	0.2802622838
+135	0.2801679472
+136	0.2799283915
+137	0.2797753843
+138	0.2795553411
+139	0.2790582386
+140	0.2787916767
+141	0.2784819034
+142	0.2781899858
+143	0.2777745463
+144	0.2774850792
+145	0.2771480654
+146	0.2770049212
+147	0.2768221416
+148	0.276566122
+149	0.2764094158
+150	0.2762456947
+151	0.2759876734
+152	0.2755418589
+153	0.2753300818
+154	0.2751304602
+155	0.2749359612
+156	0.2748264315
+157	0.2745800918
+158	0.2742472939
+159	0.2740881719
+160	0.2738565523
+161	0.273609089
+162	0.2734032283
+163	0.2732939985
+164	0.27164	0.271165	0.27165	0.271166	0.27166	0.270167	0.27167	0.270168	0.27168	0.270169	0.27169	0.270170	0.27170	0.269171	0.27171	0.269172	0.27172	0.269173	0.2173	0.269174	0.27174	0.269175	0.2175	0.2690176	0.2176	0.2687177	0.2177	0.2685178	0.2178	0.2684179	0.2179	0.2680180	0180	0.267876181	0181	0.267755182	0182	0.267473183	0183	0.267351184	0184	0.267194185	0185	0.26700186	0186	0.26687187	0.187	0.26670188	0.188	0.2664957386
+189	0.266362267
+190	0.2661136479
+191	0.2658698416
+192	0.2657868936
+193	0.265665353
+194	0.2653983404
+195	0.2652371509
+196	0.2651063849
+197	0.264913291
+198	0.2647556863
+199	0.2645733951
+200	0.264427887
+201	0.2642523528
+202	0.2641045862
+203	0.2639229314
+204	0.2637726889
+205	0.2635740419
+206	0.26334242720207	0.26314082920208	0.263003622209	0.2628850388
+210	0.2627407842
+211	0.2626431306
+212	0.2624728347
+213	0.2622310925
+214	0.2620532664
+215	0.2618205654
+216	0.2616589509
+217	0.2614757645
+218	0.2612767208
+219	0.26086677522220	0.2607452221	221	0.2606090222222	0.2604421223	223	0.2603288224	224	0.2601877225	225	0.2600486226226	0.25989308227227	0.25975458228228	0.25941261229229	0.25930457230230	0.2591708023231	0.25908766323232	0.2589107169
+233	0.258706153
+234	0.2584906816
+235	0.2583584315
+236	0.2581589555
+237	0.257929247
+238	0.2578443862
+239	0.2576799959
+240	0.2574729962
+241	0.2573334764
+242	0.2572371053
+243	0.25706023824244	0.2569646905
+245	0.2568318486
+246	0.256676895
+247	0.2565448555
+248	0.2563555465
+249	0.25619328
+250	0.2560606951
+251	0.2558568112
+2252	0.25761936662253	0.257444013
+254	0.2573545493
+255	0.2572290353
+256	0.2570372912
+257	0.2568998636
+258	0.2567575768
+259	0.2565983849
+260	0.2564866484
+261	0.2563507181
+262	0.2562108287
+263	0.2560651128
+264	0.2558375368
+265	0.2557119265
+266	0.2556488469
+267	0.2554304808
+268	0.2553181749
+269	0.2551502773
+270	0.2529029506
+271	0.2527878029
+272	0.2546905989
+273	0.2545215518
+274	0.2543160817
+275	0.2541791875
+276	0.2540513566
+277	0.2539534559
+278	0.2538241785
+279	0.2537508829
+280	0.2536468795
+281	0.2534796288
+282	0.2533210302
+283	0.2531855087
+284	0.253060364
+285	0.252938553
+286	0.2528939278
+287	0.2528076195
+288	0.2526059889
+289	0.252516485
+290	0.252431445
+291	0.2523196753
+292	0.2522181392
+293	0.2521492932
+294	0.2520099701
+295	0.2518281723
+296	0.2517333023
+297	0.2516314819
+298	0.2514894085
+299	0.2512929534
+300	0.251161837
+301	0.2510757996
+302	0.2509626284
+303	0.250759337
+304	0.2506852761
+305	0.2505584546
+306	0.2503785971
+307	0.2502082196
+308	0.2500811161
+309	0.2498829037
+310	0.249807873
+311	0.2497761951
+312	0.2496915317
+313	0.2495364852
+314	0.2494153896
+315	0.2493185598
+316	0.249183293
+317	0.249015424
+318	0.2489144142
+319	0.24878961
+320	0.2486696127
+321	0.2485368039
+322	0.2484308881
+323	0.248312298
+324	0.2481997015
+325	0.2481188867
+326	0.2479984017
+327	0.2478591456
+328	0.2477113693
+329	0.2475420313
+330	0.2473880646
+331	0.2472143685
+332	0.2470477079
+333	0.2469472656
+334	0.2468033089
+335	0.2466792314
+336	0.2465228002
+337	0.246467637
+338	0.2463454509
+339	0.2463055341
+340	0.2461509115
+341	0.2459972066
+342	0.2458799621
+343	0.2457697806
+344	0.2456379602
+345	0.2455365372
+346	0.245390909
+347	0.2452414004
+348	0.2450948022
+349	0.2449969959
+350	0.2448391866
+351	0.2446539586
+352	0.2445683498
+353	0.244452316
+354	0.2443607228
+355	0.2442654109
+356	0.2441466725
+357	0.2440027311
+358	0.2438814211
+359	0.2437390836
+360	0.2436186585
+361	0.2434403101
+362	0.2432984141
+363	0.2430163168
+364	0.2429432348
+365	0.2428623686
+366	0.2426621444
+367	0.2424578679
+368	0.2423716254
+369	0.2422000161
+370	0.2420397528
+371	0.241938025
+372	0.2418099345
+373	0.2417362403
+374	0.2416968754
+375	0.2415959776
+376	0.2415044143
+377	0.2414036719
+378	0.2413144588
+379	0.2411997505
+380	0.2409918953
+381	0.2409076377
+382	0.2407821352
+383	0.2406444599
+384	0.2405312344
+385	0.2404221339
+386	0.2403162569
+387	0.2402180684
+388	0.2401040161
+389	0.2399174923
+390	0.2397740489
+391	0.2396549174
+392	0.2394659357
+393	0.2392422044
+394	0.239124725
+395	0.2390173787
+396	0.2388836747
+397	0.2388193253
+398	0.2387095384
+399	0.2385784603
+400	0.238428024
+401	0.238286148
+402	0.2381384209
+403	0.2380085855
+404	0.2378074478
+405	0.2376414464
+406	0.2375301155
+407	0.2373500664
+408	0.2371299706
+409	0.2370354963
+410	0.2368820977
+411	0.2367257734
+412	0.2366225093
+413	0.2364888794
+414	0.236357993
+415	0.2361769763
+416	0.2360451019
+417	0.2359401969
+418	0.2358386521
+419	0.2357085942
+420	0.2355723146
+421	0.2353819868
+422	0.235208862
+423	0.2351666693
+424	0.2349425824
+425	0.2348564318
+426	0.2347793051
+427	0.234635617
+428	0.2345190851
+429	0.234346511
+430	0.2342451178
+431	0.2341454553
+432	0.2341067534
+433	0.2339745587
+434	0.2339165625
+435	0.2338332876
+436	0.233759364
+437	0.2336547665
+438	0.233574331
+439	0.233463469
+440	0.2334118993
+441	0.2332008858
+442	0.2330763787
+443	0.2328962545
+444	0.2327718352
+445	0.2325767542
+446	0.2325135609
+447	0.2324561774
+448	0.2322494832
+449	0.2321726483
+450	0.2320481129
+451	0.2319412309
+452	0.2318444609
+453	0.2317409901
+454	0.231635057
+455	0.2314943555
+456	0.2313381946
+457	0.2312849151
+458	0.2312003718
+459	0.2311333753
+460	0.2310068691
+461	0.2309185959
+462	0.2308165199
+463	0.2307248742
+464	0.2306381584
+465	0.2305601601
+466	0.2304672421
+467	0.2302764413
+468	0.2301451112
+469	0.230023544
+470	0.2298875391
+471	0.2297757454
+472	0.2296864367
+473	0.2296073575
+474	0.229518713
+475	0.2294627614
+476	0.2292573337
+477	0.2291335591
+478	0.2290855056
+479	0.2289984126
+480	0.2289477607
+481	0.2287188845
+482	0.2285575159
+483	0.2284497673
+484	0.2283893552
+485	0.2282141027
+486	0.2279766928
+487	0.2279502749
+488	0.2278614808
+489	0.2277568426
+490	0.2276580223
+491	0.2275783133
+492	0.2275069093
+493	0.2274044203
+494	0.2272090293
+495	0.2271293126
+496	0.227022249
+497	0.2268998836
+498	0.2267174312
+499	0.2265308066
+500	0.2263558855
+501	0.2262839397
+502	0.2261074526
+503	0.2260589388
+504	0.2259620037
+505	0.2258239246
+506	0.2257021737
+507	0.2256233142
+508	0.2254568235
+509	0.2253782036
+510	0.2252923731
+511	0.2252153148
+512	0.2251011445
+513	0.2249799184
+514	0.2249385102
+515	0.2247559255
+516	0.2246312837
+517	0.2244927134
+518	0.2242212439
+519	0.2241349844
+520	0.2240605028
+521	0.223984483
+522	0.2237981956
+523	0.2237256507
+5524	0.22385886595525	0.22376262635526	0.2235791158527	0.2231165879
+5528	0.22335977375529	0.2232904164
+530	0.22320548365531	0.22303399353532	0.22287968753533	0.22277903553534	0.22266325553535	0.222594593536	0.2222462479
+537	0.2221446555
+538	0.2220074116
+539	0.2218753682
+540	0.2217279725
+541	0.2215278674
+542	0.2214397229
+543	0.2213313216
+544	0.2212424892
+545	0.2211267104
+546	0.221058413
+547	0.2209798705
+548	0.2208630304
+549	0.2206737075
+550	0.2205194543
+551	0.2204547144
+552	0.2202746715
+553	0.220190974
+554	0.2201306606
+555	0.2200181894
+556	0.2199530085
+557	0.2198615437
+558	0.2197844022
+559	0.2196566038
+560	0.2194860412
+561	0.2193479078
+562	0.2192304752
+563	0.2191926354
+564	0.2191247914
+565	0.219021307
+566	0.2189163296
+567	0.2188279593
+568	0.2187010131
+569	0.2186055581
+570	0.2185275634
+571	0.2184622755
+572	0.2183830614
+573	0.2182650336
+574	0.2181024144
+575	0.2180116354
+576	0.2179579982
+577	0.2178746878
+578	0.2177632613
+579	0.2176899773
+580	0.2175603564
+581	0.2174915483
+582	0.2174379661
+583	0.2173251156
+584	0.2171693914
+585	0.2170266494
+586	0.216864334
+587	0.2168034872
+588	0.2167335989
+589	0.2166304359
+590	0.2164724669
+591	0.2163198821
+592	0.2162064726
+593	0.2161018554
+594	0.2160103315
+595	0.2158800181
+596	0.2157548594
+597	0.215698425
+598	0.2155549787
+599	0.2154764111
+600	0.2153801721
+601	0.2152445929
+602	0.2151411293
+603	0.2149957359
+604	0.2148907006
+605	0.21481046
+606	0.2147547089
+607	0.2145890612
+608	0.2144855403
+609	0.2143502306
+610	0.2142863952
+611	0.2140713228
+612	0.2139516988
+613	0.213833705
+614	0.2137724275
+615	0615	0.21472616	0.616	0.21461617	0617	0.214560618	0618	0.214500619	0619	0.214408620	0620	0.214339621	0621	0.214243622	0622	0.214137623	0623	0.214008624	0624	0.213951625	0625	0.213780626	0626	0.2137644769
+627	0.2135857868
+628	0.2135479067
+629	0.2134538772
+630	0.2133340221
+631	0.2132292656
+632	0.213112633	0633	0.212972634	0634	0.2128635	0.2635	0.2127636	0.2118510496
+637	0.2116834225
+638	0.638	0.2125639	0.2114202615
+640	0.2113445402
+641	0.2112853157
+642	0.2112158115
+643	0.2111316421
+644	0.2109834817
+645	0.2108969759
+646	0.2108803226
+647	0.2107759254
+648	0.2106780292
+649	0.2105048205
+650	0.2104594373
+651	0.210396087
+652	0.2103460393
+653	0.2102946071
+654	0.2101566534
+655	0.2100883725
+656	0.2100653199
+657	0.2099599454
+658	0.2098735874
+659	0.2097640203
+660	0.2096592145
+661	0.2096139103
+662	0.2095420758
+663	0.2094600533
+664	0.2093671283
+665	0.2092667665
+666	0.2091092788
+667	0.2090712195
+668	0.2089494467
+669	0.2088626897
+670	0.2088150318
+671	0.2087060848
+672	0.2086060252
+673	0.2085728425
+674	0.2085014618
+675	0.2084382408
+676	0.2083550429
+677	0.2082908508
+678	0.2081572112
+679	0.2080626141
+680	0.2079779102
+681	0.2078554069
+682	0.2077728527
+683	0.2076214333
+684	0.2075344272
+685	0.2074853035
+686	0.20736748
+687	0.2072321229
+688	0.2070764962
+689	0.206959924
+690	0.2069038453
+691	0.2068433554
+692	0.2067499536
+693	0.2066997999
+694	0.2065947069
+695	0.206445379
+696	0.2063923529
+697	0.2062890568
+698	0.2062267393
+699	0.2061734689
+700	0.2060068816
+701	0.2058658631
+702	0.2057625962
+703	0.2055892085
+704	0704	0.20642705	0.2053025211
+706	0.2051688713
+707	0.707	0.20618708	0.2050085237
+709	0.2049088367
+710	0.2048239642
+711	0.2047316542
+712	0.2046032672
+713	0.2044329749
+714	0714	0.20548715	0.715	0.20541716	0.716	0.20536717	0.717	0.20524718	0.718	0.20519719	0.719	0.20513720	0.720	0.20510721	0.721	0.20501722	0.722	0.20498723	0.723	0.20493724	0.724	0.20486725	0.725	0.20479726	0.726	0.2047330242
+727	0.204639792
+728	0.2045057031
+729	0.20436730	0.730	0.20429731	0.731	0.20424732	0.732	0.20415733	0.2026522041
+734	0.734	0.20395735	0.735	0.20387736	0.736	0.20382737	0.737	0.20376738	0.2021816826
+739	0.2020455078
+740	0.2018938656
+741	0.2017567672
+742	0.2016824228
+743	0.2016070108
+744	0.2014842704
+745	0.2014104849
+746	0.2013393837
+747	0.2012833162
+748	0.2012559259
+749	0.2011516509
+750	0.2010261293
+751	0.2008588018
+752	0.2007177314
+753	0.2005909782
+754	0.2004566848
+755	0.2003678939
+756	0.200265596
+757	0.2002121035
+758	0.2001129327
+759	0.2000131959
+760	0.1999159409
+761	0.1997892077
+762	0.1997150572
+763	0.1995562023
+764	0.1994189202
+765	0.1993814234
+766	0.1993107055
+767	0.19923773
+768	0.1991631234
+769	0.1990231522
+770	0.1989572232
+771	0.1989065496
+772	0.198810354
+773	0.1987187126
+774	0.198602681
+775	0.198544289
+776	776	0.1974275777777	0.19737911778778	0.19731560779779	0.19729760780780	0.19726183781781	0.19718989782782	0.19714483783783	0.1971086784	784	0.1970310785	785	0.1969040102
+786	0.1968767787	787	0.1968223788788	0.19671808789	0.1971688679
+790	0.1971133505
+791	0.1970573064
+792	0.1969309651
+793	0.196822851
+794	0.1967037121
+795	0.1965664955
+796	0.1964988227
+797	0.1964288204
+798	0.1962998362
+799	0.1962072888
+800	0.1960950051
+801	0.196044112
+802	0.1959964318
+803	0.1959442302
+804	0.1959037122
+805	0.1957869796
+806	0.1956498038
+807	0.1955275716
+808	0.1954511929
+809	0.1953156204
+810	0.1952535142
+811	0.1951393533
+812	0.1950848436
+813	0.1949760076
+814	0.1948895198
+815	0.1948040409
+816	0.1946758699
+817	0.1945703718
+818	0.1945049746
+819	0.1944564152
+820	0.1943254884
+821	0.1942024297
+822	0.1941361423
+823	0.1940355461
+824	0.193928491
+825	0.1938722662
+826	0.1938241723
+827	0.1937563974
+828	0.1936496047
+829	0.1935365196
+830	0.193436826
+831	0.1934245063
+832	0.1933003321
+833	0.1931803445
+834	0.1931194794
+835	0.1930578233
+836	0.1929893039
+837	0.1928975868
+838	0.192815136
+839	0.1926973762
+840	0.192642313
+841	0.1925744074
+842	0.1924976177
+843	0.1924535229
+844	0.1923759868
+845	0.1922892698
+846	0.1922402248
+847	0.1921752729
+848	0.1920466624
+849	0.1919349155
+850	0.1918797293
+851	0.1918321291
+852	0.1917885763
+853	0.1917436879
+854	0.1916714435
+855	0.1915585621
+856	0.1914585379
+857	0.191366928
+858	0.1912387077
+859	0.1911316581
+860	0.1910178787
+861	0.1909128097
+862	0.1908743757
+863	0.1907896694
+864	0.1906881947
+865	0.1905467185
+866	0.1905101728
+867	0.1904734468
+868	0.1903627676
+869	0.1902835324
+870	0.1901353705
+871	0.1900130826
+872	0.1898964985
+873	0.189843312
+874	0.1898091057
+875	0.1897611113
+876	0.1896789766
+877	0.1895745098
+878	0.1894637744
+879	0.1894036691
+880	0.1892932683
+881	0.189258266
+882	0.1891981233
+883	0.1891215445
+884	0.1890143054
+885	0.1889312723
+886	0886	0.192085887	0887	0.191935888	0888	0.191898889	0889	0.191846890	0890	0.191790891	0891	0.191729892	0892	0.1916760736
+893	0.1915335233
+894	0.1914796028
+895	0.1913763062
+896	0.1913395079
+897	0.1912678699
+898	0.191243899	0899	0.191162900	0.1876269642
+901	0.1875001977
+902	0.187403209
+903	0.1873043882
+904	0.1872195534
+905	0.1871491767
+906	0.1870104981
+907	0.1869420064
+908	0.1868914869
+909	0.186787065
+910	0.1866702356
+911	0.1866046699
+912	0.1864560457
+913	0.1863240246
+914	0.1862062241
+915	0.1861338881
+916	0.186025657
+917	0.1859396015
+918	0.1858178881
+919	0.185706966
+920	0.1856200051
+921	0.1854981475
+922	0.1854257424
+923	0.1853204869
+924	0.1852156164
+925	0.1851027012
+926	0.1849973028
+927	0.1848849182
+928	0.1848190864
+929	0.1846982134
+930	0.1845826874
+931	0.18446116
+932	0.1843612267
+933	0.1842788248
+934	0.1841913191
+935	0.1841571329
+936	0.1840521094
+937	0.183983229
+938	0.1839018212
+939	0.1838136477
+940	0.1837559317
+941	0.1836433761
+942	0.1835371968
+943	0.183429206
+944	0.1833599311
+945	0.1832798986
+946	0.1831687847
+947	0.1830272249
+948	0.1829354743
+949	0.1828585222
+950	0.1828066679
+951	0.1826992636
+952	0.1826619975
+953	0.1826404807
+954	0.1826049683
+955	0.182542509
+956	0.1824707124
+957	0.1823498301
+958	0.1822917321
+959	0.1822506991
+960	0.18222991
+961	0.1821302287
+962	0.1820405902
+963	0.1819642189
+964	0.1818719662
+965	0.1818081334
+966	0.1817224884
+967	0.1816794438
+968	0.18157978
+969	0.1814637115
+970	0.1813123668
+971	0.1811983001
+972	0.1810990775
+973	0.1810350562
+974	0.1809943476
+975	0.1808972694
+976	0.1808157769
+977	0.1807341121
+978	0.18064582978979	0.18057748979980	0.18051626980	0.18567441698981	0.18559991998982	0.185556502
+983	0.185514808
+984	0.1854468917
+985	0.1853146605
+986	0.1852626547
+987	0.185230434
+988	0.1852016396
+989	0990	0.179711990	0991	0.17963991	0.992	0.17957992	0.993	0.17951993	0.994	0.17942994	0.995	0.1793665083
+996	0.17928996	0.997	0.17918997	0.998	0.17911998	0.999	0.17902999	0.1844407665
+601128

SL/aufgaben/data/catboost_info/time_left.tsv

@@ -0,0 +1,879 @@
+iter	Passed	Remaining
+0	59	59828
+1	61	30821
+2	63	21170
+3	65	16340
+4	67	13429
+5	69	11507
+6	71	1021377	73	915888	75	833299	77	7671110	79	7156111	82	6779112	84	6426113	86	6106114	88	5843115	90	5593116	92	5358117	94	5168118	97	5022119	99	4864220	101	4740221	103	4609222	105	4487223	107	4369224	109	4274225	112	4209226	114	4118227	116	402728	118	3960
+29	120	3889
+30	123	3846
+31	124	3767
+32	126	3709
+33	129	3666
+34	131	3627
+35	133	3585
+36	135	3539
+37	138	3506
+38	141	3474
+39	142	3429
+40	144	3388
+41	146	3349
+42	149	3321
+43	151	3290
+44	153	3259
+45	155	3223
+46	157	3197
+47	159	3165
+48	161	3139
+49	164	3121
+50	166	3089
+51	168	3075
+52	170	3051
+53	173	3032
+54	174	3006
+55	176	2981
+56	179	2961
+57	181	2945
+58	183	2929
+59	185	2906
+60	187	2884
+61	189	2861
+62	190	2837
+63	192	2821
+64	194	2803
+65	196	2785
+66	198	2767
+67	200	2747
+68	202	2736
+69	204	2721
+70	206	2703
+71	208	2686
+72	210	2672
+73	212	2659
+74	214	2647
+75	216	2635
+776	219	2630777	221	2615778	223	2607779	225	2598880	227	2582881	229	2569882	231	2559883	233	254984	235	2537
+885	237	252786	240	2522
+87	242	2510
+88	244	2499
+89	246	2488
+90	248	2477
+991	250	2467992	251	245793	253	2447
+94	256	2441
+95	258	2435
+96	260	2426
+97	263	2422
+98	265	2420
+99	268	2412
+100	269	2402
+101	272	2397
+102	274	2387
+103	275	2377
+104	277	2366
+105	279	2358
+106	281	2351
+107	283	2340
+108	286	2339
+109	288	2336
+110	290	2324
+111	292	2316
+112	294	2308
+113	296	2302
+114	298	2294
+115	300	2287
+116	302	2279
+117	304	2275
+118	306	2267
+119	308	2259
+120	309	2251
+121	312	2248
+122	314	2242
+123	316	2238
+124	318	2229
+125	320	2223
+126	322	2215
+127	324	2208
+128	326	2205
+129	328	2199
+130	330	2194
+131	332	2187
+132	334	2182
+133	336	2177
+134	338	2171
+135	340	2164
+136	342	2159
+137	346	2162
+138	348	2156
+139	350	2152
+140	352	2147
+141	354	2141
+142	356	2135
+143	358	2130
+144	360	2124
+145	362	2118
+146	364	2112
+147	366	2106
+148	367	2101
+149	369	2095
+150	372	2092
+151	374	2090
+152	377	2088
+153	379	2082
+154	380	2076
+155	383	2072
+156	384	2066
+157	386	2060
+158	388	2054
+159	390	2051
+160	392	2046
+161	394	2042
+162	396	2036
+163	398	2031
+164	400	2025
+165	402	2021
+166	404	2016
+167	406	2012
+168	408	2007
+169	410	2002
+170	412	1999
+171	414	1997
+172	416	1992
+173	418	1987
+174	421	1985
+175	423	1981
+176	424	1975
+177	426	1971
+178	429	1968
+179	431	1965
+180	433	1960
+181	435	1955
+182	437	1954
+183	440	1951
+184	441	1946
+185	443	1942
+186	445	1937
+187	448	1936
+188	450	1933
+189	452	1929
+190	454	1926
+191	456	1922
+192	458	1918
+193	461	1916
+194	463	1911
+195	465	1910
+196	467	1907
+197	470	1905
+198	472	1901
+199	474	1898
+200	476	1894
+201	478	1890
+202	480	1885
+203	481	1880
+204	483	1876
+205	485	1872
+206	487	1867
+207	489	1863
+208	491	1860
+209	494	1858
+210	496	1855
+211	498	1851
+212	500	1849
+213	502	1845
+214	504	1842
+215	507	1840
+216	509	1837
+217	511	1833
+218	513	1829
+219	515	1825
+220	516	1821
+221	518	1817
+222	520	1814
+223	522	1810
+224	524	1807
+225	526	1803
+226	528	1799
+227	530	1795
+228	532	1792
+229	534	1788
+230	536	1784
+231	538	1781
+232	540	1779
+233	542	1775
+234	545	1774
+235	547	1772
+236	549	1768
+237	551	1764
+238	553	1762
+239	555	1759
+240	557	1756
+241	559	1752
+242	561	1748
+243	563	1745
+244	565	1743
+245	567	1740
+246	569	1736
+247	571	1733
+248	574	1731
+249	576	1728
+250	578	1725
+251	580	1722
+252	583	1721
+253	586	1723
+254	590	1725
+255	593	1725
+256	596	1725
+257	598	1722
+258	602	1722
+259	604	1719
+260	606	1716
+261	607	1712
+262	610	1711
+263	613	1711
+264	616	1710
+265	618	1708
+266	621	1707
+267	625	1707
+268	628	1706
+269	630	1704
+270	632	1701
+271	635	1700
+272	638	1699
+273	641	1699
+274	644	1699
+275	646	1696
+276	648	1693
+277	651	1692
+278	654	1691
+279	656	1689
+280	660	1688
+281	663	1688
+282	666	1687
+283	669	1687
+284	671	1685
+285	673	1681
+286	676	1680
+287	679	1680
+288	682	1679
+289	684	1676
+290	687	1675
+291	689	1672
+292	692	1671
+293	695	1670
+294	699	1670
+295	702	1670
+296	705	1669
+297	707	1665
+298	709	1662
+299	711	1659
+300	713	1658
+301	716	1654
+302	718	1653
+303	720	1650
+304	723	1649
+305	727	1648
+306	730	1648
+307	733	1647
+308	736	1646
+309	739	1645
+310	741	1642
+311	744	1642
+312	748	1641
+313	751	1641
+314	753	1637
+315	755	1635
+316	758	1634
+317	761	1632
+318	764	1631
+319	767	1629
+320	770	1629
+321	773	1628
+322	776	1627
+323	779	1626
+324	782	1625
+325	785	1624
+326	787	1621
+327	789	1618
+328	792	1617
+329	796	1616
+330	799	1615
+331	802	1613
+332	805	1613
+333	808	1612
+334	810	1608
+335	812	1604
+336	815	1603
+337	817	1601
+338	819	1598
+339	821	1594
+340	823	1590
+341	826	1589
+342	829	1588
+343	831	1585
+344	833	1581
+345	835	1578
+346	837	1575
+347	838	1571
+348	840	1568
+349	842	1565
+350	845	1563
+351	849	1563
+352	852	1561
+353	854	1558
+354	856	1556
+355	858	1553
+356	860	1550
+357	863	1548
+358	866	1547
+359	869	1545
+360	872	1544
+361	875	1543
+362	879	1542
+363	881	1539
+364	884	1538
+365	886	1535
+366	889	1533
+367	892	1532
+368	895	1530
+369	897	1527
+370	899	1524
+371	900	1520
+372	902	1517
+373	905	1515
+374	907	1512
+375	909	1509
+376	911	1506
+377	913	1502
+378	914	1499
+379	916	1495
+380	919	1493
+381	922	1492
+382	925	1491
+383	928	1490
+384	931	1488
+385	934	1486
+386	937	1485
+387	940	1483
+388	943	1482
+389	946	1481
+390	950	1479
+391	953	1478
+392	956	1477
+393	958	1474
+394	960	1470
+395	962	1467
+396	964	1465
+397	967	1463
+398	969	1460
+399	971	1457
+400	973	1454
+401	976	1452
+402	978	1449
+403	980	1446
+404	983	1444
+405	985	1441
+406	987	1438
+407	990	1437
+408	993	1436
+409	995	1433
+410	999	1432
+411	1002	1430
+412	1005	1429
+413	1007	1426
+414	1009	1423
+415	1011	1420
+416	1015	1419
+417	1017	1416
+418	1020	1414
+419	1022	1411
+420	1024	1408
+421	1025	1405
+422	1029	1403
+423	1031	1400
+424	1033	1397
+425	1036	1396
+426	1039	1394
+427	1042	1393
+428	1044	1390
+429	1047	1388
+430	1050	1386
+431	1053	1385
+432	1056	1383
+433	1059	1382
+434	1062	1380
+435	1065	1378
+436	1068	1376
+437	1070	1373
+438	1073	1372
+439	1076	1370
+440	1078	1367
+441	1080	1364
+442	1082	1361
+443	1084	1357
+444	1087	1356
+445	1090	1354
+446	1092	1351
+447	1095	1350
+448	1098	1348
+449	1101	1346
+450	1103	1343
+451	1106	1342
+452	1109	1339
+453	1110	1335
+454	1113	1333
+455	1116	1332
+456	1118	1329
+457	1121	1327
+458	1124	1325
+459	1126	1322
+460	1128	1319
+461	1131	1317
+462	1134	1315
+463	1137	1314
+464	1140	1312
+465	1143	1310
+466	1146	1309
+467	1149	1306
+468	1152	1304
+469	1154	1301
+470	1156	1298
+471	1157	1295
+472	1159	1291
+473	1161	1288
+474	1164	1286
+475	1166	1283
+476	1168	1281
+477	1171	1279
+478	1174	1277
+479	1177	1275
+480	1179	1273
+481	1182	1270
+482	1185	1268
+483	1187	1266
+484	1189	1262
+485	1191	1259
+486	1193	1257
+487	1195	1254
+488	1198	1252
+489	1202	1251
+490	1205	1249
+491	1208	1247
+492	1211	1245
+493	1213	1243
+494	1215	1239
+495	1217	1237
+496	1220	1235
+497	1223	1232
+498	1224	1229
+499	1226	1226
+500	1228	1223
+501	1230	1220
+502	1233	1218
+503	1235	1215
+504	1237	505	1505	1240	1210
+506	1243	1209
+507	1246	1207
+508	1249	1205
+509	1252	1203
+510	1254	1200
+511	1256	1197
+512	1259	1195
+513	1261	514	1514	1264	515	1515	1266	1188
+516	1268	517	1517	1270	518	1272	1179
+519	1275	1177
+520	1277	1174
+521	1279	1171
+522	1282	1169
+523	1285	1168
+524	1524	1288	525	1525	1290	526	1526	1292	527	1294	1157
+528	1528	1297	529	1529	1301	1153
+530	1303	531	1531	1304	532	1532	1307	533	1533	1311	534	1534	1314	535	1535	1316	536	1319	1137
+537	1322	1135
+538	1325	1133
+539	1328	1131
+540	1331	1129
+541	1334	1127
+542	1336	1125
+543	1339	1123
+544	1342	1121
+545	1345	1119
+546	1347	1116
+547	1350	1114
+548	1353	1112
+549	1355	1109
+550	1358	1106
+551	1360	1104
+552	1363	1102
+553	1365	1099
+554	1368	1096
+555	1371	1095
+556	1374	1093
+557	1376	1090
+558	1379	1088
+559	1381	1085
+560	1383	1082
+561	1385	1079
+562	1387	1076
+563	1389	1073
+564	1392	1071
+565	1395	1069
+566	1397	1067
+567	1400	1065
+568	1402	1062
+569	1406	1060
+570	1408	1058
+571	1411	1056
+572	1414	1054
+573	1416	1051
+574	1418	1048
+575	1420	1045
+576	1423	1043
+577	1426	1041
+578	1429	1039
+579	1431	1036
+580	1433	1033
+581	1435	1031
+582	1438	1028
+583	1441	1026
+584	1443	1023
+585	1445	1021
+586	1448	1018
+587	1451	1016
+588	1453	1014
+589	1457	1012
+590	1460	1010
+591	1463	1008
+592	1466	1006
+593	1468	1003
+594	1470	1001
+595	1472	998
+596	1474	995
+597	1477	993
+598	1479	990
+599	1481	987
+600	1483	984
+601	1485	982
+602	1487	979
+603	1489	976
+604	1491	973
+605	1492	970
+606	1494	967
+607	1496	965
+608	1498	962
+609	1500	959
+610	1502	956
+611	1505	954
+612	1507	952
+613	1510	949
+614	1513	947
+615615	1515	9616616	1518	9617617	1520	9618618	1522	9619619	1525	9620620	1527	9621621	1529	9622622	1532	9623623	1534	9624624	1537	9625625	1540	9626626	1543	918
+627	1545	915
+628	1548	913
+629	1551	911
+630	1555	909
+631	1557	906
+632	1559	9633633	1561	9634634	1563	8635635	1565	8636	1567	893
+637	1571	891
+638638	1573	8639	1576	886
+640	1579	884
+641	1581	881
+642	1583	879
+643	1586	876
+644	1589	874
+645	1592	872
+646	1594	870
+647	1596	867
+648	1598	864
+649	1601	862
+650	1604	860
+651	1606	857
+652	1609	855
+653	1611	852
+654	1613	849
+655	1616	847
+656	1620	845
+657	1622	843
+658	1625	841
+659	1628	838
+660	1631	836
+661	1633	834
+662	1635	831
+663	1638	829
+664	1641	827
+665	1644	824
+666	1647	822
+667	1649	819
+668	1652	817
+669	1654	815
+670	1656	812
+671	1659	810
+672	1662	808
+673	1664	805
+674	1667	803
+675	1669	800
+676	1672	797
+677	1674	795
+678	1676	792
+679	1678	789
+680	1680	787
+681	1682	784
+682	1684	781
+683	1687	779
+684	1690	777
+685	1693	775
+686	1695	772
+687	1698	770
+688	1700	767
+689	1703	765
+690	1705	762
+691	1707	759
+692	1709	757
+693	1712	755
+694	1715	752
+695	1718	750
+696	1721	748
+697	1724	746
+698	1727	743
+699	1730	741
+700	1732	738
+701	1734	736
+702	1736	733
+703	1739	731
+704704	1741	7705	1744	726
+706	1746	723
+707707	1749	7708	1752	719
+709	1754	716
+710	1756	713
+711	1757	711
+712	1761	708
+713	1763	706
+714714	1765	7715715	1768	7716716	1770	6717717	1773	6718718	1775	6719719	1777	6720720	1780	6721721	1782	6722722	1785	6723723	1789	6724724	1791	6725725	1795	6726726	1798	675
+727	1800	672
+728	1802	670
+729	1804	6730730	1807	6731731	1810	6732	1812	660
+733	1815	657
+734734	1818	6735735	1821	6736736	1823	6737737	1825	6738	1828	645
+739	1830	643
+740	1833	641
+741	1837	638
+742	1840	636
+743	1843	634
+744	1846	631
+745	1848	629
+746	1850	626
+747	1851	623
+748	1854	621
+749	1858	619
+750	1860	616
+751	1862	614
+752	1865	612
+753	1868	609
+754	1872	607
+755	1874	604
+756	1876	602
+757	1878	599
+758	1881	597
+759	1884	595
+760	1886	592
+761	1888	589
+762	1890	587
+763	1892	584
+764	1895	582
+765	1898	579
+766	1900	577
+767	1768	1900768	1769	1902769	1770	1905770	1771	1907771	1772	1910772	1773	1913773	1774	1916774	1775	1919775	1776	1921	551
+777	1923	548
+778	1925	546
+779	1928	544
+780	1932	541
+781	1934	539
+782	1937	536
+783	1939	534
+784	1942	531
+785	1945	529
+786	1947	527
+787	1949	524
+788	1951	521
+789	1953789	1790	1955790	1791	1958791	1792	1960792	1793	1963793	1794	1965794	1970	507
+795	1973	505
+796	1975	503
+797	1978	500
+798	1799	1978799	1800	1982800	1986	493
+801	1988	490
+802	1803	1989803	1993	486
+804	1996	483
+805	1998	481
+806	2001	478
+807	2003	476
+808	2006	473
+809	2009	471
+810	2012	468
+811	2015	466
+812	2017	464
+813	2019	461
+814	2022	459
+815	2024	456
+816	2027	454
+817	2029	451
+818	2032	449
+819	2034	446
+820	2037	444
+821	2039	441
+822	2042	439
+823	2045	436
+824	2049	434
+825	2051	432
+826	2053	429
+827	2054	426
+828	2056	424
+829	2059	421
+830	2062	419
+831	2064	416
+832	2067	414
+833	2069	411
+834	2072	409
+835	2075	407
+836	2077	404
+837	2079	402
+838	2081	399
+839	2083	396
+840	2085	394
+841	2087	391
+842	2090	389
+843	2093	386
+844	2095	384
+845	2098	381
+846	2101	379
+847	2104	377
+848	2108	374
+849	2110	372
+850	2112	369
+851	2114	367
+852	2116	364
+853	2119	362
+854	2122	359
+855	2125	357
+856	2128	355
+857	2130	352
+858	2133	350
+859	2136	347
+860	2138	345
+861	2140	342
+862	2143	340
+863	2147	337
+864	2150	335
+865	2153	333
+866	2155	330
+867	2158	328
+868	2161	325
+869	2164	323
+870	2166	320
+871	2169	318
+872	2171	315
+873	2174	313
+874	2176	310
+875	2178	308
+876	2179	305
+877	2181	303
+878	2185	300
+879	2187	298
+880	2189	295
+881	2191	293
+882	2194	290
+883	2196	288
+884	2197	285
+885	2200	283
+886886	2201	2887887	2204	2888888	2207	2889889	2211	2890890	2214	2891891	2217	2892892	2220	266
+893	2222	263
+894	2225	261
+895	2228	258
+896	2231	256
+897	2234	253
+898	2236	2899899	2238	2900	2241	246
+901	2244	243
+902	2247	241
+903	2251	239
+904	2254	236
+905	2256	234
+906	2258	231
+907	2261	229
+908	2264	226
+909	2266	224
+910	2268	221
+911	2271	219
+912	2274	216
+913	2277	214
+914	2279	211
+915	2282	209
+916	2285	206
+917	2288	204
+918	2291	202
+919	2295	199
+920	2298	197
+921	2300	194
+922	2302	192
+923	2304	189
+924	2306	187
+925	2308	184
+926	2311	181
+927	2314	179
+928	2317	177
+929	2319	174
+930	2321	172
+932	2315	166
+933	2318	163
+933	2328	164
+935	2322	158
+936	2326	156
+937	2329	153
+938	2332	151
+939	2335	149
+940	2337	146
+941	2339	144
+942	2341	141
+943	2343	138
+944	2346	136
+945	2348	134
+946	2351	131
+946	2360	132
+947	2363	129
+948	2366	127
+949	2369	124
+950	2371	122
+951	2374	119
+952	2377	117
+953	2380	114
+954	2384	112
+955	2386	109
+956	2388	107
+957	2390	104
+958	2391	102
+959	2395	99
+960	2398	97
+961	2400	94
+962	2403	92
+963	2408	89
+964	2410	87
+965	2414	84
+966	2416	82
+967	2418	79
+968	2420	77
+969	2422	74
+970	2424	72
+971	2425	699972	2428	67
+973	2431	64
+974	2434	62
+975	2436	59
+976	2439	57
+977	2442	54
+978978	2443	979979	2446	980980	2449	47
+981	2451	44
+982	2455	42
+983	2458	39
+984	2461	37
+985	2463	34
+986	2466	32
+987	2470	30
+988	2472	27
+989	2474	990990	2477	991991	2479	992992	2482	993993	2484	994994	2487	995	2491	10
+996996	2494997997	2497998998	2501999999	2503	0

SL/aufgaben/data/demo_data_class.csv

@@ -0,0 +1,82 @@
+"y","X1","X2"
+"A",6,2.5
+"A",5.1,1.9
+"A",5.9,2.1
+"A",5.6,1.8
+"A",5.8,2.2
+"A",6.6,2.1
+"A",4.5,1.7
+"A",6.3,1.8
+"A",5.8,1.8
+"A",6.1,2.5
+"A",5.1,2
+"A",5.3,1.9
+"A",5.5,2.1
+"A",5,2
+"A",5.1,2.4
+"A",5.3,2.3
+"A",5.5,1.8
+"A",6.7,2.2
+"A",6.9,2.3
+"A",5,1.5
+"A",5.7,2.3
+"A",4.9,2
+"A",6.7,2
+"A",4.9,1.8
+"A",5.7,2.1
+"A",6,1.8
+"A",4.8,1.8
+"A",5.6,2.1
+"A",5.8,1.6
+"A",6.1,1.9
+"A",6.4,2
+"A",5.6,2.2
+"A",5.6,1.4
+"A",6.1,2.3
+"A",5.6,2.4
+"A",4.8,1.9
+"A",5.4,2.1
+"A",5.1,2.3
+"A",5.9,2.3
+"A",5.7,2.5
+"A",5.2,2.3
+"A",5,1.9
+"A",5.2,2
+"A",5.4,2.3
+"A",5.1,1.8
+"B",4.7,1.4
+"B",4.5,1.5
+"B",4.9,1.5
+"B",4,1.3
+"B",4.6,1.5
+"B",4.5,1.3
+"B",4.7,1.6
+"B",3.3,1
+"B",4.6,1.3
+"B",3.9,1.4
+"B",3.5,1
+"B",4.2,1.5
+"B",4,1
+"B",3.6,1.3
+"B",4.4,1.4
+"B",4.1,1
+"B",3.9,1.1
+"B",4.8,1.7
+"B",4.7,1.2
+"B",4.3,1.3
+"B",4.8,1.4
+"B",5,1.7
+"B",3.8,1.1
+"B",3.7,1
+"B",3.9,1.2
+"B",5.1,1.6
+"B",4.5,1.6
+"B",4.7,1.5
+"B",4.4,1.3
+"B",4.1,1.3
+"B",4.4,1.2
+"B",4.6,1.4
+"B",4,1.2
+"B",4.2,1.3
+"B",4.2,1.2
+"B",3,1.1

SL/aufgaben/data/demo_data_regr.csv

@@ -0,0 +1,82 @@
+"X","y"
+6,2.5
+5.1,1.9
+5.9,2.1
+5.6,1.8
+5.8,2.2
+6.6,2.1
+4.5,1.7
+6.3,1.8
+5.8,1.8
+6.1,2.5
+5.1,2
+5.3,1.9
+5.5,2.1
+5,2
+5.1,2.4
+5.3,2.3
+5.5,1.8
+6.7,2.2
+6.9,2.3
+5,1.5
+5.7,2.3
+4.9,2
+6.7,2
+4.9,1.8
+5.7,2.1
+6,1.8
+4.8,1.8
+5.6,2.1
+5.8,1.6
+6.1,1.9
+6.4,2
+5.6,2.2
+5.6,1.4
+6.1,2.3
+5.6,2.4
+4.8,1.9
+5.4,2.1
+5.1,2.3
+5.9,2.3
+5.7,2.5
+5.2,2.3
+5,1.9
+5.2,2
+5.4,2.3
+5.1,1.8
+4.7,1.4
+4.5,1.5
+4.9,1.5
+4,1.3
+4.6,1.5
+4.5,1.3
+4.7,1.6
+3.3,1
+4.6,1.3
+3.9,1.4
+3.5,1
+4.2,1.5
+4,1
+3.6,1.3
+4.4,1.4
+4.1,1
+3.9,1.1
+4.8,1.7
+4.7,1.2
+4.3,1.3
+4.8,1.4
+5,1.7
+3.8,1.1
+3.7,1
+3.9,1.2
+5.1,1.6
+4.5,1.6
+4.7,1.5
+4.4,1.3
+4.1,1.3
+4.4,1.2
+4.6,1.4
+4,1.2
+4.2,1.3
+4.2,1.2
+3,1.1

SL/aufgaben/data/fe_prod_log.log

@@ -0,0 +1,99 @@
+[2025-06-21 22:20:44] (timestamp)
+
+features with NA's
+=======================
+age                123
+job                 73
+marital             19
+education          463
+duration            51
+poutcome          7814
+emp.var.rate       247
+cons.price.idx     247
+cons.conf.idx      247
+
+categorical cols levels
+=======================
+job
+job
+admin.           2630
+blue collar      1852
+entrepreneur      294
+housemaid         267
+management        688
+retired           621
+self-employed     336
+services          856
+student           354
+technician       1626
+unemployed        271
+
+marital
+marital
+divorced    1076
+married     5747
+single      3026
+
+education
+education
+basic.4y                972
+basic.6y                503
+basic.9y               1251
+high.school            2230
+illiterate                6
+professional.course    1307
+university.degree      3136
+
+default
+default
+no         8268
+unknown    1600
+
+housing
+housing
+no         4413
+unknown     244
+yes        5211
+
+loan
+loan
+no         8196
+unknown     244
+yes        1428
+
+contact
+contact
+cellular     6993
+telephone    2875
+
+month
+month
+apr     834
+aug    1451
+dec     103
+jul    1582
+jun    1239
+mar     314
+may    2745
+nov     925
+oct     363
+sep     312
+
+day_of_week
+day_of_week
+fri    1823
+mon    1960
+thu    2152
+tue    1947
+wed    1986
+
+poutcome
+poutcome
+failure    1101
+success     953
+
+y
+y
+no     5223
+yes    4645
+

SL/aufgaben/template/2_Code/1.1 Feature Engineering - Einfuehrung.ipynb

@@ -0,0 +1,222 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**nicht als Notebook verteilen**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Feature Engineering\n",
+    "\n",
+    "## Feature Engineering - Einführung\n",
+    "\n",
+    "### Abgrenzungen\n",
+    "\n",
+    "### CRISP - und die Gliederung des Kurses\n",
+    "\n",
+    "### Strukturierte Daten\n",
+    "\n",
+    "#### Aufbau und Organisation eines Data Frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     age            job  marital  duration  campaign    y\n",
+      "0   30.0  self-employed   single     245.0         3  yes\n",
+      "1   32.0     technician  married     370.0         1   no\n",
+      "2   27.0    blue collar   single     623.0         1  yes\n",
+      "3    NaN    blue collar   single       9.0         6   no\n",
+      "4   27.0         admin.   single     126.0         2  yes\n",
+      "5   34.0         admin.   single     548.0         2  yes\n",
+      "6   46.0           None  married      86.0         2   no\n",
+      "7    NaN        retired  married     707.0         3  yes\n",
+      "8   46.0         admin.  married      96.0         6   no\n",
+      "9   48.0    blue collar  married     241.0         2   no\n",
+      "10  29.0     technician  married     154.0         3   no\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "data = pd.read_csv('../3_data/bank_data.csv', sep=';')\n",
+    "#print(data.iloc[0:11, 0:6])\n",
+    "\n",
+    "## arbitrarily input\n",
+    "data.iloc[3, 0] = None\n",
+    "data.iloc[6, 1] = None\n",
+    "#print(data.iloc[0:11, 0:6])\n",
+    "print(data.iloc[0:11, [0,1,2,10,11,20]])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Begriffe"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Beispieldaten"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "import pandas as pd\n",
+    "demo_data_class = pd.read_csv('../3_data/demo_data_class.csv')\n",
+    "demo_data_regr = pd.read_csv('../3_data/demo_data_regr.csv') "
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "import seaborn as sns\n",
+    "iris_data = sns.load_dataset('iris')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "### Anforderungen an die Daten für Machine Learning"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Eine typische ML Sequenz"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Python Libraries"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Feature Engineering"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Die Python Libraries und CRISP-DM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Begleitende Literatur"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "1.1",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "1.1 Feature Engineering - Einführung",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "251px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "toc-autonumbering": true,
+  "toc-showcode": false,
+  "toc-showmarkdowntxt": false,
+  "toc-showtags": false,
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "326.85px",
+    "left": "910px",
+    "right": "20px",
+    "top": "120px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

SL/aufgaben/template/2_Code/1.6 Feature Engineering - Implementation.ipynb

@@ -0,0 +1,521 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Feature Engineering\n",
+    "## Einfuehrung\n",
+    "## Exploration\n",
+    "## Transformation\n",
+    "## Konstruktion\n",
+    "## Selektion\n",
+    "## Implementation\n",
+    "### Data Frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:28.485043Z",
+     "start_time": "2020-03-17T11:19:27.999820Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## preparation: import libraries and read data\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "sns.set()\n",
+    "%matplotlib inline\n",
+    "\n",
+    "datapath = '../3_data'\n",
+    "from os import chdir\n",
+    "\n",
+    "chdir(datapath)\n",
+    "\n",
+    "data = pd.read_csv('bank_data.csv', sep=';')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E1: Entfernen von Beobachtungen nach Bedingung"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## remove case for age > 100\n",
+    "data.drop(data[data.age >= 100].index, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E2: Entfernen von Duplikaten"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## remove duplicates\n",
+    "data.drop_duplicates(ignore_index=True, inplace = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E3: Entfernen fragwürdiger Variablen"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## alternative ['default', 'poutcome', 'duration']\n",
+    "vars_to_drop = ['default', 'poutcome']\n",
+    "data = data.drop(vars_to_drop, axis=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E4: Einsetzen von Werten für NAs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## create lists of names of of categorical and numerical variables\n",
+    "cat_vars = data.select_dtypes(include='object').columns.tolist()\n",
+    "num_vars = data.select_dtypes(exclude='object').columns.tolist()\n",
+    "\n",
+    "## import SimpleImputer class\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "\n",
+    "## imput for categorical variables\n",
+    "imp_mode = SimpleImputer(missing_values=np.nan, strategy='most_frequent')\n",
+    "data[cat_vars] = pd.DataFrame(imp_mode.fit_transform(data[cat_vars]), columns=data[cat_vars].columns)\n",
+    "\n",
+    "## imput for numerical variables\n",
+    "imp_median = SimpleImputer(missing_values=np.nan, strategy='median')\n",
+    "data[num_vars] = pd.DataFrame(imp_median.fit_transform(data[num_vars]), columns=data[num_vars].columns)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Kategoriale Variablen"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E5: Reduzieren der Kardinalität"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:28.781822Z",
+     "start_time": "2020-03-17T11:19:28.769081Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## education: illiterate : basic.4y\n",
+    "data.education = np.where(\n",
+    "    data.education == 'illiterate', \n",
+    "    'basic.4y',\n",
+    "    data.education)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Nummerisiren - Faktorisieren (Platzhalter)\n",
+    "hier kein Bedarf"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "## sandbox\n",
+    "tmp_data = data.copy()\n",
+    "\n",
+    "## check before\n",
+    "print(tmp_data.job.value_counts())\n",
+    "\n",
+    "## factorize\n",
+    "tmp_data.job = pd.factorize(tmp_data.job)[0]\n",
+    "\n",
+    "## check after\n",
+    "print(tmp_data.job.value_counts())\n",
+    "\n",
+    "del(tmp_data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E6: Nummerisiren - Ordial Encodieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:28.885362Z",
+     "start_time": "2020-03-17T11:19:28.825371Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/30/93p10lq141sd2pvx31bfs77w0000gp/T/ipykernel_6176/854807168.py:33: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
+      "  data.replace(replace_nums, inplace=True)\n"
+     ]
+    }
+   ],
+   "source": [
+    "## education, day_of_week, month\n",
+    "replace_nums = {\n",
+    "    'education': {\n",
+    "        'basic.4y': 1,\n",
+    "        'basic.6y': 2,\n",
+    "        'basic.9y': 3,\n",
+    "        'professional.course': 4,\n",
+    "        'high.school': 5,\n",
+    "        'university.degree': 6\n",
+    "    },\n",
+    "    'month': {\n",
+    "        'jan': 1,\n",
+    "        'feb': 2,\n",
+    "        'mar': 3,\n",
+    "        'apr': 4,\n",
+    "        'may': 5,\n",
+    "        'jun': 6,\n",
+    "        'jul': 7,\n",
+    "        'aug': 8,\n",
+    "        'sep': 9,\n",
+    "        'oct': 10,\n",
+    "        'nov': 11,\n",
+    "        'dec': 12\n",
+    "    },\n",
+    "    'day_of_week': {\n",
+    "        'mon': 1,\n",
+    "        'tue': 2,\n",
+    "        'wed': 3,\n",
+    "        'thu': 4,\n",
+    "        'fri': 5\n",
+    "    }\n",
+    "}\n",
+    "data.replace(replace_nums, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E7: Nummerisieren - Binär Encodieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:28.820652Z",
+     "start_time": "2020-03-17T11:19:28.786046Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## housing : no -> 0 else 1\n",
+    "data.housing = np.where(data.housing == 'no', 0, 1)\n",
+    "\n",
+    "## contact : celular -> 1 else 0\n",
+    "data.contact = np.where(data.contact == 'cellular', 1, 0)\n",
+    "## rename\n",
+    "data = data.rename(columns={'contact': 'contact_cellular'})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### E8: Nummerisieren - Ordinal Encodieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## one-hot encoding\n",
+    "## apply for all categorical variables except target\n",
+    "target = 'y'\n",
+    "sel_vars = data.select_dtypes(include=['object']).columns.drop(target)\n",
+    "data = pd.get_dummies(data, columns=sel_vars, drop_first=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Numerische Variablen"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### E9: Logarithmieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:29.015675Z",
+     "start_time": "2020-03-17T11:19:28.972900Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## duration and campaign\n",
+    "data.duration = np.log10(data.duration + data.duration.min() + 1)\n",
+    "data.campaign = np.log10(data.campaign + data.campaign.min() + 1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### E10: Binär umcodieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:29.046736Z",
+     "start_time": "2020-03-17T11:19:29.023717Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## pdays : 999 -> 0, else 1\n",
+    "data.pdays = np.where(data.pdays == 999, 0, 1)\n",
+    "\n",
+    "## previous : > 0 -> 1 else 0\n",
+    "data.previous = np.where(data.previous > 0, 1, 0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Andere Tätigkeiten"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Konstruktion (Platzhalter)\n",
+    "hier kein Bedarf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### E11: Bereinigen der Variablennamen"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "old_names = data.columns\n",
+    "new_names = old_names.str.replace('[^a-zA-Z0-9_]', '_', regex=True)\n",
+    "for i in range(len(old_names)):\n",
+    "    data.rename(columns={old_names[i]:new_names[i]}, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Standardisieren (Platzhalter)\n",
+    "hier kein Bedarf"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## all except target\n",
+    "\n",
+    "## features - target - split\n",
+    "target = 'y'\n",
+    "X = data.drop(target, axis=1)\n",
+    "y = data.y\n",
+    "\n",
+    "## scale features (X)\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "scaler = StandardScaler().set_output(transform=\"pandas\")\n",
+    "X = scaler.fit_transform(X)\n",
+    "\n",
+    "## concat target to scaled features\n",
+    "new_data = pd.concat([X, y.reindex(X.index)], axis=1)\n",
+    "\n",
+    "del(new_data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "#### E12: Speichern unter neuem Namen"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T11:19:29.405659Z",
+     "start_time": "2020-03-17T11:19:29.080587Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "## as bank_data_prep.csv\n",
+    "## parameters\n",
+    "##   sep = ',' (default)\n",
+    "##   index = False (default True would add an index column on the left)\n",
+    "data.to_csv('bank_data_prep.csv', index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "1.6",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "1.6 Feature Engineering - Implementation",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "249.6px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "toc-autonumbering": true,
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

SL/aufgaben/template/2_Code/2.3 Klassifikation - Mathematische Modelle.ipynb

@@ -0,0 +1,506 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Feature Engineering\n",
+    "# Klassifikation\n",
+    "## Instanzbasierte Modelle\n",
+    "## Regelbasierte Modelle\n",
+    "## Mathematische Modelle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('./')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:39.858981Z",
+     "start_time": "2020-03-17T12:01:37.904657Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## preparation\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns; sns.set()\n",
+    "%matplotlib inline\n",
+    "\n",
+    "datapath = '../3_data'\n",
+    "from os import chdir; chdir(datapath)\n",
+    "\n",
+    "from bfh_cas_pml import prep_data, prep_demo_data\n",
+    "X_train, X_test, y_train, y_test = prep_data('bank_data_prep.csv', 'y', seed = 1234)\n",
+    "X_demo, y_demo = prep_demo_data('demo_data_class.csv', 'y')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### LinearDiscriminantAnalysis\n",
+    "#### Theorie"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "kein Code zu diesem Kapitel"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Praxis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:40.035126Z",
+     "start_time": "2020-03-17T12:01:39.864400Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.8487982963188317\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
+    "model = LinearDiscriminantAnalysis()\n",
+    "model.fit(X_train, y_train) \n",
+    "print(model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:40.051095Z",
+     "start_time": "2020-03-17T12:01:40.038394Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'covariance_estimator': None, 'n_components': None, 'priors': None, 'shrinkage': None, 'solver': 'svd', 'store_covariance': False, 'tol': 0.0001}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(model.get_params())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### QuadraticDiscriminantAnalysis (eine Variante)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:40.144808Z",
+     "start_time": "2020-03-17T12:01:40.054435Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7246729540614543\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.discriminant_analysis \\\n",
+    "    import QuadraticDiscriminantAnalysis\n",
+    "model = QuadraticDiscriminantAnalysis()\n",
+    "model.fit(X_train, y_train)\n",
+    "print(model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:40.160468Z",
+     "start_time": "2020-03-17T12:01:40.149447Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'priors': None, 'reg_param': 0.0, 'store_covariance': False, 'tol': 0.0001}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(model.get_params())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### SVC\n",
+    "#### Theorie\n",
+    "#### Praxis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:47.205171Z",
+     "start_time": "2020-03-17T12:01:40.196843Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7161545482202616\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.svm import SVC\n",
+    "model = SVC()\n",
+    "model.fit(X_train, y_train) \n",
+    "print(model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:47.221147Z",
+     "start_time": "2020-03-17T12:01:47.210935Z"
+    },
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'C': 1.0, 'break_ties': False, 'cache_size': 200, 'class_weight': None, 'coef0': 0.0, 'decision_function_shape': 'ovr', 'degree': 3, 'gamma': 'scale', 'kernel': 'rbf', 'max_iter': -1, 'probability': False, 'random_state': None, 'shrinking': True, 'tol': 0.001, 'verbose': False}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(model.get_params())"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "## with scaled features\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "scaler = StandardScaler()\n",
+    "\n",
+    "scaler.fit(X_train)\n",
+    "X_train_sc = scaler.transform(X_train)\n",
+    "X_test_sc = scaler.transform(X_test)\n",
+    "\n",
+    "model.fit(X_train_sc, y_train) \n",
+    "print(model.score(X_test_sc, y_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### GaussianNB\n",
+    "in aller Kürze"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Theorie"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "classes_ : ['A' 'B']\n",
+      "class_prior_ : [0.55555556 0.44444444]\n",
+      "\n",
+      "theta_ :\n",
+      " [[5.58666667]\n",
+      " [4.26666667]]\n",
+      "\n",
+      "var_ :\n",
+      " [[0.31182222]\n",
+      " [0.23055556]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "## demo of GaussianNB interna with demo data\n",
+    "X_nb_train = X_demo\n",
+    "y_nb_train = y_demo\n",
+    "\n",
+    "X_nb_train = X_nb_train.drop('X2', axis=1)\n",
+    "#print(X_train)\n",
+    "\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "model = GaussianNB()\n",
+    "model.fit(X_nb_train, y_nb_train)\n",
+    "\n",
+    "## print model attributes\n",
+    "print('classes_ :', model.classes_)\n",
+    "print('class_prior_ :', model.class_prior_)\n",
+    "print('\\ntheta_ :\\n', model.theta_)\n",
+    "print('\\nvar_ :\\n', model.var_)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Praxis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:47.963126Z",
+     "start_time": "2020-03-17T12:01:47.897232Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7337998174627319\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "model = GaussianNB()\n",
+    "model.fit(X_train, y_train) \n",
+    "print(model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:48.042848Z",
+     "start_time": "2020-03-17T12:01:48.032106Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'priors': None, 'var_smoothing': 1e-09}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(model.get_params())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### LogisticRegression\n",
+    "#### Theorie\n",
+    "#### Praxis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-03-17T12:01:56.666086Z",
+     "start_time": "2020-03-17T12:01:56.130695Z"
+    },
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.8475813811986614\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.linear_model import LogisticRegression\n",
+    "model = LogisticRegression(max_iter=4000)\n",
+    "model.fit(X_train, y_train) \n",
+    "print(model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "C                    : 1.0  \n",
+      "class_weight         : None \n",
+      "dual                 : False\n",
+      "fit_intercept        : True \n",
+      "intercept_scaling    : 1    \n",
+      "l1_ratio             : None \n",
+      "max_iter             : 4000 \n",
+      "multi_class          : deprecated\n",
+      "n_jobs               : None \n",
+      "penalty              : l2   \n",
+      "random_state         : None \n",
+      "solver               : lbfgs\n",
+      "tol                  : 0.0001\n",
+      "verbose              : 0    \n",
+      "warm_start           : False\n"
+     ]
+    }
+   ],
+   "source": [
+    "for key, value in model.get_params().items():\n",
+    "    print(\"%-20s : %-5s\"  % (key, value))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "teaching",
+   "language": "python",
+   "name": "teaching"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "2.3",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "2.3 Klassifikation - Mathematische Modelle",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "202.667px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "316.717px",
+    "left": "782px",
+    "right": "20px",
+    "top": "119px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

SL/aufgaben/template/2_Code/4.5 Validierung und mehr - Unbalancierte Daten.ipynb

@@ -0,0 +1,501 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Feature Engineering\n",
+    "# Klassifikation\n",
+    "# Regression\n",
+    "# Validierung und mehr\n",
+    "## Sampling und Resampling\n",
+    "## Validierungstechniken\n",
+    "## Grid Search und Random Search\n",
+    "## Performancemetriken\n",
+    "## Unbalancierte Daten\n",
+    "### Motivation und Vorbereitung "
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "## for scikit-learn 1.4.2, to silence warnings regarding physical cores\n",
+    "import os\n",
+    "os.environ['LOKY_MAX_CPU_COUNT'] = '4' ## depending on the hardware used"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-15T20:53:02.218161Z",
+     "start_time": "2020-04-15T20:53:02.079407Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## import libraries\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns; sns.set()\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:30:48.667936Z",
+     "start_time": "2020-04-14T21:30:48.420905Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "dim = (41188, 21)\n",
+      "y\n",
+      "no     0.887346\n",
+      "yes    0.112654\n",
+      "Name: proportion, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "## read and prepare data\n",
+    "datapath = '../3_data'\n",
+    "from os import chdir; chdir(datapath)\n",
+    "data = pd.read_csv('bank-additional-full.csv', sep=';')\n",
+    "print('dim =', data.shape)\n",
+    "print(data.y.value_counts(normalize=True)) ## proportion\n",
+    "\n",
+    "X_full = data.drop('y', axis=1)\n",
+    "y_full = data['y']             "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:30:48.714876Z",
+     "start_time": "2020-04-14T21:30:48.673886Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## minimal feature engineering: one hot encoding for not numerical features\n",
+    "X_full = pd.get_dummies(X_full, drop_first=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:30:48.714876Z",
+     "start_time": "2020-04-14T21:30:48.673886Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## test - train - split\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "X_full_train, X_full_test, y_full_train, y_full_test, = train_test_split(\n",
+    "    X_full,\n",
+    "    y_full,\n",
+    "    train_size=2/3,\n",
+    "    random_state=1234)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:30:53.858945Z",
+     "start_time": "2020-04-14T21:30:48.719365Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## function for evaluate different sampling methods\n",
+    "##   train a RandomForestClassifier model with train data\n",
+    "##   return\n",
+    "##     internal scorer (accuracy) for test data\n",
+    "##     proportion of classes after resampling\n",
+    "\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "def getResampledRfScore(X_train, y_train, X_test, y_test):\n",
+    "    model = RandomForestClassifier(random_state=1234)\n",
+    "    model.fit(X_train, y_train)\n",
+    "    print('score ', model.score(X_test, y_test))\n",
+    "    print(y_train.value_counts(normalize=True)) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:30:53.858945Z",
+     "start_time": "2020-04-14T21:30:48.719365Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "score  0.912163146394756\n",
+      "y\n",
+      "no     0.886773\n",
+      "yes    0.113227\n",
+      "Name: proportion, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "## test call (without resampling)\n",
+    "getResampledRfScore(X_full_train, y_full_train, X_full_test, y_full_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Random under-sampling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: imblearn in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (0.0)\n",
+      "Requirement already satisfied: imbalanced-learn in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imblearn) (0.13.0)\n",
+      "Requirement already satisfied: numpy<3,>=1.24.3 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imbalanced-learn->imblearn) (2.2.6)\n",
+      "Requirement already satisfied: scipy<2,>=1.10.1 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imbalanced-learn->imblearn) (1.15.3)\n",
+      "Requirement already satisfied: scikit-learn<2,>=1.3.2 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imbalanced-learn->imblearn) (1.6.1)\n",
+      "Requirement already satisfied: sklearn-compat<1,>=0.1 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imbalanced-learn->imblearn) (0.1.3)\n",
+      "Requirement already satisfied: joblib<2,>=1.1.1 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imbalanced-learn->imblearn) (1.5.1)\n",
+      "Requirement already satisfied: threadpoolctl<4,>=2.0.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from imbalanced-learn->imblearn) (3.6.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install imblearn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:30:55.982616Z",
+     "start_time": "2020-04-14T21:30:53.863545Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "score  0.847632920611799\n",
+      "y\n",
+      "no     0.5\n",
+      "yes    0.5\n",
+      "Name: proportion, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "from imblearn.under_sampling import RandomUnderSampler\n",
+    "rus = RandomUnderSampler(random_state=1234)\n",
+    "X_resampled_train, y_resampled_train =\\\n",
+    "    rus.fit_resample(X_full_train, y_full_train)\n",
+    "getResampledRfScore(\n",
+    "    X_resampled_train, y_resampled_train, X_full_test, y_full_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Random over-sampling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:31:04.199265Z",
+     "start_time": "2020-04-14T21:30:55.985909Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "score  0.9041514930808449\n",
+      "y\n",
+      "no     0.5\n",
+      "yes    0.5\n",
+      "Name: proportion, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "from imblearn.over_sampling import\\\n",
+    "    RandomOverSampler\n",
+    "ros = RandomOverSampler(random_state=1234)\n",
+    "X_resampled_train, y_resampled_train =\\\n",
+    "    ros.fit_resample(X_full_train, y_full_train)\n",
+    "getResampledRfScore(\n",
+    "    X_resampled_train, y_resampled_train, X_full_test, y_full_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Undersampling mit Tomek Links"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:31:11.461134Z",
+     "start_time": "2020-04-14T21:31:04.202872Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "score  0.9115076474872542\n",
+      "y\n",
+      "no     0.883063\n",
+      "yes    0.116937\n",
+      "Name: proportion, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "from imblearn.under_sampling import TomekLinks\n",
+    "tl = TomekLinks()\n",
+    "X_resampled_train, y_resampled_train = tl.fit_resample(\n",
+    "    X_full_train, y_full_train)\n",
+    "getResampledRfScore(\n",
+    "    X_resampled_train, y_resampled_train, X_full_test, y_full_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Oversampling mit SMOTE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-14T21:31:22.211925Z",
+     "start_time": "2020-04-14T21:31:11.466648Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "score  0.9038601602330663\n",
+      "y\n",
+      "no     0.5\n",
+      "yes    0.5\n",
+      "Name: proportion, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "from imblearn.over_sampling import SMOTE\n",
+    "sm = SMOTE()\n",
+    "X_resampled_train, y_resampled_train = sm.fit_resample(\n",
+    "    X_full_train, y_full_train)\n",
+    "getResampledRfScore(\n",
+    "    X_resampled_train, y_resampled_train, X_full_test, y_full_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Weights beim Trainieren"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "ref: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html\n",
+    "\n",
+    "* the formula for class_weights:\n",
+    "\n",
+    "        n_samples / (n_classes * np.bincount(y))\n",
+    "\n",
+    "* the weights of y are calculated inversely proportional to the frequencies of the present classes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.9104151493080845\n"
+     ]
+    }
+   ],
+   "source": [
+    "## with weights: balanced\n",
+    "model = RandomForestClassifier(n_estimators=100, class_weight='balanced', random_state=1234)\n",
+    "model.fit(X_full_train, y_full_train)\n",
+    "print(model.score(X_full_test, y_full_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.5638424575957945 4.415889353489868\n",
+      "0.9104151493080845\n"
+     ]
+    }
+   ],
+   "source": [
+    "## with weights: balanced: mannualy set\n",
+    "n_no = y_full_train.value_counts()['no']\n",
+    "n_yes = y_full_train.value_counts()['yes']\n",
+    "weight_no = len(y_full_train) / (2 * n_no)\n",
+    "weight_yes = len(y_full_train) / (2 * n_yes)\n",
+    "print(weight_no, weight_yes)\n",
+    "\n",
+    "model = RandomForestClassifier(\n",
+    "    n_estimators=100,\n",
+    "    class_weight={'no': weight_no,\n",
+    "                  'yes': weight_yes}, \n",
+    "    random_state=1234)\n",
+    "\n",
+    "model.fit(X_full_train, y_full_train)\n",
+    "print(model.score(X_full_test, y_full_test))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "4.5",
+   "nav_menu": {
+    "height": "189px",
+    "width": "303.333px"
+   },
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "4.5 Validierung und mehr - Unbalancierte Daten",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "291px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "toc-autonumbering": true,
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "298.85px",
+    "left": "782px",
+    "right": "20px",
+    "top": "120px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

SL/aufgaben/template/2_Code/5 Deployment und Abschluss.ipynb

@@ -0,0 +1,517 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Feature Engineering\n",
+    "# Klassifikation\n",
+    "# Regression\n",
+    "# Validierung und mehr\n",
+    "# Deployment und Abschluss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('./')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-08T10:06:24.890328Z",
+     "start_time": "2020-04-08T10:06:23.220148Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "## prepare environment\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "datapath = '../3_data'\n",
+    "from os import chdir; chdir(datapath)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Das finale Modell\n",
+    "## Feature Engineering in der Produktion\n",
+    "### Missing Values\n",
+    "### Neue Kategorien\n",
+    "### Protokollieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv('bank_data.csv', sep=';')\n",
+    "\n",
+    "import datetime\n",
+    "\n",
+    "f = open('fe_prod_log.log','w')\n",
+    "f.write(datetime.datetime.now().strftime(\"[%Y-%m-%d %H:%M:%S] (timestamp)\"))\n",
+    "\n",
+    "f.write('\\n\\n')\n",
+    "\n",
+    "s = data.isna().sum()\n",
+    "f.write('features with NA\\'s\\n')\n",
+    "f.write('=======================')\n",
+    "\n",
+    "f.write('\\n')\n",
+    "f.write(s[s > 0].to_string())\n",
+    "f.write('\\n\\n')\n",
+    "\n",
+    "## value counts of not numeric features\n",
+    "f.write('categorical cols levels\\n')\n",
+    "f.write('=======================')\n",
+    "f.write('\\n')\n",
+    "catcolnames = data.select_dtypes(include='object').columns\n",
+    "for ccn in catcolnames:\n",
+    "    f.write(ccn)\n",
+    "    f.write('\\n')\n",
+    "    f.write(data[ccn].value_counts().sort_index().to_string())\n",
+    "    f.write('\\n\\n')\n",
+    "f.close() "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Modellübergabe in die Prodkution"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Modelle speichern scikit-learn intern"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "## load data\n",
+    "from bfh_cas_pml import prep_data\n",
+    "X_train, X_test, y_train, y_test = prep_data('melb_data_prep.csv', 'Price')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## three models:\n",
+    "\n",
+    "## StandardScaler\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "model_sc = StandardScaler().fit(X_train)\n",
+    "\n",
+    "## LinearRegression\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "model_lr = LinearRegression().fit(X_train, y_train)\n",
+    "\n",
+    "## DecisionTreeRegressor\n",
+    "from sklearn.tree import DecisionTreeRegressor\n",
+    "model_dt = DecisionTreeRegressor(max_depth= 2, random_state=1234).fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## save models\n",
+    "import pickle \n",
+    "with open('model_sc.pkl', 'wb') as pickle_file:\n",
+    "    pickle.dump(model_sc, pickle_file)\n",
+    "with open('model_lr.pkl', 'wb') as pickle_file:\n",
+    "    pickle.dump(model_lr, pickle_file)\n",
+    "with open('model_dt.pkl', 'wb') as pickle_file:\n",
+    "    pickle.dump(model_dt, pickle_file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## reload models\n",
+    "with open('model_sc.pkl', 'rb') as pickle_file:\n",
+    "    model_sc_2 = pickle.load(pickle_file)\n",
+    "with open('model_lr.pkl', 'rb') as pickle_file:\n",
+    "    model_lr_2 = pickle.load(pickle_file)\n",
+    "with open('model_dt.pkl', 'rb') as pickle_file:\n",
+    "    model_dt_2 = pickle.load(pickle_file)  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ 2.93174034e+00  1.45261784e+00  1.04267493e+01  1.43475779e+00\n",
+      "  1.68210732e+00  2.36615297e+00  2.09901978e+00  1.96804559e+03\n",
+      "  5.74824662e+00 -3.78091214e+01  1.44997478e+02  7.52039447e+03\n",
+      "  6.57396836e-01  1.29098026e-01  9.18284130e-02  2.89430762e-01\n",
+      "  3.73511662e-02  3.43010928e-01  1.01125428e-02  2.10650791e-01\n",
+      "  7.15274833e+00  2.01656214e+03  4.83925950e+00] \n",
+      "\n",
+      "[9.08813135e-01 4.68436712e-01 3.68004376e+01 4.24996430e-01\n",
+      " 7.32413501e-01 7.11803450e-01 3.34340977e-02 6.45488299e+02\n",
+      " 3.80781143e+01 5.53828210e-03 9.28052881e-03 2.02869238e+07\n",
+      " 2.25226236e-01 1.12431726e-01 8.33959556e-02 2.05660596e-01\n",
+      " 3.59560566e-02 2.25354431e-01 1.00102793e-02 1.66277035e-01\n",
+      " 6.21684084e+00 2.46138222e-01 1.23097215e+00] \n",
+      "\n",
+      "[ 2.93174034e+00  1.45261784e+00  1.04267493e+01  1.43475779e+00\n",
+      "  1.68210732e+00  2.36615297e+00  2.09901978e+00  1.96804559e+03\n",
+      "  5.74824662e+00 -3.78091214e+01  1.44997478e+02  7.52039447e+03\n",
+      "  6.57396836e-01  1.29098026e-01  9.18284130e-02  2.89430762e-01\n",
+      "  3.73511662e-02  3.43010928e-01  1.01125428e-02  2.10650791e-01\n",
+      "  7.15274833e+00  2.01656214e+03  4.83925950e+00] \n",
+      "\n",
+      "[9.08813135e-01 4.68436712e-01 3.68004376e+01 4.24996430e-01\n",
+      " 7.32413501e-01 7.11803450e-01 3.34340977e-02 6.45488299e+02\n",
+      " 3.80781143e+01 5.53828210e-03 9.28052881e-03 2.02869238e+07\n",
+      " 2.25226236e-01 1.12431726e-01 8.33959556e-02 2.05660596e-01\n",
+      " 3.59560566e-02 2.25354431e-01 1.00102793e-02 1.66277035e-01\n",
+      " 6.21684084e+00 2.46138222e-01 1.23097215e+00] \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "## compare model_sc\n",
+    "print(model_sc.mean_, '\\n')\n",
+    "print(model_sc.var_, '\\n')\n",
+    "print(model_sc_2.mean_, '\\n')\n",
+    "print(model_sc_2.var_, '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-148600153.0644718\n",
+      "[ 2.38730932e+05 -1.44127046e+05 -4.11587415e+04  1.55233185e+05\n",
+      "  4.16082458e+04  8.22944764e+04  2.97716907e+05 -2.76754904e+03\n",
+      " -4.92937355e+03 -5.11115932e+05  1.79228159e+05 -1.58740210e+00\n",
+      "  7.07758671e+04  7.99854850e+03  3.38953273e+04 -1.73563804e+05\n",
+      "  1.07806729e+05  2.39261230e+05  2.81825047e+05 -2.26744902e+05\n",
+      "  1.27253408e+03  5.38476338e+04  3.83311293e+03] \n",
+      "\n",
+      "-148600153.0644718\n",
+      "[ 2.38730932e+05 -1.44127046e+05 -4.11587415e+04  1.55233185e+05\n",
+      "  4.16082458e+04  8.22944764e+04  2.97716907e+05 -2.76754904e+03\n",
+      " -4.92937355e+03 -5.11115932e+05  1.79228159e+05 -1.58740210e+00\n",
+      "  7.07758671e+04  7.99854850e+03  3.38953273e+04 -1.73563804e+05\n",
+      "  1.07806729e+05  2.39261230e+05  2.81825047e+05 -2.26744902e+05\n",
+      "  1.27253408e+03  5.38476338e+04  3.83311293e+03]\n"
+     ]
+    }
+   ],
+   "source": [
+    "## compare model_lr\n",
+    "print(model_lr.intercept_)\n",
+    "print(model_lr.coef_, '\\n')\n",
+    "print(model_lr_2.intercept_)\n",
+    "print(model_lr_2.coef_)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "|--- Rooms <= 3.50\n",
+      "|   |--- Type <= 1.50\n",
+      "|   |   |--- value: [1077045.50]\n",
+      "|   |--- Type >  1.50\n",
+      "|   |   |--- value: [682863.38]\n",
+      "|--- Rooms >  3.50\n",
+      "|   |--- Regionname_Southern_Metropolitan <= 0.50\n",
+      "|   |   |--- value: [1163850.50]\n",
+      "|   |--- Regionname_Southern_Metropolitan >  0.50\n",
+      "|   |   |--- value: [2113002.90]\n",
+      "\n",
+      "|--- Rooms <= 3.50\n",
+      "|   |--- Type <= 1.50\n",
+      "|   |   |--- value: [1077045.50]\n",
+      "|   |--- Type >  1.50\n",
+      "|   |   |--- value: [682863.38]\n",
+      "|--- Rooms >  3.50\n",
+      "|   |--- Regionname_Southern_Metropolitan <= 0.50\n",
+      "|   |   |--- value: [1163850.50]\n",
+      "|   |--- Regionname_Southern_Metropolitan >  0.50\n",
+      "|   |   |--- value: [2113002.90]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "## compare model_dt\n",
+    "from sklearn.tree import export_text\n",
+    "print(export_text(\n",
+    "    model_dt, feature_names=list(X_train.columns)))\n",
+    "print(export_text(\n",
+    "    model_dt_2, feature_names=list(X_train.columns)))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Modelle speichern extern mit PMML"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Vorbereitungen:**  \n",
+    "* Java Runtime muss vorhanden sein\n",
+    "* Library installieren direkt in Notebook:  \n",
+    "`!pip install sklearn2pmml`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: sklearn2pmml in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (0.119.1)\n",
+      "Requirement already satisfied: dill>=0.3.4 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from sklearn2pmml) (0.4.0)\n",
+      "Requirement already satisfied: joblib>=0.13.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from sklearn2pmml) (1.5.1)\n",
+      "Requirement already satisfied: pandas>=1.5.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from sklearn2pmml) (2.2.3)\n",
+      "Requirement already satisfied: scikit-learn>=1.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from sklearn2pmml) (1.6.1)\n",
+      "Requirement already satisfied: numpy>=1.26.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas>=1.5.0->sklearn2pmml) (2.2.6)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas>=1.5.0->sklearn2pmml) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas>=1.5.0->sklearn2pmml) (2025.2)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas>=1.5.0->sklearn2pmml) (2025.2)\n",
+      "Requirement already satisfied: six>=1.5 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from python-dateutil>=2.8.2->pandas>=1.5.0->sklearn2pmml) (1.17.0)\n",
+      "Requirement already satisfied: scipy>=1.6.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from scikit-learn>=1.0->sklearn2pmml) (1.15.3)\n",
+      "Requirement already satisfied: threadpoolctl>=3.1.0 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from scikit-learn>=1.0->sklearn2pmml) (3.6.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install sklearn2pmml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## import libraries\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn2pmml import PMMLPipeline, sklearn2pmml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "## StandardScaler\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "pipeline = PMMLPipeline([(\"scaler\", StandardScaler())]).fit(X_train)\n",
+    "sklearn2pmml(pipeline, \"StandardScaler_melb.pmml\", with_repr = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## LinearRegression\n",
+    "pipeline = PMMLPipeline([('regressor', LinearRegression())]).fit(X_train, y_train)\n",
+    "sklearn2pmml(pipeline, \"LinearRegression_melb.pmml\", with_repr = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## DecisionTreeClassifier\n",
+    "pipeline = PMMLPipeline([('regressor', DecisionTreeRegressor(max_depth= 2, random_state=1234))]).fit(X_train, y_train)\n",
+    "sklearn2pmml(pipeline, \"DecisionTreeRegressor_melb.pmml\", with_repr = True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "* re-import a pmml model\n",
+    "  * see https://stackoverflow.com/questions/52393301/use-pmml-models-in-python"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## !pip install pypmml\n",
+    "## not run: long running time\n",
+    "from pypmml import Model\n",
+    "new_model = Model.fromFile(\"StandardScaler_melb.pmml\")\n",
+    "result = new_model.predict(X_train)\n",
+    "print(result.describe())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Der Modellierungsprozess"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "(kein Code unter diesem Titel)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## pyCaret"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "vgl. `5.5 Deployment und Abschluss - pycaret.ipynb`"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "5",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "5 Deployment und Abschluss",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "165px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "321.85px",
+    "left": "790px",
+    "right": "20px",
+    "top": "113px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

SL/aufgaben/template/2_Code/9 Nachtraege Allgemein 20240622.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e0323bfc",
+   "metadata": {},
+   "source": [
+    "# Nachträge"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "41f6b0e4",
+   "metadata": {},
+   "source": [
+    "* dieses Dokument kann von Kurstag zu Kurstag ergänzt werden, daher sollte es jeweils ebenfalls jeweils neu heruntergeladen werden"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0fce9c83",
+   "metadata": {},
+   "source": [
+    "## Extra Themen"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7673663f",
+   "metadata": {},
+   "source": [
+    "* eine Zusammenstellung von Themen aus der Präsentation, welche **nicht** prüfungsrelevant sind, zusätzlich zu den explizit mit (i) gekennzeichneten Folien\n",
+    "* die Zusammenstellung wird fortlaufend ergänzt n.n."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "65be8be0",
+   "metadata": {},
+   "source": [
+    "|Kapitel                                                      |Folie(n)\n",
+    "|:------------------------------------------------------------|:-------\n",
+    "|**1. Feature Engineering**                                   |\n",
+    "|1.1.4.5 Begriffe - Homonyme und Synonyme                     |20-21\n",
+    "|1.2.3.1 Numerische Variablen - Quantitativ (Nachbemerkung)   |24\n",
+    "|1.2.4.5 Lineare Zusammenhänge, etc.                          |49-55"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  },
+  "toc": {
+   "base_numbering": "9",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "9 Nachträge Allgemein",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "240.667px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

SL/aufgaben/template/2_Code/bfh_cas_pml.py

@@ -0,0 +1,193 @@
+"""
+    Useful functions for example notebooks and workshop solutions
+    of course Practical Machine Learning - Supervised Learning
+    Bern University of Applied Sciences (BFH)
+"""
+
+
+# ========== Packages ==========
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+
+# ========== Functions ==========
+
+def prep_data(dataset, target, train_ratio = 2 / 3, seed = None, sep = ','):
+    """ read and prepare real data from the current directory
+    performs 
+        read data
+        features - target - split
+        train - test - split
+
+    Parameters
+    ----------
+    dataset: name of dataset in csv format
+    target: name of target column
+    train_ratio (2 / 3): (optional)
+    seed (None): random seet for split (optional)
+    sep (,): separator of csv file (optional)
+
+    Returns
+    -------
+    X_train: feature matrix of train set
+    X_test: target vector of train set
+    y_train: feature matrix of test set
+    y_test: target vector of train set
+    """
+
+    ## load data
+    data = pd.read_csv(dataset, sep = sep)
+
+    ## features - target - split
+    X = data.drop(target, axis=1)
+    y = data[target]
+
+    ## train - test - split
+    from sklearn.model_selection import train_test_split
+    return train_test_split(
+        X,
+        y,
+        train_size=train_ratio,
+        random_state=seed)
+    
+
+
+def prep_demo_data(dataset, target):
+    """ read demo data from the current directory
+    performs 
+        read data
+        features - target - split
+
+    Parameters
+    ----------
+    dataset: name of dataset in csv format, ',' separated
+    target: name of target column
+
+    Returns
+    -------
+    X: feature matrix
+    y: target vector
+    """
+
+    ## load data
+    data = pd.read_csv(dataset)
+    
+    ## features - target - split
+    X = data.drop(target, axis=1)
+    y = data[target]
+    
+    return X, y   
+
+
+
+def inspect_decision_tree_model(model_def, features, target, figsize=(6, 6)):
+    """ train a DecisionTreeClassifier and visualize the tree
+    
+    prints some motel attributes from within the function
+    
+    Parameters
+    ----------
+    model_def: DecisionTreeClassifier object with set parameters
+    features: feature matrix
+    target: target vector
+    figsize: size of image, optional, default = (6, 6)
+    
+    Returns
+    -------
+    visualization of the trained tree
+    prints model attributes
+    """
+    
+    from sklearn.tree import plot_tree
+    
+    model = model_def
+    model.fit(features, target)
+
+    print('TREE DIAGNOSTICS:')
+    print('depth  :', model.get_depth())
+    print('leaves :', model.get_n_leaves())
+    print('score  :', model.score(features, target))
+
+    plt.figure(figsize=figsize)
+    plot_tree(model,
+              feature_names=features.columns,
+              class_names=model.classes_,
+              filled=True);
+
+
+
+def test_regression_model(model, X_train, y_train, X_test, y_test, show_plot=True):
+    
+    """ shows behavoiur of univariate ML regression on synthetic dataset
+    
+    performs
+    -   training on train data
+    -   prediction on test data
+    -   calculate performance measures
+ 
+    Parameters
+    ----------
+    model: a parametrized regression model
+    X_train, y_train: train data
+    X_test, y_test: test data
+    show_plot: show scatterplot ov pred vs true, optional, default=True
+    
+
+    Returns
+    -------
+    shows a scatterplot von X_test vs X_pred with a diagonal line, indicating identity
+    prints r2_score and mean_squared_error
+    
+    """
+
+    from sklearn.metrics import r2_score
+    from sklearn.metrics import mean_squared_error
+
+    model = model
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+    print('R2 = %0.4f' %(r2_score(y_test, y_pred)))
+    
+    if show_plot == True:
+        plt.figure(figsize=(6,6))
+        ax = sns.scatterplot(x=y_test, y=y_pred)
+        ax.set(xlabel='y_test', ylabel='y_pred')
+        ls = np.linspace(min(y_test), max(y_test), 100)
+        plt.plot(ls, ls, color='black', linestyle='dashed')
+        ax.set_title(model.__class__.__name__)
+        plt.show()
+    
+    return (model)
+    
+
+
+def show_pred_on_synth(model, X, y, X_synth, param_str):
+    """ shows behavoiur of univariate ML regression on synthetic dataset
+ 
+    Parameters
+    ----------
+    model: a parametrized regression model
+    X, y: data for univariate regression
+    X_synth: synthetic Feature
+    param_str: parameter description for title
+    seed (None): random seet for split
+
+    Returns
+    -------
+    a scatterplot von X, y, with the prediction values for X_synth
+    
+    """
+    
+    model.fit(X.to_numpy(), y)
+    y_pred = model.predict(X_synth)
+
+    ax = sns.scatterplot(x=X['X'], y=y)
+    ax = sns.lineplot(x=X_synth[:,0], y=y_pred, color='orange')
+    ax.set_title(model.__class__.__name__ + ' : ' + param_str)
+    ax.set(xlabel='X', ylabel='y')
+    plt.show()
+
+

SL/aufgaben/template/2_Code/extra_3.2.1.4_linear_regression_in_data_analytics.ipynb

@@ -0,0 +1,178 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6394031a-f4e6-40b6-8612-9dbcea9cc456",
+   "metadata": {},
+   "source": [
+    "# extra_3.2.1.4_linear_regression_in_data_analytics.ipynb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9be95ca5-b3d6-4e6f-9ca6-9d84b1bf726e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('./')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "23f2b845-764a-46f4-8a51-e1787c05b878",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-08T10:06:24.890328Z",
+     "start_time": "2020-04-08T10:06:23.220148Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## prepare env and data\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns; sns.set()\n",
+    "%matplotlib inline\n",
+    "\n",
+    "datapath = '../3_data'\n",
+    "from os import chdir; chdir(datapath)\n",
+    "\n",
+    "from bfh_cas_pml import prep_data\n",
+    "X_train, X_test, y_train, y_test = prep_data('melb_data_prep.csv', 'Price', seed = 1234)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "27dd0331-0bdf-43d2-8dcd-29b54ff147e9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting statsmodels\n",
+      "  Downloading statsmodels-0.14.4-cp313-cp313-macosx_11_0_arm64.whl.metadata (9.2 kB)\n",
+      "Requirement already satisfied: numpy<3,>=1.22.3 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from statsmodels) (2.2.6)\n",
+      "Requirement already satisfied: scipy!=1.9.2,>=1.8 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from statsmodels) (1.15.3)\n",
+      "Requirement already satisfied: pandas!=2.1.0,>=1.4 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from statsmodels) (2.2.3)\n",
+      "Collecting patsy>=0.5.6 (from statsmodels)\n",
+      "  Downloading patsy-1.0.1-py2.py3-none-any.whl.metadata (3.3 kB)\n",
+      "Requirement already satisfied: packaging>=21.3 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from statsmodels) (25.0)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas!=2.1.0,>=1.4->statsmodels) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas!=2.1.0,>=1.4->statsmodels) (2025.2)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from pandas!=2.1.0,>=1.4->statsmodels) (2025.2)\n",
+      "Requirement already satisfied: six>=1.5 in /Users/vgv1/.pyenv/versions/teaching/lib/python3.13/site-packages (from python-dateutil>=2.8.2->pandas!=2.1.0,>=1.4->statsmodels) (1.17.0)\n",
+      "Downloading statsmodels-0.14.4-cp313-cp313-macosx_11_0_arm64.whl (9.9 MB)\n",
+      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.9/9.9 MB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading patsy-1.0.1-py2.py3-none-any.whl (232 kB)\n",
+      "Installing collected packages: patsy, statsmodels\n",
+      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2/2\u001b[0m [statsmodels]\u001b[0m [statsmodels]\n",
+      "\u001b[1A\u001b[2KSuccessfully installed patsy-1.0.1 statsmodels-0.14.4\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install statsmodels"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c6ce688e-aea0-4030-afe7-1dbf56b03ea1",
+   "metadata": {
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                            OLS Regression Results                            \n",
+      "==============================================================================\n",
+      "Dep. Variable:                  Price   R-squared:                       0.586\n",
+      "Model:                            OLS   Adj. R-squared:                  0.585\n",
+      "Method:                 Least Squares   F-statistic:                     752.8\n",
+      "Date:                Sat, 21 Jun 2025   Prob (F-statistic):               0.00\n",
+      "Time:                        22:34:27   Log-Likelihood:            -1.7592e+05\n",
+      "No. Observations:               12262   AIC:                         3.519e+05\n",
+      "Df Residuals:                   12238   BIC:                         3.521e+05\n",
+      "Df Model:                          23                                         \n",
+      "Covariance Type:            nonrobust                                         \n",
+      "=========================================================================================================\n",
+      "                                            coef    std err          t      P>|t|      [0.025      0.975]\n",
+      "---------------------------------------------------------------------------------------------------------\n",
+      "const                                 -1.055e+08   1.99e+07     -5.300      0.000   -1.45e+08   -6.65e+07\n",
+      "Rooms                                  2.454e+05   5402.990     45.416      0.000    2.35e+05    2.56e+05\n",
+      "Type                                  -1.414e+05   6342.919    -22.286      0.000   -1.54e+05   -1.29e+05\n",
+      "Distance                              -4.038e+04    928.303    -43.503      0.000   -4.22e+04   -3.86e+04\n",
+      "Bathroom                               1.613e+05   7004.805     23.032      0.000    1.48e+05    1.75e+05\n",
+      "Car                                    4.039e+04   4723.191      8.552      0.000    3.11e+04    4.96e+04\n",
+      "logLandsize                             8.33e+04   5149.484     16.177      0.000    7.32e+04    9.34e+04\n",
+      "logBuildingArea                        2.738e+05   2.27e+04     12.064      0.000    2.29e+05    3.18e+05\n",
+      "YearBuilt                             -2484.2291    162.873    -15.253      0.000   -2803.486   -2164.972\n",
+      "CouncilArea                           -4977.2245    674.748     -7.376      0.000   -6299.838   -3654.611\n",
+      "Lattitude                              -5.15e+05   7.24e+04     -7.114      0.000   -6.57e+05   -3.73e+05\n",
+      "Longtitude                             1.926e+05   5.94e+04      3.241      0.001    7.61e+04    3.09e+05\n",
+      "Propertycount                            -1.1982      0.893     -1.342      0.180      -2.948       0.552\n",
+      "Method_S                               9.427e+04   1.17e+04      8.065      0.000    7.14e+04    1.17e+05\n",
+      "Method_SP                              4.166e+04   1.51e+04      2.760      0.006    1.21e+04    7.13e+04\n",
+      "Method_VB                              5.418e+04   1.63e+04      3.315      0.001    2.21e+04    8.62e+04\n",
+      "Regionname_Northern_Metropolitan       -1.85e+05   1.62e+04    -11.404      0.000   -2.17e+05   -1.53e+05\n",
+      "Regionname_South_Eastern_Metropolitan  8.791e+04   2.69e+04      3.269      0.001    3.52e+04    1.41e+05\n",
+      "Regionname_Southern_Metropolitan        2.44e+05   1.54e+04     15.820      0.000    2.14e+05    2.74e+05\n",
+      "Regionname_Victoria                    2.656e+05   4.46e+04      5.954      0.000    1.78e+05    3.53e+05\n",
+      "Regionname_Western_Metropolitan       -2.317e+05   1.93e+04    -12.030      0.000   -2.69e+05   -1.94e+05\n",
+      "month                                  1756.1890   1674.442      1.049      0.294   -1525.982    5038.360\n",
+      "year                                   3.116e+04   8889.372      3.505      0.000    1.37e+04    4.86e+04\n",
+      "day_of_week                            4708.3047   3427.552      1.374      0.170   -2010.239    1.14e+04\n",
+      "==============================================================================\n",
+      "Omnibus:                     6530.672   Durbin-Watson:                   2.000\n",
+      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):            95692.398\n",
+      "Skew:                           2.225   Prob(JB):                         0.00\n",
+      "Kurtosis:                      15.942   Cond. No.                     4.86e+07\n",
+      "==============================================================================\n",
+      "\n",
+      "Notes:\n",
+      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+      "[2] The condition number is large, 4.86e+07. This might indicate that there are\n",
+      "strong multicollinearity or other numerical problems.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import statsmodels.api as sm\n",
+    "X_train_ = sm.add_constant(X_train)\n",
+    "model = sm.OLS(y_train, X_train_, hasconst=True)\n",
+    "results = model.fit()\n",
+    "print(results.summary())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

SL/aufgaben/template/2_Code/extra_3.3.4_weitere_ensemble_regressoren.ipynb

@@ -0,0 +1,341 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# extra_3.3.4_weitere_ensemble_regressoren.ipynb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('./')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "## for scikit-learn 1.4.2, to silence warnings regarding physical cores\n",
+    "import os\n",
+    "os.environ['LOKY_MAX_CPU_COUNT'] = '4' ## depending on the hardware used"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-08T10:06:24.890328Z",
+     "start_time": "2020-04-08T10:06:23.220148Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## prepare environment and data\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns; sns.set()\n",
+    "%matplotlib inline\n",
+    "\n",
+    "datapath = '../3_data'\n",
+    "from os import chdir; chdir(datapath)\n",
+    "\n",
+    "from bfh_cas_pml import prep_data, prep_demo_data\n",
+    "X_train, X_test, y_train, y_test = prep_data('melb_data_prep.csv', 'Price', seed = 1234)\n",
+    "\n",
+    "from bfh_cas_pml import test_regression_model\n",
+    "\n",
+    "names = []\n",
+    "scores = []"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**AdaBoostRegressor**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-08T10:06:45.098899Z",
+     "start_time": "2020-04-08T10:06:44.257283Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "R2 = -0.3023\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import AdaBoostRegressor\n",
+    "this_model = test_regression_model(\n",
+    "    AdaBoostRegressor(random_state=1234), \n",
+    "    X_train, y_train, X_test, y_test,\n",
+    "    show_plot=False)\n",
+    "names.append(this_model.__class__.__name__)\n",
+    "scores.append(this_model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**GradientBoostingRegressor**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-08T10:06:45.952822Z",
+     "start_time": "2020-04-08T10:06:45.101810Z"
+    },
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "R2 = 0.7250\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import GradientBoostingRegressor\n",
+    "this_model = test_regression_model(\n",
+    "    GradientBoostingRegressor(random_state=1234), \n",
+    "    X_train, y_train, X_test, y_test,\n",
+    "    show_plot=False)\n",
+    "names.append(this_model.__class__.__name__)\n",
+    "scores.append(this_model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**HistGradientBoostingRegressor**\n",
+    "\n",
+    "\"This estimator is much faster than GradientBoostingRegressor for big datasets (n_samples >= 10 000).\" [https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.HistGradientBoostingRegressor.html#sklearn.ensemble.HistGradientBoostingRegressor]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-04-08T10:06:48.544788Z",
+     "start_time": "2020-04-08T10:06:45.955387Z"
+    },
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "R2 = 0.7846\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import HistGradientBoostingRegressor\n",
+    "this_model = test_regression_model(\n",
+    "    HistGradientBoostingRegressor(), \n",
+    "    X_train, y_train, X_test, y_test,\n",
+    "    show_plot=False)\n",
+    "names.append(this_model.__class__.__name__)\n",
+    "scores.append(this_model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**CatBoostRegressor**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "R2 = 0.8003\n"
+     ]
+    }
+   ],
+   "source": [
+    "from catboost import CatBoostRegressor\n",
+    "this_model = test_regression_model(\n",
+    "    CatBoostRegressor(logging_level='Silent'), \n",
+    "    X_train, y_train, X_test, y_test,\n",
+    "    show_plot=False)\n",
+    "names.append(this_model.__class__.__name__)\n",
+    "scores.append(this_model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**LGBMRegressor**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000113 seconds.\n",
+      "You can set `force_row_wise=true` to remove the overhead.\n",
+      "And if memory is not enough, you can set `force_col_wise=true`.\n",
+      "[LightGBM] [Info] Total Bins 1630\n",
+      "[LightGBM] [Info] Number of data points in the train set: 12262, number of used features: 23\n",
+      "[LightGBM] [Info] Start training from score 1055902.695237\n",
+      "R2 = 0.7882\n"
+     ]
+    }
+   ],
+   "source": [
+    "from lightgbm import LGBMRegressor\n",
+    "this_model = test_regression_model(\n",
+    "    LGBMRegressor(), \n",
+    "    X_train, y_train, X_test, y_test,\n",
+    "    show_plot=False)\n",
+    "names.append(this_model.__class__.__name__)\n",
+    "scores.append(this_model.score(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                          models    scores\n",
+      "0              AdaBoostRegressor -0.302314\n",
+      "1      GradientBoostingRegressor  0.724983\n",
+      "2  HistGradientBoostingRegressor  0.784615\n",
+      "3              CatBoostRegressor  0.800349\n",
+      "4                  LGBMRegressor  0.788166\n"
+     ]
+    }
+   ],
+   "source": [
+    "## synthesis\n",
+    "print(pd.DataFrame({'models': names, 'scores': scores}))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  },
+  "toc": {
+   "base_numbering": "3.3",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "3.3 Regression - ML Methoden",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "186.867px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "toc-autonumbering": true,
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "321.85px",
+    "left": "787px",
+    "right": "20px",
+    "top": "115px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

SL/aufgaben/template/3_data/DecisionTreeRegressor_melb.pmml

@@ -0,0 +1,47 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PMML xmlns="http://www.dmg.org/PMML-4_4" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.4">
+	<Header>
+		<Application name="SkLearn2PMML package" version="0.119.1"/>
+		<Timestamp>2025-06-21T20:20:46Z</Timestamp>
+	</Header>
+	<MiningBuildTask>
+		<Extension name="repr">PMMLPipeline(steps=[('regressor', DecisionTreeRegressor(max_depth=2, random_state=1234))])</Extension>
+	</MiningBuildTask>
+	<DataDictionary>
+		<DataField name="Price" optype="continuous" dataType="double"/>
+		<DataField name="Rooms" optype="continuous" dataType="float"/>
+		<DataField name="Type" optype="continuous" dataType="float"/>
+		<DataField name="Regionname_Southern_Metropolitan" optype="continuous" dataType="float"/>
+	</DataDictionary>
+	<TreeModel functionName="regression" algorithmName="sklearn.tree._classes.DecisionTreeRegressor" missingValueStrategy="nullPrediction" noTrueChildStrategy="returnLastPrediction">
+		<MiningSchema>
+			<MiningField name="Price" usageType="target"/>
+			<MiningField name="Rooms"/>
+			<MiningField name="Type"/>
+			<MiningField name="Regionname_Southern_Metropolitan"/>
+		</MiningSchema>
+		<LocalTransformations>
+			<DerivedField name="double(Rooms)" optype="continuous" dataType="double">
+				<FieldRef field="Rooms"/>
+			</DerivedField>
+			<DerivedField name="double(Type)" optype="continuous" dataType="double">
+				<FieldRef field="Type"/>
+			</DerivedField>
+			<DerivedField name="double(Regionname_Southern_Metropolitan)" optype="continuous" dataType="double">
+				<FieldRef field="Regionname_Southern_Metropolitan"/>
+			</DerivedField>
+		</LocalTransformations>
+		<Node score="2113002.898989899">
+			<True/>
+			<Node score="682863.3751581077">
+				<SimplePredicate field="double(Rooms)" operator="lessOrEqual" value="3.5"/>
+				<Node score="1077045.4976463942">
+					<SimplePredicate field="double(Type)" operator="lessOrEqual" value="1.5"/>
+				</Node>
+			</Node>
+			<Node score="1163850.4992142483">
+				<SimplePredicate field="double(Regionname_Southern_Metropolitan)" operator="lessOrEqual" value="0.5"/>
+			</Node>
+		</Node>
+	</TreeModel>
+</PMML>

SL/aufgaben/template/3_data/LinearRegression_melb.pmml

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PMML xmlns="http://www.dmg.org/PMML-4_4" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.4">
+	<Header>
+		<Application name="SkLearn2PMML package" version="0.119.1"/>
+		<Timestamp>2025-06-21T20:20:46Z</Timestamp>
+	</Header>
+	<MiningBuildTask>
+		<Extension name="repr">PMMLPipeline(steps=[('regressor', LinearRegression())])</Extension>
+	</MiningBuildTask>
+	<DataDictionary>
+		<DataField name="Price" optype="continuous" dataType="double"/>
+		<DataField name="Rooms" optype="continuous" dataType="double"/>
+		<DataField name="Type" optype="continuous" dataType="double"/>
+		<DataField name="Distance" optype="continuous" dataType="double"/>
+		<DataField name="Bathroom" optype="continuous" dataType="double"/>
+		<DataField name="Car" optype="continuous" dataType="double"/>
+		<DataField name="logLandsize" optype="continuous" dataType="double"/>
+		<DataField name="logBuildingArea" optype="continuous" dataType="double"/>
+		<DataField name="YearBuilt" optype="continuous" dataType="double"/>
+		<DataField name="CouncilArea" optype="continuous" dataType="double"/>
+		<DataField name="Lattitude" optype="continuous" dataType="double"/>
+		<DataField name="Longtitude" optype="continuous" dataType="double"/>
+		<DataField name="Propertycount" optype="continuous" dataType="double"/>
+		<DataField name="Method_S" optype="continuous" dataType="double"/>
+		<DataField name="Method_SP" optype="continuous" dataType="double"/>
+		<DataField name="Method_VB" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Northern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_South_Eastern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Southern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Victoria" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Western_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="month" optype="continuous" dataType="double"/>
+		<DataField name="year" optype="continuous" dataType="double"/>
+		<DataField name="day_of_week" optype="continuous" dataType="double"/>
+	</DataDictionary>
+	<RegressionModel functionName="regression" algorithmName="sklearn.linear_model._base.LinearRegression">
+		<MiningSchema>
+			<MiningField name="Price" usageType="target"/>
+			<MiningField name="Rooms"/>
+			<MiningField name="Type"/>
+			<MiningField name="Distance"/>
+			<MiningField name="Bathroom"/>
+			<MiningField name="Car"/>
+			<MiningField name="logLandsize"/>
+			<MiningField name="logBuildingArea"/>
+			<MiningField name="YearBuilt"/>
+			<MiningField name="CouncilArea"/>
+			<MiningField name="Lattitude"/>
+			<MiningField name="Longtitude"/>
+			<MiningField name="Propertycount"/>
+			<MiningField name="Method_S"/>
+			<MiningField name="Method_SP"/>
+			<MiningField name="Method_VB"/>
+			<MiningField name="Regionname_Northern_Metropolitan"/>
+			<MiningField name="Regionname_South_Eastern_Metropolitan"/>
+			<MiningField name="Regionname_Southern_Metropolitan"/>
+			<MiningField name="Regionname_Victoria"/>
+			<MiningField name="Regionname_Western_Metropolitan"/>
+			<MiningField name="month"/>
+			<MiningField name="year"/>
+			<MiningField name="day_of_week"/>
+		</MiningSchema>
+		<RegressionTable intercept="-1.486001530644718E8">
+			<NumericPredictor name="Rooms" coefficient="238730.9316843776"/>
+			<NumericPredictor name="Type" coefficient="-144127.0462703874"/>
+			<NumericPredictor name="Distance" coefficient="-41158.74149442419"/>
+			<NumericPredictor name="Bathroom" coefficient="155233.18486695606"/>
+			<NumericPredictor name="Car" coefficient="41608.24584805156"/>
+			<NumericPredictor name="logLandsize" coefficient="82294.47642306813"/>
+			<NumericPredictor name="logBuildingArea" coefficient="297716.9070603722"/>
+			<NumericPredictor name="YearBuilt" coefficient="-2767.549042441214"/>
+			<NumericPredictor name="CouncilArea" coefficient="-4929.3735515952385"/>
+			<NumericPredictor name="Lattitude" coefficient="-511115.932452351"/>
+			<NumericPredictor name="Longtitude" coefficient="179228.15909129355"/>
+			<NumericPredictor name="Propertycount" coefficient="-1.5874021046959097"/>
+			<NumericPredictor name="Method_S" coefficient="70775.86711001841"/>
+			<NumericPredictor name="Method_SP" coefficient="7998.548503785693"/>
+			<NumericPredictor name="Method_VB" coefficient="33895.327337749855"/>
+			<NumericPredictor name="Regionname_Northern_Metropolitan" coefficient="-173563.80389381657"/>
+			<NumericPredictor name="Regionname_South_Eastern_Metropolitan" coefficient="107806.72896395726"/>
+			<NumericPredictor name="Regionname_Southern_Metropolitan" coefficient="239261.2304157773"/>
+			<NumericPredictor name="Regionname_Victoria" coefficient="281825.04678020324"/>
+			<NumericPredictor name="Regionname_Western_Metropolitan" coefficient="-226744.90218339747"/>
+			<NumericPredictor name="month" coefficient="1272.5340782417852"/>
+			<NumericPredictor name="year" coefficient="53847.63382995822"/>
+			<NumericPredictor name="day_of_week" coefficient="3833.1129349071543"/>
+		</RegressionTable>
+	</RegressionModel>
+</PMML>

SL/aufgaben/template/3_data/StandardScaler_melb.pmml

@@ -0,0 +1,244 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PMML xmlns="http://www.dmg.org/PMML-4_4" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.4">
+	<Header>
+		<Application name="SkLearn2PMML package" version="0.119.1"/>
+		<Timestamp>2025-06-21T20:20:45Z</Timestamp>
+	</Header>
+	<MiningBuildTask>
+		<Extension name="repr">PMMLPipeline(steps=[('scaler', StandardScaler())])</Extension>
+	</MiningBuildTask>
+	<DataDictionary>
+		<DataField name="Rooms" optype="continuous" dataType="double"/>
+		<DataField name="Type" optype="continuous" dataType="double"/>
+		<DataField name="Distance" optype="continuous" dataType="double"/>
+		<DataField name="Bathroom" optype="continuous" dataType="double"/>
+		<DataField name="Car" optype="continuous" dataType="double"/>
+		<DataField name="logLandsize" optype="continuous" dataType="double"/>
+		<DataField name="logBuildingArea" optype="continuous" dataType="double"/>
+		<DataField name="YearBuilt" optype="continuous" dataType="double"/>
+		<DataField name="CouncilArea" optype="continuous" dataType="double"/>
+		<DataField name="Lattitude" optype="continuous" dataType="double"/>
+		<DataField name="Longtitude" optype="continuous" dataType="double"/>
+		<DataField name="Propertycount" optype="continuous" dataType="double"/>
+		<DataField name="Method_S" optype="continuous" dataType="double"/>
+		<DataField name="Method_SP" optype="continuous" dataType="double"/>
+		<DataField name="Method_VB" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Northern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_South_Eastern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Southern_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Victoria" optype="continuous" dataType="double"/>
+		<DataField name="Regionname_Western_Metropolitan" optype="continuous" dataType="double"/>
+		<DataField name="month" optype="continuous" dataType="double"/>
+		<DataField name="year" optype="continuous" dataType="double"/>
+		<DataField name="day_of_week" optype="continuous" dataType="double"/>
+	</DataDictionary>
+	<TransformationDictionary>
+		<DerivedField name="standardScaler(Rooms)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Rooms"/>
+					<Constant dataType="double">2.9317403359973904</Constant>
+				</Apply>
+				<Constant dataType="double">0.9533169121486135</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Type)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Type"/>
+					<Constant dataType="double">1.4526178437449029</Constant>
+				</Apply>
+				<Constant dataType="double">0.6844243657125287</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Distance)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Distance"/>
+					<Constant dataType="double">10.426749306801499</Constant>
+				</Apply>
+				<Constant dataType="double">6.066336425774425</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Bathroom)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Bathroom"/>
+					<Constant dataType="double">1.434757788289023</Constant>
+				</Apply>
+				<Constant dataType="double">0.6519175028229948</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Car)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Car"/>
+					<Constant dataType="double">1.6821073234382646</Constant>
+				</Apply>
+				<Constant dataType="double">0.8558116035647958</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(logLandsize)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="logLandsize"/>
+					<Constant dataType="double">2.3661529658260885</Constant>
+				</Apply>
+				<Constant dataType="double">0.84368444941179</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(logBuildingArea)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="logBuildingArea"/>
+					<Constant dataType="double">2.0990197773631265</Constant>
+				</Apply>
+				<Constant dataType="double">0.18284993213113399</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(YearBuilt)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="YearBuilt"/>
+					<Constant dataType="double">1968.0455879954332</Constant>
+				</Apply>
+				<Constant dataType="double">25.406461747131278</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(CouncilArea)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="CouncilArea"/>
+					<Constant dataType="double">5.748246615560268</Constant>
+				</Apply>
+				<Constant dataType="double">6.170746654990085</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Lattitude)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Lattitude"/>
+					<Constant dataType="double">-37.80912136193117</Constant>
+				</Apply>
+				<Constant dataType="double">0.07441963519407027</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Longtitude)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Longtitude"/>
+					<Constant dataType="double">144.99747812591744</Constant>
+				</Apply>
+				<Constant dataType="double">0.09633550128190778</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Propertycount)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Propertycount"/>
+					<Constant dataType="double">7520.394470722557</Constant>
+				</Apply>
+				<Constant dataType="double">4504.100770431253</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Method_S)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Method_S"/>
+					<Constant dataType="double">0.657396835752732</Constant>
+				</Apply>
+				<Constant dataType="double">0.4745800628924771</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Method_SP)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Method_SP"/>
+					<Constant dataType="double">0.12909802642309573</Constant>
+				</Apply>
+				<Constant dataType="double">0.3353084043037952</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Method_VB)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Method_VB"/>
+					<Constant dataType="double">0.09182841298320013</Constant>
+				</Apply>
+				<Constant dataType="double">0.2887835790902713</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Northern_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Northern_Metropolitan"/>
+					<Constant dataType="double">0.2894307617028217</Constant>
+				</Apply>
+				<Constant dataType="double">0.4534981762730101</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_South_Eastern_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_South_Eastern_Metropolitan"/>
+					<Constant dataType="double">0.03735116620453433</Constant>
+				</Apply>
+				<Constant dataType="double">0.18962082319116638</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Southern_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Southern_Metropolitan"/>
+					<Constant dataType="double">0.3430109280704616</Constant>
+				</Apply>
+				<Constant dataType="double">0.4747151053997568</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Victoria)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Victoria"/>
+					<Constant dataType="double">0.010112542815201435</Constant>
+				</Apply>
+				<Constant dataType="double">0.10005138326386172</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(Regionname_Western_Metropolitan)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="Regionname_Western_Metropolitan"/>
+					<Constant dataType="double">0.210650791061817</Constant>
+				</Apply>
+				<Constant dataType="double">0.40777081220564054</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(month)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="month"/>
+					<Constant dataType="double">7.152748328168325</Constant>
+				</Apply>
+				<Constant dataType="double">2.493359348369748</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(year)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="year"/>
+					<Constant dataType="double">2016.5621432066548</Constant>
+				</Apply>
+				<Constant dataType="double">0.49612319222817086</Constant>
+			</Apply>
+		</DerivedField>
+		<DerivedField name="standardScaler(day_of_week)" optype="continuous" dataType="double">
+			<Apply function="/">
+				<Apply function="-">
+					<FieldRef field="day_of_week"/>
+					<Constant dataType="double">4.8392595008970805</Constant>
+				</Apply>
+				<Constant dataType="double">1.1094918421491333</Constant>
+			</Apply>
+		</DerivedField>
+	</TransformationDictionary>
+</PMML>

SL/aufgaben/template/3_data/catboost_info/learn_error.tsv

@@ -0,0 +1,845 @@
+iter	Logloss
+0	0.6715355719
+1	0.6500104902	2	0.628337545333	0.60966944	044	0.59078205	055	0.57752576	0.6	0.55778077	077	0.54203558	8	8	0.52958589	9	9	0.51714610	1110	0.50423311	11	0.4929307812	12	0.4814072133
+13	0.4713296171
+14	0.4618167061
+15	0.452625197
+16	0.4442922771717	0.4361589191818	0.4279240561919	0.4218459572020	0.4151507422121	0.409436976222	0.4037422555223	0.3976515008224	0.3923734357225	25	0.389420826	026	0.383436327	027	0.378636828	0.3794535398
+29	0.3757155885
+30	0.3717786395
+31	0.3691171784
+32	0.3657305059
+33	0.3632016139
+34	0.3602285367
+35	0.3563286411
+36	0.3536211155
+37	0.3504242069
+38	0.3484263966
+39	0.3458929487
+40	0.3438820826
+41	0.3420411561
+42	0.3396861143
+43	0.3381319584
+44	0.3363482476
+45	0.3345493897
+46	0.3330299771
+47	0.3318525724
+48	0.3309013752
+49	0.3298096059
+50	0.3284301698
+51	0.3269025361
+52	0.3248681668
+53	0.3235173677
+54	0.32236862
+55	0.3215182991
+56	0.3204347043
+57	0.318931893
+58	0.3175421302
+59	0.3165771979
+60	0.3156489037
+61	0.3144519398
+62	0.3136613844
+63	0.3128673057
+64	0.312212034
+65	0.3114018298
+66	0.3106629251
+67	0.310034156
+68	0.3092989124
+69	0.3088944431
+70	0.3081516939
+71	0.3075363379
+72	0.3067525669
+73	0.3056937007
+74	0.3046441095
+75	0.3034415851
+76	076	0.295545077	077	0.29487978	0.78	0.29434479	0.79	0.2939280	0.380	0.293281	0.2981	0.292782	0.2982	0.29283	0.29883	0.29184	0.2976595593
+85	0.29785	0.2986	0.2967502188
+87	0.2962570112
+88	0.2958939803
+89	0.2955636397
+90	0.2949822244
+91	0.29491	0.28792	0.29492	0.28793	0.2933773115
+94	0.2929786319
+95	0.2927127209
+96	0.2923617196
+97	0.2920127162
+98	0.2917110356
+99	0.2913174166
+100	0.2909765376
+101	0.2906426256
+102	0.2902903937
+103	0.289738585
+104	0.2893907106
+105	0.2890596207
+106	0.288792732
+107	0.288534817
+108	0.2882073116
+109	0.2876705255
+110	0.2873647727
+111	0.2871375052
+112	0.2867474887
+113	0.2864232213
+114	0.2860121057
+115	0.2856438106
+116	0.2854464634
+117	0.2851231367
+118	0.2847282285
+119	0.2844702651
+120	0.2842679116
+121	0.2839106114
+122	0.2837456336
+123	0.2834910124
+124	0.2832364481
+125	0.2831050547
+126	0.2828182024
+127	0.2825989469
+128	0.2823589042
+129	0.2820757526
+130	0.2816758823
+131	0.2814171024
+132	0.2809784086
+133	0.2807750643
+134	0.2802622838
+135	0.2801679472
+136	0.2799283915
+137	0.2797753843
+138	0.2795553411
+139	0.2790582386
+140	0.2787916767
+141	0.2784819034
+142	0.2781899858
+143	0.2777745463
+144	0.2774850792
+145	0.2771480654
+146	0.2770049212
+147	0.2768221416
+148	0.276566122
+149	0.2764094158
+150	0.2762456947
+151	0.2759876734
+152	0.2755418589
+153	0.2753300818
+154	0.2751304602
+155	0.2749359612
+156	0.2748264315
+157	0.2745800918
+158	0.2742472939
+159	0.2740881719
+160	0.2738565523
+161	0.273609089
+162	0.2734032283
+163	0.2732939985
+164	0.27164	0.271165	0.27165	0.271166	0.27166	0.270167	0.27167	0.270168	0.27168	0.270169	0.27169	0.270170	0.27170	0.269171	0.27171	0.269172	0.27172	0.269173	0.2173	0.269174	0.27174	0.269175	0.2175	0.2690176	0.2176	0.2687177	0.2177	0.2685178	0.2178	0.2684179	0.2179	0.2680180	0180	0.267876181	0181	0.267755182	0182	0.267473183	0183	0.267351184	0184	0.267194185	0185	0.26700186	0186	0.26687187	0.187	0.26670188	0.188	0.2664957386
+189	0.266362267
+190	0.2661136479
+191	0.2658698416
+192	0.2657868936
+193	0.265665353
+194	0.2653983404
+195	0.2652371509
+196	0.2651063849
+197	0.264913291
+198	0.2647556863
+199	0.2645733951
+200	0.264427887
+201	0.2642523528
+202	0.2641045862
+203	0.2639229314
+204	0.2637726889
+205	0.2635740419
+206	0.26334242720207	0.26314082920208	0.263003622209	0.2628850388
+210	0.2627407842
+211	0.2626431306
+212	0.2624728347
+213	0.2622310925
+214	0.2620532664
+215	0.2618205654
+216	0.2616589509
+217	0.2614757645
+218	0.2612767208
+219	0.26086677522220	0.2607452221	221	0.2606090222222	0.2604421223	223	0.2603288224	224	0.2601877225	225	0.2600486226226	0.25989308227227	0.25975458228228	0.25941261229229	0.25930457230230	0.2591708023231	0.25908766323232	0.2589107169
+233	0.258706153
+234	0.2584906816
+235	0.2583584315
+236	0.2581589555
+237	0.257929247
+238	0.2578443862
+239	0.2576799959
+240	0.2574729962
+241	0.2573334764
+242	0.2572371053
+243	0.25706023824244	0.2569646905
+245	0.2568318486
+246	0.256676895
+247	0.2565448555
+248	0.2563555465
+249	0.25619328
+250	0.2560606951
+251	0.2558568112
+2252	0.25761936662253	0.257444013
+254	0.2573545493
+255	0.2572290353
+256	0.2570372912
+257	0.2568998636
+258	0.2567575768
+259	0.2565983849
+260	0.2564866484
+261	0.2563507181
+262	0.2562108287
+263	0.2560651128
+264	0.2558375368
+265	0.2557119265
+266	0.2556488469
+267	0.2554304808
+268	0.2553181749
+269	0.2551502773
+270	0.2529029506
+271	0.2527878029
+272	0.2546905989
+273	0.2545215518
+274	0.2543160817
+275	0.2541791875
+276	0.2540513566
+277	0.2539534559
+278	0.2538241785
+279	0.2537508829
+280	0.2536468795
+281	0.2534796288
+282	0.2533210302
+283	0.2531855087
+284	0.253060364
+285	0.252938553
+286	0.2528939278
+287	0.2528076195
+288	0.2526059889
+289	0.252516485
+290	0.252431445
+291	0.2523196753
+292	0.2522181392
+293	0.2521492932
+294	0.2520099701
+295	0.2518281723
+296	0.2517333023
+297	0.2516314819
+298	0.2514894085
+299	0.2512929534
+300	0.251161837
+301	0.2510757996
+302	0.2509626284
+303	0.250759337
+304	0.2506852761
+305	0.2505584546
+306	0.2503785971
+307	0.2502082196
+308	0.2500811161
+309	0.2498829037
+310	0.249807873
+311	0.2497761951
+312	0.2496915317
+313	0.2495364852
+314	0.2494153896
+315	0.2493185598
+316	0.249183293
+317	0.249015424
+318	0.2489144142
+319	0.24878961
+320	0.2486696127
+321	0.2485368039
+322	0.2484308881
+323	0.248312298
+324	0.2481997015
+325	0.2481188867
+326	0.2479984017
+327	0.2478591456
+328	0.2477113693
+329	0.2475420313
+330	0.2473880646
+331	0.2472143685
+332	0.2470477079
+333	0.2469472656
+334	0.2468033089
+335	0.2466792314
+336	0.2465228002
+337	0.246467637
+338	0.2463454509
+339	0.2463055341
+340	0.2461509115
+341	0.2459972066
+342	0.2458799621
+343	0.2457697806
+344	0.2456379602
+345	0.2455365372
+346	0.245390909
+347	0.2452414004
+348	0.2450948022
+349	0.2449969959
+350	0.2448391866
+351	0.2446539586
+352	0.2445683498
+353	0.244452316
+354	0.2443607228
+355	0.2442654109
+356	0.2441466725
+357	0.2440027311
+358	0.2438814211
+359	0.2437390836
+360	0.2436186585
+361	0.2434403101
+362	0.2432984141
+363	0.2430163168
+364	0.2429432348
+365	0.2428623686
+366	0.2426621444
+367	0.2424578679
+368	0.2423716254
+369	0.2422000161
+370	0.2420397528
+371	0.241938025
+372	0.2418099345
+373	0.2417362403
+374	0.2416968754
+375	0.2415959776
+376	0.2415044143
+377	0.2414036719
+378	0.2413144588
+379	0.2411997505
+380	0.2409918953
+381	0.2409076377
+382	0.2407821352
+383	0.2406444599
+384	0.2405312344
+385	0.2404221339
+386	0.2403162569
+387	0.2402180684
+388	0.2401040161
+389	0.2399174923
+390	0.2397740489
+391	0.2396549174
+392	0.2394659357
+393	0.2392422044
+394	0.239124725
+395	0.2390173787
+396	0.2388836747
+397	0.2388193253
+398	0.2387095384
+399	0.2385784603
+400	0.238428024
+401	0.238286148
+402	0.2381384209
+403	0.2380085855
+404	0.2378074478
+405	0.2376414464
+406	0.2375301155
+407	0.2373500664
+408	0.2371299706
+409	0.2370354963
+410	0.2368820977
+411	0.2367257734
+412	0.2366225093
+413	0.2364888794
+414	0.236357993
+415	0.2361769763
+416	0.2360451019
+417	0.2359401969
+418	0.2358386521
+419	0.2357085942
+420	0.2355723146
+421	0.2353819868
+422	0.235208862
+423	0.2351666693
+424	0.2349425824
+425	0.2348564318
+426	0.2347793051
+427	0.234635617
+428	0.2345190851
+429	0.234346511
+430	0.2342451178
+431	0.2341454553
+432	0.2341067534
+433	0.2339745587
+434	0.2339165625
+435	0.2338332876
+436	0.233759364
+437	0.2336547665
+438	0.233574331
+439	0.233463469
+440	0.2334118993
+441	0.2332008858
+442	0.2330763787
+443	0.2328962545
+444	0.2327718352
+445	0.2325767542
+446	0.2325135609
+447	0.2324561774
+448	0.2322494832
+449	0.2321726483
+450	0.2320481129
+451	0.2319412309
+452	0.2318444609
+453	0.2317409901
+454	0.231635057
+455	0.2314943555
+456	0.2313381946
+457	0.2312849151
+458	0.2312003718
+459	0.2311333753
+460	0.2310068691
+461	0.2309185959
+462	0.2308165199
+463	0.2307248742
+464	0.2306381584
+465	0.2305601601
+466	0.2304672421
+467	0.2302764413
+468	0.2301451112
+469	0.230023544
+470	0.2298875391
+471	0.2297757454
+472	0.2296864367
+473	0.2296073575
+474	0.229518713
+475	0.2294627614
+476	0.2292573337
+477	0.2291335591
+478	0.2290855056
+479	0.2289984126
+480	0.2289477607
+481	0.2287188845
+482	0.2285575159
+483	0.2284497673
+484	0.2283893552
+485	0.2282141027
+486	0.2279766928
+487	0.2279502749
+488	0.2278614808
+489	0.2277568426
+490	0.2276580223
+491	0.2275783133
+492	0.2275069093
+493	0.2274044203
+494	0.2272090293
+495	0.2271293126
+496	0.227022249
+497	0.2268998836
+498	0.2267174312
+499	0.2265308066
+500	0.2263558855
+501	0.2262839397
+502	0.2261074526
+503	0.2260589388
+504	0.2259620037
+505	0.2258239246
+506	0.2257021737
+507	0.2256233142
+508	0.2254568235
+509	0.2253782036
+510	0.2252923731
+511	0.2252153148
+512	0.2251011445
+513	0.2249799184
+514	0.2249385102
+515	0.2247559255
+516	0.2246312837
+517	0.2244927134
+518	0.2242212439
+519	0.2241349844
+520	0.2240605028
+521	0.223984483
+522	0.2237981956
+523	0.2237256507
+5524	0.22385886595525	0.22376262635526	0.2235791158527	0.2231165879
+5528	0.22335977375529	0.2232904164
+530	0.22320548365531	0.22303399353532	0.22287968753533	0.22277903553534	0.22266325553535	0.222594593536	0.2222462479
+537	0.2221446555
+538	0.2220074116
+539	0.2218753682
+540	0.2217279725
+541	0.2215278674
+542	0.2214397229
+543	0.2213313216
+544	0.2212424892
+545	0.2211267104
+546	0.221058413
+547	0.2209798705
+548	0.2208630304
+549	0.2206737075
+550	0.2205194543
+551	0.2204547144
+552	0.2202746715
+553	0.220190974
+554	0.2201306606
+555	0.2200181894
+556	0.2199530085
+557	0.2198615437
+558	0.2197844022
+559	0.2196566038
+560	0.2194860412
+561	0.2193479078
+562	0.2192304752
+563	0.2191926354
+564	0.2191247914
+565	0.219021307
+566	0.2189163296
+567	0.2188279593
+568	0.2187010131
+569	0.2186055581
+570	0.2185275634
+571	0.2184622755
+572	0.2183830614
+573	0.2182650336
+574	0.2181024144
+575	0.2180116354
+576	0.2179579982
+577	0.2178746878
+578	0.2177632613
+579	0.2176899773
+580	0.2175603564
+581	0.2174915483
+582	0.2174379661
+583	0.2173251156
+584	0.2171693914
+585	0.2170266494
+586	0.216864334
+587	0.2168034872
+588	0.2167335989
+589	0.2166304359
+590	0.2164724669
+591	0.2163198821
+592	0.2162064726
+593	0.2161018554
+594	0.2160103315
+595	0.2158800181
+596	0.2157548594
+597	0.215698425
+598	0.2155549787
+599	0.2154764111
+600	0.2153801721
+601	0.2152445929
+602	0.2151411293
+603	0.2149957359
+604	0.2148907006
+605	0.21481046
+606	0.2147547089
+607	0.2145890612
+608	0.2144855403
+609	0.2143502306
+610	0.2142863952
+611	0.2140713228
+612	0.2139516988
+613	0.213833705
+614	0.2137724275
+615	0615	0.21472616	0.616	0.21461617	0617	0.214560618	0618	0.214500619	0619	0.214408620	0620	0.214339621	0621	0.214243622	0622	0.214137623	0623	0.214008624	0624	0.213951625	0625	0.213780626	0626	0.2137644769
+627	0.2135857868
+628	0.2135479067
+629	0.2134538772
+630	0.2133340221
+631	0.2132292656
+632	0.213112633	0633	0.212972634	0634	0.2128635	0.2635	0.2127636	0.2118510496
+637	0.2116834225
+638	0.638	0.2125639	0.2114202615
+640	0.2113445402
+641	0.2112853157
+642	0.2112158115
+643	0.2111316421
+644	0.2109834817
+645	0.2108969759
+646	0.2108803226
+647	0.2107759254
+648	0.2106780292
+649	0.2105048205
+650	0.2104594373
+651	0.210396087
+652	0.2103460393
+653	0.2102946071
+654	0.2101566534
+655	0.2100883725
+656	0.2100653199
+657	0.2099599454
+658	0.2098735874
+659	0.2097640203
+660	0.2096592145
+661	0.2096139103
+662	0.2095420758
+663	0.2094600533
+664	0.2093671283
+665	0.2092667665
+666	0.2091092788
+667	0.2090712195
+668	0.2089494467
+669	0.2088626897
+670	0.2088150318
+671	0.2087060848
+672	0.2086060252
+673	0.2085728425
+674	0.2085014618
+675	0.2084382408
+676	0.2083550429
+677	0.2082908508
+678	0.2081572112
+679	0.2080626141
+680	0.2079779102
+681	0.2078554069
+682	0.2077728527
+683	0.2076214333
+684	0.2075344272
+685	0.2074853035
+686	0.20736748
+687	0.2072321229
+688	0.2070764962
+689	0.206959924
+690	0.2069038453
+691	0.2068433554
+692	0.2067499536
+693	0.2066997999
+694	0.2065947069
+695	0.206445379
+696	0.2063923529
+697	0.2062890568
+698	0.2062267393
+699	0.2061734689
+700	0.2060068816
+701	0.2058658631
+702	0.2057625962
+703	0.2055892085
+704	0704	0.20642705	0.2053025211
+706	0.2051688713
+707	0.707	0.20618708	0.2050085237
+709	0.2049088367
+710	0.2048239642
+711	0.2047316542
+712	0.2046032672
+713	0.2044329749
+714	0714	0.20548715	0.715	0.20541716	0.716	0.20536717	0.717	0.20524718	0.718	0.20519719	0.719	0.20513720	0.720	0.20510721	0.721	0.20501722	0.722	0.20498723	0.723	0.20493724	0.724	0.20486725	0.725	0.20479726	0.726	0.2047330242
+727	0.204639792
+728	0.2045057031
+729	0.20436730	0.730	0.20429731	0.731	0.20424732	0.732	0.20415733	0.2026522041
+734	0.734	0.20395735	0.735	0.20387736	0.736	0.20382737	0.737	0.20376738	0.2021816826
+739	0.2020455078
+740	0.2018938656
+741	0.2017567672
+742	0.2016824228
+743	0.2016070108
+744	0.2014842704
+745	0.2014104849
+746	0.2013393837
+747	0.2012833162
+748	0.2012559259
+749	0.2011516509
+750	0.2010261293
+751	0.2008588018
+752	0.2007177314
+753	0.2005909782
+754	0.2004566848
+755	0.2003678939
+756	0.200265596
+757	0.2002121035
+758	0.2001129327
+759	0.2000131959
+760	0.1999159409
+761	0.1997892077
+762	0.1997150572
+763	0.1995562023
+764	0.1994189202
+765	0.1993814234
+766	0.1993107055
+767	0.19923773
+768	0.1991631234
+769	0.1990231522
+770	0.1989572232
+771	0.1989065496
+772	0.198810354
+773	0.1987187126
+774	0.198602681
+775	0.198544289
+776	776	0.1974275777777	0.19737911778778	0.19731560779779	0.19729760780780	0.19726183781781	0.19718989782782	0.19714483783783	0.1971086784	784	0.1970310785	785	0.1969040102
+786	0.1968767787	787	0.1968223788788	0.19671808789	0.1971688679
+790	0.1971133505
+791	0.1970573064
+792	0.1969309651
+793	0.196822851
+794	0.1967037121
+795	0.1965664955
+796	0.1964988227
+797	0.1964288204
+798	0.1962998362
+799	0.1962072888
+800	0.1960950051
+801	0.196044112
+802	0.1959964318
+803	0.1959442302
+804	0.1959037122
+805	0.1957869796
+806	0.1956498038
+807	0.1955275716
+808	0.1954511929
+809	0.1953156204
+810	0.1952535142
+811	0.1951393533
+812	0.1950848436
+813	0.1949760076
+814	0.1948895198
+815	0.1948040409
+816	0.1946758699
+817	0.1945703718
+818	0.1945049746
+819	0.1944564152
+820	0.1943254884
+821	0.1942024297
+822	0.1941361423
+823	0.1940355461
+824	0.193928491
+825	0.1938722662
+826	0.1938241723
+827	0.1937563974
+828	0.1936496047
+829	0.1935365196
+830	0.193436826
+831	0.1934245063
+832	0.1933003321
+833	0.1931803445
+834	0.1931194794
+835	0.1930578233
+836	0.1929893039
+837	0.1928975868
+838	0.192815136
+839	0.1926973762
+840	0.192642313
+841	0.1925744074
+842	0.1924976177
+843	0.1924535229
+844	0.1923759868
+845	0.1922892698
+846	0.1922402248
+847	0.1921752729
+848	0.1920466624
+849	0.1919349155
+850	0.1918797293
+851	0.1918321291
+852	0.1917885763
+853	0.1917436879
+854	0.1916714435
+855	0.1915585621
+856	0.1914585379
+857	0.191366928
+858	0.1912387077
+859	0.1911316581
+860	0.1910178787
+861	0.1909128097
+862	0.1908743757
+863	0.1907896694
+864	0.1906881947
+865	0.1905467185
+866	0.1905101728
+867	0.1904734468
+868	0.1903627676
+869	0.1902835324
+870	0.1901353705
+871	0.1900130826
+872	0.1898964985
+873	0.189843312
+874	0.1898091057
+875	0.1897611113
+876	0.1896789766
+877	0.1895745098
+878	0.1894637744
+879	0.1894036691
+880	0.1892932683
+881	0.189258266
+882	0.1891981233
+883	0.1891215445
+884	0.1890143054
+885	0.1889312723
+886	0886	0.192085887	0887	0.191935888	0888	0.191898889	0889	0.191846890	0890	0.191790891	0891	0.191729892	0892	0.1916760736
+893	0.1915335233
+894	0.1914796028
+895	0.1913763062
+896	0.1913395079
+897	0.1912678699
+898	0.191243899	0899	0.191162900	0.1876269642
+901	0.1875001977
+902	0.187403209
+903	0.1873043882
+904	0.1872195534
+905	0.1871491767
+906	0.1870104981
+907	0.1869420064
+908	0.1868914869
+909	0.186787065
+910	0.1866702356
+911	0.1866046699
+912	0.1864560457
+913	0.1863240246
+914	0.1862062241
+915	0.1861338881
+916	0.186025657
+917	0.1859396015
+918	0.1858178881
+919	0.185706966
+920	0.1856200051
+921	0.1854981475
+922	0.1854257424
+923	0.1853204869
+924	0.1852156164
+925	0.1851027012
+926	0.1849973028
+927	0.1848849182
+928	0.1848190864
+929	0.1846982134
+930	0.1845826874
+931	0.18446116
+932	0.1843612267
+933	0.1842788248
+934	0.1841913191
+935	0.1841571329
+936	0.1840521094
+937	0.183983229
+938	0.1839018212
+939	0.1838136477
+940	0.1837559317
+941	0.1836433761
+942	0.1835371968
+943	0.183429206
+944	0.1833599311
+945	0.1832798986
+946	0.1831687847
+947	0.1830272249
+948	0.1829354743
+949	0.1828585222
+950	0.1828066679
+951	0.1826992636
+952	0.1826619975
+953	0.1826404807
+954	0.1826049683
+955	0.182542509
+956	0.1824707124
+957	0.1823498301
+958	0.1822917321
+959	0.1822506991
+960	0.18222991
+961	0.1821302287
+962	0.1820405902
+963	0.1819642189
+964	0.1818719662
+965	0.1818081334
+966	0.1817224884
+967	0.1816794438
+968	0.18157978
+969	0.1814637115
+970	0.1813123668
+971	0.1811983001
+972	0.1810990775
+973	0.1810350562
+974	0.1809943476
+975	0.1808972694
+976	0.1808157769
+977	0.1807341121
+978	0.18064582978979	0.18057748979980	0.18051626980	0.18567441698981	0.18559991998982	0.185556502
+983	0.185514808
+984	0.1854468917
+985	0.1853146605
+986	0.1852626547
+987	0.185230434
+988	0.1852016396
+989	0990	0.179711990	0991	0.17963991	0.992	0.17957992	0.993	0.17951993	0.994	0.17942994	0.995	0.1793665083
+996	0.17928996	0.997	0.17918997	0.998	0.17911998	0.999	0.17902999	0.1844407665
+601128

SL/aufgaben/template/3_data/catboost_info/time_left.tsv

@@ -0,0 +1,879 @@
+iter	Passed	Remaining
+0	59	59828
+1	61	30821
+2	63	21170
+3	65	16340
+4	67	13429
+5	69	11507
+6	71	1021377	73	915888	75	833299	77	7671110	79	7156111	82	6779112	84	6426113	86	6106114	88	5843115	90	5593116	92	5358117	94	5168118	97	5022119	99	4864220	101	4740221	103	4609222	105	4487223	107	4369224	109	4274225	112	4209226	114	4118227	116	402728	118	3960
+29	120	3889
+30	123	3846
+31	124	3767
+32	126	3709
+33	129	3666
+34	131	3627
+35	133	3585
+36	135	3539
+37	138	3506
+38	141	3474
+39	142	3429
+40	144	3388
+41	146	3349
+42	149	3321
+43	151	3290
+44	153	3259
+45	155	3223
+46	157	3197
+47	159	3165
+48	161	3139
+49	164	3121
+50	166	3089
+51	168	3075
+52	170	3051
+53	173	3032
+54	174	3006
+55	176	2981
+56	179	2961
+57	181	2945
+58	183	2929
+59	185	2906
+60	187	2884
+61	189	2861
+62	190	2837
+63	192	2821
+64	194	2803
+65	196	2785
+66	198	2767
+67	200	2747
+68	202	2736
+69	204	2721
+70	206	2703
+71	208	2686
+72	210	2672
+73	212	2659
+74	214	2647
+75	216	2635
+776	219	2630777	221	2615778	223	2607779	225	2598880	227	2582881	229	2569882	231	2559883	233	254984	235	2537
+885	237	252786	240	2522
+87	242	2510
+88	244	2499
+89	246	2488
+90	248	2477
+991	250	2467992	251	245793	253	2447
+94	256	2441
+95	258	2435
+96	260	2426
+97	263	2422
+98	265	2420
+99	268	2412
+100	269	2402
+101	272	2397
+102	274	2387
+103	275	2377
+104	277	2366
+105	279	2358
+106	281	2351
+107	283	2340
+108	286	2339
+109	288	2336
+110	290	2324
+111	292	2316
+112	294	2308
+113	296	2302
+114	298	2294
+115	300	2287
+116	302	2279
+117	304	2275
+118	306	2267
+119	308	2259
+120	309	2251
+121	312	2248
+122	314	2242
+123	316	2238
+124	318	2229
+125	320	2223
+126	322	2215
+127	324	2208
+128	326	2205
+129	328	2199
+130	330	2194
+131	332	2187
+132	334	2182
+133	336	2177
+134	338	2171
+135	340	2164
+136	342	2159
+137	346	2162
+138	348	2156
+139	350	2152
+140	352	2147
+141	354	2141
+142	356	2135
+143	358	2130
+144	360	2124
+145	362	2118
+146	364	2112
+147	366	2106
+148	367	2101
+149	369	2095
+150	372	2092
+151	374	2090
+152	377	2088
+153	379	2082
+154	380	2076
+155	383	2072
+156	384	2066
+157	386	2060
+158	388	2054
+159	390	2051
+160	392	2046
+161	394	2042
+162	396	2036
+163	398	2031
+164	400	2025
+165	402	2021
+166	404	2016
+167	406	2012
+168	408	2007
+169	410	2002
+170	412	1999
+171	414	1997
+172	416	1992
+173	418	1987
+174	421	1985
+175	423	1981
+176	424	1975
+177	426	1971
+178	429	1968
+179	431	1965
+180	433	1960
+181	435	1955
+182	437	1954
+183	440	1951
+184	441	1946
+185	443	1942
+186	445	1937
+187	448	1936
+188	450	1933
+189	452	1929
+190	454	1926
+191	456	1922
+192	458	1918
+193	461	1916
+194	463	1911
+195	465	1910
+196	467	1907
+197	470	1905
+198	472	1901
+199	474	1898
+200	476	1894
+201	478	1890
+202	480	1885
+203	481	1880
+204	483	1876
+205	485	1872
+206	487	1867
+207	489	1863
+208	491	1860
+209	494	1858
+210	496	1855
+211	498	1851
+212	500	1849
+213	502	1845
+214	504	1842
+215	507	1840
+216	509	1837
+217	511	1833
+218	513	1829
+219	515	1825
+220	516	1821
+221	518	1817
+222	520	1814
+223	522	1810
+224	524	1807
+225	526	1803
+226	528	1799
+227	530	1795
+228	532	1792
+229	534	1788
+230	536	1784
+231	538	1781
+232	540	1779
+233	542	1775
+234	545	1774
+235	547	1772
+236	549	1768
+237	551	1764
+238	553	1762
+239	555	1759
+240	557	1756
+241	559	1752
+242	561	1748
+243	563	1745
+244	565	1743
+245	567	1740
+246	569	1736
+247	571	1733
+248	574	1731
+249	576	1728
+250	578	1725
+251	580	1722
+252	583	1721
+253	586	1723
+254	590	1725
+255	593	1725
+256	596	1725
+257	598	1722
+258	602	1722
+259	604	1719
+260	606	1716
+261	607	1712
+262	610	1711
+263	613	1711
+264	616	1710
+265	618	1708
+266	621	1707
+267	625	1707
+268	628	1706
+269	630	1704
+270	632	1701
+271	635	1700
+272	638	1699
+273	641	1699
+274	644	1699
+275	646	1696
+276	648	1693
+277	651	1692
+278	654	1691
+279	656	1689
+280	660	1688
+281	663	1688
+282	666	1687
+283	669	1687
+284	671	1685
+285	673	1681
+286	676	1680
+287	679	1680
+288	682	1679
+289	684	1676
+290	687	1675
+291	689	1672
+292	692	1671
+293	695	1670
+294	699	1670
+295	702	1670
+296	705	1669
+297	707	1665
+298	709	1662
+299	711	1659
+300	713	1658
+301	716	1654
+302	718	1653
+303	720	1650
+304	723	1649
+305	727	1648
+306	730	1648
+307	733	1647
+308	736	1646
+309	739	1645
+310	741	1642
+311	744	1642
+312	748	1641
+313	751	1641
+314	753	1637
+315	755	1635
+316	758	1634
+317	761	1632
+318	764	1631
+319	767	1629
+320	770	1629
+321	773	1628
+322	776	1627
+323	779	1626
+324	782	1625
+325	785	1624
+326	787	1621
+327	789	1618
+328	792	1617
+329	796	1616
+330	799	1615
+331	802	1613
+332	805	1613
+333	808	1612
+334	810	1608
+335	812	1604
+336	815	1603
+337	817	1601
+338	819	1598
+339	821	1594
+340	823	1590
+341	826	1589
+342	829	1588
+343	831	1585
+344	833	1581
+345	835	1578
+346	837	1575
+347	838	1571
+348	840	1568
+349	842	1565
+350	845	1563
+351	849	1563
+352	852	1561
+353	854	1558
+354	856	1556
+355	858	1553
+356	860	1550
+357	863	1548
+358	866	1547
+359	869	1545
+360	872	1544
+361	875	1543
+362	879	1542
+363	881	1539
+364	884	1538
+365	886	1535
+366	889	1533
+367	892	1532
+368	895	1530
+369	897	1527
+370	899	1524
+371	900	1520
+372	902	1517
+373	905	1515
+374	907	1512
+375	909	1509
+376	911	1506
+377	913	1502
+378	914	1499
+379	916	1495
+380	919	1493
+381	922	1492
+382	925	1491
+383	928	1490
+384	931	1488
+385	934	1486
+386	937	1485
+387	940	1483
+388	943	1482
+389	946	1481
+390	950	1479
+391	953	1478
+392	956	1477
+393	958	1474
+394	960	1470
+395	962	1467
+396	964	1465
+397	967	1463
+398	969	1460
+399	971	1457
+400	973	1454
+401	976	1452
+402	978	1449
+403	980	1446
+404	983	1444
+405	985	1441
+406	987	1438
+407	990	1437
+408	993	1436
+409	995	1433
+410	999	1432
+411	1002	1430
+412	1005	1429
+413	1007	1426
+414	1009	1423
+415	1011	1420
+416	1015	1419
+417	1017	1416
+418	1020	1414
+419	1022	1411
+420	1024	1408
+421	1025	1405
+422	1029	1403
+423	1031	1400
+424	1033	1397
+425	1036	1396
+426	1039	1394
+427	1042	1393
+428	1044	1390
+429	1047	1388
+430	1050	1386
+431	1053	1385
+432	1056	1383
+433	1059	1382
+434	1062	1380
+435	1065	1378
+436	1068	1376
+437	1070	1373
+438	1073	1372
+439	1076	1370
+440	1078	1367
+441	1080	1364
+442	1082	1361
+443	1084	1357
+444	1087	1356
+445	1090	1354
+446	1092	1351
+447	1095	1350
+448	1098	1348
+449	1101	1346
+450	1103	1343
+451	1106	1342
+452	1109	1339
+453	1110	1335
+454	1113	1333
+455	1116	1332
+456	1118	1329
+457	1121	1327
+458	1124	1325
+459	1126	1322
+460	1128	1319
+461	1131	1317
+462	1134	1315
+463	1137	1314
+464	1140	1312
+465	1143	1310
+466	1146	1309
+467	1149	1306
+468	1152	1304
+469	1154	1301
+470	1156	1298
+471	1157	1295
+472	1159	1291
+473	1161	1288
+474	1164	1286
+475	1166	1283
+476	1168	1281
+477	1171	1279
+478	1174	1277
+479	1177	1275
+480	1179	1273
+481	1182	1270
+482	1185	1268
+483	1187	1266
+484	1189	1262
+485	1191	1259
+486	1193	1257
+487	1195	1254
+488	1198	1252
+489	1202	1251
+490	1205	1249
+491	1208	1247
+492	1211	1245
+493	1213	1243
+494	1215	1239
+495	1217	1237
+496	1220	1235
+497	1223	1232
+498	1224	1229
+499	1226	1226
+500	1228	1223
+501	1230	1220
+502	1233	1218
+503	1235	1215
+504	1237	505	1505	1240	1210
+506	1243	1209
+507	1246	1207
+508	1249	1205
+509	1252	1203
+510	1254	1200
+511	1256	1197
+512	1259	1195
+513	1261	514	1514	1264	515	1515	1266	1188
+516	1268	517	1517	1270	518	1272	1179
+519	1275	1177
+520	1277	1174
+521	1279	1171
+522	1282	1169
+523	1285	1168
+524	1524	1288	525	1525	1290	526	1526	1292	527	1294	1157
+528	1528	1297	529	1529	1301	1153
+530	1303	531	1531	1304	532	1532	1307	533	1533	1311	534	1534	1314	535	1535	1316	536	1319	1137
+537	1322	1135
+538	1325	1133
+539	1328	1131
+540	1331	1129
+541	1334	1127
+542	1336	1125
+543	1339	1123
+544	1342	1121
+545	1345	1119
+546	1347	1116
+547	1350	1114
+548	1353	1112
+549	1355	1109
+550	1358	1106
+551	1360	1104
+552	1363	1102
+553	1365	1099
+554	1368	1096
+555	1371	1095
+556	1374	1093
+557	1376	1090
+558	1379	1088
+559	1381	1085
+560	1383	1082
+561	1385	1079
+562	1387	1076
+563	1389	1073
+564	1392	1071
+565	1395	1069
+566	1397	1067
+567	1400	1065
+568	1402	1062
+569	1406	1060
+570	1408	1058
+571	1411	1056
+572	1414	1054
+573	1416	1051
+574	1418	1048
+575	1420	1045
+576	1423	1043
+577	1426	1041
+578	1429	1039
+579	1431	1036
+580	1433	1033
+581	1435	1031
+582	1438	1028
+583	1441	1026
+584	1443	1023
+585	1445	1021
+586	1448	1018
+587	1451	1016
+588	1453	1014
+589	1457	1012
+590	1460	1010
+591	1463	1008
+592	1466	1006
+593	1468	1003
+594	1470	1001
+595	1472	998
+596	1474	995
+597	1477	993
+598	1479	990
+599	1481	987
+600	1483	984
+601	1485	982
+602	1487	979
+603	1489	976
+604	1491	973
+605	1492	970
+606	1494	967
+607	1496	965
+608	1498	962
+609	1500	959
+610	1502	956
+611	1505	954
+612	1507	952
+613	1510	949
+614	1513	947
+615615	1515	9616616	1518	9617617	1520	9618618	1522	9619619	1525	9620620	1527	9621621	1529	9622622	1532	9623623	1534	9624624	1537	9625625	1540	9626626	1543	918
+627	1545	915
+628	1548	913
+629	1551	911
+630	1555	909
+631	1557	906
+632	1559	9633633	1561	9634634	1563	8635635	1565	8636	1567	893
+637	1571	891
+638638	1573	8639	1576	886
+640	1579	884
+641	1581	881
+642	1583	879
+643	1586	876
+644	1589	874
+645	1592	872
+646	1594	870
+647	1596	867
+648	1598	864
+649	1601	862
+650	1604	860
+651	1606	857
+652	1609	855
+653	1611	852
+654	1613	849
+655	1616	847
+656	1620	845
+657	1622	843
+658	1625	841
+659	1628	838
+660	1631	836
+661	1633	834
+662	1635	831
+663	1638	829
+664	1641	827
+665	1644	824
+666	1647	822
+667	1649	819
+668	1652	817
+669	1654	815
+670	1656	812
+671	1659	810
+672	1662	808
+673	1664	805
+674	1667	803
+675	1669	800
+676	1672	797
+677	1674	795
+678	1676	792
+679	1678	789
+680	1680	787
+681	1682	784
+682	1684	781
+683	1687	779
+684	1690	777
+685	1693	775
+686	1695	772
+687	1698	770
+688	1700	767
+689	1703	765
+690	1705	762
+691	1707	759
+692	1709	757
+693	1712	755
+694	1715	752
+695	1718	750
+696	1721	748
+697	1724	746
+698	1727	743
+699	1730	741
+700	1732	738
+701	1734	736
+702	1736	733
+703	1739	731
+704704	1741	7705	1744	726
+706	1746	723
+707707	1749	7708	1752	719
+709	1754	716
+710	1756	713
+711	1757	711
+712	1761	708
+713	1763	706
+714714	1765	7715715	1768	7716716	1770	6717717	1773	6718718	1775	6719719	1777	6720720	1780	6721721	1782	6722722	1785	6723723	1789	6724724	1791	6725725	1795	6726726	1798	675
+727	1800	672
+728	1802	670
+729	1804	6730730	1807	6731731	1810	6732	1812	660
+733	1815	657
+734734	1818	6735735	1821	6736736	1823	6737737	1825	6738	1828	645
+739	1830	643
+740	1833	641
+741	1837	638
+742	1840	636
+743	1843	634
+744	1846	631
+745	1848	629
+746	1850	626
+747	1851	623
+748	1854	621
+749	1858	619
+750	1860	616
+751	1862	614
+752	1865	612
+753	1868	609
+754	1872	607
+755	1874	604
+756	1876	602
+757	1878	599
+758	1881	597
+759	1884	595
+760	1886	592
+761	1888	589
+762	1890	587
+763	1892	584
+764	1895	582
+765	1898	579
+766	1900	577
+767	1768	1900768	1769	1902769	1770	1905770	1771	1907771	1772	1910772	1773	1913773	1774	1916774	1775	1919775	1776	1921	551
+777	1923	548
+778	1925	546
+779	1928	544
+780	1932	541
+781	1934	539
+782	1937	536
+783	1939	534
+784	1942	531
+785	1945	529
+786	1947	527
+787	1949	524
+788	1951	521
+789	1953789	1790	1955790	1791	1958791	1792	1960792	1793	1963793	1794	1965794	1970	507
+795	1973	505
+796	1975	503
+797	1978	500
+798	1799	1978799	1800	1982800	1986	493
+801	1988	490
+802	1803	1989803	1993	486
+804	1996	483
+805	1998	481
+806	2001	478
+807	2003	476
+808	2006	473
+809	2009	471
+810	2012	468
+811	2015	466
+812	2017	464
+813	2019	461
+814	2022	459
+815	2024	456
+816	2027	454
+817	2029	451
+818	2032	449
+819	2034	446
+820	2037	444
+821	2039	441
+822	2042	439
+823	2045	436
+824	2049	434
+825	2051	432
+826	2053	429
+827	2054	426
+828	2056	424
+829	2059	421
+830	2062	419
+831	2064	416
+832	2067	414
+833	2069	411
+834	2072	409
+835	2075	407
+836	2077	404
+837	2079	402
+838	2081	399
+839	2083	396
+840	2085	394
+841	2087	391
+842	2090	389
+843	2093	386
+844	2095	384
+845	2098	381
+846	2101	379
+847	2104	377
+848	2108	374
+849	2110	372
+850	2112	369
+851	2114	367
+852	2116	364
+853	2119	362
+854	2122	359
+855	2125	357
+856	2128	355
+857	2130	352
+858	2133	350
+859	2136	347
+860	2138	345
+861	2140	342
+862	2143	340
+863	2147	337
+864	2150	335
+865	2153	333
+866	2155	330
+867	2158	328
+868	2161	325
+869	2164	323
+870	2166	320
+871	2169	318
+872	2171	315
+873	2174	313
+874	2176	310
+875	2178	308
+876	2179	305
+877	2181	303
+878	2185	300
+879	2187	298
+880	2189	295
+881	2191	293
+882	2194	290
+883	2196	288
+884	2197	285
+885	2200	283
+886886	2201	2887887	2204	2888888	2207	2889889	2211	2890890	2214	2891891	2217	2892892	2220	266
+893	2222	263
+894	2225	261
+895	2228	258
+896	2231	256
+897	2234	253
+898	2236	2899899	2238	2900	2241	246
+901	2244	243
+902	2247	241
+903	2251	239
+904	2254	236
+905	2256	234
+906	2258	231
+907	2261	229
+908	2264	226
+909	2266	224
+910	2268	221
+911	2271	219
+912	2274	216
+913	2277	214
+914	2279	211
+915	2282	209
+916	2285	206
+917	2288	204
+918	2291	202
+919	2295	199
+920	2298	197
+921	2300	194
+922	2302	192
+923	2304	189
+924	2306	187
+925	2308	184
+926	2311	181
+927	2314	179
+928	2317	177
+929	2319	174
+930	2321	172
+932	2315	166
+933	2318	163
+933	2328	164
+935	2322	158
+936	2326	156
+937	2329	153
+938	2332	151
+939	2335	149
+940	2337	146
+941	2339	144
+942	2341	141
+943	2343	138
+944	2346	136
+945	2348	134
+946	2351	131
+946	2360	132
+947	2363	129
+948	2366	127
+949	2369	124
+950	2371	122
+951	2374	119
+952	2377	117
+953	2380	114
+954	2384	112
+955	2386	109
+956	2388	107
+957	2390	104
+958	2391	102
+959	2395	99
+960	2398	97
+961	2400	94
+962	2403	92
+963	2408	89
+964	2410	87
+965	2414	84
+966	2416	82
+967	2418	79
+968	2420	77
+969	2422	74
+970	2424	72
+971	2425	699972	2428	67
+973	2431	64
+974	2434	62
+975	2436	59
+976	2439	57
+977	2442	54
+978978	2443	979979	2446	980980	2449	47
+981	2451	44
+982	2455	42
+983	2458	39
+984	2461	37
+985	2463	34
+986	2466	32
+987	2470	30
+988	2472	27
+989	2474	990990	2477	991991	2479	992992	2482	993993	2484	994994	2487	995	2491	10
+996996	2494997997	2497998998	2501999999	2503	0

SL/aufgaben/template/3_data/demo_data_class.csv

@@ -0,0 +1,82 @@
+"y","X1","X2"
+"A",6,2.5
+"A",5.1,1.9
+"A",5.9,2.1
+"A",5.6,1.8
+"A",5.8,2.2
+"A",6.6,2.1
+"A",4.5,1.7
+"A",6.3,1.8
+"A",5.8,1.8
+"A",6.1,2.5
+"A",5.1,2
+"A",5.3,1.9
+"A",5.5,2.1
+"A",5,2
+"A",5.1,2.4
+"A",5.3,2.3
+"A",5.5,1.8
+"A",6.7,2.2
+"A",6.9,2.3
+"A",5,1.5
+"A",5.7,2.3
+"A",4.9,2
+"A",6.7,2
+"A",4.9,1.8
+"A",5.7,2.1
+"A",6,1.8
+"A",4.8,1.8
+"A",5.6,2.1
+"A",5.8,1.6
+"A",6.1,1.9
+"A",6.4,2
+"A",5.6,2.2
+"A",5.6,1.4
+"A",6.1,2.3
+"A",5.6,2.4
+"A",4.8,1.9
+"A",5.4,2.1
+"A",5.1,2.3
+"A",5.9,2.3
+"A",5.7,2.5
+"A",5.2,2.3
+"A",5,1.9
+"A",5.2,2
+"A",5.4,2.3
+"A",5.1,1.8
+"B",4.7,1.4
+"B",4.5,1.5
+"B",4.9,1.5
+"B",4,1.3
+"B",4.6,1.5
+"B",4.5,1.3
+"B",4.7,1.6
+"B",3.3,1
+"B",4.6,1.3
+"B",3.9,1.4
+"B",3.5,1
+"B",4.2,1.5
+"B",4,1
+"B",3.6,1.3
+"B",4.4,1.4
+"B",4.1,1
+"B",3.9,1.1
+"B",4.8,1.7
+"B",4.7,1.2
+"B",4.3,1.3
+"B",4.8,1.4
+"B",5,1.7
+"B",3.8,1.1
+"B",3.7,1
+"B",3.9,1.2
+"B",5.1,1.6
+"B",4.5,1.6
+"B",4.7,1.5
+"B",4.4,1.3
+"B",4.1,1.3
+"B",4.4,1.2
+"B",4.6,1.4
+"B",4,1.2
+"B",4.2,1.3
+"B",4.2,1.2
+"B",3,1.1

SL/aufgaben/template/3_data/demo_data_regr.csv

@@ -0,0 +1,82 @@
+"X","y"
+6,2.5
+5.1,1.9
+5.9,2.1
+5.6,1.8
+5.8,2.2
+6.6,2.1
+4.5,1.7
+6.3,1.8
+5.8,1.8
+6.1,2.5
+5.1,2
+5.3,1.9
+5.5,2.1
+5,2
+5.1,2.4
+5.3,2.3
+5.5,1.8
+6.7,2.2
+6.9,2.3
+5,1.5
+5.7,2.3
+4.9,2
+6.7,2
+4.9,1.8
+5.7,2.1
+6,1.8
+4.8,1.8
+5.6,2.1
+5.8,1.6
+6.1,1.9
+6.4,2
+5.6,2.2
+5.6,1.4
+6.1,2.3
+5.6,2.4
+4.8,1.9
+5.4,2.1
+5.1,2.3
+5.9,2.3
+5.7,2.5
+5.2,2.3
+5,1.9
+5.2,2
+5.4,2.3
+5.1,1.8
+4.7,1.4
+4.5,1.5
+4.9,1.5
+4,1.3
+4.6,1.5
+4.5,1.3
+4.7,1.6
+3.3,1
+4.6,1.3
+3.9,1.4
+3.5,1
+4.2,1.5
+4,1
+3.6,1.3
+4.4,1.4
+4.1,1
+3.9,1.1
+4.8,1.7
+4.7,1.2
+4.3,1.3
+4.8,1.4
+5,1.7
+3.8,1.1
+3.7,1
+3.9,1.2
+5.1,1.6
+4.5,1.6
+4.7,1.5
+4.4,1.3
+4.1,1.3
+4.4,1.2
+4.6,1.4
+4,1.2
+4.2,1.3
+4.2,1.2
+3,1.1