bfh/cas-pml
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feature(unterlagen): add course material from course one

Browse Source
This commit is contained in:
Aaron
2026-04-28 15:26:12 +02:00
parent 2e83296876
commit 25a1acd0b1
15 changed files with 1433 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notes/Notizen_CAS_PML_1.md → Einfuehrung/notizen/L1_Notizen.md
View File
Einfuehrung/unterlagen/01_ML_Overview_v05.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/02_Python_v06.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/03_Python_ML_Intro_project_v04.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/03_decisiontree.ipynb
+417
View File
File diff suppressed because one or more lines are too long
Einfuehrung/unterlagen/03_tree.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 121 KiB

Einfuehrung/unterlagen/04_Evaluation_v08.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/05_UnsupervisedLearning_v01.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/06_KMeans_project_v02.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/06_Kmeans_Digits.ipynb
+479
View File
File diff suppressed because one or more lines are too long
Einfuehrung/unterlagen/06_Kmeans_Iris.ipynb
+255
View File
@@ -0,0 +1,255 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"iris = datasets.load_iris()\n",
"\n",
"from sklearn.cluster import KMeans\n",
"from sklearn import metrics"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
" 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
" 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2\n",
" 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n",
" 2 2]\n"
]
}
],
"source": [
"print(iris.target)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"KMeans(algorithm='auto', copy_x=True, init='random', max_iter=300,\n",
" n_clusters=3, n_init=1, n_jobs=None, precompute_distances='auto',\n",
" random_state=None, tol=0.0001, verbose=0)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kmeans = KMeans(n_clusters=3, init='random', n_init=1)\n",
"kmeans.fit(iris.data)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[(0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (1, 0), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1)]\n"
]
}
],
"source": [
"print(list(zip(iris.target,kmeans.labels_)))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.7364192881252849\n",
"0.7474865805095326\n",
"0.7163421126838475\n",
"0.5511916046195915\n"
]
}
],
"source": [
"print(metrics.homogeneity_score(iris.target, kmeans.labels_))\n",
"print(metrics.completeness_score(iris.target, kmeans.labels_))\n",
"print(metrics.adjusted_rand_score(iris.target, kmeans.labels_))\n",
"print(metrics.silhouette_score(iris.data, kmeans.labels_))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"KMeans(algorithm='auto', copy_x=True, init='random', max_iter=300,\n",
" n_clusters=3, n_init=10, n_jobs=None, precompute_distances='auto',\n",
" random_state=None, tol=0.0001, verbose=0)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kmeans_init = KMeans(n_clusters=3, init='random', n_init=10)\n",
"kmeans_init.fit(iris.data)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[(0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (1, 0), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1)]\n"
]
}
],
"source": [
"print(list(zip(iris.target,kmeans.labels_)))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.7514854021988338\n",
"0.7649861514489815\n",
"0.7302382722834697\n",
"0.5528190123564091\n"
]
}
],
"source": [
"print(metrics.homogeneity_score(iris.target, kmeans_init.labels_))\n",
"print(metrics.completeness_score(iris.target, kmeans_init.labels_))\n",
"print(metrics.adjusted_rand_score(iris.target, kmeans_init.labels_))\n",
"print(metrics.silhouette_score(iris.data, kmeans_init.labels_))"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,\n",
" n_clusters=3, n_init=10, n_jobs=None, precompute_distances='auto',\n",
" random_state=None, tol=0.0001, verbose=0)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kmeans2 = KMeans(n_clusters=3)\n",
"kmeans2.fit(iris.data)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[(0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (1, 0), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1)]\n"
]
}
],
"source": [
"print(list(zip(iris.target,kmeans.labels_)))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.7514854021988338\n",
"0.7649861514489815\n",
"0.7302382722834697\n",
"0.5528190123564091\n"
]
}
],
"source": [
"print(metrics.homogeneity_score(iris.target, kmeans2.labels_))\n",
"print(metrics.completeness_score(iris.target, kmeans2.labels_))\n",
"print(metrics.adjusted_rand_score(iris.target, kmeans2.labels_))\n",
"print(metrics.silhouette_score(iris.data, kmeans2.labels_))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Einfuehrung/unterlagen/07_SupervisedLearning_v02.pdf
BIN
View File
Binary file not shown.
Einfuehrung/unterlagen/08_NB_Digits.ipynb
+141
View File
@@ -0,0 +1,141 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(1797, 64)\n"
]
}
],
"source": [
"from sklearn import datasets\n",
"digits = datasets.load_digits()\n",
"print(digits.data.shape)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(1437, 64)\n",
"(1437,)\n"
]
}
],
"source": [
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target, test_size=0.2, random_state=0)\n",
"print(X_train.shape)\n",
"print(y_train.shape)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.82499999999999996"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.naive_bayes import GaussianNB\n",
"nb = GaussianNB()\n",
"nb.fit(X_train, y_train)\n",
"nb.score(X_test,y_test)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.85833333333333328"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.tree import DecisionTreeClassifier\n",
"dt = DecisionTreeClassifier()\n",
"dt.fit(X_train, y_train)\n",
"dt.score(X_test,y_test)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy 0.95 confidence interval: 0.81 (+/- 0.11)\n"
]
}
],
"source": [
"from sklearn.naive_bayes import GaussianNB\n",
"from sklearn.model_selection import cross_val_score\n",
"nb2 = GaussianNB()\n",
"scores = cross_val_score(nb2, digits.data, digits.target, cv=10)\n",
"print(\"Accuracy 0.95 confidence interval: %0.2f (+/- %0.2f)\" % (scores.mean(), scores.std() * 2))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Einfuehrung/unterlagen/08_NB_Iris.ipynb
+141
View File
@@ -0,0 +1,141 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(150, 4)\n"
]
}
],
"source": [
"from sklearn import datasets\n",
"iris = datasets.load_iris()\n",
"print(iris.data.shape)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(120, 4)\n",
"(120,)\n"
]
}
],
"source": [
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=0)\n",
"print(X_train.shape)\n",
"print(y_train.shape)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.96666666666666667"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.naive_bayes import GaussianNB\n",
"nb = GaussianNB()\n",
"nb.fit(X_train, y_train)\n",
"nb.score(X_test,y_test)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1.0"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.tree import DecisionTreeClassifier\n",
"dt = DecisionTreeClassifier()\n",
"dt.fit(X_train, y_train)\n",
"dt.score(X_test,y_test)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy 0.95 confidence interval: 0.95 (+/- 0.09)\n"
]
}
],
"source": [
"from sklearn.naive_bayes import GaussianNB\n",
"from sklearn.model_selection import cross_val_score\n",
"nb2 = GaussianNB()\n",
"scores = cross_val_score(nb2, iris.data, iris.target, cv=10)\n",
"print(\"Accuracy 0.95 confidence interval: %0.2f (+/- %0.2f)\" % (scores.mean(), scores.std() * 2))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Einfuehrung/unterlagen/08_NaiveBayes_project_v02.pdf
BIN
View File
Binary file not shown.