noshot 0.3.3__py3-none-any.whl → 0.3.5__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 (29) hide show
  1. noshot/data/ML TS XAI/ML/data/balance-scale.csv +626 -626
  2. noshot/data/ML TS XAI/ML/data/balance-scale.txt +624 -624
  3. noshot/data/ML TS XAI/ML/data/machine-data.csv +210 -210
  4. noshot/data/ML TS XAI/ML/data/wine-dataset.csv +179 -179
  5. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/1/1.ipynb +255 -0
  6. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/1/Question.txt +12 -0
  7. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/1/airfoil_self_noise.dat +1503 -0
  8. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/2/2.ipynb +399 -0
  9. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/2/Question.txt +12 -0
  10. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/2/pop_failures.dat +143 -0
  11. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/3/3.ipynb +276 -0
  12. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/3/Qu.txt +1 -0
  13. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/3/go_track_tracks.csv +164 -0
  14. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/4/4.ipynb +265 -0
  15. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/4/Wilt.csv +4340 -0
  16. noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/4/qu.txt +1 -0
  17. noshot/data/ML TS XAI/TS/data/daily-min-temperatures.csv +3650 -3650
  18. noshot/data/ML TS XAI/TS/data/daily-total-female-births.csv +365 -365
  19. noshot/data/ML TS XAI/TS/data/raw_sales.csv +29580 -29580
  20. noshot/data/ML TS XAI/TS/data/shampoo_sales.csv +36 -36
  21. noshot/main.py +18 -18
  22. noshot/utils/__init__.py +2 -2
  23. noshot/utils/shell_utils.py +56 -56
  24. {noshot-0.3.3.dist-info → noshot-0.3.5.dist-info}/LICENSE.txt +20 -20
  25. {noshot-0.3.3.dist-info → noshot-0.3.5.dist-info}/METADATA +55 -55
  26. noshot-0.3.5.dist-info/RECORD +42 -0
  27. {noshot-0.3.3.dist-info → noshot-0.3.5.dist-info}/WHEEL +1 -1
  28. noshot-0.3.3.dist-info/RECORD +0 -30
  29. {noshot-0.3.3.dist-info → noshot-0.3.5.dist-info}/top_level.txt +0 -0
noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/2/2.ipynb ADDED
@@ -0,0 +1,399 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "id": "0c44baad-6341-4743-ae5d-502ce6647dfc",
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
+ "import seaborn as sns\n",
14
+ "from sklearn.decomposition import PCA\n",
15
+ "from sklearn.neighbors import KNeighborsClassifier\n",
16
+ "from sklearn.model_selection import train_test_split\n",
17
+ "from sklearn.preprocessing import StandardScaler\n",
18
+ "from sklearn.metrics import accuracy_score"
19
+ ]
20
+ },
21
+ {
22
+ "cell_type": "code",
23
+ "execution_count": 2,
24
+ "id": "328266f0-f099-47a9-b146-0a1df89d5b47",
25
+ "metadata": {},
26
+ "outputs": [],
27
+ "source": [
28
+ "import warnings\n",
29
+ "warnings.filterwarnings('ignore')"
30
+ ]
31
+ },
32
+ {
33
+ "cell_type": "code",
34
+ "execution_count": 3,
35
+ "id": "d4ad00b9-b339-4af3-9fdc-aada76a5eac5",
36
+ "metadata": {},
37
+ "outputs": [
38
+ {
39
+ "name": "stdout",
40
+ "output_type": "stream",
41
+ "text": [
42
+ "Dataset Shape: (142, 21)\n"
43
+ ]
44
+ },
45
+ {
46
+ "data": {
47
+ "text/html": [
48
+ "<div>\n",
49
+ "<style scoped>\n",
50
+ " .dataframe tbody tr th:only-of-type {\n",
51
+ " vertical-align: middle;\n",
52
+ " }\n",
53
+ "\n",
54
+ " .dataframe tbody tr th {\n",
55
+ " vertical-align: top;\n",
56
+ " }\n",
57
+ "\n",
58
+ " .dataframe thead th {\n",
59
+ " text-align: right;\n",
60
+ " }\n",
61
+ "</style>\n",
62
+ "<table border=\"1\" class=\"dataframe\">\n",
63
+ " <thead>\n",
64
+ " <tr style=\"text-align: right;\">\n",
65
+ " <th></th>\n",
66
+ " <th>Study</th>\n",
67
+ " <th>Run</th>\n",
68
+ " <th>vconst_corr</th>\n",
69
+ " <th>vconst_2</th>\n",
70
+ " <th>vconst_3</th>\n",
71
+ " <th>vconst_4</th>\n",
72
+ " <th>vconst_5</th>\n",
73
+ " <th>vconst_7</th>\n",
74
+ " <th>ah_corr</th>\n",
75
+ " <th>ah_bolus</th>\n",
76
+ " <th>...</th>\n",
77
+ " <th>efficiency_factor</th>\n",
78
+ " <th>tidal_mix_max</th>\n",
79
+ " <th>vertical_decay_scale</th>\n",
80
+ " <th>convect_corr</th>\n",
81
+ " <th>bckgrnd_vdc1</th>\n",
82
+ " <th>bckgrnd_vdc_ban</th>\n",
83
+ " <th>bckgrnd_vdc_eq</th>\n",
84
+ " <th>bckgrnd_vdc_psim</th>\n",
85
+ " <th>Prandtl</th>\n",
86
+ " <th>outcome</th>\n",
87
+ " </tr>\n",
88
+ " </thead>\n",
89
+ " <tbody>\n",
90
+ " <tr>\n",
91
+ " <th>0</th>\n",
92
+ " <td>1</td>\n",
93
+ " <td>1</td>\n",
94
+ " <td>0.859036</td>\n",
95
+ " <td>0.927825</td>\n",
96
+ " <td>0.252866</td>\n",
97
+ " <td>0.298838</td>\n",
98
+ " <td>0.170521</td>\n",
99
+ " <td>0.735936</td>\n",
100
+ " <td>0.428325</td>\n",
101
+ " <td>0.567947</td>\n",
102
+ " <td>...</td>\n",
103
+ " <td>0.245675</td>\n",
104
+ " <td>0.104226</td>\n",
105
+ " <td>0.869091</td>\n",
106
+ " <td>0.997518</td>\n",
107
+ " <td>0.448620</td>\n",
108
+ " <td>0.307522</td>\n",
109
+ " <td>0.858310</td>\n",
110
+ " <td>0.796997</td>\n",
111
+ " <td>0.869893</td>\n",
112
+ " <td>0.0</td>\n",
113
+ " </tr>\n",
114
+ " <tr>\n",
115
+ " <th>1</th>\n",
116
+ " <td>1</td>\n",
117
+ " <td>2</td>\n",
118
+ " <td>0.606041</td>\n",
119
+ " <td>0.457728</td>\n",
120
+ " <td>0.359448</td>\n",
121
+ " <td>0.306957</td>\n",
122
+ " <td>0.843331</td>\n",
123
+ " <td>0.934851</td>\n",
124
+ " <td>0.444572</td>\n",
125
+ " <td>0.828015</td>\n",
126
+ " <td>...</td>\n",
127
+ " <td>0.616870</td>\n",
128
+ " <td>0.975786</td>\n",
129
+ " <td>0.914344</td>\n",
130
+ " <td>0.845247</td>\n",
131
+ " <td>0.864152</td>\n",
132
+ " <td>0.346713</td>\n",
133
+ " <td>0.356573</td>\n",
134
+ " <td>0.438447</td>\n",
135
+ " <td>0.512256</td>\n",
136
+ " <td>1.0</td>\n",
137
+ " </tr>\n",
138
+ " <tr>\n",
139
+ " <th>2</th>\n",
140
+ " <td>1</td>\n",
141
+ " <td>3</td>\n",
142
+ " <td>0.997600</td>\n",
143
+ " <td>0.373238</td>\n",
144
+ " <td>0.517399</td>\n",
145
+ " <td>0.504993</td>\n",
146
+ " <td>0.618903</td>\n",
147
+ " <td>0.605571</td>\n",
148
+ " <td>0.746225</td>\n",
149
+ " <td>0.195928</td>\n",
150
+ " <td>...</td>\n",
151
+ " <td>0.679355</td>\n",
152
+ " <td>0.803413</td>\n",
153
+ " <td>0.643995</td>\n",
154
+ " <td>0.718441</td>\n",
155
+ " <td>0.924775</td>\n",
156
+ " <td>0.315371</td>\n",
157
+ " <td>0.250642</td>\n",
158
+ " <td>0.285636</td>\n",
159
+ " <td>0.365858</td>\n",
160
+ " <td>1.0</td>\n",
161
+ " </tr>\n",
162
+ " <tr>\n",
163
+ " <th>3</th>\n",
164
+ " <td>1</td>\n",
165
+ " <td>4</td>\n",
166
+ " <td>0.783408</td>\n",
167
+ " <td>0.104055</td>\n",
168
+ " <td>0.197533</td>\n",
169
+ " <td>0.421837</td>\n",
170
+ " <td>0.742056</td>\n",
171
+ " <td>0.490828</td>\n",
172
+ " <td>0.005525</td>\n",
173
+ " <td>0.392123</td>\n",
174
+ " <td>...</td>\n",
175
+ " <td>0.471463</td>\n",
176
+ " <td>0.597879</td>\n",
177
+ " <td>0.761659</td>\n",
178
+ " <td>0.362751</td>\n",
179
+ " <td>0.912819</td>\n",
180
+ " <td>0.977971</td>\n",
181
+ " <td>0.845921</td>\n",
182
+ " <td>0.699431</td>\n",
183
+ " <td>0.475987</td>\n",
184
+ " <td>1.0</td>\n",
185
+ " </tr>\n",
186
+ " <tr>\n",
187
+ " <th>4</th>\n",
188
+ " <td>1</td>\n",
189
+ " <td>5</td>\n",
190
+ " <td>0.406250</td>\n",
191
+ " <td>0.513199</td>\n",
192
+ " <td>0.061812</td>\n",
193
+ " <td>0.635837</td>\n",
194
+ " <td>0.844798</td>\n",
195
+ " <td>0.441502</td>\n",
196
+ " <td>0.191926</td>\n",
197
+ " <td>0.487546</td>\n",
198
+ " <td>...</td>\n",
199
+ " <td>0.551543</td>\n",
200
+ " <td>0.743877</td>\n",
201
+ " <td>0.312349</td>\n",
202
+ " <td>0.650223</td>\n",
203
+ " <td>0.522261</td>\n",
204
+ " <td>0.043545</td>\n",
205
+ " <td>0.376660</td>\n",
206
+ " <td>0.280098</td>\n",
207
+ " <td>0.132283</td>\n",
208
+ " <td>1.0</td>\n",
209
+ " </tr>\n",
210
+ " </tbody>\n",
211
+ "</table>\n",
212
+ "<p>5 rows × 21 columns</p>\n",
213
+ "</div>"
214
+ ],
215
+ "text/plain": [
216
+ " Study Run vconst_corr vconst_2 vconst_3 vconst_4 vconst_5 vconst_7 \\\n",
217
+ "0 1 1 0.859036 0.927825 0.252866 0.298838 0.170521 0.735936 \n",
218
+ "1 1 2 0.606041 0.457728 0.359448 0.306957 0.843331 0.934851 \n",
219
+ "2 1 3 0.997600 0.373238 0.517399 0.504993 0.618903 0.605571 \n",
220
+ "3 1 4 0.783408 0.104055 0.197533 0.421837 0.742056 0.490828 \n",
221
+ "4 1 5 0.406250 0.513199 0.061812 0.635837 0.844798 0.441502 \n",
222
+ "\n",
223
+ " ah_corr ah_bolus ... efficiency_factor tidal_mix_max \\\n",
224
+ "0 0.428325 0.567947 ... 0.245675 0.104226 \n",
225
+ "1 0.444572 0.828015 ... 0.616870 0.975786 \n",
226
+ "2 0.746225 0.195928 ... 0.679355 0.803413 \n",
227
+ "3 0.005525 0.392123 ... 0.471463 0.597879 \n",
228
+ "4 0.191926 0.487546 ... 0.551543 0.743877 \n",
229
+ "\n",
230
+ " vertical_decay_scale convect_corr bckgrnd_vdc1 bckgrnd_vdc_ban \\\n",
231
+ "0 0.869091 0.997518 0.448620 0.307522 \n",
232
+ "1 0.914344 0.845247 0.864152 0.346713 \n",
233
+ "2 0.643995 0.718441 0.924775 0.315371 \n",
234
+ "3 0.761659 0.362751 0.912819 0.977971 \n",
235
+ "4 0.312349 0.650223 0.522261 0.043545 \n",
236
+ "\n",
237
+ " bckgrnd_vdc_eq bckgrnd_vdc_psim Prandtl outcome \n",
238
+ "0 0.858310 0.796997 0.869893 0.0 \n",
239
+ "1 0.356573 0.438447 0.512256 1.0 \n",
240
+ "2 0.250642 0.285636 0.365858 1.0 \n",
241
+ "3 0.845921 0.699431 0.475987 1.0 \n",
242
+ "4 0.376660 0.280098 0.132283 1.0 \n",
243
+ "\n",
244
+ "[5 rows x 21 columns]"
245
+ ]
246
+ },
247
+ "execution_count": 3,
248
+ "metadata": {},
249
+ "output_type": "execute_result"
250
+ }
251
+ ],
252
+ "source": [
253
+ "file_path = \"pop_failures.dat\"\n",
254
+ "df = pd.read_table(file_path, sep=\"\\s+\")\n",
255
+ "print(\"Dataset Shape:\", df.shape)\n",
256
+ "df.head()"
257
+ ]
258
+ },
259
+ {
260
+ "cell_type": "code",
261
+ "execution_count": 4,
262
+ "id": "8bf01bf7-e86b-43dc-8787-d4d50afc5f56",
263
+ "metadata": {},
264
+ "outputs": [
265
+ {
266
+ "name": "stdout",
267
+ "output_type": "stream",
268
+ "text": [
269
+ "<class 'pandas.core.frame.DataFrame'>\n",
270
+ "RangeIndex: 142 entries, 0 to 141\n",
271
+ "Data columns (total 21 columns):\n",
272
+ " # Column Non-Null Count Dtype \n",
273
+ "--- ------ -------------- ----- \n",
274
+ " 0 Study 142 non-null int64 \n",
275
+ " 1 Run 142 non-null int64 \n",
276
+ " 2 vconst_corr 142 non-null float64\n",
277
+ " 3 vconst_2 142 non-null float64\n",
278
+ " 4 vconst_3 142 non-null float64\n",
279
+ " 5 vconst_4 142 non-null float64\n",
280
+ " 6 vconst_5 142 non-null float64\n",
281
+ " 7 vconst_7 142 non-null float64\n",
282
+ " 8 ah_corr 142 non-null float64\n",
283
+ " 9 ah_bolus 142 non-null float64\n",
284
+ " 10 slm_corr 142 non-null float64\n",
285
+ " 11 efficiency_factor 141 non-null float64\n",
286
+ " 12 tidal_mix_max 141 non-null float64\n",
287
+ " 13 vertical_decay_scale 141 non-null float64\n",
288
+ " 14 convect_corr 141 non-null float64\n",
289
+ " 15 bckgrnd_vdc1 141 non-null float64\n",
290
+ " 16 bckgrnd_vdc_ban 141 non-null float64\n",
291
+ " 17 bckgrnd_vdc_eq 141 non-null float64\n",
292
+ " 18 bckgrnd_vdc_psim 141 non-null float64\n",
293
+ " 19 Prandtl 141 non-null float64\n",
294
+ " 20 outcome 141 non-null float64\n",
295
+ "dtypes: float64(19), int64(2)\n",
296
+ "memory usage: 23.4 KB\n"
297
+ ]
298
+ }
299
+ ],
300
+ "source": [
301
+ "df.info()"
302
+ ]
303
+ },
304
+ {
305
+ "cell_type": "code",
306
+ "execution_count": 5,
307
+ "id": "b21b1c88-35e1-477a-9c8c-469ff2cb49ea",
308
+ "metadata": {},
309
+ "outputs": [],
310
+ "source": [
311
+ "df.dropna(inplace = True)"
312
+ ]
313
+ },
314
+ {
315
+ "cell_type": "code",
316
+ "execution_count": 6,
317
+ "id": "3f459656-d365-4d6c-9a2a-63f021d3d27e",
318
+ "metadata": {},
319
+ "outputs": [],
320
+ "source": [
321
+ "X = df.iloc[:, 2:20].values\n",
322
+ "y = df.iloc[:, 20].values\n",
323
+ "\n",
324
+ "scaler = StandardScaler()\n",
325
+ "X_scaled = scaler.fit_transform(X)\n",
326
+ "\n",
327
+ "pca = PCA(n_components=2)\n",
328
+ "X_pca = pca.fit_transform(X_scaled)\n",
329
+ "\n",
330
+ "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
331
+ "X_pca_train, X_pca_test, _, _ = train_test_split(X_pca, y, test_size=0.2, random_state=42)\n",
332
+ "\n",
333
+ "k_values = range(1, 21)\n",
334
+ "accuracies_original = []\n",
335
+ "accuracies_pca = []\n",
336
+ "\n",
337
+ "for k in k_values:\n",
338
+ " knn = KNeighborsClassifier(n_neighbors=k)\n",
339
+ " knn.fit(X_train, y_train)\n",
340
+ " y_pred_original = knn.predict(X_test)\n",
341
+ " accuracies_original.append(accuracy_score(y_test, y_pred_original))\n",
342
+ " \n",
343
+ " knn.fit(X_pca_train, y_train)\n",
344
+ " y_pred_pca = knn.predict(X_pca_test)\n",
345
+ " accuracies_pca.append(accuracy_score(y_test, y_pred_pca))"
346
+ ]
347
+ },
348
+ {
349
+ "cell_type": "code",
350
+ "execution_count": 7,
351
+ "id": "f4ff07e6-a4af-433b-b9fe-f9134dea12e1",
352
+ "metadata": {},
353
+ "outputs": [
354
+ {
355
+ "data": {
356
+ "image/png": "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",
357
+ "text/plain": [
358
+ "<Figure size 1000x500 with 1 Axes>"
359
+ ]
360
+ },
361
+ "metadata": {},
362
+ "output_type": "display_data"
363
+ }
364
+ ],
365
+ "source": [
366
+ "plt.figure(figsize=(10, 5))\n",
367
+ "plt.plot(k_values, accuracies_original, label='KNN without PCA', marker='o')\n",
368
+ "plt.plot(k_values, accuracies_pca, label='KNN with PCA', marker='s')\n",
369
+ "plt.xlabel(\"K Value\")\n",
370
+ "plt.ylabel(\"Accuracy\")\n",
371
+ "plt.title(\"KNN Accuracy Comparison with and without PCA\")\n",
372
+ "plt.legend()\n",
373
+ "plt.grid()\n",
374
+ "plt.show()"
375
+ ]
376
+ }
377
+ ],
378
+ "metadata": {
379
+ "kernelspec": {
380
+ "display_name": "Python 3 (ipykernel)",
381
+ "language": "python",
382
+ "name": "python3"
383
+ },
384
+ "language_info": {
385
+ "codemirror_mode": {
386
+ "name": "ipython",
387
+ "version": 3
388
+ },
389
+ "file_extension": ".py",
390
+ "mimetype": "text/x-python",
391
+ "name": "python",
392
+ "nbconvert_exporter": "python",
393
+ "pygments_lexer": "ipython3",
394
+ "version": "3.12.4"
395
+ }
396
+ },
397
+ "nbformat": 4,
398
+ "nbformat_minor": 5
399
+ }
noshot/data/ML TS XAI/ML Lab CIA - Healthy directly upload file/2/Question.txt ADDED
@@ -0,0 +1,12 @@
1
+ Apply KNN (with and without PCA) with different K values and analyze accuracy with a line plot.
2
+ Attribute Information:
3
+
4
+ The goal is to predict climate model simulation outcomes (column 21, fail or succeed) given scaled values of climate model input parameters (columns 3-20).
5
+
6
+ Column 1: Latin hypercube study ID (study 1 to study 3)
7
+
8
+ Column 2: simulation ID (run 1 to run 180)
9
+
10
+ Columns 3-20: values of 18 climate model parameters scaled in the interval [0, 1]
11
+
12
+ Column 21: simulation outcome (0 = failure, 1 = success)