refactor: rename folder structure to sort for algorithms

ML/aufgaben/a2/kmeans_digits.py

@@ -1,24 +0,0 @@
-#import numpy as np
-
-from sklearn import datasets
-from sklearn.cluster import KMeans
-from sklearn import metrics
-
-digits = datasets.load_digits()
-
-# 100 samples pro ziffer
-# 64 pixel pro zahl
-print(digits.data.shape)
-#print(len(np.unique(digits.target)))
-
-# 10 cluster, random, n_init=1
-kmeans = KMeans(n_clusters=10, init='random', n_init=1)
-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_))
-
-# auch hier ist kmeans nicht der richtige algorithmus, weil die Daten nicht schön kugelförmig verteilt sind und sich nicht gut clustern lassen

ML/aufgaben/a2/kmeans_iris.py

@@ -1,28 +0,0 @@
-from sklearn import datasets
-from sklearn.cluster import KMeans
-from sklearn import metrics
-
-iris = datasets.load_iris()
-
-# print 150 samples
-print(iris.target)
-
-# clusters=3, centroiden zufällig wählen, n_init=50
-kmeans = KMeans(n_clusters=3, init='random', n_init=50)
-# fit auf daten
-kmeans.fit(iris.data)
-
-# print alle daten
-#print(list(zip(iris.target, kmeans.labels_)))
-
-# gegenüberstellung
-print("gold standard vs. prediction")
-for target_label, predicted_label in zip(iris.target, kmeans.labels_):
-    print(f'{target_label} vs. {predicted_label}')
-
-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_))
-
-# erkenntnis, der Algo ist nicht perfekt für diese Art von Daten!!

ML/aufgaben/decisiontree/decisiontree_iris.py

@@ -1,5 +1,9 @@
 """
-Use a decision tree classifier to predict flowers based on sepal and petal length/width
+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
@@ -35,4 +39,4 @@ tree.plot_tree(
     rounded=True,
     ax=ax,
 )
-fig.savefig("tree.png", dpi=150, bbox_inches="tight")
+fig.savefig("decisiontree_iris.png", dpi=150, bbox_inches="tight")

ML/aufgaben/kmeans/kmeans_digits.py

@@ -0,0 +1,60 @@
+"""
+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 on the training data
+    - it discovers the structure on its own
+    - thus the cluster numbers are arbitrary and do not correspond to the class labels
+"""
+
+import matplotlib.pyplot as plt
+
+from sklearn import datasets
+from sklearn.cluster import KMeans
+from sklearn import metrics
+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_))
+
+pca = PCA(n_components=2)
+X2d = pca.fit_transform(digits.data)
+centroids2d = pca.transform(kmeans.cluster_centers_)
+
+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')
+
+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')
+
+"""
+Takaway:
+- Hier ist k-means nicht der richtige algorithmus, weil die Daten nicht schön kugelförmig verteilt sind und sich nicht gut clustern lassen.
+"""

ML/aufgaben/kmeans/kmeans_iris.py

@@ -0,0 +1,58 @@
+"""
+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
+pca = PCA(n_components=2)
+X2d = pca.fit_transform(iris.data)
+centroids2d = pca.transform(kmeans.cluster_centers_)
+
+# plot
+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)