noshot 7.0.0__py3-none-any.whl → 9.0.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (67) hide show
  1. noshot/data/ML TS XAI/ML/CNN(Image_for_Folders_5).ipynb +201 -0
  2. noshot/data/ML TS XAI/ML/CNN(Image_form_Folder_2).ipynb +201 -0
  3. noshot/data/ML TS XAI/ML/Json Codes/ML LAB CIA 2.ipynb +409 -0
  4. noshot/data/ML TS XAI/ML/ML 3 (Latest)/1. PCA EDA.ipynb +274 -0
  5. noshot/data/ML TS XAI/ML/ML 3 (Latest)/10. CNN.ipynb +170 -0
  6. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM 2.ipynb +1087 -0
  7. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM 3.ipynb +178 -0
  8. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM 4.ipynb +185 -0
  9. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM.ipynb +106 -0
  10. noshot/data/ML TS XAI/ML/ML 3 (Latest)/2. KNN.ipynb +177 -0
  11. noshot/data/ML TS XAI/ML/ML 3 (Latest)/3. LDA.ipynb +195 -0
  12. noshot/data/ML TS XAI/ML/ML 3 (Latest)/4. Linear Regression.ipynb +267 -0
  13. noshot/data/ML TS XAI/ML/ML 3 (Latest)/5. Logistic Regression.ipynb +104 -0
  14. noshot/data/ML TS XAI/ML/ML 3 (Latest)/6. Bayesian Classifier.ipynb +109 -0
  15. noshot/data/ML TS XAI/ML/ML 3 (Latest)/7. SVM.ipynb +220 -0
  16. noshot/data/ML TS XAI/ML/ML 3 (Latest)/8. MLP.ipynb +99 -0
  17. noshot/data/ML TS XAI/ML/ML 3 (Latest)/9. Ridge - Lasso.ipynb +211 -0
  18. noshot/data/ML TS XAI/ML/ML 3 (Latest)/9. Ridge Lasso 2.ipynb +99 -0
  19. noshot/data/ML TS XAI/ML/ML 3 (Latest)/Image Load Example.ipynb +118 -0
  20. noshot/data/ML TS XAI/ML/ML 3 (Latest)/Updated_Untitled.ipynb +603 -0
  21. noshot/data/ML TS XAI/ML/ML Lab H Sec/1. Iris Dataset (Softmax vs Sigmoid).ipynb +231 -0
  22. noshot/data/ML TS XAI/ML/ML Lab H Sec/2. Student Dataset (Overfit vs Regularized).ipynb +269 -0
  23. noshot/data/ML TS XAI/ML/ML Lab H Sec/3. Insurance Target Categorical (Overfit vs Regularized).ipynb +274 -0
  24. noshot/data/ML TS XAI/ML/ML Lab H Sec/3. Insurance Target Numerical (Overfit vs Regularized).ipynb +263 -0
  25. noshot/data/ML TS XAI/ML/ML Lab H Sec/4. Smart House System HMM.ipynb +198 -0
  26. noshot/data/ML TS XAI/ML/ML Lab H Sec/5. Fraud Detection System HMM.ipynb +201 -0
  27. noshot/data/ML TS XAI/ML/ML Lab H Sec/insurance.csv +1339 -0
  28. noshot/data/ML TS XAI/ML/ML Lab H Sec/iris1.data +151 -0
  29. noshot/data/ML TS XAI/ML/ML Lab H Sec/student-mat.csv +396 -0
  30. noshot/data/ML TS XAI/ML/ML Lab H Sec/student-por.csv +650 -0
  31. {noshot-7.0.0.dist-info → noshot-9.0.0.dist-info}/METADATA +1 -1
  32. noshot-9.0.0.dist-info/RECORD +71 -0
  33. noshot-7.0.0.dist-info/RECORD +0 -41
  34. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/1. EDA-PCA (Balance Scale Dataset).ipynb +0 -0
  35. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/1. EDA-PCA (Rice Dataset).ipynb +0 -0
  36. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/10. HMM Veterbi.ipynb +0 -0
  37. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/2. KNN (Balance Scale Dataset).ipynb +0 -0
  38. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/2. KNN (Iris Dataset).ipynb +0 -0
  39. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/2. KNN (Sobar-72 Dataset).ipynb +0 -0
  40. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/3. LDA (Balance Scale Dataset).ipynb +0 -0
  41. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/3. LDA (NPHA Doctor Visits Dataset).ipynb +0 -0
  42. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/4. Linear Regression (Machine Dataset).ipynb +0 -0
  43. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/4. Linear Regression (Real Estate Dataset).ipynb +0 -0
  44. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/5. Logistic Regression (Magic04 Dataset).ipynb +0 -0
  45. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/5. Logistic Regression (Wine Dataset).ipynb +0 -0
  46. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/6. Naive Bayes Classifier (Agaricus Lepiota Dataset).ipynb +0 -0
  47. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/6. Naive Bayes Classifier (Wine Dataset).ipynb +0 -0
  48. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/7. SVM (Rice Dataset).ipynb +0 -0
  49. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/8. FeedForward NN (Sobar72 Dataset).ipynb +0 -0
  50. /noshot/data/ML TS XAI/ML/{Tamilan Code → ML 1}/9. CNN (Cifar10 Dataset).ipynb +0 -0
  51. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/1. PCA.ipynb +0 -0
  52. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/10. CNN.ipynb +0 -0
  53. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/11. HMM.ipynb +0 -0
  54. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/2. KNN.ipynb +0 -0
  55. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/3. LDA.ipynb +0 -0
  56. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/4. Linear Regression.ipynb +0 -0
  57. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/5. Logistic Regression.ipynb +0 -0
  58. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/6. Naive Bayes (Titanic).ipynb +0 -0
  59. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/6. Naive Bayes (Wine).ipynb +0 -0
  60. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/7. SVM Linear.ipynb +0 -0
  61. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/8. SVM Non-Linear.ipynb +0 -0
  62. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/9. FNN With Regularization.ipynb +0 -0
  63. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/9. FNN Without Regularization.ipynb +0 -0
  64. /noshot/data/ML TS XAI/ML/{Whitefang Code → ML 2}/All in One Lab CIA 1 Q.ipynb +0 -0
  65. {noshot-7.0.0.dist-info → noshot-9.0.0.dist-info}/WHEEL +0 -0
  66. {noshot-7.0.0.dist-info → noshot-9.0.0.dist-info}/licenses/LICENSE.txt +0 -0
  67. {noshot-7.0.0.dist-info → noshot-9.0.0.dist-info}/top_level.txt +0 -0
noshot/data/ML TS XAI/ML/ML 3 (Latest)/7. SVM.ipynb ADDED
@@ -0,0 +1,220 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "a2ef0ba6",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import numpy as np\n",
12
+ "import matplotlib.pyplot as plt\n",
13
+ "from sklearn.model_selection import train_test_split\n",
14
+ "from sklearn.preprocessing import StandardScaler\n",
15
+ "from sklearn import svm\n",
16
+ "import seaborn as sns\n",
17
+ "from sklearn.metrics import confusion_matrix,classification_report"
18
+ ]
19
+ },
20
+ {
21
+ "cell_type": "code",
22
+ "execution_count": null,
23
+ "id": "00a3a522",
24
+ "metadata": {},
25
+ "outputs": [],
26
+ "source": [
27
+ "df = pd.read_csv(r'heart.csv')"
28
+ ]
29
+ },
30
+ {
31
+ "cell_type": "code",
32
+ "execution_count": null,
33
+ "id": "585147d0",
34
+ "metadata": {},
35
+ "outputs": [],
36
+ "source": [
37
+ "df"
38
+ ]
39
+ },
40
+ {
41
+ "cell_type": "code",
42
+ "execution_count": null,
43
+ "id": "37e34b42",
44
+ "metadata": {},
45
+ "outputs": [],
46
+ "source": [
47
+ "plt.figure(figsize=(12,12))\n",
48
+ "sns.heatmap(df.corr(),annot = True)"
49
+ ]
50
+ },
51
+ {
52
+ "cell_type": "code",
53
+ "execution_count": null,
54
+ "id": "3cfbbed7",
55
+ "metadata": {},
56
+ "outputs": [],
57
+ "source": [
58
+ "X = pd.DataFrame(df, columns = ['cp','oldpeak']) #pd.DataFrame(df, columns = ['cp','thalach','exang','oldpeak'])\n",
59
+ "X\n",
60
+ "feature_names = X.columns"
61
+ ]
62
+ },
63
+ {
64
+ "cell_type": "code",
65
+ "execution_count": null,
66
+ "id": "376a937f",
67
+ "metadata": {},
68
+ "outputs": [],
69
+ "source": [
70
+ "y = pd.DataFrame(df, columns = ['target'])\n",
71
+ "y"
72
+ ]
73
+ },
74
+ {
75
+ "cell_type": "code",
76
+ "execution_count": null,
77
+ "id": "e36bd8e4",
78
+ "metadata": {},
79
+ "outputs": [],
80
+ "source": [
81
+ "scaler = StandardScaler()"
82
+ ]
83
+ },
84
+ {
85
+ "cell_type": "code",
86
+ "execution_count": null,
87
+ "id": "d44d0fc8",
88
+ "metadata": {},
89
+ "outputs": [],
90
+ "source": [
91
+ "X = scaler.fit_transform(X)"
92
+ ]
93
+ },
94
+ {
95
+ "cell_type": "code",
96
+ "execution_count": null,
97
+ "id": "f4134da1",
98
+ "metadata": {},
99
+ "outputs": [],
100
+ "source": [
101
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
102
+ ]
103
+ },
104
+ {
105
+ "cell_type": "code",
106
+ "execution_count": null,
107
+ "id": "a51186d3",
108
+ "metadata": {},
109
+ "outputs": [],
110
+ "source": [
111
+ "model = svm.SVC(kernel='linear', C=0.01)"
112
+ ]
113
+ },
114
+ {
115
+ "cell_type": "code",
116
+ "execution_count": null,
117
+ "id": "ea6edc2d",
118
+ "metadata": {},
119
+ "outputs": [],
120
+ "source": [
121
+ "model.fit(X_train, y_train)"
122
+ ]
123
+ },
124
+ {
125
+ "cell_type": "code",
126
+ "execution_count": null,
127
+ "id": "19476831",
128
+ "metadata": {},
129
+ "outputs": [],
130
+ "source": [
131
+ "y_train_pred = model.predict(X_train)\n",
132
+ "y_test_pred = model.predict(X_test)"
133
+ ]
134
+ },
135
+ {
136
+ "cell_type": "code",
137
+ "execution_count": null,
138
+ "id": "2a02f42a",
139
+ "metadata": {},
140
+ "outputs": [],
141
+ "source": [
142
+ "y_test_pred"
143
+ ]
144
+ },
145
+ {
146
+ "cell_type": "code",
147
+ "execution_count": null,
148
+ "id": "f73bfed0",
149
+ "metadata": {},
150
+ "outputs": [],
151
+ "source": [
152
+ "x_min, x_max = X_train[:, 0].min() - 1, X_train[:, 0].max() + 1\n",
153
+ "y_min, y_max = X_train[:, 1].min() - 1, X_train[:, 1].max() + 1\n",
154
+ "xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),\n",
155
+ " np.arange(y_min, y_max, 0.02))\n",
156
+ " \n",
157
+ "# Predict the decision boundary\n",
158
+ "Z = model.predict(np.c_[xx.ravel(), yy.ravel()])\n",
159
+ "Z = Z.reshape(xx.shape)\n",
160
+ "\n",
161
+ "# Plot the decision boundary\n",
162
+ "plt.contourf(xx, yy, Z, alpha=0.8)\n",
163
+ "plt.scatter(X[:, 0], X[:, 1], c=np.array(y), edgecolors='k', marker='o')\n",
164
+ "plt.title('SVM Decision Boundary')\n",
165
+ "plt.xlabel('Feature 1')\n",
166
+ "plt.ylabel('Feature 2')\n",
167
+ "plt.show()"
168
+ ]
169
+ },
170
+ {
171
+ "cell_type": "code",
172
+ "execution_count": null,
173
+ "id": "19439ba8",
174
+ "metadata": {},
175
+ "outputs": [],
176
+ "source": [
177
+ "y_pred = model.predict(X)\n",
178
+ "\n",
179
+ "# Create the confusion matrix\n",
180
+ "cm = confusion_matrix(y_test, y_test_pred)\n",
181
+ "class_report = classification_report(y_test, y_test_pred)\n",
182
+ "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')\n",
183
+ "plt.xlabel('Predicted')\n",
184
+ "plt.ylabel('True')\n",
185
+ "plt.title('Confusion Matrix')\n",
186
+ "plt.show()\n",
187
+ "print(class_report)"
188
+ ]
189
+ },
190
+ {
191
+ "cell_type": "code",
192
+ "execution_count": null,
193
+ "id": "6625955c",
194
+ "metadata": {},
195
+ "outputs": [],
196
+ "source": []
197
+ }
198
+ ],
199
+ "metadata": {
200
+ "kernelspec": {
201
+ "display_name": "Python 3 (ipykernel)",
202
+ "language": "python",
203
+ "name": "python3"
204
+ },
205
+ "language_info": {
206
+ "codemirror_mode": {
207
+ "name": "ipython",
208
+ "version": 3
209
+ },
210
+ "file_extension": ".py",
211
+ "mimetype": "text/x-python",
212
+ "name": "python",
213
+ "nbconvert_exporter": "python",
214
+ "pygments_lexer": "ipython3",
215
+ "version": "3.12.4"
216
+ }
217
+ },
218
+ "nbformat": 4,
219
+ "nbformat_minor": 5
220
+ }
noshot/data/ML TS XAI/ML/ML 3 (Latest)/8. MLP.ipynb ADDED
@@ -0,0 +1,99 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "17a00ba2-2808-4921-9df4-79a2911bc670",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import numpy as np\n",
12
+ "import matplotlib.pyplot as plt\n",
13
+ "from sklearn.model_selection import train_test_split\n",
14
+ "from sklearn.metrics import classification_report, confusion_matrix\n",
15
+ "from sklearn.neural_network import MLPClassifier\n",
16
+ "\n",
17
+ "# Upload and read dataset\n",
18
+ "df = pd.read_csv('heart.csv')\n",
19
+ "print(f\"Dataset shape: {df.shape}\")\n",
20
+ "\n",
21
+ "# Normalize predictors\n",
22
+ "target_column = 'target'\n",
23
+ "predictors = [col for col in df.columns if col != target_column]\n",
24
+ "df[predictors] = df[predictors] / df[predictors].max()\n",
25
+ "\n",
26
+ "# Split data\n",
27
+ "X = df[predictors].values\n",
28
+ "y = df[target_column].values\n",
29
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=40)\n",
30
+ "print(f\"Training shape: {X_train.shape} | Testing shape: {X_test.shape}\")\n",
31
+ "\n",
32
+ "# Function to train and evaluate MLPClassifier\n",
33
+ "def train_and_evaluate(activation, hidden_layers=(8,8,8), max_iter=500):\n",
34
+ " print(f\"\\nTraining with activation='{activation}' and hidden_layers={hidden_layers}\")\n",
35
+ " mlp = MLPClassifier(hidden_layer_sizes=hidden_layers, activation=activation,\n",
36
+ " solver='adam', max_iter=max_iter, random_state=42)\n",
37
+ " mlp.fit(X_train, y_train)\n",
38
+ "\n",
39
+ " predict_train = mlp.predict(X_train)\n",
40
+ " predict_test = mlp.predict(X_test)\n",
41
+ "\n",
42
+ " print(\"\\nTrain Results:\")\n",
43
+ " print(confusion_matrix(y_train, predict_train))\n",
44
+ " print(classification_report(y_train, predict_train, zero_division=0))\n",
45
+ "\n",
46
+ " print(\"\\nTest Results:\")\n",
47
+ " print(confusion_matrix(y_test, predict_test))\n",
48
+ " print(classification_report(y_test, predict_test, zero_division=0))\n",
49
+ "\n",
50
+ "\n",
51
+ "# Try different activation functions\n",
52
+ "for activation in ['relu', 'identity', 'tanh', 'logistic']:\n",
53
+ " train_and_evaluate(activation)\n",
54
+ "\n",
55
+ "# Try different hidden layer configuration\n",
56
+ "train_and_evaluate('relu', hidden_layers=(10,10,10))\n"
57
+ ]
58
+ },
59
+ {
60
+ "cell_type": "code",
61
+ "execution_count": null,
62
+ "id": "171896d2-bf99-4d87-9cde-212df4c49cc1",
63
+ "metadata": {},
64
+ "outputs": [],
65
+ "source": [
66
+ "X_train"
67
+ ]
68
+ },
69
+ {
70
+ "cell_type": "code",
71
+ "execution_count": null,
72
+ "id": "59dd64e2-cca8-4b35-93d8-dbe7b30da280",
73
+ "metadata": {},
74
+ "outputs": [],
75
+ "source": []
76
+ }
77
+ ],
78
+ "metadata": {
79
+ "kernelspec": {
80
+ "display_name": "Python 3 (ipykernel)",
81
+ "language": "python",
82
+ "name": "python3"
83
+ },
84
+ "language_info": {
85
+ "codemirror_mode": {
86
+ "name": "ipython",
87
+ "version": 3
88
+ },
89
+ "file_extension": ".py",
90
+ "mimetype": "text/x-python",
91
+ "name": "python",
92
+ "nbconvert_exporter": "python",
93
+ "pygments_lexer": "ipython3",
94
+ "version": "3.12.4"
95
+ }
96
+ },
97
+ "nbformat": 4,
98
+ "nbformat_minor": 5
99
+ }
noshot/data/ML TS XAI/ML/ML 3 (Latest)/9. Ridge - Lasso.ipynb ADDED
@@ -0,0 +1,211 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "80023338-3fbf-47f2-adf2-0692417a70fe",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import numpy as np\n",
11
+ "import pandas as pd\n",
12
+ "import matplotlib.pyplot as plt\n",
13
+ "from sklearn.linear_model import Ridge, Lasso, LinearRegression, SGDRegressor\n",
14
+ "from sklearn.pipeline import make_pipeline\n",
15
+ "from sklearn.preprocessing import PolynomialFeatures, StandardScaler\n",
16
+ "\n",
17
+ "# --------------------------\n",
18
+ "# Data Preparation\n",
19
+ "# --------------------------\n",
20
+ "np.random.seed(42)\n",
21
+ "m = 20\n",
22
+ "x = 3 * np.random.rand(m, 1)\n",
23
+ "y = 1 + 0.5 * x + np.random.randn(m, 1) / 1.5\n",
24
+ "x_new = np.linspace(0, 3, 100).reshape(100, 1)\n",
25
+ "\n",
26
+ "# --------------------------\n",
27
+ "# Helper Functions\n",
28
+ "# --------------------------\n",
29
+ "def plot_data(x, y):\n",
30
+ " plt.figure(figsize=(6, 4))\n",
31
+ " plt.plot(x, y, \"b.\")\n",
32
+ " plt.xlabel(\"x1\")\n",
33
+ " plt.ylabel(\"y\")\n",
34
+ " plt.axis([0, 3, 0, 3.5])\n",
35
+ " plt.grid()\n",
36
+ " plt.show()\n",
37
+ "\n",
38
+ "def plot_model(model_class, polynomial, alphas, **model_kwargs):\n",
39
+ " plt.plot(x, y, \"b.\", linewidth=3)\n",
40
+ " for alpha, style in zip(alphas, (\"b:\", \"g--\", \"r-\")):\n",
41
+ " model = model_class(alpha, **model_kwargs) if alpha > 0 else LinearRegression()\n",
42
+ " if polynomial:\n",
43
+ " model = make_pipeline(\n",
44
+ " PolynomialFeatures(degree=10, include_bias=False),\n",
45
+ " StandardScaler(),\n",
46
+ " model\n",
47
+ " )\n",
48
+ " model.fit(x, y)\n",
49
+ " y_pred = model.predict(x_new)\n",
50
+ " plt.plot(x_new, y_pred, style, linewidth=2, label=fr\"$\\alpha = {alpha}$\")\n",
51
+ " plt.legend(loc=\"upper left\")\n",
52
+ " plt.xlabel(\"$x_1$\")\n",
53
+ " plt.axis([0, 3, 0, 3.5])\n",
54
+ " plt.grid()\n",
55
+ "\n",
56
+ "# --------------------------\n",
57
+ "# Initial Data Plot\n",
58
+ "# --------------------------\n",
59
+ "plot_data(x, y)\n",
60
+ "\n",
61
+ "# --------------------------\n",
62
+ "# Ridge Regression\n",
63
+ "# --------------------------\n",
64
+ "ridge = Ridge(alpha=0.1, solver=\"cholesky\")\n",
65
+ "ridge.fit(x, y)\n",
66
+ "print(\"Ridge prediction at x=1.5:\", ridge.predict([[1.5]]))\n",
67
+ "\n",
68
+ "plt.figure(figsize=(9, 3.5))\n",
69
+ "plt.subplot(121)\n",
70
+ "plot_model(Ridge, polynomial=False, alphas=(0, 10, 100), random_state=42)\n",
71
+ "plt.ylabel(\"$y$\", rotation=0)\n",
72
+ "plt.subplot(122)\n",
73
+ "plot_model(Ridge, polynomial=True, alphas=(0, 1e-5, 1), random_state=42)\n",
74
+ "plt.gca().axes.yaxis.set_ticklabels([])\n",
75
+ "plt.show()\n",
76
+ "\n",
77
+ "# --------------------------\n",
78
+ "# Stochastic Gradient Descent Ridge\n",
79
+ "# --------------------------\n",
80
+ "sgd_reg = SGDRegressor(penalty=\"l2\", alpha=0.1/m, tol=None,\n",
81
+ " max_iter=1000, eta0=0.01, random_state=42)\n",
82
+ "sgd_reg.fit(x, y.ravel())\n",
83
+ "print(\"SGD prediction at x=1.5:\", sgd_reg.predict([[1.5]]))\n",
84
+ "\n",
85
+ "# Ridge with SAG solver\n",
86
+ "ridge_reg = Ridge(alpha=0.1, solver=\"sag\", random_state=42)\n",
87
+ "ridge_reg.fit(x, y)\n",
88
+ "print(\"Ridge (sag) prediction at x=1.5:\", ridge_reg.predict([[1.5]]))\n",
89
+ "\n",
90
+ "# Closed form Ridge solution\n",
91
+ "alpha = 0.1\n",
92
+ "A = np.array([[0., 0.], [0., 1.]])\n",
93
+ "X_b = np.c_[np.ones((m, 1)), x]\n",
94
+ "theta_ridge = np.linalg.inv(X_b.T @ X_b + alpha * A) @ X_b.T @ y\n",
95
+ "print(\"Closed-form Ridge solution:\\n\", theta_ridge)\n",
96
+ "print(\"Model intercept and coefficients:\", ridge_reg.intercept_, ridge_reg.coef_)\n",
97
+ "\n",
98
+ "# --------------------------\n",
99
+ "# Lasso Regression\n",
100
+ "# --------------------------\n",
101
+ "lasso_reg = Lasso(alpha=0.1)\n",
102
+ "lasso_reg.fit(x, y)\n",
103
+ "print(\"Lasso prediction at x=1.5:\", lasso_reg.predict([[1.5]]))\n",
104
+ "\n",
105
+ "plt.figure(figsize=(9, 3.5))\n",
106
+ "plt.subplot(121)\n",
107
+ "plot_model(Lasso, polynomial=False, alphas=(0, 0.1, 1), random_state=42)\n",
108
+ "plt.ylabel(\"$y$\", rotation=0)\n",
109
+ "plt.subplot(122)\n",
110
+ "plot_model(Lasso, polynomial=True, alphas=(0, 1e-2, 1), random_state=42)\n",
111
+ "plt.gca().axes.yaxis.set_ticklabels([])\n",
112
+ "plt.show()\n",
113
+ "\n",
114
+ "# --------------------------\n",
115
+ "# Contour Plot: L1 (Lasso) vs L2 (Ridge)\n",
116
+ "# --------------------------\n",
117
+ "def bgd_path(theta, X, y, l1, l2, core=1, eta=0.05, n_iterations=200):\n",
118
+ " path = [theta]\n",
119
+ " for _ in range(n_iterations):\n",
120
+ " gradients = (core * 2 / len(X) * X.T @ (X @ theta - y)\n",
121
+ " + l1 * np.sign(theta) + l2 * theta)\n",
122
+ " theta = theta - eta * gradients\n",
123
+ " path.append(theta)\n",
124
+ " return np.array(path)\n",
125
+ "\n",
126
+ "# Prepare data for contour plots\n",
127
+ "t1s = np.linspace(-1, 3, 500)\n",
128
+ "t2s = np.linspace(-1.5, 1.5, 500)\n",
129
+ "t1, t2 = np.meshgrid(t1s, t2s)\n",
130
+ "T = np.c_[t1.ravel(), t2.ravel()]\n",
131
+ "Xr = np.array([[1, 1], [1, -1], [1, 0.5]])\n",
132
+ "yr = 2 * Xr[:, :1] + 0.5 * Xr[:, 1:]\n",
133
+ "J = (1 / len(Xr) * ((T @ Xr.T - yr.T) ** 2).sum(axis=1)).reshape(t1.shape)\n",
134
+ "N1 = np.linalg.norm(T, ord=1, axis=1).reshape(t1.shape)\n",
135
+ "N2 = np.linalg.norm(T, ord=2, axis=1).reshape(t1.shape)\n",
136
+ "\n",
137
+ "# Plot contours\n",
138
+ "fig, axes = plt.subplots(2, 2, sharex=True, sharey=True, figsize=(10.1, 8))\n",
139
+ "titles = [\"Lasso\", \"Ridge\"]\n",
140
+ "\n",
141
+ "for i, (N, l1, l2) in enumerate([(N1, 2.0, 0), (N2, 0, 2.0)]):\n",
142
+ " JR = J + l1 * N1 + l2 * 0.5 * N2**2\n",
143
+ " t_min_idx = np.unravel_index(J.argmin(), J.shape)\n",
144
+ " t1_min, t2_min = t1[t_min_idx], t2[t_min_idx]\n",
145
+ " tr_min_idx = np.unravel_index(JR.argmin(), JR.shape)\n",
146
+ " t1r_min, t2r_min = t1[tr_min_idx], t2[tr_min_idx]\n",
147
+ "\n",
148
+ " levelsJ = np.exp(np.linspace(0, 1, 20)) - 1\n",
149
+ " levelsJR = levelsJ * (JR.max() - JR.min()) + JR.min()\n",
150
+ " levelsN = np.linspace(0, N.max(), 10)\n",
151
+ "\n",
152
+ " path_J = bgd_path(np.array([[0.25], [-1]]), Xr, yr, l1=0, l2=0)\n",
153
+ " path_JR = bgd_path(np.array([[0.25], [-1]]), Xr, yr, l1, l2)\n",
154
+ " path_N = bgd_path(np.array([[2.0], [0.5]]), Xr, yr, l1=np.sign(l1)/3, l2=np.sign(l2), core=0)\n",
155
+ "\n",
156
+ " ax = axes[i, 0]\n",
157
+ " ax.contourf(t1, t2, N/2, levels=levelsN)\n",
158
+ " ax.plot(path_N[:, 0], path_N[:, 1], \"y--\")\n",
159
+ " ax.plot(0, 0, \"ys\")\n",
160
+ " ax.plot(t1_min, t2_min, \"ys\")\n",
161
+ " ax.set_title(fr\"$\\ell_{i + 1}$ penalty\")\n",
162
+ " ax.grid()\n",
163
+ " if i == 1:\n",
164
+ " ax.set_xlabel(r\"$\\theta_1$\")\n",
165
+ " ax.set_ylabel(r\"$\\theta_2$\", rotation=0)\n",
166
+ "\n",
167
+ " ax = axes[i, 1]\n",
168
+ " ax.contourf(t1, t2, JR, levels=levelsJR, alpha=0.9)\n",
169
+ " ax.plot(path_JR[:, 0], path_JR[:, 1], \"w-o\")\n",
170
+ " ax.plot(path_N[:, 0], path_N[:, 1], \"y--\")\n",
171
+ " ax.plot(0, 0, \"ys\")\n",
172
+ " ax.plot(t1_min, t2_min, \"ys\")\n",
173
+ " ax.plot(t1r_min, t2r_min, \"rs\")\n",
174
+ " ax.set_title(titles[i])\n",
175
+ " ax.grid()\n",
176
+ " if i == 1:\n",
177
+ " ax.set_xlabel(r\"$\\theta_1$\")\n",
178
+ "plt.show()\n"
179
+ ]
180
+ },
181
+ {
182
+ "cell_type": "code",
183
+ "execution_count": null,
184
+ "id": "6b3caebd-8202-4f65-8b66-0a6e09d81b3a",
185
+ "metadata": {},
186
+ "outputs": [],
187
+ "source": []
188
+ }
189
+ ],
190
+ "metadata": {
191
+ "kernelspec": {
192
+ "display_name": "Python 3 (ipykernel)",
193
+ "language": "python",
194
+ "name": "python3"
195
+ },
196
+ "language_info": {
197
+ "codemirror_mode": {
198
+ "name": "ipython",
199
+ "version": 3
200
+ },
201
+ "file_extension": ".py",
202
+ "mimetype": "text/x-python",
203
+ "name": "python",
204
+ "nbconvert_exporter": "python",
205
+ "pygments_lexer": "ipython3",
206
+ "version": "3.12.4"
207
+ }
208
+ },
209
+ "nbformat": 4,
210
+ "nbformat_minor": 5
211
+ }
noshot/data/ML TS XAI/ML/ML 3 (Latest)/9. Ridge Lasso 2.ipynb ADDED
@@ -0,0 +1,99 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "d239aa84-e577-42a1-98d3-127530ffb38e",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import numpy as np\n",
11
+ "import matplotlib.pyplot as plt\n",
12
+ "from sklearn.linear_model import Ridge, Lasso\n",
13
+ "from sklearn.datasets import make_regression\n",
14
+ "\n",
15
+ "# Create a sample dataset\n",
16
+ "X, y = make_regression(n_samples=100, n_features=20, noise=0.1, random_state=42)\n",
17
+ "\n",
18
+ "# Range of alpha values (regularization strength)\n",
19
+ "alphas = np.logspace(-3, 3, 100)\n",
20
+ "\n",
21
+ "ridge_coefs = []\n",
22
+ "lasso_coefs = []\n",
23
+ "\n",
24
+ "for alpha in alphas:\n",
25
+ " # Ridge\n",
26
+ " ridge = Ridge(alpha=alpha)\n",
27
+ " ridge.fit(X, y)\n",
28
+ " ridge_coefs.append(ridge.coef_)\n",
29
+ " \n",
30
+ " # Lasso\n",
31
+ " lasso = Lasso(alpha=alpha, max_iter=10000)\n",
32
+ " lasso.fit(X, y)\n",
33
+ " lasso_coefs.append(lasso.coef_)\n",
34
+ "\n",
35
+ "ridge_coefs = np.array(ridge_coefs)\n",
36
+ "lasso_coefs = np.array(lasso_coefs)\n",
37
+ "\n",
38
+ "# ----------------------\n",
39
+ "# Ridge plot\n",
40
+ "# ----------------------\n",
41
+ "plt.figure(figsize=(10, 6))\n",
42
+ "for i in range(X.shape[1]):\n",
43
+ " plt.plot(alphas, ridge_coefs[:, i], label=f'Feature {i}')\n",
44
+ "plt.xscale('log')\n",
45
+ "plt.title('Ridge Coefficients vs Alpha')\n",
46
+ "plt.xlabel('Alpha (log scale)')\n",
47
+ "plt.ylabel('Coefficient value')\n",
48
+ "plt.grid(True)\n",
49
+ "plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left', fontsize=8)\n",
50
+ "plt.tight_layout()\n",
51
+ "plt.show()\n",
52
+ "\n",
53
+ "# ----------------------\n",
54
+ "# Lasso plot\n",
55
+ "# ----------------------\n",
56
+ "plt.figure(figsize=(10, 6))\n",
57
+ "for i in range(X.shape[1]):\n",
58
+ " plt.plot(alphas, lasso_coefs[:, i], label=f'Feature {i}')\n",
59
+ "plt.xscale('log')\n",
60
+ "plt.title('Lasso Coefficients vs Alpha')\n",
61
+ "plt.xlabel('Alpha (log scale)')\n",
62
+ "plt.ylabel('Coefficient value')\n",
63
+ "plt.grid(True)\n",
64
+ "plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left', fontsize=8)\n",
65
+ "plt.tight_layout()\n",
66
+ "plt.show()\n"
67
+ ]
68
+ },
69
+ {
70
+ "cell_type": "code",
71
+ "execution_count": null,
72
+ "id": "afdde643-5984-485e-aa6d-508602cc8f51",
73
+ "metadata": {},
74
+ "outputs": [],
75
+ "source": []
76
+ }
77
+ ],
78
+ "metadata": {
79
+ "kernelspec": {
80
+ "display_name": "Python 3 (ipykernel)",
81
+ "language": "python",
82
+ "name": "python3"
83
+ },
84
+ "language_info": {
85
+ "codemirror_mode": {
86
+ "name": "ipython",
87
+ "version": 3
88
+ },
89
+ "file_extension": ".py",
90
+ "mimetype": "text/x-python",
91
+ "name": "python",
92
+ "nbconvert_exporter": "python",
93
+ "pygments_lexer": "ipython3",
94
+ "version": "3.12.4"
95
+ }
96
+ },
97
+ "nbformat": 4,
98
+ "nbformat_minor": 5
99
+ }