noshot 0.3.9__py3-none-any.whl → 0.4.0__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 (48) hide show
  1. noshot/data/ML TS XAI/CIA-1-Delhi Boy.ipynb +535 -0
  2. noshot/data/ML TS XAI/Football Player/4.ipynb +395 -0
  3. noshot/data/ML TS XAI/ML Lab CIA - Our Class/AllinOne.ipynb +1 -0
  4. noshot/data/ML TS XAI/ML Lab CIA - Our Class/Heart-Disease-UCI-0.ipynb +886 -0
  5. noshot/data/ML TS XAI/ML Lab CIA - Our Class/Housing-0.ipynb +292 -0
  6. noshot/data/ML TS XAI/ML Lab CIA - Our Class/Lab Code Ex 1-4.ipynb +1 -0
  7. noshot/data/ML TS XAI/ML Lab CIA - Our Class/data/Housing.csv +546 -0
  8. noshot/data/ML TS XAI/ML Lab CIA - Our Class/data/heart_disease_uci.csv +921 -0
  9. {noshot-0.3.9.dist-info → noshot-0.4.0.dist-info}/METADATA +1 -1
  10. noshot-0.4.0.dist-info/RECORD +48 -0
  11. noshot/data/ML TS XAI/TS/1. EDA - Handling Time Series Data.ipynb +0 -247
  12. noshot/data/ML TS XAI/TS/2. Feature Engineering.ipynb +0 -183
  13. noshot/data/ML TS XAI/TS/3. Temporal Relationships.ipynb +0 -172
  14. noshot/data/ML TS XAI/TS/4. Up-Down-Sampling and Interpolation.ipynb +0 -146
  15. noshot/data/ML TS XAI/TS/5. Stationarity - Trend - Seasonality.ipynb +0 -173
  16. noshot/data/ML TS XAI/TS/6. Autocorrelation - Partial Autocorrelation.ipynb +0 -77
  17. noshot/data/ML TS XAI/TS/AllinOne.ipynb +0 -1416
  18. noshot/data/ML TS XAI/TS/data/daily-min-temperatures.csv +0 -3651
  19. noshot/data/ML TS XAI/TS/data/daily-total-female-births.csv +0 -366
  20. noshot/data/ML TS XAI/TS/data/raw_sales.csv +0 -29581
  21. noshot/data/ML TS XAI/TS/data/shampoo_sales.csv +0 -37
  22. noshot/data/ML TS XAI/TS Lab CIA/1 - AirPassengers/1 - AirPassengers.ipynb +0 -198
  23. noshot/data/ML TS XAI/TS Lab CIA/1 - AirPassengers/AirPassengers.csv +0 -145
  24. noshot/data/ML TS XAI/TS Lab CIA/2 - Daily-total-female-births/2 - daily-total-female-births.ipynb +0 -209
  25. noshot/data/ML TS XAI/TS Lab CIA/2 - Daily-total-female-births/daily-total-female-births.csv +0 -366
  26. noshot/data/ML TS XAI/TS Lab CIA/3 - Bill Charge/3 - Bill Charge.ipynb +0 -169
  27. noshot/data/ML TS XAI/TS Lab CIA/3 - Bill Charge/bill charge.csv +0 -21
  28. noshot/data/ML TS XAI/TS Lab CIA/4 - Daily min temperatures/4 - daily-min-temperatures.ipynb +0 -181
  29. noshot/data/ML TS XAI/TS Lab CIA/4 - Daily min temperatures/daily-min-temperatures.csv +0 -3651
  30. noshot/data/ML TS XAI/TS Lab CIA/5 - shampoo sales/5 - Shampoo sales.ipynb +0 -213
  31. noshot/data/ML TS XAI/TS Lab CIA/5 - shampoo sales/shampoo_sales.csv +0 -37
  32. noshot/data/ML TS XAI/TS Lab CIA/Questions TMS 27 Feb 25.pdf +0 -0
  33. noshot-0.3.9.dist-info/RECORD +0 -62
  34. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/1/1.ipynb +0 -0
  35. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/1/Question.txt +0 -0
  36. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/1/airfoil_self_noise.dat +0 -0
  37. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/2/2.ipynb +0 -0
  38. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/2/Question.txt +0 -0
  39. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/2/pop_failures.dat +0 -0
  40. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/3/3.ipynb +0 -0
  41. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/3/Qu.txt +0 -0
  42. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/3/go_track_tracks.csv +0 -0
  43. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/4/4.ipynb +0 -0
  44. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/4/Wilt.csv +0 -0
  45. /noshot/data/ML TS XAI/{ML Lab CIA → ML Lab CIA - Healthy Class}/4/qu.txt +0 -0
  46. {noshot-0.3.9.dist-info → noshot-0.4.0.dist-info}/LICENSE.txt +0 -0
  47. {noshot-0.3.9.dist-info → noshot-0.4.0.dist-info}/WHEEL +0 -0
  48. {noshot-0.3.9.dist-info → noshot-0.4.0.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,395 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 28,
6
+ "id": "8b01d639-7417-4a71-a735-d519043691ac",
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.decomposition import PCA\n",
14
+ "from sklearn.neighbors import KNeighborsClassifier\n",
15
+ "from sklearn.model_selection import train_test_split\n",
16
+ "from sklearn.preprocessing import StandardScaler, LabelEncoder,MinMaxScaler\n",
17
+ "from sklearn.metrics import accuracy_score,confusion_matrix"
18
+ ]
19
+ },
20
+ {
21
+ "cell_type": "code",
22
+ "execution_count": 3,
23
+ "id": "03cbb0a7-0a95-4e08-94a9-028c664ecbe1",
24
+ "metadata": {},
25
+ "outputs": [
26
+ {
27
+ "data": {
28
+ "text/html": [
29
+ "<div>\n",
30
+ "<style scoped>\n",
31
+ " .dataframe tbody tr th:only-of-type {\n",
32
+ " vertical-align: middle;\n",
33
+ " }\n",
34
+ "\n",
35
+ " .dataframe tbody tr th {\n",
36
+ " vertical-align: top;\n",
37
+ " }\n",
38
+ "\n",
39
+ " .dataframe thead th {\n",
40
+ " text-align: right;\n",
41
+ " }\n",
42
+ "</style>\n",
43
+ "<table border=\"1\" class=\"dataframe\">\n",
44
+ " <thead>\n",
45
+ " <tr style=\"text-align: right;\">\n",
46
+ " <th></th>\n",
47
+ " <th>class</th>\n",
48
+ " <th>GLCM_pan</th>\n",
49
+ " <th>Mean_Green</th>\n",
50
+ " <th>Mean_Red</th>\n",
51
+ " <th>Mean_NIR</th>\n",
52
+ " <th>SD_pan</th>\n",
53
+ " </tr>\n",
54
+ " </thead>\n",
55
+ " <tbody>\n",
56
+ " <tr>\n",
57
+ " <th>0</th>\n",
58
+ " <td>w</td>\n",
59
+ " <td>120.362774</td>\n",
60
+ " <td>205.500000</td>\n",
61
+ " <td>119.395349</td>\n",
62
+ " <td>416.581395</td>\n",
63
+ " <td>20.676318</td>\n",
64
+ " </tr>\n",
65
+ " <tr>\n",
66
+ " <th>1</th>\n",
67
+ " <td>w</td>\n",
68
+ " <td>124.739583</td>\n",
69
+ " <td>202.800000</td>\n",
70
+ " <td>115.333333</td>\n",
71
+ " <td>354.333333</td>\n",
72
+ " <td>16.707151</td>\n",
73
+ " </tr>\n",
74
+ " <tr>\n",
75
+ " <th>2</th>\n",
76
+ " <td>w</td>\n",
77
+ " <td>134.691964</td>\n",
78
+ " <td>199.285714</td>\n",
79
+ " <td>116.857143</td>\n",
80
+ " <td>477.857143</td>\n",
81
+ " <td>22.496712</td>\n",
82
+ " </tr>\n",
83
+ " <tr>\n",
84
+ " <th>3</th>\n",
85
+ " <td>w</td>\n",
86
+ " <td>127.946309</td>\n",
87
+ " <td>178.368421</td>\n",
88
+ " <td>92.368421</td>\n",
89
+ " <td>278.473684</td>\n",
90
+ " <td>14.977453</td>\n",
91
+ " </tr>\n",
92
+ " <tr>\n",
93
+ " <th>4</th>\n",
94
+ " <td>w</td>\n",
95
+ " <td>135.431548</td>\n",
96
+ " <td>197.000000</td>\n",
97
+ " <td>112.690476</td>\n",
98
+ " <td>532.952381</td>\n",
99
+ " <td>17.604193</td>\n",
100
+ " </tr>\n",
101
+ " </tbody>\n",
102
+ "</table>\n",
103
+ "</div>"
104
+ ],
105
+ "text/plain": [
106
+ " class GLCM_pan Mean_Green Mean_Red Mean_NIR SD_pan\n",
107
+ "0 w 120.362774 205.500000 119.395349 416.581395 20.676318\n",
108
+ "1 w 124.739583 202.800000 115.333333 354.333333 16.707151\n",
109
+ "2 w 134.691964 199.285714 116.857143 477.857143 22.496712\n",
110
+ "3 w 127.946309 178.368421 92.368421 278.473684 14.977453\n",
111
+ "4 w 135.431548 197.000000 112.690476 532.952381 17.604193"
112
+ ]
113
+ },
114
+ "execution_count": 3,
115
+ "metadata": {},
116
+ "output_type": "execute_result"
117
+ }
118
+ ],
119
+ "source": [
120
+ "file_path = \"Wilt.csv\"\n",
121
+ "df = pd.read_csv(file_path)\n",
122
+ "df.head()"
123
+ ]
124
+ },
125
+ {
126
+ "cell_type": "code",
127
+ "execution_count": 4,
128
+ "id": "0a4961c3-0fea-401b-a7f0-5f6fd0eb9e69",
129
+ "metadata": {},
130
+ "outputs": [],
131
+ "source": [
132
+ "y = df.iloc[:, 0]\n",
133
+ "X = df.iloc[:, 1:]"
134
+ ]
135
+ },
136
+ {
137
+ "cell_type": "code",
138
+ "execution_count": 5,
139
+ "id": "d6699a1a-5436-40d7-84b9-f2c3d5e87850",
140
+ "metadata": {},
141
+ "outputs": [],
142
+ "source": [
143
+ "if y.dtype == 'object':\n",
144
+ " class_mapping = {label: idx for idx, label in enumerate(y.unique())}\n",
145
+ " y = y.map(class_mapping)\n",
146
+ "\n",
147
+ "scaler = StandardScaler()\n",
148
+ "X_scaled = scaler.fit_transform(X)\n",
149
+ "\n",
150
+ "pca = PCA(n_components=2)\n",
151
+ "X_pca = pca.fit_transform(X_scaled)\n",
152
+ "\n",
153
+ "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
154
+ "X_pca_train, X_pca_test, _, _ = train_test_split(X_pca, y, test_size=0.2, random_state=42)"
155
+ ]
156
+ },
157
+ {
158
+ "cell_type": "code",
159
+ "execution_count": 6,
160
+ "id": "0c6c271e-3725-4472-b082-a96aa9850ec6",
161
+ "metadata": {},
162
+ "outputs": [
163
+ {
164
+ "name": "stdout",
165
+ "output_type": "stream",
166
+ "text": [
167
+ "Accuracy without PCA: 0.9838709677419355\n",
168
+ "Accuracy with PCA: 0.978110599078341\n"
169
+ ]
170
+ }
171
+ ],
172
+ "source": [
173
+ "knn_original = KNeighborsClassifier(n_neighbors=5)\n",
174
+ "knn_original.fit(X_train, y_train)\n",
175
+ "y_pred_original = knn_original.predict(X_test)\n",
176
+ "accuracy_original = accuracy_score(y_test, y_pred_original)\n",
177
+ "\n",
178
+ "knn_pca = KNeighborsClassifier(n_neighbors=5)\n",
179
+ "knn_pca.fit(X_pca_train, y_train)\n",
180
+ "y_pred_pca = knn_pca.predict(X_pca_test)\n",
181
+ "accuracy_pca = accuracy_score(y_test, y_pred_pca)\n",
182
+ "\n",
183
+ "print(\"Accuracy without PCA:\", accuracy_original)\n",
184
+ "print(\"Accuracy with PCA:\", accuracy_pca)"
185
+ ]
186
+ },
187
+ {
188
+ "cell_type": "code",
189
+ "execution_count": 12,
190
+ "id": "5b129aaa-8fba-4dac-a4be-e94c277d40ae",
191
+ "metadata": {},
192
+ "outputs": [
193
+ {
194
+ "data": {
195
+ "image/png": "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",
196
+ "text/plain": [
197
+ "<Figure size 600x400 with 2 Axes>"
198
+ ]
199
+ },
200
+ "metadata": {},
201
+ "output_type": "display_data"
202
+ }
203
+ ],
204
+ "source": [
205
+ "plt.figure(figsize=(6, 4))\n",
206
+ "plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='coolwarm', alpha=0.5)\n",
207
+ "plt.xlabel(\"Principal Component 1\")\n",
208
+ "plt.ylabel(\"Principal Component 2\")\n",
209
+ "plt.title(\"PCA Visualization of Wilt Dataset\")\n",
210
+ "plt.colorbar(label=\"Class\")\n",
211
+ "plt.show()"
212
+ ]
213
+ },
214
+ {
215
+ "cell_type": "code",
216
+ "execution_count": 20,
217
+ "id": "a4b9dcf0-d091-4ece-9651-e84932fb1eba",
218
+ "metadata": {},
219
+ "outputs": [
220
+ {
221
+ "data": {
222
+ "image/png": "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",
223
+ "text/plain": [
224
+ "<Figure size 600x400 with 1 Axes>"
225
+ ]
226
+ },
227
+ "metadata": {},
228
+ "output_type": "display_data"
229
+ }
230
+ ],
231
+ "source": [
232
+ "labels = ['Without PCA', 'With PCA']\n",
233
+ "accuracies = [accuracy_original, accuracy_pca]\n",
234
+ "plt.figure(figsize=(6, 4))\n",
235
+ "plt.bar(labels, accuracies, color=['blue', 'orange'])\n",
236
+ "plt.xlabel(\"Model\")\n",
237
+ "plt.ylabel(\"Accuracy\")\n",
238
+ "plt.title(\"KNN Classification Accuracy Comparison\")\n",
239
+ "plt.ylim(0, 1)\n",
240
+ "plt.show()"
241
+ ]
242
+ },
243
+ {
244
+ "cell_type": "code",
245
+ "execution_count": 26,
246
+ "id": "cec1e8f8-d63a-4e5d-8810-dfb6f5026027",
247
+ "metadata": {},
248
+ "outputs": [
249
+ {
250
+ "name": "stdout",
251
+ "output_type": "stream",
252
+ "text": [
253
+ "True Positive: 849 \n",
254
+ " True Negative: 0 \n",
255
+ " False Positive: 19 \n",
256
+ " False Negative: 0\n"
257
+ ]
258
+ }
259
+ ],
260
+ "source": [
261
+ "conf_matrix = confusion_matrix(y_test, y_pred_pca)\n",
262
+ "print(\"True Positive:\",conf_matrix[1,1],\"\\n\",\"True Negative:\",conf_matrix[0,0],\"\\n\",\"False Positive:\",conf_matrix[0,1],\"\\n\",\"False Negative:\",conf_matrix[1,0])"
263
+ ]
264
+ },
265
+ {
266
+ "cell_type": "code",
267
+ "execution_count": 30,
268
+ "id": "a9eda891-c876-45f2-b16e-560491c7cc89",
269
+ "metadata": {},
270
+ "outputs": [],
271
+ "source": [
272
+ "minmax = MinMaxScaler()\n",
273
+ "X_minmaxscaler = minmax.fit_transform(X)"
274
+ ]
275
+ },
276
+ {
277
+ "cell_type": "code",
278
+ "execution_count": null,
279
+ "id": "4b968883-e765-44ed-a562-0e90fc924e82",
280
+ "metadata": {},
281
+ "outputs": [],
282
+ "source": [
283
+ "from sklearn.decomposition import PCA\n",
284
+ "from sklearn.preprocessing import StandardScaler\n",
285
+ "from sklearn.metrics import mean_squared_error\n",
286
+ "import numpy as np\n",
287
+ "\n",
288
+ "# Standardize the data\n",
289
+ "scaler = StandardScaler()\n",
290
+ "X_scaled = scaler.fit_transform(X) # Normalize dataset\n",
291
+ "\n",
292
+ "# Apply PCA\n",
293
+ "pca = PCA(n_components=2) # Reduce to 2 components\n",
294
+ "X_pca = pca.fit_transform(X_scaled)\n",
295
+ "\n",
296
+ "# Reconstruct data\n",
297
+ "X_reconstructed = pca.inverse_transform(X_pca)\n",
298
+ "\n",
299
+ "# Compute Reconstruction Error (MSE)\n",
300
+ "reconstruction_error = mean_squared_error(X_scaled, X_reconstructed)\n",
301
+ "\n",
302
+ "print(f\"Reconstruction Error: {reconstruction_error:.4f}\")\n"
303
+ ]
304
+ },
305
+ {
306
+ "cell_type": "code",
307
+ "execution_count": null,
308
+ "id": "0d5c2293-560c-4ee4-a656-e07e8e2a0b3c",
309
+ "metadata": {},
310
+ "outputs": [],
311
+ "source": [
312
+ "from sklearn.decomposition import PCA\n",
313
+ "from sklearn.preprocessing import StandardScaler\n",
314
+ "from sklearn.metrics import mean_squared_error\n",
315
+ "import numpy as np\n",
316
+ "\n",
317
+ "# Standardize the data\n",
318
+ "scaler = StandardScaler()\n",
319
+ "X_scaled = scaler.fit_transform(X) \n",
320
+ "\n",
321
+ "# Apply PCA (choose number of components)\n",
322
+ "pca = PCA(n_components=2) \n",
323
+ "X_pca = pca.fit_transform(X_scaled)\n",
324
+ "\n",
325
+ "# Reconstruct data\n",
326
+ "X_reconstructed = pca.inverse_transform(X_pca)\n",
327
+ "\n",
328
+ "# Compute Reconstruction Error (MSE)\n",
329
+ "reconstruction_error = mean_squared_error(X_scaled, X_reconstructed)\n",
330
+ "\n",
331
+ "# Information Loss (Percentage)\n",
332
+ "original_variance = np.var(X_scaled, axis=0).sum() # Total variance before PCA\n",
333
+ "reconstruction_variance = np.var(X_reconstructed, axis=0).sum() # Variance after PCA\n",
334
+ "info_lost = (original_variance - reconstruction_variance) / original_variance\n",
335
+ "\n",
336
+ "print(f\"Reconstruction Error (MSE): {reconstruction_error:.4f}\")\n",
337
+ "print(f\"Information Lost: {info_lost * 100:.2f}%\")\n"
338
+ ]
339
+ },
340
+ {
341
+ "cell_type": "code",
342
+ "execution_count": null,
343
+ "id": "31328128-b838-452d-a617-18e453a97f84",
344
+ "metadata": {},
345
+ "outputs": [],
346
+ "source": [
347
+ "from sklearn.metrics import f1_score\n",
348
+ "\n",
349
+ "# Example: True labels and predicted labels\n",
350
+ "y_true = [0, 1, 1, 1, 0, 1, 0, 0, 1, 0] # Actual values\n",
351
+ "y_pred = [0, 1, 1, 0, 0, 1, 0, 1, 1, 0] # Predicted values\n",
352
+ "\n",
353
+ "# Compute F1-score\n",
354
+ "f1 = f1_score(y_true, y_pred) # Default: 'binary' classification\n",
355
+ "print(f\"F1-score: {f1:.4f}\")\n"
356
+ ]
357
+ },
358
+ {
359
+ "cell_type": "code",
360
+ "execution_count": null,
361
+ "id": "a9c36666-3ff7-4f6b-b9cc-1354b0e80ffa",
362
+ "metadata": {},
363
+ "outputs": [],
364
+ "source": [
365
+ "from sklearn.decomposition import PCA\n",
366
+ "\n",
367
+ "pca = PCA(n_components=0.90) # Automatically chooses components for 90% variance\n",
368
+ "X_pca = pca.fit_transform(X_scaled)\n",
369
+ "\n",
370
+ "print(f'Number of components needed: {pca.n_components_}')\n"
371
+ ]
372
+ }
373
+ ],
374
+ "metadata": {
375
+ "kernelspec": {
376
+ "display_name": "Python [conda env:base] *",
377
+ "language": "python",
378
+ "name": "conda-base-py"
379
+ },
380
+ "language_info": {
381
+ "codemirror_mode": {
382
+ "name": "ipython",
383
+ "version": 3
384
+ },
385
+ "file_extension": ".py",
386
+ "mimetype": "text/x-python",
387
+ "name": "python",
388
+ "nbconvert_exporter": "python",
389
+ "pygments_lexer": "ipython3",
390
+ "version": "3.12.7"
391
+ }
392
+ },
393
+ "nbformat": 4,
394
+ "nbformat_minor": 5
395
+ }