noshot 5.0.0__py3-none-any.whl → 7.0.0__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 (43) hide show
  1. noshot/data/ML TS XAI/ML/Rolls Royce AllinOne.ipynb +691 -0
  2. noshot/data/ML TS XAI/ML/Tamilan Code/1. EDA-PCA (Balance Scale Dataset).ipynb +147 -0
  3. noshot/data/ML TS XAI/ML/Tamilan Code/1. EDA-PCA (Rice Dataset).ipynb +181 -0
  4. noshot/data/ML TS XAI/ML/Tamilan Code/10. HMM Veterbi.ipynb +152 -0
  5. noshot/data/ML TS XAI/ML/Tamilan Code/2. KNN (Balance Scale Dataset).ipynb +117 -0
  6. noshot/data/ML TS XAI/ML/Tamilan Code/2. KNN (Iris Dataset).ipynb +156 -0
  7. noshot/data/ML TS XAI/ML/Tamilan Code/2. KNN (Sobar-72 Dataset).ipynb +215 -0
  8. noshot/data/ML TS XAI/ML/Tamilan Code/3. LDA (Balance Scale Dataset).ipynb +78 -0
  9. noshot/data/ML TS XAI/ML/Tamilan Code/3. LDA (NPHA Doctor Visits Dataset).ipynb +114 -0
  10. noshot/data/ML TS XAI/ML/Tamilan Code/4. Linear Regression (Machine Dataset).ipynb +115 -0
  11. noshot/data/ML TS XAI/ML/Tamilan Code/4. Linear Regression (Real Estate Dataset).ipynb +146 -0
  12. noshot/data/ML TS XAI/ML/Tamilan Code/5. Logistic Regression (Magic04 Dataset).ipynb +130 -0
  13. noshot/data/ML TS XAI/ML/Tamilan Code/5. Logistic Regression (Wine Dataset).ipynb +112 -0
  14. noshot/data/ML TS XAI/ML/Tamilan Code/6. Naive Bayes Classifier (Agaricus Lepiota Dataset).ipynb +118 -0
  15. noshot/data/ML TS XAI/ML/Tamilan Code/6. Naive Bayes Classifier (Wine Dataset).ipynb +89 -0
  16. noshot/data/ML TS XAI/ML/Tamilan Code/7. SVM (Rice Dataset).ipynb +120 -0
  17. noshot/data/ML TS XAI/ML/Tamilan Code/8. FeedForward NN (Sobar72 Dataset).ipynb +262 -0
  18. noshot/data/ML TS XAI/ML/Tamilan Code/9. CNN (Cifar10 Dataset).ipynb +156 -0
  19. noshot/data/ML TS XAI/ML/Whitefang Code/1. PCA.ipynb +162 -0
  20. noshot/data/ML TS XAI/ML/Whitefang Code/10. CNN.ipynb +100 -0
  21. noshot/data/ML TS XAI/ML/Whitefang Code/11. HMM.ipynb +336 -0
  22. noshot/data/ML TS XAI/ML/Whitefang Code/2. KNN.ipynb +149 -0
  23. noshot/data/ML TS XAI/ML/Whitefang Code/3. LDA.ipynb +132 -0
  24. noshot/data/ML TS XAI/ML/Whitefang Code/4. Linear Regression.ipynb +86 -0
  25. noshot/data/ML TS XAI/ML/Whitefang Code/5. Logistic Regression.ipynb +115 -0
  26. noshot/data/ML TS XAI/ML/Whitefang Code/6. Naive Bayes (Titanic).ipynb +196 -0
  27. noshot/data/ML TS XAI/ML/Whitefang Code/6. Naive Bayes (Wine).ipynb +98 -0
  28. noshot/data/ML TS XAI/ML/Whitefang Code/7. SVM Linear.ipynb +109 -0
  29. noshot/data/ML TS XAI/ML/Whitefang Code/8. SVM Non-Linear.ipynb +195 -0
  30. noshot/data/ML TS XAI/ML/Whitefang Code/9. FNN With Regularization.ipynb +189 -0
  31. noshot/data/ML TS XAI/ML/Whitefang Code/9. FNN Without Regularization.ipynb +197 -0
  32. noshot/data/ML TS XAI/ML/Whitefang Code/All in One Lab CIA 1 Q.ipynb +1087 -0
  33. {noshot-5.0.0.dist-info → noshot-7.0.0.dist-info}/METADATA +1 -1
  34. noshot-7.0.0.dist-info/RECORD +41 -0
  35. {noshot-5.0.0.dist-info → noshot-7.0.0.dist-info}/WHEEL +1 -1
  36. noshot/data/ML TS XAI/XAI/Q1.ipynb +0 -535
  37. noshot/data/ML TS XAI/XAI/Q2.ipynb +0 -38129
  38. noshot/data/ML TS XAI/XAI/Q3.ipynb +0 -1340
  39. noshot/data/ML TS XAI/XAI/Q4.ipynb +0 -246
  40. noshot/data/ML TS XAI/XAI/Q5.ipynb +0 -2450
  41. noshot-5.0.0.dist-info/RECORD +0 -14
  42. {noshot-5.0.0.dist-info → noshot-7.0.0.dist-info}/licenses/LICENSE.txt +0 -0
  43. {noshot-5.0.0.dist-info → noshot-7.0.0.dist-info}/top_level.txt +0 -0
noshot/data/ML TS XAI/ML/Tamilan Code/7. SVM (Rice Dataset).ipynb ADDED
@@ -0,0 +1,120 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "4362a048-8226-4172-ad6b-97109238a33f",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import numpy as np\n",
12
+ "import seaborn as sns\n",
13
+ "import matplotlib.pyplot as plt\n",
14
+ "from sklearn.model_selection import train_test_split\n",
15
+ "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, ConfusionMatrixDisplay, roc_curve, auc\n",
16
+ "from sklearn.preprocessing import StandardScaler\n",
17
+ "from sklearn.decomposition import PCA\n",
18
+ "from sklearn.svm import SVC\n",
19
+ "from sklearn.pipeline import make_pipeline\n",
20
+ "from mlxtend.plotting import plot_decision_regions\n",
21
+ "from scipy.io import arff"
22
+ ]
23
+ },
24
+ {
25
+ "cell_type": "code",
26
+ "execution_count": null,
27
+ "id": "921ad1a4-cb33-4a06-862e-3c172da5ca3a",
28
+ "metadata": {},
29
+ "outputs": [],
30
+ "source": [
31
+ "data = arff.loadarff(\"data/rice.arff\")\n",
32
+ "df = pd.DataFrame(data[0])"
33
+ ]
34
+ },
35
+ {
36
+ "cell_type": "code",
37
+ "execution_count": null,
38
+ "id": "6c5497e5-76e2-461b-956a-e6fdb10707a9",
39
+ "metadata": {},
40
+ "outputs": [],
41
+ "source": [
42
+ "df['Class'] = df['Class'].map({b'Cammeo': 0, b'Osmancik': 1})\n",
43
+ "X = df.drop(columns=['Class'])\n",
44
+ "y = df['Class']\n",
45
+ "X = PCA(n_components=2).fit_transform(X)"
46
+ ]
47
+ },
48
+ {
49
+ "cell_type": "code",
50
+ "execution_count": null,
51
+ "id": "029f62b3-db5d-4284-b829-2708342ed440",
52
+ "metadata": {},
53
+ "outputs": [],
54
+ "source": [
55
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
56
+ "\n",
57
+ "models = [\n",
58
+ " SVC(kernel='linear', C=1, degree=5, gamma=\"auto\", probability=True),\n",
59
+ " SVC(kernel='rbf', C=1, gamma='scale', probability=True),\n",
60
+ " SVC(kernel='poly', C=1, degree=5, gamma=\"auto\", probability=True)\n",
61
+ "]"
62
+ ]
63
+ },
64
+ {
65
+ "cell_type": "code",
66
+ "execution_count": null,
67
+ "id": "cad66559-bd1e-4dbb-b656-453aa8a4d0a0",
68
+ "metadata": {},
69
+ "outputs": [],
70
+ "source": [
71
+ "for model in models:\n",
72
+ " pipeline = make_pipeline(StandardScaler(), model)\n",
73
+ " pipeline.fit(X_train, y_train)\n",
74
+ " y_pred = pipeline.predict(X_test)\n",
75
+ " \n",
76
+ " print(f\"SVM ({model.kernel} kernel) Accuracy: {accuracy_score(y_test, y_pred):.2f}\")\n",
77
+ " print(classification_report(y_test, y_pred))\n",
78
+ " \n",
79
+ " plot_decision_regions(X=X_train, y=y_train.values, clf=pipeline, legend=2)\n",
80
+ " plt.title(f'SVM Decision Region Boundary ({model.kernel} kernel)')\n",
81
+ " plt.show()\n",
82
+ " \n",
83
+ " ConfusionMatrixDisplay(confusion_matrix(y_test, y_pred), display_labels=[0, 1]).plot(cmap='Blues')\n",
84
+ " plt.show()\n",
85
+ " \n",
86
+ " y_pred_proba = pipeline.predict_proba(X_test)[:, 1]\n",
87
+ " fpr, tpr, _ = roc_curve(y_test, y_pred_proba)\n",
88
+ " roc_auc = auc(fpr, tpr)\n",
89
+ " plt.plot(fpr, tpr, label=f'ROC curve (area = {roc_auc:.2f})')\n",
90
+ " plt.plot([0, 1], [0, 1], 'k--', label='No Skill')\n",
91
+ " plt.xlabel('False Positive Rate')\n",
92
+ " plt.ylabel('True Positive Rate')\n",
93
+ " plt.title('ROC Curve for Rice Classification')\n",
94
+ " plt.legend()\n",
95
+ " plt.show()"
96
+ ]
97
+ }
98
+ ],
99
+ "metadata": {
100
+ "kernelspec": {
101
+ "display_name": "Python 3 (ipykernel)",
102
+ "language": "python",
103
+ "name": "python3"
104
+ },
105
+ "language_info": {
106
+ "codemirror_mode": {
107
+ "name": "ipython",
108
+ "version": 3
109
+ },
110
+ "file_extension": ".py",
111
+ "mimetype": "text/x-python",
112
+ "name": "python",
113
+ "nbconvert_exporter": "python",
114
+ "pygments_lexer": "ipython3",
115
+ "version": "3.12.4"
116
+ }
117
+ },
118
+ "nbformat": 4,
119
+ "nbformat_minor": 5
120
+ }
noshot/data/ML TS XAI/ML/Tamilan Code/8. FeedForward NN (Sobar72 Dataset).ipynb ADDED
@@ -0,0 +1,262 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "metadata": {
7
+ "colab": {
8
+ "base_uri": "https://localhost:8080/"
9
+ },
10
+ "id": "1PZHOQQp6NpP",
11
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
12
+ },
13
+ "outputs": [],
14
+ "source": [
15
+ "import numpy as np\n",
16
+ "import pandas as pd\n",
17
+ "import matplotlib.pyplot as plt\n",
18
+ "import tensorflow as tf\n",
19
+ "from tensorflow.keras.models import Sequential\n",
20
+ "from tensorflow.keras.layers import Dense, Dropout\n",
21
+ "from tensorflow.keras.optimizers import Adam\n",
22
+ "from tensorflow.keras import regularizers\n",
23
+ "from sklearn.model_selection import train_test_split\n",
24
+ "from sklearn.metrics import classification_report, confusion_matrix, ConfusionMatrixDisplay, accuracy_score, roc_curve, auc\n",
25
+ "\n",
26
+ "import warnings\n",
27
+ "warnings.filterwarnings('ignore')"
28
+ ]
29
+ },
30
+ {
31
+ "cell_type": "code",
32
+ "execution_count": null,
33
+ "metadata": {
34
+ "colab": {
35
+ "base_uri": "https://localhost:8080/"
36
+ },
37
+ "id": "1PZHOQQp6NpP",
38
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
39
+ },
40
+ "outputs": [],
41
+ "source": [
42
+ "df = pd.read_csv(\"data/sobar-72.csv\")\n",
43
+ "df.head()"
44
+ ]
45
+ },
46
+ {
47
+ "cell_type": "code",
48
+ "execution_count": null,
49
+ "metadata": {
50
+ "colab": {
51
+ "base_uri": "https://localhost:8080/"
52
+ },
53
+ "id": "1PZHOQQp6NpP",
54
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
55
+ },
56
+ "outputs": [],
57
+ "source": [
58
+ "X = df.drop(columns=['ca_cervix'])\n",
59
+ "y = tf.keras.utils.to_categorical(df['ca_cervix'], num_classes=2)"
60
+ ]
61
+ },
62
+ {
63
+ "cell_type": "code",
64
+ "execution_count": null,
65
+ "metadata": {
66
+ "colab": {
67
+ "base_uri": "https://localhost:8080/"
68
+ },
69
+ "id": "1PZHOQQp6NpP",
70
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
71
+ },
72
+ "outputs": [],
73
+ "source": [
74
+ "x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
75
+ ]
76
+ },
77
+ {
78
+ "cell_type": "code",
79
+ "execution_count": null,
80
+ "metadata": {
81
+ "colab": {
82
+ "base_uri": "https://localhost:8080/"
83
+ },
84
+ "id": "1PZHOQQp6NpP",
85
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
86
+ },
87
+ "outputs": [],
88
+ "source": [
89
+ "model = Sequential([\n",
90
+ " Dense(128, activation='relu', input_shape=(19,), kernel_regularizer=regularizers.l2(0.001)),\n",
91
+ " Dropout(0.3),\n",
92
+ " Dense(64, activation='relu', kernel_regularizer=regularizers.l2(0.001)),\n",
93
+ " Dropout(0.3),\n",
94
+ " Dense(2, activation='softmax')\n",
95
+ "])\n",
96
+ "\n",
97
+ "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])"
98
+ ]
99
+ },
100
+ {
101
+ "cell_type": "code",
102
+ "execution_count": null,
103
+ "metadata": {
104
+ "colab": {
105
+ "base_uri": "https://localhost:8080/"
106
+ },
107
+ "id": "1PZHOQQp6NpP",
108
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
109
+ },
110
+ "outputs": [],
111
+ "source": [
112
+ "early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss', \n",
113
+ " patience=10, \n",
114
+ " restore_best_weights=True)\n",
115
+ "history = model.fit(x_train, y_train, epochs=50, \n",
116
+ " batch_size=32, validation_split=0.2,\n",
117
+ " callbacks=[early_stopping], verbose=1)"
118
+ ]
119
+ },
120
+ {
121
+ "cell_type": "code",
122
+ "execution_count": null,
123
+ "metadata": {
124
+ "colab": {
125
+ "base_uri": "https://localhost:8080/"
126
+ },
127
+ "id": "1PZHOQQp6NpP",
128
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
129
+ },
130
+ "outputs": [],
131
+ "source": [
132
+ "def plot_history(history):\n",
133
+ " plt.figure(figsize=(12, 5))\n",
134
+ "\n",
135
+ " plt.subplot(1, 2, 1)\n",
136
+ " plt.plot(history.history['loss'], label='Training Loss')\n",
137
+ " plt.plot(history.history['val_loss'], label='Validation Loss')\n",
138
+ " plt.title('Loss')\n",
139
+ " plt.xlabel('Epoch')\n",
140
+ " plt.ylabel('Loss')\n",
141
+ " plt.legend()\n",
142
+ "\n",
143
+ " plt.subplot(1, 2, 2)\n",
144
+ " plt.plot(history.history['accuracy'], label='Training Accuracy')\n",
145
+ " plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
146
+ " plt.title('Accuracy')\n",
147
+ " plt.xlabel('Epoch')\n",
148
+ " plt.ylabel('Accuracy')\n",
149
+ " plt.legend()\n",
150
+ "\n",
151
+ " plt.tight_layout()\n",
152
+ " plt.show()\n",
153
+ "\n",
154
+ "plot_history(history)"
155
+ ]
156
+ },
157
+ {
158
+ "cell_type": "code",
159
+ "execution_count": null,
160
+ "metadata": {
161
+ "colab": {
162
+ "base_uri": "https://localhost:8080/"
163
+ },
164
+ "id": "1PZHOQQp6NpP",
165
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
166
+ },
167
+ "outputs": [],
168
+ "source": [
169
+ "loss, accuracy = model.evaluate(x_test, y_test)\n",
170
+ "print(f'Test accuracy: {accuracy:.4f}')\n",
171
+ "print(f'Test loss: {loss:.4f}')"
172
+ ]
173
+ },
174
+ {
175
+ "cell_type": "code",
176
+ "execution_count": null,
177
+ "metadata": {
178
+ "colab": {
179
+ "base_uri": "https://localhost:8080/"
180
+ },
181
+ "id": "1PZHOQQp6NpP",
182
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
183
+ },
184
+ "outputs": [],
185
+ "source": [
186
+ "y_pred = np.argmax(model.predict(x_test), axis=1)\n",
187
+ "y_test = np.argmax(y_test, axis=1)\n",
188
+ "print(\"Classification Report:\")\n",
189
+ "print(classification_report(y_test, y_pred))\n",
190
+ "print(f\"Accuracy: {accuracy_score(y_test, y_pred):.2f}\")"
191
+ ]
192
+ },
193
+ {
194
+ "cell_type": "code",
195
+ "execution_count": null,
196
+ "metadata": {
197
+ "colab": {
198
+ "base_uri": "https://localhost:8080/"
199
+ },
200
+ "id": "1PZHOQQp6NpP",
201
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
202
+ },
203
+ "outputs": [],
204
+ "source": [
205
+ "conf = confusion_matrix(y_test, y_pred)\n",
206
+ "ConfusionMatrixDisplay(conf).plot(cmap='Blues')\n",
207
+ "plt.show()"
208
+ ]
209
+ },
210
+ {
211
+ "cell_type": "code",
212
+ "execution_count": null,
213
+ "metadata": {
214
+ "colab": {
215
+ "base_uri": "https://localhost:8080/"
216
+ },
217
+ "id": "1PZHOQQp6NpP",
218
+ "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
219
+ },
220
+ "outputs": [],
221
+ "source": [
222
+ "y_pred_proba = model.predict(x_test)[:, 1]\n",
223
+ "fpr, tpr, _ = roc_curve(y_test, y_pred_proba)\n",
224
+ "roc_auc = auc(fpr, tpr)\n",
225
+ "\n",
226
+ "plt.plot(fpr, tpr, label=f'ROC curve (area = {roc_auc:.2f})', color='darkorange')\n",
227
+ "plt.plot([0, 1], [0, 1], color='navy', linestyle='--')\n",
228
+ "plt.xlim([0.0, 1.0])\n",
229
+ "plt.ylim([0.0, 1.05])\n",
230
+ "plt.xlabel('False Positive Rate')\n",
231
+ "plt.ylabel('True Positive Rate')\n",
232
+ "plt.title('Receiver Operating Characteristic')\n",
233
+ "plt.legend(loc=\"lower right\")\n",
234
+ "plt.show()"
235
+ ]
236
+ }
237
+ ],
238
+ "metadata": {
239
+ "colab": {
240
+ "provenance": []
241
+ },
242
+ "kernelspec": {
243
+ "display_name": "NEW-VENV-1",
244
+ "language": "python",
245
+ "name": "new-venv-1"
246
+ },
247
+ "language_info": {
248
+ "codemirror_mode": {
249
+ "name": "ipython",
250
+ "version": 3
251
+ },
252
+ "file_extension": ".py",
253
+ "mimetype": "text/x-python",
254
+ "name": "python",
255
+ "nbconvert_exporter": "python",
256
+ "pygments_lexer": "ipython3",
257
+ "version": "3.11.5"
258
+ }
259
+ },
260
+ "nbformat": 4,
261
+ "nbformat_minor": 4
262
+ }
noshot/data/ML TS XAI/ML/Tamilan Code/9. CNN (Cifar10 Dataset).ipynb ADDED
@@ -0,0 +1,156 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "metadata": {
7
+ "id": "wHmdCsrz61l7"
8
+ },
9
+ "outputs": [],
10
+ "source": [
11
+ "import tensorflow as tf\n",
12
+ "from tensorflow import keras\n",
13
+ "from tensorflow.keras import layers\n",
14
+ "from keras.datasets import cifar10\n",
15
+ "from keras.utils import to_categorical\n",
16
+ "import matplotlib.pyplot as plt\n",
17
+ "from sklearn.metrics import roc_curve, auc\n",
18
+ "from sklearn.preprocessing import label_binarize\n",
19
+ "\n",
20
+ "import warnings\n",
21
+ "warnings.filterwarnings('ignore')"
22
+ ]
23
+ },
24
+ {
25
+ "cell_type": "code",
26
+ "execution_count": null,
27
+ "metadata": {
28
+ "id": "wHmdCsrz61l7"
29
+ },
30
+ "outputs": [],
31
+ "source": [
32
+ "(X_train, y_train), (X_test, y_test) = cifar10.load_data()"
33
+ ]
34
+ },
35
+ {
36
+ "cell_type": "code",
37
+ "execution_count": null,
38
+ "metadata": {
39
+ "id": "wHmdCsrz61l7"
40
+ },
41
+ "outputs": [],
42
+ "source": [
43
+ "def preprocess_data(X, y):\n",
44
+ " X = X.astype('float32') / 255.0\n",
45
+ " y = to_categorical(y, num_classes=10)\n",
46
+ " return X, y"
47
+ ]
48
+ },
49
+ {
50
+ "cell_type": "code",
51
+ "execution_count": null,
52
+ "metadata": {
53
+ "id": "wHmdCsrz61l7"
54
+ },
55
+ "outputs": [],
56
+ "source": [
57
+ "x_train, y_train = preprocess_data(X_train, y_train)\n",
58
+ "x_test, y_test = preprocess_data(X_test, y_test)"
59
+ ]
60
+ },
61
+ {
62
+ "cell_type": "code",
63
+ "execution_count": null,
64
+ "metadata": {
65
+ "id": "wHmdCsrz61l7"
66
+ },
67
+ "outputs": [],
68
+ "source": [
69
+ "model = keras.Sequential([\n",
70
+ " layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\", input_shape=(32, 32, 3)),\n",
71
+ " layers.MaxPooling2D(pool_size=(2, 2)),\n",
72
+ " layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n",
73
+ " layers.MaxPooling2D(pool_size=(2, 2)),\n",
74
+ " layers.Flatten(),\n",
75
+ " layers.Dense(10, activation=\"softmax\")\n",
76
+ "])\n",
77
+ "\n",
78
+ "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])"
79
+ ]
80
+ },
81
+ {
82
+ "cell_type": "code",
83
+ "execution_count": null,
84
+ "metadata": {
85
+ "id": "wHmdCsrz61l7"
86
+ },
87
+ "outputs": [],
88
+ "source": [
89
+ "early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss', \n",
90
+ " patience=10, \n",
91
+ " restore_best_weights=True)\n",
92
+ "\n",
93
+ "history = model.fit(x_train, y_train, epochs=5, \n",
94
+ " batch_size=32, validation_split=0.2, callbacks=[early_stopping])"
95
+ ]
96
+ },
97
+ {
98
+ "cell_type": "code",
99
+ "execution_count": null,
100
+ "metadata": {
101
+ "id": "wHmdCsrz61l7"
102
+ },
103
+ "outputs": [],
104
+ "source": [
105
+ "y_test_bin = label_binarize(y_test, classes=list(range(10)))\n",
106
+ "y_pred_proba = model.predict(x_test)"
107
+ ]
108
+ },
109
+ {
110
+ "cell_type": "code",
111
+ "execution_count": null,
112
+ "metadata": {
113
+ "id": "wHmdCsrz61l7"
114
+ },
115
+ "outputs": [],
116
+ "source": [
117
+ "fpr, tpr, _ = roc_curve(y_test_bin[:, 0], y_pred_proba[:, 0])\n",
118
+ "roc_auc = auc(fpr, tpr)\n",
119
+ "\n",
120
+ "plt.plot(fpr, tpr, color='darkorange', lw=2, label=f'Class 0 ROC curve (area = {roc_auc:.2f})')\n",
121
+ "plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\n",
122
+ "plt.xlim([0.0, 1.0])\n",
123
+ "plt.ylim([0.0, 1.05])\n",
124
+ "plt.xlabel('False Positive Rate')\n",
125
+ "plt.ylabel('True Positive Rate')\n",
126
+ "plt.title('ROC Curve for Class 0')\n",
127
+ "plt.legend(loc=\"lower right\")\n",
128
+ "plt.show()"
129
+ ]
130
+ }
131
+ ],
132
+ "metadata": {
133
+ "colab": {
134
+ "provenance": []
135
+ },
136
+ "kernelspec": {
137
+ "display_name": "NEW-VENV-1",
138
+ "language": "python",
139
+ "name": "new-venv-1"
140
+ },
141
+ "language_info": {
142
+ "codemirror_mode": {
143
+ "name": "ipython",
144
+ "version": 3
145
+ },
146
+ "file_extension": ".py",
147
+ "mimetype": "text/x-python",
148
+ "name": "python",
149
+ "nbconvert_exporter": "python",
150
+ "pygments_lexer": "ipython3",
151
+ "version": "3.11.5"
152
+ }
153
+ },
154
+ "nbformat": 4,
155
+ "nbformat_minor": 4
156
+ }
noshot/data/ML TS XAI/ML/Whitefang Code/1. PCA.ipynb ADDED
@@ -0,0 +1,162 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "markdown",
5
+ "id": "cfbb1d58-7c8f-4a0c-b6e2-914469a7e49d",
6
+ "metadata": {},
7
+ "source": [
8
+ "Principal Component Analysis & Exploratory Data Analysis"
9
+ ]
10
+ },
11
+ {
12
+ "cell_type": "code",
13
+ "execution_count": null,
14
+ "id": "d3b0a49d-a326-4bb3-b868-cfeaaaa50d3e",
15
+ "metadata": {},
16
+ "outputs": [],
17
+ "source": [
18
+ "#required packages.\n",
19
+ "\n",
20
+ "import pandas as pd\n",
21
+ "import matplotlib.pyplot as plt\n",
22
+ "import numpy as np\n",
23
+ "from sklearn.preprocessing import StandardScaler\n",
24
+ "from sklearn.decomposition import PCA"
25
+ ]
26
+ },
27
+ {
28
+ "cell_type": "code",
29
+ "execution_count": null,
30
+ "id": "e1c8f709-35bc-4eec-987e-cd1e6780d877",
31
+ "metadata": {},
32
+ "outputs": [],
33
+ "source": [
34
+ "#Load dataset, print few rows, get info, describe dataset.\n",
35
+ "\n",
36
+ "df=pd.read_csv(\"E:/126156055/dataset_ex_1.csv\",names=[\"class name\",'left-weight','left-distance','right-weight','right-distance'])\n",
37
+ "print(\"First Five rows : \\n\",df.head())\n",
38
+ "print(\"\\nInfo : \\n\",df.info)\n",
39
+ "print(\"\\nDescribe : \\n\",df.describe())"
40
+ ]
41
+ },
42
+ {
43
+ "cell_type": "markdown",
44
+ "id": "ee7c0104-4a32-4c28-b3fc-080c77461100",
45
+ "metadata": {},
46
+ "source": [
47
+ "PCA"
48
+ ]
49
+ },
50
+ {
51
+ "cell_type": "code",
52
+ "execution_count": null,
53
+ "id": "6af99020-e017-478a-9e18-ed098f4167ed",
54
+ "metadata": {},
55
+ "outputs": [],
56
+ "source": [
57
+ "features=['left-weight','left-distance','right-weight','right-distance']\n",
58
+ "x=df.loc[:,features]\n",
59
+ "y=df.loc[:,'class name']\n",
60
+ "x=StandardScaler().fit_transform(x)\n",
61
+ "x"
62
+ ]
63
+ },
64
+ {
65
+ "cell_type": "code",
66
+ "execution_count": null,
67
+ "id": "ff575de1-483a-48c2-be39-2cf91b082aff",
68
+ "metadata": {},
69
+ "outputs": [],
70
+ "source": [
71
+ "pca=PCA(n_components=2)\n",
72
+ "pca_x=pca.fit_transform(x)\n",
73
+ "pca_x"
74
+ ]
75
+ },
76
+ {
77
+ "cell_type": "code",
78
+ "execution_count": null,
79
+ "id": "9f7d8296-1c1e-47ed-a2c5-cf499423dbfa",
80
+ "metadata": {},
81
+ "outputs": [],
82
+ "source": [
83
+ "principal_df=pd.DataFrame(pca_x,columns=['pc1','pc2'])\n",
84
+ "principal_df"
85
+ ]
86
+ },
87
+ {
88
+ "cell_type": "code",
89
+ "execution_count": null,
90
+ "id": "f1481c63-6fbf-4028-a88f-3ef492e44119",
91
+ "metadata": {},
92
+ "outputs": [],
93
+ "source": [
94
+ "final_df=pd.concat([principal_df,df['class name']],axis=1)\n",
95
+ "final_df"
96
+ ]
97
+ },
98
+ {
99
+ "cell_type": "code",
100
+ "execution_count": null,
101
+ "id": "72d8f4bc-0db2-4a1a-bac2-403455b6b3a3",
102
+ "metadata": {},
103
+ "outputs": [],
104
+ "source": [
105
+ "plt.xlabel(\"Component 1\")\n",
106
+ "plt.ylabel(\"Component 2\")\n",
107
+ "plt.title(\"2 Component PCA\")\n",
108
+ "targets=['L','B','R']\n",
109
+ "colors=['r','g','b']\n",
110
+ "for target,color in zip(targets,colors):\n",
111
+ " indicesToKeep=final_df['class name']==target\n",
112
+ " plt.scatter(final_df.loc[indicesToKeep,'pc1'],final_df.loc[indicesToKeep,\"pc2\"],c=color,s=20)\n",
113
+ "\n",
114
+ "plt.legend(targets)\n",
115
+ "plt.grid()\n",
116
+ " "
117
+ ]
118
+ },
119
+ {
120
+ "cell_type": "markdown",
121
+ "id": "58a3f3db-1a05-4dd7-b428-b28ef3061b3b",
122
+ "metadata": {},
123
+ "source": [
124
+ "EDA"
125
+ ]
126
+ },
127
+ {
128
+ "cell_type": "code",
129
+ "execution_count": null,
130
+ "id": "9ad2b51e-4a22-4285-959e-38d3c7ec55a0",
131
+ "metadata": {},
132
+ "outputs": [],
133
+ "source": [
134
+ "df2=df.copy()\n",
135
+ "print(\"\\nShape : \",df2.shape)\n",
136
+ "print('\\nColumns : ',df2.columns)\n",
137
+ "print('\\nDtype : ',df2.dtypes)"
138
+ ]
139
+ }
140
+ ],
141
+ "metadata": {
142
+ "kernelspec": {
143
+ "display_name": "Python 3 (ipykernel)",
144
+ "language": "python",
145
+ "name": "python3"
146
+ },
147
+ "language_info": {
148
+ "codemirror_mode": {
149
+ "name": "ipython",
150
+ "version": 3
151
+ },
152
+ "file_extension": ".py",
153
+ "mimetype": "text/x-python",
154
+ "name": "python",
155
+ "nbconvert_exporter": "python",
156
+ "pygments_lexer": "ipython3",
157
+ "version": "3.12.4"
158
+ }
159
+ },
160
+ "nbformat": 4,
161
+ "nbformat_minor": 5
162
+ }