├── Cloud_AutoML_Vision
    ├── Data Preparation.ipynb
    ├── Kaggle Data Download.ipynb
    ├── README.md
    └── predict.ipynb
├── GCP_Serverless_AppEngine
    ├── ComplaintsFlask.py
    ├── ComplaintsServer.py
    ├── Dockerfile
    ├── README.md
    ├── Text_Classification_using_TFIDF_AutoML_scikit_learn.ipynb
    ├── app.yaml
    ├── preprocessing
    │   └── functions.py
    └── requirements.txt
├── Google_Kubernetes_Engine
    ├── ComplaintsFlask.py
    ├── Dockerfile
    ├── README.md
    ├── Text_Classification_using_TFIDF_AutoML_scikit_learn.ipynb
    ├── deployment.yaml
    ├── preprocessing
    │   └── functions.py
    ├── requirements.txt
    └── service.yaml
├── README.md
├── Telecom_churn_AI_Platform
    ├── Churn_model.ipynb
    ├── README.md
    ├── data
    │   ├── README.md
    │   └── telecom_customer_churn.csv
    ├── input.json
    ├── predict_setup.ipynb
    ├── predictor.py
    ├── serving.ipynb
    └── setup.py
├── bigquery_logisticsregression
    └── README.md
├── bigqueryml_datastudio
    └── README.md
└── gke_autopilot
    ├── Dockerfile
    ├── README.md
    ├── deployment.yaml
    ├── imgwebapp.py
    ├── models
        ├── assets
        │   └── README.md
        ├── saved_model.pb
        └── variables
        │   ├── variables.data-00000-of-00002
        │   ├── variables.data-00001-of-00002
        │   └── variables.index
    ├── requirements.txt
    └── service.yaml


/Cloud_AutoML_Vision/Data Preparation.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 36,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": 37,
 15 |    "metadata": {},
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "df=pd.read_csv('train.csv')"
 19 |    ]
 20 |   },
 21 |   {
 22 |    "cell_type": "code",
 23 |    "execution_count": 38,
 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>image_id</th>\n",
 48 |        "      <th>label</th>\n",
 49 |        "    </tr>\n",
 50 |        "  </thead>\n",
 51 |        "  <tbody>\n",
 52 |        "    <tr>\n",
 53 |        "      <th>0</th>\n",
 54 |        "      <td>1000015157.jpg</td>\n",
 55 |        "      <td>0</td>\n",
 56 |        "    </tr>\n",
 57 |        "    <tr>\n",
 58 |        "      <th>1</th>\n",
 59 |        "      <td>1000201771.jpg</td>\n",
 60 |        "      <td>3</td>\n",
 61 |        "    </tr>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>2</th>\n",
 64 |        "      <td>100042118.jpg</td>\n",
 65 |        "      <td>1</td>\n",
 66 |        "    </tr>\n",
 67 |        "    <tr>\n",
 68 |        "      <th>3</th>\n",
 69 |        "      <td>1000723321.jpg</td>\n",
 70 |        "      <td>1</td>\n",
 71 |        "    </tr>\n",
 72 |        "    <tr>\n",
 73 |        "      <th>4</th>\n",
 74 |        "      <td>1000812911.jpg</td>\n",
 75 |        "      <td>3</td>\n",
 76 |        "    </tr>\n",
 77 |        "    <tr>\n",
 78 |        "      <th>...</th>\n",
 79 |        "      <td>...</td>\n",
 80 |        "      <td>...</td>\n",
 81 |        "    </tr>\n",
 82 |        "    <tr>\n",
 83 |        "      <th>21392</th>\n",
 84 |        "      <td>999068805.jpg</td>\n",
 85 |        "      <td>3</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>21393</th>\n",
 89 |        "      <td>999329392.jpg</td>\n",
 90 |        "      <td>3</td>\n",
 91 |        "    </tr>\n",
 92 |        "    <tr>\n",
 93 |        "      <th>21394</th>\n",
 94 |        "      <td>999474432.jpg</td>\n",
 95 |        "      <td>1</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>21395</th>\n",
 99 |        "      <td>999616605.jpg</td>\n",
100 |        "      <td>4</td>\n",
101 |        "    </tr>\n",
102 |        "    <tr>\n",
103 |        "      <th>21396</th>\n",
104 |        "      <td>999998473.jpg</td>\n",
105 |        "      <td>4</td>\n",
106 |        "    </tr>\n",
107 |        "  </tbody>\n",
108 |        "</table>\n",
109 |        "<p>21397 rows × 2 columns</p>\n",
110 |        "</div>"
111 |       ],
112 |       "text/plain": [
113 |        "             image_id  label\n",
114 |        "0      1000015157.jpg      0\n",
115 |        "1      1000201771.jpg      3\n",
116 |        "2       100042118.jpg      1\n",
117 |        "3      1000723321.jpg      1\n",
118 |        "4      1000812911.jpg      3\n",
119 |        "...               ...    ...\n",
120 |        "21392   999068805.jpg      3\n",
121 |        "21393   999329392.jpg      3\n",
122 |        "21394   999474432.jpg      1\n",
123 |        "21395   999616605.jpg      4\n",
124 |        "21396   999998473.jpg      4\n",
125 |        "\n",
126 |        "[21397 rows x 2 columns]"
127 |       ]
128 |      },
129 |      "execution_count": 38,
130 |      "metadata": {},
131 |      "output_type": "execute_result"
132 |     }
133 |    ],
134 |    "source": [
135 |     "df"
136 |    ]
137 |   },
138 |   {
139 |    "cell_type": "code",
140 |    "execution_count": null,
141 |    "metadata": {},
142 |    "outputs": [],
143 |    "source": [
144 |     "label ={0:'CBB', 1:'CBSD', 2:'CGM', 3:'CMD', 4:'Healthy'}"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "code",
149 |    "execution_count": 39,
150 |    "metadata": {},
151 |    "outputs": [],
152 |    "source": [
153 |     "df['image_path'] = 'gs://srivatsan-project-vcm/train_images/' + df['image_id']"
154 |    ]
155 |   },
156 |   {
157 |    "cell_type": "code",
158 |    "execution_count": 40,
159 |    "metadata": {},
160 |    "outputs": [
161 |     {
162 |      "data": {
163 |       "text/html": [
164 |        "<div>\n",
165 |        "<style scoped>\n",
166 |        "    .dataframe tbody tr th:only-of-type {\n",
167 |        "        vertical-align: middle;\n",
168 |        "    }\n",
169 |        "\n",
170 |        "    .dataframe tbody tr th {\n",
171 |        "        vertical-align: top;\n",
172 |        "    }\n",
173 |        "\n",
174 |        "    .dataframe thead th {\n",
175 |        "        text-align: right;\n",
176 |        "    }\n",
177 |        "</style>\n",
178 |        "<table border=\"1\" class=\"dataframe\">\n",
179 |        "  <thead>\n",
180 |        "    <tr style=\"text-align: right;\">\n",
181 |        "      <th></th>\n",
182 |        "      <th>image_id</th>\n",
183 |        "      <th>label</th>\n",
184 |        "      <th>image_path</th>\n",
185 |        "    </tr>\n",
186 |        "  </thead>\n",
187 |        "  <tbody>\n",
188 |        "    <tr>\n",
189 |        "      <th>0</th>\n",
190 |        "      <td>1000015157.jpg</td>\n",
191 |        "      <td>0</td>\n",
192 |        "      <td>gs://srivatsan-project-vcm/train_images/100001...</td>\n",
193 |        "    </tr>\n",
194 |        "    <tr>\n",
195 |        "      <th>1</th>\n",
196 |        "      <td>1000201771.jpg</td>\n",
197 |        "      <td>3</td>\n",
198 |        "      <td>gs://srivatsan-project-vcm/train_images/100020...</td>\n",
199 |        "    </tr>\n",
200 |        "    <tr>\n",
201 |        "      <th>2</th>\n",
202 |        "      <td>100042118.jpg</td>\n",
203 |        "      <td>1</td>\n",
204 |        "      <td>gs://srivatsan-project-vcm/train_images/100042...</td>\n",
205 |        "    </tr>\n",
206 |        "    <tr>\n",
207 |        "      <th>3</th>\n",
208 |        "      <td>1000723321.jpg</td>\n",
209 |        "      <td>1</td>\n",
210 |        "      <td>gs://srivatsan-project-vcm/train_images/100072...</td>\n",
211 |        "    </tr>\n",
212 |        "    <tr>\n",
213 |        "      <th>4</th>\n",
214 |        "      <td>1000812911.jpg</td>\n",
215 |        "      <td>3</td>\n",
216 |        "      <td>gs://srivatsan-project-vcm/train_images/100081...</td>\n",
217 |        "    </tr>\n",
218 |        "    <tr>\n",
219 |        "      <th>...</th>\n",
220 |        "      <td>...</td>\n",
221 |        "      <td>...</td>\n",
222 |        "      <td>...</td>\n",
223 |        "    </tr>\n",
224 |        "    <tr>\n",
225 |        "      <th>21392</th>\n",
226 |        "      <td>999068805.jpg</td>\n",
227 |        "      <td>3</td>\n",
228 |        "      <td>gs://srivatsan-project-vcm/train_images/999068...</td>\n",
229 |        "    </tr>\n",
230 |        "    <tr>\n",
231 |        "      <th>21393</th>\n",
232 |        "      <td>999329392.jpg</td>\n",
233 |        "      <td>3</td>\n",
234 |        "      <td>gs://srivatsan-project-vcm/train_images/999329...</td>\n",
235 |        "    </tr>\n",
236 |        "    <tr>\n",
237 |        "      <th>21394</th>\n",
238 |        "      <td>999474432.jpg</td>\n",
239 |        "      <td>1</td>\n",
240 |        "      <td>gs://srivatsan-project-vcm/train_images/999474...</td>\n",
241 |        "    </tr>\n",
242 |        "    <tr>\n",
243 |        "      <th>21395</th>\n",
244 |        "      <td>999616605.jpg</td>\n",
245 |        "      <td>4</td>\n",
246 |        "      <td>gs://srivatsan-project-vcm/train_images/999616...</td>\n",
247 |        "    </tr>\n",
248 |        "    <tr>\n",
249 |        "      <th>21396</th>\n",
250 |        "      <td>999998473.jpg</td>\n",
251 |        "      <td>4</td>\n",
252 |        "      <td>gs://srivatsan-project-vcm/train_images/999998...</td>\n",
253 |        "    </tr>\n",
254 |        "  </tbody>\n",
255 |        "</table>\n",
256 |        "<p>21397 rows × 3 columns</p>\n",
257 |        "</div>"
258 |       ],
259 |       "text/plain": [
260 |        "             image_id  label  \\\n",
261 |        "0      1000015157.jpg      0   \n",
262 |        "1      1000201771.jpg      3   \n",
263 |        "2       100042118.jpg      1   \n",
264 |        "3      1000723321.jpg      1   \n",
265 |        "4      1000812911.jpg      3   \n",
266 |        "...               ...    ...   \n",
267 |        "21392   999068805.jpg      3   \n",
268 |        "21393   999329392.jpg      3   \n",
269 |        "21394   999474432.jpg      1   \n",
270 |        "21395   999616605.jpg      4   \n",
271 |        "21396   999998473.jpg      4   \n",
272 |        "\n",
273 |        "                                              image_path  \n",
274 |        "0      gs://srivatsan-project-vcm/train_images/100001...  \n",
275 |        "1      gs://srivatsan-project-vcm/train_images/100020...  \n",
276 |        "2      gs://srivatsan-project-vcm/train_images/100042...  \n",
277 |        "3      gs://srivatsan-project-vcm/train_images/100072...  \n",
278 |        "4      gs://srivatsan-project-vcm/train_images/100081...  \n",
279 |        "...                                                  ...  \n",
280 |        "21392  gs://srivatsan-project-vcm/train_images/999068...  \n",
281 |        "21393  gs://srivatsan-project-vcm/train_images/999329...  \n",
282 |        "21394  gs://srivatsan-project-vcm/train_images/999474...  \n",
283 |        "21395  gs://srivatsan-project-vcm/train_images/999616...  \n",
284 |        "21396  gs://srivatsan-project-vcm/train_images/999998...  \n",
285 |        "\n",
286 |        "[21397 rows x 3 columns]"
287 |       ]
288 |      },
289 |      "execution_count": 40,
290 |      "metadata": {},
291 |      "output_type": "execute_result"
292 |     }
293 |    ],
294 |    "source": [
295 |     "df"
296 |    ]
297 |   },
298 |   {
299 |    "cell_type": "code",
300 |    "execution_count": 41,
301 |    "metadata": {},
302 |    "outputs": [],
303 |    "source": [
304 |     "df=df.replace({'label':label})"
305 |    ]
306 |   },
307 |   {
308 |    "cell_type": "code",
309 |    "execution_count": 42,
310 |    "metadata": {},
311 |    "outputs": [
312 |     {
313 |      "data": {
314 |       "text/html": [
315 |        "<div>\n",
316 |        "<style scoped>\n",
317 |        "    .dataframe tbody tr th:only-of-type {\n",
318 |        "        vertical-align: middle;\n",
319 |        "    }\n",
320 |        "\n",
321 |        "    .dataframe tbody tr th {\n",
322 |        "        vertical-align: top;\n",
323 |        "    }\n",
324 |        "\n",
325 |        "    .dataframe thead th {\n",
326 |        "        text-align: right;\n",
327 |        "    }\n",
328 |        "</style>\n",
329 |        "<table border=\"1\" class=\"dataframe\">\n",
330 |        "  <thead>\n",
331 |        "    <tr style=\"text-align: right;\">\n",
332 |        "      <th></th>\n",
333 |        "      <th>image_id</th>\n",
334 |        "      <th>label</th>\n",
335 |        "      <th>image_path</th>\n",
336 |        "    </tr>\n",
337 |        "  </thead>\n",
338 |        "  <tbody>\n",
339 |        "    <tr>\n",
340 |        "      <th>0</th>\n",
341 |        "      <td>1000015157.jpg</td>\n",
342 |        "      <td>CBB</td>\n",
343 |        "      <td>gs://srivatsan-project-vcm/train_images/100001...</td>\n",
344 |        "    </tr>\n",
345 |        "    <tr>\n",
346 |        "      <th>1</th>\n",
347 |        "      <td>1000201771.jpg</td>\n",
348 |        "      <td>CMD</td>\n",
349 |        "      <td>gs://srivatsan-project-vcm/train_images/100020...</td>\n",
350 |        "    </tr>\n",
351 |        "    <tr>\n",
352 |        "      <th>2</th>\n",
353 |        "      <td>100042118.jpg</td>\n",
354 |        "      <td>CBSD</td>\n",
355 |        "      <td>gs://srivatsan-project-vcm/train_images/100042...</td>\n",
356 |        "    </tr>\n",
357 |        "    <tr>\n",
358 |        "      <th>3</th>\n",
359 |        "      <td>1000723321.jpg</td>\n",
360 |        "      <td>CBSD</td>\n",
361 |        "      <td>gs://srivatsan-project-vcm/train_images/100072...</td>\n",
362 |        "    </tr>\n",
363 |        "    <tr>\n",
364 |        "      <th>4</th>\n",
365 |        "      <td>1000812911.jpg</td>\n",
366 |        "      <td>CMD</td>\n",
367 |        "      <td>gs://srivatsan-project-vcm/train_images/100081...</td>\n",
368 |        "    </tr>\n",
369 |        "    <tr>\n",
370 |        "      <th>...</th>\n",
371 |        "      <td>...</td>\n",
372 |        "      <td>...</td>\n",
373 |        "      <td>...</td>\n",
374 |        "    </tr>\n",
375 |        "    <tr>\n",
376 |        "      <th>21392</th>\n",
377 |        "      <td>999068805.jpg</td>\n",
378 |        "      <td>CMD</td>\n",
379 |        "      <td>gs://srivatsan-project-vcm/train_images/999068...</td>\n",
380 |        "    </tr>\n",
381 |        "    <tr>\n",
382 |        "      <th>21393</th>\n",
383 |        "      <td>999329392.jpg</td>\n",
384 |        "      <td>CMD</td>\n",
385 |        "      <td>gs://srivatsan-project-vcm/train_images/999329...</td>\n",
386 |        "    </tr>\n",
387 |        "    <tr>\n",
388 |        "      <th>21394</th>\n",
389 |        "      <td>999474432.jpg</td>\n",
390 |        "      <td>CBSD</td>\n",
391 |        "      <td>gs://srivatsan-project-vcm/train_images/999474...</td>\n",
392 |        "    </tr>\n",
393 |        "    <tr>\n",
394 |        "      <th>21395</th>\n",
395 |        "      <td>999616605.jpg</td>\n",
396 |        "      <td>Healthy</td>\n",
397 |        "      <td>gs://srivatsan-project-vcm/train_images/999616...</td>\n",
398 |        "    </tr>\n",
399 |        "    <tr>\n",
400 |        "      <th>21396</th>\n",
401 |        "      <td>999998473.jpg</td>\n",
402 |        "      <td>Healthy</td>\n",
403 |        "      <td>gs://srivatsan-project-vcm/train_images/999998...</td>\n",
404 |        "    </tr>\n",
405 |        "  </tbody>\n",
406 |        "</table>\n",
407 |        "<p>21397 rows × 3 columns</p>\n",
408 |        "</div>"
409 |       ],
410 |       "text/plain": [
411 |        "             image_id    label  \\\n",
412 |        "0      1000015157.jpg      CBB   \n",
413 |        "1      1000201771.jpg      CMD   \n",
414 |        "2       100042118.jpg     CBSD   \n",
415 |        "3      1000723321.jpg     CBSD   \n",
416 |        "4      1000812911.jpg      CMD   \n",
417 |        "...               ...      ...   \n",
418 |        "21392   999068805.jpg      CMD   \n",
419 |        "21393   999329392.jpg      CMD   \n",
420 |        "21394   999474432.jpg     CBSD   \n",
421 |        "21395   999616605.jpg  Healthy   \n",
422 |        "21396   999998473.jpg  Healthy   \n",
423 |        "\n",
424 |        "                                              image_path  \n",
425 |        "0      gs://srivatsan-project-vcm/train_images/100001...  \n",
426 |        "1      gs://srivatsan-project-vcm/train_images/100020...  \n",
427 |        "2      gs://srivatsan-project-vcm/train_images/100042...  \n",
428 |        "3      gs://srivatsan-project-vcm/train_images/100072...  \n",
429 |        "4      gs://srivatsan-project-vcm/train_images/100081...  \n",
430 |        "...                                                  ...  \n",
431 |        "21392  gs://srivatsan-project-vcm/train_images/999068...  \n",
432 |        "21393  gs://srivatsan-project-vcm/train_images/999329...  \n",
433 |        "21394  gs://srivatsan-project-vcm/train_images/999474...  \n",
434 |        "21395  gs://srivatsan-project-vcm/train_images/999616...  \n",
435 |        "21396  gs://srivatsan-project-vcm/train_images/999998...  \n",
436 |        "\n",
437 |        "[21397 rows x 3 columns]"
438 |       ]
439 |      },
440 |      "execution_count": 42,
441 |      "metadata": {},
442 |      "output_type": "execute_result"
443 |     }
444 |    ],
445 |    "source": [
446 |     "df"
447 |    ]
448 |   },
449 |   {
450 |    "cell_type": "code",
451 |    "execution_count": 43,
452 |    "metadata": {},
453 |    "outputs": [
454 |     {
455 |      "data": {
456 |       "text/plain": [
457 |        "CMD        13158\n",
458 |        "Healthy     2577\n",
459 |        "CGM         2386\n",
460 |        "CBSD        2189\n",
461 |        "CBB         1087\n",
462 |        "Name: label, dtype: int64"
463 |       ]
464 |      },
465 |      "execution_count": 43,
466 |      "metadata": {},
467 |      "output_type": "execute_result"
468 |     }
469 |    ],
470 |    "source": [
471 |     "df['label'].value_counts()"
472 |    ]
473 |   },
474 |   {
475 |    "cell_type": "code",
476 |    "execution_count": 44,
477 |    "metadata": {},
478 |    "outputs": [
479 |     {
480 |      "data": {
481 |       "text/html": [
482 |        "<div>\n",
483 |        "<style scoped>\n",
484 |        "    .dataframe tbody tr th:only-of-type {\n",
485 |        "        vertical-align: middle;\n",
486 |        "    }\n",
487 |        "\n",
488 |        "    .dataframe tbody tr th {\n",
489 |        "        vertical-align: top;\n",
490 |        "    }\n",
491 |        "\n",
492 |        "    .dataframe thead th {\n",
493 |        "        text-align: right;\n",
494 |        "    }\n",
495 |        "</style>\n",
496 |        "<table border=\"1\" class=\"dataframe\">\n",
497 |        "  <thead>\n",
498 |        "    <tr style=\"text-align: right;\">\n",
499 |        "      <th></th>\n",
500 |        "      <th>image_id</th>\n",
501 |        "      <th>label</th>\n",
502 |        "      <th>image_path</th>\n",
503 |        "    </tr>\n",
504 |        "  </thead>\n",
505 |        "  <tbody>\n",
506 |        "    <tr>\n",
507 |        "      <th>0</th>\n",
508 |        "      <td>1000015157.jpg</td>\n",
509 |        "      <td>CBB</td>\n",
510 |        "      <td>gs://srivatsan-project-vcm/train_images/100001...</td>\n",
511 |        "    </tr>\n",
512 |        "    <tr>\n",
513 |        "      <th>1</th>\n",
514 |        "      <td>1000201771.jpg</td>\n",
515 |        "      <td>CMD</td>\n",
516 |        "      <td>gs://srivatsan-project-vcm/train_images/100020...</td>\n",
517 |        "    </tr>\n",
518 |        "    <tr>\n",
519 |        "      <th>2</th>\n",
520 |        "      <td>100042118.jpg</td>\n",
521 |        "      <td>CBSD</td>\n",
522 |        "      <td>gs://srivatsan-project-vcm/train_images/100042...</td>\n",
523 |        "    </tr>\n",
524 |        "    <tr>\n",
525 |        "      <th>3</th>\n",
526 |        "      <td>1000723321.jpg</td>\n",
527 |        "      <td>CBSD</td>\n",
528 |        "      <td>gs://srivatsan-project-vcm/train_images/100072...</td>\n",
529 |        "    </tr>\n",
530 |        "    <tr>\n",
531 |        "      <th>4</th>\n",
532 |        "      <td>1000812911.jpg</td>\n",
533 |        "      <td>CMD</td>\n",
534 |        "      <td>gs://srivatsan-project-vcm/train_images/100081...</td>\n",
535 |        "    </tr>\n",
536 |        "    <tr>\n",
537 |        "      <th>...</th>\n",
538 |        "      <td>...</td>\n",
539 |        "      <td>...</td>\n",
540 |        "      <td>...</td>\n",
541 |        "    </tr>\n",
542 |        "    <tr>\n",
543 |        "      <th>21392</th>\n",
544 |        "      <td>999068805.jpg</td>\n",
545 |        "      <td>CMD</td>\n",
546 |        "      <td>gs://srivatsan-project-vcm/train_images/999068...</td>\n",
547 |        "    </tr>\n",
548 |        "    <tr>\n",
549 |        "      <th>21393</th>\n",
550 |        "      <td>999329392.jpg</td>\n",
551 |        "      <td>CMD</td>\n",
552 |        "      <td>gs://srivatsan-project-vcm/train_images/999329...</td>\n",
553 |        "    </tr>\n",
554 |        "    <tr>\n",
555 |        "      <th>21394</th>\n",
556 |        "      <td>999474432.jpg</td>\n",
557 |        "      <td>CBSD</td>\n",
558 |        "      <td>gs://srivatsan-project-vcm/train_images/999474...</td>\n",
559 |        "    </tr>\n",
560 |        "    <tr>\n",
561 |        "      <th>21395</th>\n",
562 |        "      <td>999616605.jpg</td>\n",
563 |        "      <td>Healthy</td>\n",
564 |        "      <td>gs://srivatsan-project-vcm/train_images/999616...</td>\n",
565 |        "    </tr>\n",
566 |        "    <tr>\n",
567 |        "      <th>21396</th>\n",
568 |        "      <td>999998473.jpg</td>\n",
569 |        "      <td>Healthy</td>\n",
570 |        "      <td>gs://srivatsan-project-vcm/train_images/999998...</td>\n",
571 |        "    </tr>\n",
572 |        "  </tbody>\n",
573 |        "</table>\n",
574 |        "<p>21397 rows × 3 columns</p>\n",
575 |        "</div>"
576 |       ],
577 |       "text/plain": [
578 |        "             image_id    label  \\\n",
579 |        "0      1000015157.jpg      CBB   \n",
580 |        "1      1000201771.jpg      CMD   \n",
581 |        "2       100042118.jpg     CBSD   \n",
582 |        "3      1000723321.jpg     CBSD   \n",
583 |        "4      1000812911.jpg      CMD   \n",
584 |        "...               ...      ...   \n",
585 |        "21392   999068805.jpg      CMD   \n",
586 |        "21393   999329392.jpg      CMD   \n",
587 |        "21394   999474432.jpg     CBSD   \n",
588 |        "21395   999616605.jpg  Healthy   \n",
589 |        "21396   999998473.jpg  Healthy   \n",
590 |        "\n",
591 |        "                                              image_path  \n",
592 |        "0      gs://srivatsan-project-vcm/train_images/100001...  \n",
593 |        "1      gs://srivatsan-project-vcm/train_images/100020...  \n",
594 |        "2      gs://srivatsan-project-vcm/train_images/100042...  \n",
595 |        "3      gs://srivatsan-project-vcm/train_images/100072...  \n",
596 |        "4      gs://srivatsan-project-vcm/train_images/100081...  \n",
597 |        "...                                                  ...  \n",
598 |        "21392  gs://srivatsan-project-vcm/train_images/999068...  \n",
599 |        "21393  gs://srivatsan-project-vcm/train_images/999329...  \n",
600 |        "21394  gs://srivatsan-project-vcm/train_images/999474...  \n",
601 |        "21395  gs://srivatsan-project-vcm/train_images/999616...  \n",
602 |        "21396  gs://srivatsan-project-vcm/train_images/999998...  \n",
603 |        "\n",
604 |        "[21397 rows x 3 columns]"
605 |       ]
606 |      },
607 |      "execution_count": 44,
608 |      "metadata": {},
609 |      "output_type": "execute_result"
610 |     }
611 |    ],
612 |    "source": [
613 |     "df"
614 |    ]
615 |   },
616 |   {
617 |    "cell_type": "code",
618 |    "execution_count": 45,
619 |    "metadata": {},
620 |    "outputs": [],
621 |    "source": [
622 |     "df[['image_path','label']].to_csv('labels.csv', index=False, header=False)"
623 |    ]
624 |   },
625 |   {
626 |    "cell_type": "code",
627 |    "execution_count": 46,
628 |    "metadata": {},
629 |    "outputs": [
630 |     {
631 |      "name": "stdout",
632 |      "output_type": "stream",
633 |      "text": [
634 |       "Copying file://labels.csv [Content-Type=text/csv]...\n",
635 |       "/ [1 files][  1.2 MiB/  1.2 MiB]                                                \n",
636 |       "Operation completed over 1 objects/1.2 MiB.                                      \n"
637 |      ]
638 |     }
639 |    ],
640 |    "source": [
641 |     "!gsutil cp labels.csv gs://srivatsan-project-vcm/"
642 |    ]
643 |   },
644 |   {
645 |    "cell_type": "code",
646 |    "execution_count": null,
647 |    "metadata": {},
648 |    "outputs": [],
649 |    "source": []
650 |   },
651 |   {
652 |    "cell_type": "code",
653 |    "execution_count": null,
654 |    "metadata": {},
655 |    "outputs": [],
656 |    "source": []
657 |   },
658 |   {
659 |    "cell_type": "code",
660 |    "execution_count": null,
661 |    "metadata": {},
662 |    "outputs": [],
663 |    "source": []
664 |   },
665 |   {
666 |    "cell_type": "code",
667 |    "execution_count": null,
668 |    "metadata": {},
669 |    "outputs": [],
670 |    "source": []
671 |   },
672 |   {
673 |    "cell_type": "code",
674 |    "execution_count": null,
675 |    "metadata": {},
676 |    "outputs": [],
677 |    "source": []
678 |   },
679 |   {
680 |    "cell_type": "code",
681 |    "execution_count": null,
682 |    "metadata": {},
683 |    "outputs": [],
684 |    "source": []
685 |   },
686 |   {
687 |    "cell_type": "code",
688 |    "execution_count": null,
689 |    "metadata": {},
690 |    "outputs": [],
691 |    "source": []
692 |   },
693 |   {
694 |    "cell_type": "code",
695 |    "execution_count": null,
696 |    "metadata": {},
697 |    "outputs": [],
698 |    "source": []
699 |   },
700 |   {
701 |    "cell_type": "code",
702 |    "execution_count": null,
703 |    "metadata": {},
704 |    "outputs": [],
705 |    "source": [
706 |     "!curl -X GET -H \"Authorization: Bearer \"$(gcloud auth application-default print-access-token) https://automl.googleapis.com/v1/projects/srivatsan-project/locations/us-central1/operations/8525331686798393344"
707 |    ]
708 |   },
709 |   {
710 |    "cell_type": "code",
711 |    "execution_count": null,
712 |    "metadata": {},
713 |    "outputs": [],
714 |    "source": []
715 |   }
716 |  ],
717 |  "metadata": {
718 |   "environment": {
719 |    "name": "common-cpu.m59",
720 |    "type": "gcloud",
721 |    "uri": "gcr.io/deeplearning-platform-release/base-cpu:m59"
722 |   },
723 |   "kernelspec": {
724 |    "display_name": "Python 3",
725 |    "language": "python",
726 |    "name": "python3"
727 |   },
728 |   "language_info": {
729 |    "codemirror_mode": {
730 |     "name": "ipython",
731 |     "version": 3
732 |    },
733 |    "file_extension": ".py",
734 |    "mimetype": "text/x-python",
735 |    "name": "python",
736 |    "nbconvert_exporter": "python",
737 |    "pygments_lexer": "ipython3",
738 |    "version": "3.7.8"
739 |   }
740 |  },
741 |  "nbformat": 4,
742 |  "nbformat_minor": 4
743 | }
744 | 


--------------------------------------------------------------------------------
/Cloud_AutoML_Vision/README.md:
--------------------------------------------------------------------------------
 1 | This repository contains code and steps to train a image classifier model on Google Cloud AutoML Vision
 2 | 
 3 | Cloud ML Vision is trained on Kaggle Cassava Leaf Disease detection dataset - https://www.kaggle.com/c/cassava-leaf-disease-classification
 4 | 
 5 | Kaggle Data Download.ipynb - contains code to pull data from Kaggle and move the data to google cloud storage
 6 | 
 7 | Data Preparation.ipynb - contains code to prepare csv file containing image file and label information. This file will be used for training Cloud AutoML Vision models
 8 | 
 9 | On how to use google cloud UI to create AutoML vision model you can check this video - https://youtu.be/XZMU9uNbQvs
10 | 
11 | Once model is train you can deploy it and use predict.ipynb file to predict new instances of input
12 | 
13 | 


--------------------------------------------------------------------------------
/Cloud_AutoML_Vision/predict.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 12,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "from google.cloud import aiplatform\n",
 10 |     "\n",
 11 |     "def predict_image_classification_sample(\n",
 12 |     "    endpoint: str, instance: dict, parameters_dict: dict\n",
 13 |     "):\n",
 14 |     "    client_options = dict(api_endpoint=\"us-central1-prediction-aiplatform.googleapis.com\")\n",
 15 |     "    client = aiplatform.PredictionServiceClient(client_options=client_options)\n",
 16 |     "    from google.protobuf import json_format\n",
 17 |     "    from google.protobuf.struct_pb2 import Value\n",
 18 |     "\n",
 19 |     "    # See gs://google-cloud-aiplatform/schema/predict/params/image_classification_1.0.0.yaml for the format of the parameters.\n",
 20 |     "    parameters = json_format.ParseDict(parameters_dict, Value())\n",
 21 |     "\n",
 22 |     "    # See gs://google-cloud-aiplatform/schema/predict/instance/image_classification_1.0.0.yaml for the format of the instances.\n",
 23 |     "    instances_list = [instance]\n",
 24 |     "    instances = [json_format.ParseDict(s, Value()) for s in instances_list]\n",
 25 |     "    response = client.predict(\n",
 26 |     "        endpoint=endpoint, instances=instances, parameters=parameters\n",
 27 |     "    )\n",
 28 |     "\n",
 29 |     "    print(\"response\")\n",
 30 |     "    print(\" deployed_model_id:\", response.deployed_model_id)\n",
 31 |     "    predictions = response.predictions\n",
 32 |     "    print(\"predictions\")\n",
 33 |     "    for prediction in predictions:\n",
 34 |     "        # See gs://google-cloud-aiplatform/schema/predict/prediction/classification_1.0.0.yaml for the format of the predictions.\n",
 35 |     "        print(\" prediction:\", dict(prediction))"
 36 |    ]
 37 |   },
 38 |   {
 39 |    "cell_type": "code",
 40 |    "execution_count": 13,
 41 |    "metadata": {},
 42 |    "outputs": [],
 43 |    "source": [
 44 |     "import base64\n",
 45 |     "\n",
 46 |     "with open('test_images/2216849948.jpg', \"rb\") as imageFile:\n",
 47 |     "    str = base64.b64encode(imageFile.read())"
 48 |    ]
 49 |   },
 50 |   {
 51 |    "cell_type": "code",
 52 |    "execution_count": 30,
 53 |    "metadata": {},
 54 |    "outputs": [],
 55 |    "source": [
 56 |     "from google.cloud import automl\n",
 57 |     "\n",
 58 |     "def predict():\n",
 59 |     "    \"\"\"Predict.\"\"\"\n",
 60 |     "    # [START automl_vision_classification_predict]\n",
 61 |     "\n",
 62 |     "    project_id = \"srivatsan-project\"\n",
 63 |     "    model_id = \"cassava\"\n",
 64 |     "\n",
 65 |     "    file_path = \"test_images/2216849948.jpg\"\n",
 66 |     "\n",
 67 |     "    prediction_client = automl.PredictionServiceClient()\n",
 68 |     "\n",
 69 |     "    # Get the full path of the model.\n",
 70 |     "    model_full_id = automl.AutoMlClient.model_path(\n",
 71 |     "        project_id, \"us-central1\", model_id\n",
 72 |     "    )\n",
 73 |     "\n",
 74 |     "    # Read the file.\n",
 75 |     "    with open(file_path, \"rb\") as content_file:\n",
 76 |     "        content = content_file.read()\n",
 77 |     "\n",
 78 |     "    image = automl.Image(image_bytes=content)\n",
 79 |     "    payload = automl.ExamplePayload(image=image)\n",
 80 |     "\n",
 81 |     "    # params is additional domain-specific parameters.\n",
 82 |     "    # score_threshold is used to filter the result\n",
 83 |     "    # https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest\n",
 84 |     "    params = {\"score_threshold\": \"0.8\"}\n",
 85 |     "\n",
 86 |     "    request = automl.PredictRequest(\n",
 87 |     "        name=model_full_id,\n",
 88 |     "        payload=payload,\n",
 89 |     "        params=params\n",
 90 |     "    )\n",
 91 |     "    response = prediction_client.predict(request=request)\n",
 92 |     "\n",
 93 |     "    print(\"Prediction results:\")\n",
 94 |     "    for result in response.payload:\n",
 95 |     "        print(\"Predicted class name: {}\".format(result.display_name))\n",
 96 |     "        print(\"Predicted class score: {}\".format(result.classification.score))"
 97 |    ]
 98 |   },
 99 |   {
100 |    "cell_type": "code",
101 |    "execution_count": 31,
102 |    "metadata": {},
103 |    "outputs": [
104 |     {
105 |      "ename": "NotFound",
106 |      "evalue": "404 Invalid resource ID",
107 |      "output_type": "error",
108 |      "traceback": [
109 |       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
110 |       "\u001b[0;31m_InactiveRpcError\u001b[0m                         Traceback (most recent call last)",
111 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/google/api_core/grpc_helpers.py\u001b[0m in \u001b[0;36merror_remapped_callable\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     56\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 57\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mcallable_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     58\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mgrpc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mRpcError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
112 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/grpc/_channel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, request, timeout, metadata, credentials, wait_for_ready, compression)\u001b[0m\n\u001b[1;32m    922\u001b[0m                                       wait_for_ready, compression)\n\u001b[0;32m--> 923\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0m_end_unary_response_blocking\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcall\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    924\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
113 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/grpc/_channel.py\u001b[0m in \u001b[0;36m_end_unary_response_blocking\u001b[0;34m(state, call, with_call, deadline)\u001b[0m\n\u001b[1;32m    825\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 826\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0m_InactiveRpcError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    827\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
114 |       "\u001b[0;31m_InactiveRpcError\u001b[0m: <_InactiveRpcError of RPC that terminated with:\n\tstatus = StatusCode.NOT_FOUND\n\tdetails = \"Invalid resource ID\"\n\tdebug_error_string = \"{\"created\":\"@1608932170.899453921\",\"description\":\"Error received from peer ipv4:74.125.124.95:443\",\"file\":\"src/core/lib/surface/call.cc\",\"file_line\":1062,\"grpc_message\":\"Invalid resource ID\",\"grpc_status\":5}\"\n>",
115 |       "\nThe above exception was the direct cause of the following exception:\n",
116 |       "\u001b[0;31mNotFound\u001b[0m                                  Traceback (most recent call last)",
117 |       "\u001b[0;32m<ipython-input-31-919f7be2ba45>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
118 |       "\u001b[0;32m<ipython-input-30-b91328d2b4d0>\u001b[0m in \u001b[0;36mpredict\u001b[0;34m()\u001b[0m\n\u001b[1;32m     34\u001b[0m         \u001b[0mparams\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparams\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     35\u001b[0m     )\n\u001b[0;32m---> 36\u001b[0;31m     \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mprediction_client\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     37\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     38\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Prediction results:\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
119 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/google/cloud/automl_v1/services/prediction_service/client.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, request, name, payload, params, retry, timeout, metadata)\u001b[0m\n\u001b[1;32m    411\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    412\u001b[0m         \u001b[0;31m# Send the request.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 413\u001b[0;31m         \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrpc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretry\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mretry\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    414\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    415\u001b[0m         \u001b[0;31m# Done; return the response.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
120 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/google/api_core/gapic_v1/method.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    143\u001b[0m             \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"metadata\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    144\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 145\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapped_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    146\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    147\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
121 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/google/api_core/grpc_helpers.py\u001b[0m in \u001b[0;36merror_remapped_callable\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     57\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mcallable_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     58\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mgrpc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mRpcError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 59\u001b[0;31m             \u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraise_from\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexceptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_grpc_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     60\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     61\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0merror_remapped_callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
122 |       "\u001b[0;32m/opt/conda/lib/python3.7/site-packages/six.py\u001b[0m in \u001b[0;36mraise_from\u001b[0;34m(value, from_value)\u001b[0m\n",
123 |       "\u001b[0;31mNotFound\u001b[0m: 404 Invalid resource ID"
124 |      ]
125 |     }
126 |    ],
127 |    "source": [
128 |     "predict()"
129 |    ]
130 |   },
131 |   {
132 |    "cell_type": "code",
133 |    "execution_count": null,
134 |    "metadata": {},
135 |    "outputs": [],
136 |    "source": []
137 |   }
138 |  ],
139 |  "metadata": {
140 |   "environment": {
141 |    "name": "common-cpu.m59",
142 |    "type": "gcloud",
143 |    "uri": "gcr.io/deeplearning-platform-release/base-cpu:m59"
144 |   },
145 |   "kernelspec": {
146 |    "display_name": "Python 3",
147 |    "language": "python",
148 |    "name": "python3"
149 |   },
150 |   "language_info": {
151 |    "codemirror_mode": {
152 |     "name": "ipython",
153 |     "version": 3
154 |    },
155 |    "file_extension": ".py",
156 |    "mimetype": "text/x-python",
157 |    "name": "python",
158 |    "nbconvert_exporter": "python",
159 |    "pygments_lexer": "ipython3",
160 |    "version": "3.7.8"
161 |   }
162 |  },
163 |  "nbformat": 4,
164 |  "nbformat_minor": 4
165 | }
166 | 


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/ComplaintsFlask.py:
--------------------------------------------------------------------------------
 1 | from flask import Flask, jsonify, request
 2 | from preprocessing.functions import tokenize
 3 | import xgboost as xgb
 4 | import joblib
 5 | from healthcheck import HealthCheck
 6 | 
 7 | import os
 8 | import logging
 9 | 
10 | logging.basicConfig(format='%(message)s', level=logging.INFO)
11 | app = Flask(__name__)
12 | 
13 | target={0:'Debt collection', 1:'Credit card or prepaid card', 2:'Mortgage', 
14 |         3:'Checking or savings account', 4:'Student loan', 
15 |         5:'Vehicle loan or lease'}
16 | 
17 | tfvectorizer = joblib.load('models/tfvectroizer.pkl') 
18 | xgb_clf = xgb.Booster({'nthread': 3})
19 | xgb_clf.load_model('models/complaints.booster')
20 | 
21 | logging.info('All models loaded succcessfully')
22 | 
23 | health = HealthCheck(app, "/hcheck")
24 | 
25 | def howami():
26 |     return True, "I am alive. Thanks for checking.."
27 | 
28 | health.add_check(howami)
29 | 
30 | def scorer(text):
31 |    encoded_text = tfvectorizer.transform([text])
32 |    score = xgb_clf.predict(xgb.DMatrix(encoded_text))
33 |    return score
34 | 
35 | @app.route('/score', methods=['POST'])
36 | def predict_fn():
37 |     text = request.get_json()['text']
38 |     logging.info('Received incoming message - '+ text)
39 |     predictions = scorer(text)
40 |     predictions = predictions.argmax(axis=1)[0]
41 |     return jsonify({'predictions ': str(predictions), 'Category ': target.get(predictions)})
42 | 
43 | @app.route('/')
44 | def hello():
45 |     return 'Welcome to Complaints Prediction Application'
46 | 
47 | if __name__ == "__main__":
48 |     app.run(host='0.0.0.0', port=int(os.environ.get('PORT', 5000)))


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/ComplaintsServer.py:
--------------------------------------------------------------------------------
1 | from ComplaintsFlask import app
2 | 
3 | if __name__ == "__main__":
4 |     app.run()


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/Dockerfile:
--------------------------------------------------------------------------------
 1 | # lightweight python
 2 | FROM python:3.7-slim
 3 | 
 4 | RUN apt-get update && apt-get install -y libgomp1
 5 | 
 6 | # Copy local code to the container image.
 7 | ENV APP_HOME /app
 8 | WORKDIR $APP_HOME
 9 | COPY . ./
10 | 
11 | RUN ls -la $APP_HOME/
12 | 
13 | ENV NLTK_DATA $APP_HOME/nltk_data
14 | 
15 | # Install dependencies
16 | RUN pip install -r requirements.txt
17 | 
18 | ENV PORT 5000
19 | 
20 | # Run the flask service on container startup
21 | #CMD exec gunicorn --bind :$PORT --workers 1 --threads 8 ComplaintsServer
22 | CMD [ "python", "ComplaintsFlask.py" ]
23 | 


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/README.md:
--------------------------------------------------------------------------------
 1 | This repository contains details and code for deploying machine learning models on Google Cloud Serverless platform and Google Cloud App Engine
 2 | 
 3 | Details of the code and working is covered in detailed in my YouTube channel (AIEngineering) here - https://youtu.be/kyQH71pB0vI 
 4 | 
 5 | Before getting started with deployment the container expects trained models and also downloaded nltk corpus
 6 | 
 7 | For model files you are run associated notebook in this repository or else download the trained models and use it using below 2 command
 8 | 
 9 | wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1m1bVxlUjrJ_tmWApYJHlk2q5bikGyIxr' -O complaints.booster
10 | 
11 | wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1WURdboJjF27g9bZG_CGCCGSYWi0EvxJR' -O tfvectroizer.pkl
12 | 
13 | If you want more details on model training you can check the video here - https://youtu.be/EHt_x8r1exU
14 | 
15 | For NLTK you have to download stopwords and tokenizer corpa. One can download it using nltk.download()
16 | 
17 | 
18 | To deploy the model on serverless infrastructure (Cloud Run), execute the below commands
19 | ------------------------------------------------------------------------------------------
20 | 
21 | Building the container image - gcloud builds submit --tag gcr.io/<your GCP project>/complaintsapi .
22 | 
23 | List the image - gcloud builds list --filter complaints
24 | 
25 | Checking logs of built image - gcloud builds log <container id from list command above>
26 | 
27 | Deploy the container on google cloud run - gcloud run deploy complaintsapi --image gcr.io/<your GCP project>/complaintsapi --platform managed --memory 1G
28 |   
29 | To deploy the model on App Engine run below commands
30 | -----------------------------------------------------
31 | 
32 | gcloud app create
33 | 
34 | gcloud app deploy
35 | 


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/app.yaml:
--------------------------------------------------------------------------------
1 | runtime: custom
2 | env: flex


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/preprocessing/functions.py:
--------------------------------------------------------------------------------
 1 | import re
 2 | import nltk
 3 | 
 4 | stemmer = nltk.stem.SnowballStemmer('english')
 5 | stop_words = set(nltk.corpus.stopwords.words('english'))
 6 | 
 7 | def tokenize(text):
 8 |    tokens = [word for word in nltk.word_tokenize(text) if (len(word) > 3 and len(word.strip('Xx/')) > 2 and len(re.sub('\d+', '', word.strip('Xx/'))) > 3) ]
 9 |    tokens = map(str.lower, tokens)
10 |    stems = [stemmer.stem(item) for item in tokens if (item not in stop_words)]
11 |    return stems
12 | 


--------------------------------------------------------------------------------
/GCP_Serverless_AppEngine/requirements.txt:
--------------------------------------------------------------------------------
 1 | flask
 2 | scikit-learn==0.22
 3 | xgboost==0.90
 4 | nltk
 5 | joblib
 6 | gunicorn
 7 | healthcheck
 8 | six
 9 | 
10 | #Run this file with - pip3 install -r requirements.txt


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/ComplaintsFlask.py:
--------------------------------------------------------------------------------
 1 | from flask import Flask, jsonify, request
 2 | from preprocessing.functions import tokenize
 3 | import xgboost as xgb
 4 | import joblib
 5 | from healthcheck import HealthCheck
 6 | 
 7 | import os
 8 | import logging
 9 | 
10 | logging.basicConfig(format='%(message)s', level=logging.INFO)
11 | app = Flask(__name__)
12 | 
13 | target={0:'Debt collection', 1:'Credit card or prepaid card', 2:'Mortgage', 
14 |         3:'Checking or savings account', 4:'Student loan', 
15 |         5:'Vehicle loan or lease'}
16 | 
17 | tfvectorizer = joblib.load('models/tfvectroizer.pkl') 
18 | xgb_clf = xgb.Booster({'nthread': 3})
19 | xgb_clf.load_model('models/complaints.booster')
20 | 
21 | logging.info('All models loaded succcessfully')
22 | 
23 | health = HealthCheck(app, "/hcheck")
24 | 
25 | def howami():
26 |     return True, "I am alive. Thanks for checking.."
27 | 
28 | health.add_check(howami)
29 | 
30 | def scorer(text):
31 |    encoded_text = tfvectorizer.transform([text])
32 |    score = xgb_clf.predict(xgb.DMatrix(encoded_text))
33 |    return score
34 | 
35 | @app.route('/score', methods=['POST'])
36 | def predict_fn():
37 |     text = request.get_json()['text']
38 |     logging.info('Received incoming message - '+ text)
39 |     predictions = scorer(text)
40 |     predictions = predictions.argmax(axis=1)[0]
41 |     return jsonify({'predictions ': str(predictions), 'Category ': target.get(predictions)})
42 | 
43 | @app.route('/')
44 | def hello():
45 |     return 'Welcome to Complaints Prediction Application'
46 | 
47 | if __name__ == "__main__":
48 |     app.run(host='0.0.0.0', port=int(os.environ.get('PORT', 5000)))


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/Dockerfile:
--------------------------------------------------------------------------------
 1 | # lightweight python
 2 | FROM python:3.7-slim
 3 | 
 4 | RUN apt-get update && apt-get install -y libgomp1
 5 | 
 6 | # Copy local code to the container image.
 7 | ENV APP_HOME /app
 8 | WORKDIR $APP_HOME
 9 | COPY . ./
10 | 
11 | RUN ls -la $APP_HOME/
12 | 
13 | ENV NLTK_DATA $APP_HOME/nltk_data
14 | 
15 | # Install dependencies
16 | RUN pip install -r requirements.txt
17 | 
18 | ENV PORT 5000
19 | 
20 | # Run the flask service on container startup
21 | #CMD exec gunicorn --bind :$PORT --workers 1 --threads 8 ComplaintsServer
22 | CMD [ "python", "ComplaintsFlask.py" ]
23 | 


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/README.md:
--------------------------------------------------------------------------------
 1 | This repository contains details and code for deploying machine learning models on Google Kubernetes Engine Engine
 2 | 
 3 | Details of the code and working is covered in detailed in my YouTube channel (AIEngineering) here - https://youtu.be/Hfgla4ViIwU
 4 | 
 5 | Before getting started with deployment the container expects trained models and also downloaded nltk corpus
 6 | 
 7 | For model files you are run associated notebook in this repository or else download the trained models and use it using below 2 command
 8 | 
 9 | wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1m1bVxlUjrJ_tmWApYJHlk2q5bikGyIxr' -O complaints.booster
10 | 
11 | wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=1WURdboJjF27g9bZG_CGCCGSYWi0EvxJR' -O tfvectroizer.pkl
12 | 
13 | If you want more details on model training you can check the video here - https://youtu.be/EHt_x8r1exU
14 | 
15 | For NLTK you have to download stopwords and tokenizer corpa. One can download it using nltk.download()
16 | 
17 | 
18 | To deploy the model on Google Kubernetes Engine, execute the below commands
19 | ------------------------------------------------------------------------------------------
20 | 
21 | Building the container image - gcloud builds submit --tag gcr.io/<your GCP project>/complaintsapi .
22 | 
23 | List the image - gcloud builds list --filter complaints
24 | 
25 | Checking logs of built image - gcloud builds log <container id from list command above>
26 | 
27 | Create Kubernetes Cluster - gcloud container clusters create complaints-gke --zone "us-west1-b" --machine-type "n1-standard-1" --num-nodes "1" --service-account srivatsan-gke@srivatsan-project.iam.gserviceaccount.com (Change to your service account)
28 | 
29 | Create Kubernetes Deployment - kubectl apply -f deployment.yaml   
30 | 
31 | Get details on deployed application - kubectl get deployments
32 | 
33 | Get info of created pods via deployment - kubectl get pods
34 | 
35 | Decribe deployed pod - kubectl describe pod <pod info from above command>
36 | 
37 | Get pod logs - kubectl logs <pod info from above command>
38 | 
39 | Create service for deployment - kubectl apply -f service.yaml
40 | 
41 | Get service details - kubectl get services
42 | 
43 | Add nodes to cluster - gcloud container clusters resize complaints-gke --num-nodes 3 --zone us-west1-b
44 | 
45 | Get details on cluster - gcloud container clusters list
46 | 
47 | Scale pod replicas - kubectl scale deployment complaints --replicas 2
48 | 
49 | Auto Scale setting in deployment - kubectl autoscale deployment complaints --max 6 --min 2 --cpu-percent 50
50 | 
51 | Get details on horizontal pod autoscaler - kubectl get hpa
52 | 


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/deployment.yaml:
--------------------------------------------------------------------------------
 1 | apiVersion: apps/v1
 2 | kind: Deployment
 3 | metadata:
 4 |   name: complaints
 5 | spec:
 6 |   replicas: 1
 7 |   selector:
 8 |     matchLabels:
 9 |       app: complaintsclassifier
10 |   template:
11 |     metadata:
12 |       labels:
13 |         app: complaintsclassifier
14 |     spec:
15 |       containers:
16 |       - name: complaints-app
17 |         image: gcr.io/srivatsan-project/complaintsapi
18 |         ports:
19 |         - containerPort: 8080
20 |         env:
21 |           - name: PORT
22 |             value: "8080"


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/preprocessing/functions.py:
--------------------------------------------------------------------------------
 1 | import re
 2 | import nltk
 3 | 
 4 | stemmer = nltk.stem.SnowballStemmer('english')
 5 | stop_words = set(nltk.corpus.stopwords.words('english'))
 6 | 
 7 | def tokenize(text):
 8 |    tokens = [word for word in nltk.word_tokenize(text) if (len(word) > 3 and len(word.strip('Xx/')) > 2 and len(re.sub('\d+', '', word.strip('Xx/'))) > 3) ]
 9 |    tokens = map(str.lower, tokens)
10 |    stems = [stemmer.stem(item) for item in tokens if (item not in stop_words)]
11 |    return stems
12 | 


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/requirements.txt:
--------------------------------------------------------------------------------
 1 | flask
 2 | scikit-learn==0.22
 3 | xgboost==0.90
 4 | nltk
 5 | joblib
 6 | gunicorn
 7 | healthcheck
 8 | six
 9 | 
10 | #Run this file with - pip3 install -r requirements.txt


--------------------------------------------------------------------------------
/Google_Kubernetes_Engine/service.yaml:
--------------------------------------------------------------------------------
 1 | apiVersion: v1
 2 | kind: Service
 3 | metadata:
 4 |   name: complaintsclassifier
 5 | spec:
 6 |   type: LoadBalancer
 7 |   selector:
 8 |     app: complaintsclassifier
 9 |   ports:
10 |   - port: 80
11 |     targetPort: 8080


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # google_cloud_AI_ML
 2 | This repository contains code to learn AI and ML on Google Cloud Platform
 3 | 
 4 | Detailed code walkthrough of different Google Cloud AI services available in this repo can be found in my video playlist - https://www.youtube.com/playlist?list=PL3N9eeOlCrP6Nhv4UFp67IsQ_TVDpXqXK
 5 | 
 6 | <h1><b>GCP AI Project Details <b></h1>
 7 |   
 8 |  <b>Project 1 - Telecom Churn on AI Platform Notebook and AI Platform Prediction  </b>
 9 |  
10 |  In this project we will be building a scikit learn model using AI Platform Notebook and deploying it on AI Platform prediction service
11 |  
12 |  <b>Project 2 - Model Deployment on Google Cloud Platform  </b>
13 |   
14 |  In this project we will be deploying machine learning models on Google Cloud Serverless platform (Cloud Run) and Google Cloud App Engine
15 |   
16 |  <b>Project 3 - Building Time Series model using BigQuery ML and Data Analysis using Cloud Datastudio  </b>
17 |   
18 |  In this project we will be analyzing SFO bikeshare dataset and building multiple time series model using BigQuery ML
19 |  
20 |  <b>Project 4 - Image Classification using Google Cloud AutoML Vision  </b>
21 | 
22 |  In this project we will be training image classifier using Google Cloud ML Vision on Kaggle Cassava Leaf Disease detection dataset
23 |   
24 |  <b>Project 5 - Logistics Regression and Feature Engineering using BigQuery ML </b>
25 |  
26 |  This project is end to end demo of using BigQuery ML for feature engineering and for building Logistics Regression model
27 | 
28 |  <h1><b>Quick Start Projects to learn GCP </b></h1>
29 |  
30 |  <b>Speech to Text API - </b> https://www.youtube.com/watch?v=ZkTiKPUSYj4
31 |   
32 |  <b>Big Query Data Q&A - </b> https://www.youtube.com/watch?v=nhAm7q826qk
33 |  
34 |  <b>Google Cloud Data Products Overview and Professional ML Engineer Certification Discussion - </b> https://www.youtube.com/watch?v=pIzX7wk56iA&list=PL3N9eeOlCrP6Nhv4UFp67IsQ_TVDpXqXK&index=9
35 |  
36 |  <b>Google Cloud AI Platform overview - </b> https://www.youtube.com/watch?v=dx5kyKZ7Q0I
37 |  
38 |  <b>Google data studio getting started - </b> https://www.youtube.com/watch?v=DMRC90qvwFo
39 | 
40 | 
41 | 


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/README.md:
--------------------------------------------------------------------------------
 1 | Video accompanying this notebook can be found here -  https://www.youtube.com/watch?v=y63OIKPe52Y
 2 | 
 3 | This repository demonstrated how to get started with Google Cloud AI Platform and further use AI Prediction Service for deploying the trained model
 4 | 
 5 | <b>Churn_model.ipynb</b> is the main file for building the model and further saving the trained model in Google Cloud Storage
 6 | 
 7 | <b>predictor.py</b> is standalone prediction code to test the model before deploying it on AI Prediction Platform
 8 | 
 9 | <b>serving.ipynb</b> is client program used to invoke model deployed on AI prediction service
10 | 


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/data/README.md:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/input.json:
--------------------------------------------------------------------------------
1 | {"instances":["7317-GGVPB", "Male", 0, "Yes", "No", 71, "Yes", "Yes", "Fiber optic", "No", "Yes", "Yes", "Yes", "Yes", "Yes", "Two year", "Yes", "Credit card (automatic)", 108.6, "7690.9"]}


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/predict_setup.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [
  8 |     {
  9 |      "name": "stdout",
 10 |      "output_type": "stream",
 11 |      "text": [
 12 |       "Writing predictor.py\n"
 13 |      ]
 14 |     }
 15 |    ],
 16 |    "source": [
 17 |     "%%writefile predictor.py\n",
 18 |     "\n",
 19 |     "import os\n",
 20 |     "\n",
 21 |     "import numpy as np\n",
 22 |     "import joblib\n",
 23 |     "import pandas as pd\n",
 24 |     "\n",
 25 |     "class ChurnPredictor(object):\n",
 26 |     "\n",
 27 |     "  _COLUMN_NAMES=['customerID', 'gender', 'SeniorCitizen', 'Partner', 'Dependents', 'tenure', 'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies', 'Contract', 'PaperlessBilling','PaymentMethod', 'MonthlyCharges', 'TotalCharges']\n",
 28 |     "\n",
 29 |     "  def __init__(self, model):\n",
 30 |     "    self._model = model\n",
 31 |     "\n",
 32 |     "  def predict(self, instances, **kwargs):\n",
 33 |     "    inputs = pd.DataFrame(data=[instances], columns=self._COLUMN_NAMES)\n",
 34 |     "    outputs = self._model.predict(inputs)\n",
 35 |     "    return outputs.tolist()\n",
 36 |     "\n",
 37 |     "  @classmethod\n",
 38 |     "  def from_path(cls, model_dir):\n",
 39 |     "    model_path = os.path.join(model_dir, 'model.joblib')\n",
 40 |     "    model = joblib.load(model_path)\n",
 41 |     "    return cls(model)"
 42 |    ]
 43 |   },
 44 |   {
 45 |    "cell_type": "code",
 46 |    "execution_count": 2,
 47 |    "metadata": {},
 48 |    "outputs": [
 49 |     {
 50 |      "name": "stdout",
 51 |      "output_type": "stream",
 52 |      "text": [
 53 |       "['No']\n"
 54 |      ]
 55 |     }
 56 |    ],
 57 |    "source": [
 58 |     "from predictor import ChurnPredictor\n",
 59 |     "model = ChurnPredictor.from_path('.')\n",
 60 |     "instance = ['7317-GGVPB', 'Male', 0, 'Yes', 'No', 71, 'Yes', 'Yes', 'Fiber optic', 'No', 'Yes', 'Yes', 'Yes', 'Yes', 'Yes', 'Two year', 'Yes', 'Credit card (automatic)', 108.6, '7690.9']\n",
 61 |     "print(model.predict(instance))"
 62 |    ]
 63 |   },
 64 |   {
 65 |    "cell_type": "code",
 66 |    "execution_count": 3,
 67 |    "metadata": {},
 68 |    "outputs": [
 69 |     {
 70 |      "name": "stdout",
 71 |      "output_type": "stream",
 72 |      "text": [
 73 |       "Writing setup.py\n"
 74 |      ]
 75 |     }
 76 |    ],
 77 |    "source": [
 78 |     "%%writefile setup.py\n",
 79 |     "from setuptools import setup\n",
 80 |     "from setuptools import find_packages\n",
 81 |     "\n",
 82 |     "REQUIRED_PACKAGES = ['xgboost']\n",
 83 |     "\n",
 84 |     "setup(\n",
 85 |     "    name='custom_predict',\n",
 86 |     "    version='0.1',\n",
 87 |     "    install_requires=REQUIRED_PACKAGES,\n",
 88 |     "    packages=find_packages(),\n",
 89 |     "    include_package_data=True,\n",
 90 |     "    scripts=['predictor.py'])"
 91 |    ]
 92 |   },
 93 |   {
 94 |    "cell_type": "code",
 95 |    "execution_count": 4,
 96 |    "metadata": {},
 97 |    "outputs": [
 98 |     {
 99 |      "name": "stdout",
100 |      "output_type": "stream",
101 |      "text": [
102 |       "running sdist\n",
103 |       "running egg_info\n",
104 |       "creating custom_predict.egg-info\n",
105 |       "writing custom_predict.egg-info/PKG-INFO\n",
106 |       "writing dependency_links to custom_predict.egg-info/dependency_links.txt\n",
107 |       "writing requirements to custom_predict.egg-info/requires.txt\n",
108 |       "writing top-level names to custom_predict.egg-info/top_level.txt\n",
109 |       "writing manifest file 'custom_predict.egg-info/SOURCES.txt'\n",
110 |       "reading manifest file 'custom_predict.egg-info/SOURCES.txt'\n",
111 |       "writing manifest file 'custom_predict.egg-info/SOURCES.txt'\n",
112 |       "running check\n",
113 |       "warning: check: missing required meta-data: url\n",
114 |       "\n",
115 |       "warning: check: missing meta-data: either (author and author_email) or (maintainer and maintainer_email) must be supplied\n",
116 |       "\n",
117 |       "creating custom_predict-0.1\n",
118 |       "creating custom_predict-0.1/custom_predict.egg-info\n",
119 |       "copying files to custom_predict-0.1...\n",
120 |       "copying README.md -> custom_predict-0.1\n",
121 |       "copying predictor.py -> custom_predict-0.1\n",
122 |       "copying setup.py -> custom_predict-0.1\n",
123 |       "copying custom_predict.egg-info/PKG-INFO -> custom_predict-0.1/custom_predict.egg-info\n",
124 |       "copying custom_predict.egg-info/SOURCES.txt -> custom_predict-0.1/custom_predict.egg-info\n",
125 |       "copying custom_predict.egg-info/dependency_links.txt -> custom_predict-0.1/custom_predict.egg-info\n",
126 |       "copying custom_predict.egg-info/requires.txt -> custom_predict-0.1/custom_predict.egg-info\n",
127 |       "copying custom_predict.egg-info/top_level.txt -> custom_predict-0.1/custom_predict.egg-info\n",
128 |       "Writing custom_predict-0.1/setup.cfg\n",
129 |       "creating dist\n",
130 |       "Creating tar archive\n",
131 |       "removing 'custom_predict-0.1' (and everything under it)\n"
132 |      ]
133 |     }
134 |    ],
135 |    "source": [
136 |     "!python setup.py sdist --formats=gztar"
137 |    ]
138 |   },
139 |   {
140 |    "cell_type": "code",
141 |    "execution_count": 5,
142 |    "metadata": {},
143 |    "outputs": [
144 |     {
145 |      "name": "stdout",
146 |      "output_type": "stream",
147 |      "text": [
148 |       "Copying file://./dist/custom_predict-0.1.tar.gz [Content-Type=application/x-tar]...\n",
149 |       "/ [1 files][  1.2 KiB/  1.2 KiB]                                                \n",
150 |       "Operation completed over 1 objects/1.2 KiB.                                      \n"
151 |      ]
152 |     }
153 |    ],
154 |    "source": [
155 |     "!gsutil cp ./dist/custom_predict-0.1.tar.gz gs://churn-model-sri/custom_predict-0.1.tar.gz"
156 |    ]
157 |   },
158 |   {
159 |    "cell_type": "code",
160 |    "execution_count": null,
161 |    "metadata": {},
162 |    "outputs": [],
163 |    "source": []
164 |   },
165 |   {
166 |    "cell_type": "code",
167 |    "execution_count": 6,
168 |    "metadata": {},
169 |    "outputs": [
170 |     {
171 |      "name": "stdout",
172 |      "output_type": "stream",
173 |      "text": [
174 |       "Using endpoint [https://ml.googleapis.com/]\n",
175 |       "Created ml engine model [projects/srivatsan-project/models/ChurnPredictor].\n"
176 |      ]
177 |     }
178 |    ],
179 |    "source": [
180 |     "!gcloud beta ai-platform models create ChurnPredictor --regions us-central1 --enable-console-logging"
181 |    ]
182 |   },
183 |   {
184 |    "cell_type": "code",
185 |    "execution_count": 7,
186 |    "metadata": {},
187 |    "outputs": [
188 |     {
189 |      "name": "stdout",
190 |      "output_type": "stream",
191 |      "text": [
192 |       "Using endpoint [https://ml.googleapis.com/]\n",
193 |       "Creating version (this might take a few minutes)......done.                    \n"
194 |      ]
195 |     }
196 |    ],
197 |    "source": [
198 |     "! gcloud --quiet beta ai-platform versions create V1 \\\n",
199 |     "  --model ChurnPredictor \\\n",
200 |     "  --runtime-version 2.3 \\\n",
201 |     "  --python-version 3.7 \\\n",
202 |     "  --origin gs://churn-model-sri/ \\\n",
203 |     "  --package-uris gs://churn-model-sri/custom_predict-0.1.tar.gz \\\n",
204 |     "  --prediction-class predictor.ChurnPredictor "
205 |    ]
206 |   },
207 |   {
208 |    "cell_type": "code",
209 |    "execution_count": null,
210 |    "metadata": {},
211 |    "outputs": [],
212 |    "source": [
213 |     "#{\"instances\": [\"7317-GGVPB\", \"Male\", 0, \"Yes\", \"No\", 71, \"Yes\", \"Yes\", \"Fiber optic\", \"No\", \"Yes\", \"Yes\", \"Yes\", \"Yes\", \"Yes\", \"Two year\", \"Yes\", \"Credit card (automatic)\", 108.6, \"7690.9\"]}"
214 |    ]
215 |   },
216 |   {
217 |    "cell_type": "code",
218 |    "execution_count": 8,
219 |    "metadata": {},
220 |    "outputs": [
221 |     {
222 |      "name": "stdout",
223 |      "output_type": "stream",
224 |      "text": [
225 |       "Using endpoint [https://ml.googleapis.com/]\n",
226 |       "['No']\n"
227 |      ]
228 |     }
229 |    ],
230 |    "source": [
231 |     "!gcloud ai-platform predict --model ChurnPredictor --version V1 --json-request input.json"
232 |    ]
233 |   },
234 |   {
235 |    "cell_type": "code",
236 |    "execution_count": null,
237 |    "metadata": {},
238 |    "outputs": [],
239 |    "source": []
240 |   }
241 |  ],
242 |  "metadata": {
243 |   "environment": {
244 |    "name": "common-cpu.m59",
245 |    "type": "gcloud",
246 |    "uri": "gcr.io/deeplearning-platform-release/base-cpu:m59"
247 |   },
248 |   "kernelspec": {
249 |    "display_name": "Python 3",
250 |    "language": "python",
251 |    "name": "python3"
252 |   },
253 |   "language_info": {
254 |    "codemirror_mode": {
255 |     "name": "ipython",
256 |     "version": 3
257 |    },
258 |    "file_extension": ".py",
259 |    "mimetype": "text/x-python",
260 |    "name": "python",
261 |    "nbconvert_exporter": "python",
262 |    "pygments_lexer": "ipython3",
263 |    "version": "3.7.8"
264 |   }
265 |  },
266 |  "nbformat": 4,
267 |  "nbformat_minor": 4
268 | }
269 | 


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/predictor.py:
--------------------------------------------------------------------------------
 1 | 
 2 | import os
 3 | 
 4 | import numpy as np
 5 | import joblib
 6 | import pandas as pd
 7 | 
 8 | class ChurnPredictor(object):
 9 | 
10 |   _COLUMN_NAMES=['customerID', 'gender', 'SeniorCitizen', 'Partner', 'Dependents', 'tenure', 'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies', 'Contract', 'PaperlessBilling','PaymentMethod', 'MonthlyCharges', 'TotalCharges']
11 | 
12 |   def __init__(self, model):
13 |     self._model = model
14 | 
15 |   def predict(self, instances, **kwargs):
16 |     inputs = pd.DataFrame(data=[instances], columns=self._COLUMN_NAMES)
17 |     outputs = self._model.predict(inputs)
18 |     return outputs.tolist()
19 | 
20 |   @classmethod
21 |   def from_path(cls, model_dir):
22 |     model_path = os.path.join(model_dir, 'model.joblib')
23 |     model = joblib.load(model_path)
24 |     return cls(model)
25 | 


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/serving.ipynb:
--------------------------------------------------------------------------------
 1 | {
 2 |  "cells": [
 3 |   {
 4 |    "cell_type": "code",
 5 |    "execution_count": 1,
 6 |    "metadata": {},
 7 |    "outputs": [],
 8 |    "source": [
 9 |     "import googleapiclient.discovery"
10 |    ]
11 |   },
12 |   {
13 |    "cell_type": "code",
14 |    "execution_count": 2,
15 |    "metadata": {},
16 |    "outputs": [],
17 |    "source": [
18 |     "instances = [\"7317-GGVPB\", \"Male\", 0, \"Yes\", \"No\", 71, \"Yes\", \"Yes\", \"Fiber optic\", \"No\", \"Yes\", \"Yes\", \"Yes\", \"Yes\", \"Yes\", \"Two year\", \"Yes\", \"Credit card (automatic)\", 108.6, \"7690.9\"]"
19 |    ]
20 |   },
21 |   {
22 |    "cell_type": "code",
23 |    "execution_count": 3,
24 |    "metadata": {},
25 |    "outputs": [],
26 |    "source": [
27 |     "service = googleapiclient.discovery.build('ml', 'v1')\n",
28 |     "name = 'projects/{}/models/{}/versions/{}'.format(\"srivatsan-project\", \"ChurnPredictor\", \"V1\")"
29 |    ]
30 |   },
31 |   {
32 |    "cell_type": "code",
33 |    "execution_count": 4,
34 |    "metadata": {},
35 |    "outputs": [
36 |     {
37 |      "name": "stdout",
38 |      "output_type": "stream",
39 |      "text": [
40 |       "['No']\n"
41 |      ]
42 |     }
43 |    ],
44 |    "source": [
45 |     "response = service.projects().predict(\n",
46 |     "    name=name,\n",
47 |     "    body={'instances': instances}\n",
48 |     ").execute()\n",
49 |     "\n",
50 |     "if 'error' in response:\n",
51 |     "    raise RuntimeError(response['error'])\n",
52 |     "else:\n",
53 |     "  print(response['predictions'])"
54 |    ]
55 |   },
56 |   {
57 |    "cell_type": "code",
58 |    "execution_count": null,
59 |    "metadata": {},
60 |    "outputs": [],
61 |    "source": [
62 |     "#end"
63 |    ]
64 |   }
65 |  ],
66 |  "metadata": {
67 |   "environment": {
68 |    "name": "common-cpu.m59",
69 |    "type": "gcloud",
70 |    "uri": "gcr.io/deeplearning-platform-release/base-cpu:m59"
71 |   },
72 |   "kernelspec": {
73 |    "display_name": "Python 3",
74 |    "language": "python",
75 |    "name": "python3"
76 |   },
77 |   "language_info": {
78 |    "codemirror_mode": {
79 |     "name": "ipython",
80 |     "version": 3
81 |    },
82 |    "file_extension": ".py",
83 |    "mimetype": "text/x-python",
84 |    "name": "python",
85 |    "nbconvert_exporter": "python",
86 |    "pygments_lexer": "ipython3",
87 |    "version": "3.7.8"
88 |   }
89 |  },
90 |  "nbformat": 4,
91 |  "nbformat_minor": 4
92 | }
93 | 


--------------------------------------------------------------------------------
/Telecom_churn_AI_Platform/setup.py:
--------------------------------------------------------------------------------
 1 | from setuptools import setup
 2 | from setuptools import find_packages
 3 | 
 4 | REQUIRED_PACKAGES = ['xgboost']
 5 | 
 6 | setup(
 7 |     name='custom_predict',
 8 |     version='0.1',
 9 |     install_requires=REQUIRED_PACKAGES,
10 |     packages=find_packages(),
11 |     include_package_data=True,
12 |     scripts=['predictor.py'])
13 | 


--------------------------------------------------------------------------------
/bigquery_logisticsregression/README.md:
--------------------------------------------------------------------------------
  1 | This folder contains demonstration of using BigQuery ML for feature engineering and for building logistics regression model
  2 | 
  3 | Dataset used for this demonstration is available in UCI ML repository - https://archive.ics.uci.edu/ml/datasets/Bank+Marketing
  4 | 
  5 | You can watch the video demonstration of code here - https://youtu.be/pX4P6uG1CuU
  6 | 
  7 | You can store the data in GCS bucket and import into bigquery. Once done follow the below steps
  8 | 
  9 | <b>Step 1 - Query table to quickly validate the load and get understanding of data </b>
 10 | 
 11 | select
 12 | age,	
 13 | job,	
 14 | marital,	
 15 | education,
 16 | 'default',	
 17 | balance,
 18 | housing,	
 19 | loan,	
 20 | contact,	
 21 | day,	
 22 | month,	
 23 | campaign,	
 24 | pdays,
 25 | previous,	
 26 | poutcome,	
 27 | y as target
 28 | from
 29 | `srivatsan-project.bank.bank_marketing` 
 30 | 
 31 | <b> Step 2 - Check target value distribution. This dataset target instances are imbalanced </b>
 32 | 
 33 | select
 34 | y as target, count(*)
 35 | from
 36 | `srivatsan-project.bank.bank_marketing` 
 37 | group by y	
 38 | 
 39 | <b> Step 3: Query to split data on train/validation and test </b>
 40 | 
 41 | select 
 42 | age, job, marital, education, 'default', balance, housing, loan,	
 43 | contact, day, month, campaign, pdays, previous,	
 44 | poutcome, target,
 45 | CASE
 46 |     WHEN split_field < 0.8 THEN 'training'
 47 |     WHEN split_field = 0.8 THEN 'evaluation'
 48 |     WHEN split_field > 0.8 THEN 'prediction'
 49 |   END AS dataframe
 50 | from (
 51 | select
 52 | age, job, marital, education, 'default', balance, housing, loan,	
 53 | contact, day, month, campaign, pdays, previous,	
 54 | poutcome, y as target,
 55 | ROUND(ABS(RAND()),1) as split_field
 56 | from
 57 | `srivatsan-project.bank.bank_marketing` ) 
 58 | 
 59 | <b> Query 4: Store the data split into new table for using it in model. Creating physical table to keep consistent data sets from random splits </b>
 60 | 
 61 | 
 62 | CREATE OR REPLACE table `bank.marketing_tab` AS
 63 | select 
 64 | age, job, marital, education, 'default' as derog, balance, housing, loan,	
 65 | contact, day, month, campaign, pdays, previous,	
 66 | poutcome, target,
 67 | CASE
 68 |     WHEN split_field < 0.8 THEN 'training'
 69 |     WHEN split_field = 0.8 THEN 'evaluation'
 70 |     WHEN split_field > 0.8 THEN 'prediction'
 71 |   END AS dataframe
 72 | from (
 73 | select
 74 | age, job, marital, education, 'default', balance, housing, loan,	
 75 | contact, day, month, campaign, pdays, previous,	
 76 | poutcome, y as target,
 77 | ROUND(ABS(RAND()),1) as split_field
 78 | from
 79 | `srivatsan-project.bank.bank_marketing` ) 
 80 | 
 81 | <b> Query 5: validate target variable distribution in splits </b>
 82 | 
 83 | select 
 84 | dataframe, target, count(*)
 85 | from `srivatsan-project.bank.marketing_tab`
 86 | group by dataframe, target
 87 | order by dataframe
 88 | 
 89 | <b> Query 6: Create Logistics Regression model </b>
 90 | 
 91 | 
 92 | CREATE OR REPLACE MODEL
 93 |   `bank.marketing_model`
 94 | OPTIONS
 95 |   ( model_type='LOGISTIC_REG',
 96 |     auto_class_weights=TRUE,
 97 |     input_label_cols=['target']
 98 |   ) AS
 99 | SELECT
100 |   * EXCEPT(dataframe)
101 | FROM
102 |   `bank.marketing_tab`
103 | WHERE
104 |   dataframe = 'training'
105 | 
106 | <b> Query 7: Get Training and Feature Info from trained model </b>
107 | 
108 | SELECT
109 |   *
110 | FROM
111 |   ML.TRAINING_INFO(MODEL `bank.marketing_model`)
112 | 
113 | SELECT
114 |   *
115 | FROM
116 |   ML.FEATURE_INFO(MODEL `bank.marketing_model`)
117 | 
118 | 
119 |   SELECT
120 |   *
121 | FROM
122 |   ML.WEIGHTS(MODEL `bank.marketing_model`)
123 | 
124 | <b> Query 8: Evaluate using the trained model </b>
125 | 
126 | 
127 | SELECT
128 |   *
129 | FROM
130 |   ML.EVALUATE (MODEL `bank.marketing_model`,
131 |     (
132 |     SELECT
133 |       *
134 |     FROM
135 |       `bank.marketing_tab`
136 |     WHERE
137 |       dataframe = 'evaluation'
138 |     )
139 |   )
140 | 
141 | <b> Query 8: Predict new data using the trained model </b>
142 | 
143 | 
144 | SELECT
145 |   *
146 | FROM
147 |   ML.PREDICT (MODEL `bank.marketing_model`,
148 |     (
149 |     SELECT
150 |       *
151 |     FROM
152 |       `bank.marketing_tab`
153 |     WHERE
154 |       dataframe = 'prediction'
155 |      )
156 |   )
157 | 
158 | 
159 | <b> Query 9: Add feature engineering to the model to increase model performance </b>
160 | 
161 | 
162 | CREATE OR REPLACE MODEL
163 |   `bank.marketing_model_feat`
164 | TRANSFORM(
165 |     ML.QUANTILE_BUCKETIZE(age,5) OVER() AS bucketized_age, 
166 |     ML.FEATURE_CROSS(STRUCT(job, education)) job_education,
167 | marital, balance, housing, loan,	
168 | contact, day, month, pdays, previous,	
169 | poutcome, target)
170 | OPTIONS
171 |   ( model_type='LOGISTIC_REG',
172 |     auto_class_weights=TRUE,
173 |     input_label_cols=['target']
174 |   ) AS
175 | SELECT
176 |   * EXCEPT(dataframe, campaign, derog)
177 | FROM
178 |   `bank.marketing_tab`
179 | WHERE
180 |   dataframe = 'training'
181 | 
182 | <b> Query 10: Get training and feature info from newly trained model </b>
183 | 
184 | SELECT
185 |   *
186 | FROM
187 |   ML.TRAINING_INFO(MODEL `bank.marketing_model_feat`)
188 | 
189 | SELECT
190 |   *
191 | FROM
192 |   ML.FEATURE_INFO(MODEL `bank.marketing_model_feat`)
193 | 
194 |   SELECT
195 |   *
196 | FROM
197 |   ML.WEIGHTS(MODEL `bank.marketing_model_feat`)
198 | 
199 | <b> Query 11: Evaluate the model </b>
200 | 
201 | 
202 | SELECT
203 |   *
204 | FROM
205 |   ML.EVALUATE (MODEL `bank.marketing_model_feat`,
206 |     (
207 |     SELECT
208 |       *
209 |     FROM
210 |       `bank.marketing_tab`
211 |     WHERE
212 |       dataframe = 'evaluation'
213 |     )
214 |   )
215 | 
216 | 


--------------------------------------------------------------------------------
/bigqueryml_datastudio/README.md:
--------------------------------------------------------------------------------
  1 | 
  2 | This repo contains SQL queries for my live session on BigQuery, BigQuery ML and Google Data Studio
  3 | 
  4 | Live session video is available here - https://youtu.be/5l4Qb6Fy3E0
  5 | 
  6 | In below set of SQL queries we will be analyzing SFO bikeshare dataset and as well will be building multiple time series model using BigQuery ML
  7 | 
  8 | Query 1: Query to select limited columns for analysis in data studio
  9 | 
 10 | SELECT
 11 |    start_date, duration_sec, start_station_name, subscriber_type, zip_code
 12 | FROM
 13 |   `bigquery-public-data.san_francisco_bikeshare.bikeshare_trips`
 14 | 
 15 | Query 2: Select columns for understanding time series pattern
 16 | 
 17 | SELECT
 18 |    start_station_name,
 19 |    EXTRACT(DATE from start_date) AS date,
 20 |    COUNT(*) AS num_trips
 21 | FROM
 22 |   `bigquery-public-data.san_francisco_bikeshare.bikeshare_trips`
 23 | GROUP BY start_station_name, date
 24 | order by start_station_name, date
 25 | 
 26 | Query 3: Understand minimum and maximum dates grouped by station
 27 | 
 28 | SELECT
 29 |    start_station_name,
 30 |    min(EXTRACT(DATE from start_date)) as min_date,
 31 |    max(EXTRACT(DATE from start_date)) as max_date
 32 | FROM
 33 |   `bigquery-public-data.san_francisco_bikeshare.bikeshare_trips`
 34 | WHERE
 35 |   start_station_name IN ('Harry Bridges Plaza (Ferry Building)','Embarcadero at Sansome','2nd at Townsend')
 36 | group by start_station_name
 37 | 
 38 | Query 4: Create multiple time series model using SFO bikeshare data
 39 | 
 40 | CREATE OR REPLACE MODEL bike_share_ml.sfo_bike
 41 | OPTIONS
 42 |   (model_type = 'ARIMA',
 43 |    time_series_timestamp_col = 'date',
 44 |    time_series_data_col = 'num_trips',
 45 |    time_series_id_col = 'start_station_name'
 46 |   ) AS
 47 | SELECT
 48 |    start_station_name,
 49 |    EXTRACT(DATE from start_date) AS date,
 50 |    COUNT(*) AS num_trips
 51 | FROM
 52 |   `bigquery-public-data.san_francisco_bikeshare.bikeshare_trips`
 53 | WHERE
 54 |   start_station_name IN ('Harry Bridges Plaza (Ferry Building)','Embarcadero at Sansome','2nd at Townsend') AND
 55 | EXTRACT(DATE from start_date) <= '2016-07-31'
 56 | GROUP BY start_station_name, date
 57 | 
 58 | Query 5: Evaluate the developed model
 59 | 
 60 | SELECT
 61 |   *
 62 | FROM
 63 |   ML.EVALUATE(MODEL `bike_share_ml.sfo_bike`)
 64 | 
 65 | Query 6: Understand trained model co-efficients
 66 | 
 67 | SELECT
 68 |   *
 69 | FROM
 70 |   ML.ARIMA_COEFFICIENTS(MODEL `bike_share_ml.sfo_bike`)
 71 | 
 72 | 
 73 | Query 7: Forecast for 3 future time period
 74 | 
 75 | SELECT
 76 |   *
 77 | FROM
 78 |   ML.FORECAST(MODEL `bike_share_ml.sfo_bike`,
 79 |               STRUCT(3 AS horizon, 0.9 AS confidence_level))
 80 | 
 81 | Query 8: Combine historical data and future 365 days forecast for visualization
 82 | 
 83 | SELECT
 84 |  start_station_name,
 85 |  date AS timestamp,
 86 |  num_trips AS history_value,
 87 |  NULL AS forecast_value,
 88 |  NULL AS prediction_interval_lower_bound,
 89 |  NULL AS prediction_interval_upper_bound
 90 | FROM
 91 |  (
 92 |   SELECT
 93 |      start_station_name,
 94 |      EXTRACT(DATE from start_date) AS date,
 95 |      COUNT(*) AS num_trips
 96 |   FROM
 97 |     `bigquery-public-data.san_francisco_bikeshare.bikeshare_trips`
 98 |   WHERE
 99 |   start_station_name IN ('Harry Bridges Plaza (Ferry Building)','Embarcadero at Sansome','2nd at Townsend')
100 |   GROUP BY start_station_name, date
101 |  )
102 | UNION ALL
103 | SELECT
104 |  start_station_name,
105 |  EXTRACT(DATE from forecast_timestamp) AS timestamp,
106 |  NULL AS history_value,
107 |  forecast_value,
108 |  prediction_interval_lower_bound,
109 |  prediction_interval_upper_bound
110 | FROM
111 |  ML.FORECAST(MODEL `bike_share_ml.sfo_bike`,
112 |              STRUCT(365 AS horizon, 0.9 AS confidence_level))
113 | WHERE
114 |   start_station_name IN ('Harry Bridges Plaza (Ferry Building)','Embarcadero at Sansome','2nd at Townsend')
115 | 


--------------------------------------------------------------------------------
/gke_autopilot/Dockerfile:
--------------------------------------------------------------------------------
 1 | # lightweight python
 2 | FROM python:3.7-slim
 3 | 
 4 | RUN apt-get update
 5 | 
 6 | # Copy local code to the container image.
 7 | ENV APP_HOME /app
 8 | WORKDIR $APP_HOME
 9 | COPY . ./
10 | 
11 | RUN ls -la $APP_HOME/
12 | 
13 | # Install dependencies
14 | RUN pip install -r requirements.txt
15 | 
16 | # Run the streamlit on container startup
17 | CMD [ "streamlit", "run","imgwebapp.py" ]


--------------------------------------------------------------------------------
/gke_autopilot/README.md:
--------------------------------------------------------------------------------
1 | TBF
2 | 


--------------------------------------------------------------------------------
/gke_autopilot/deployment.yaml:
--------------------------------------------------------------------------------
 1 | apiVersion: apps/v1
 2 | kind: Deployment
 3 | metadata:
 4 |   name: imgclass
 5 | spec:
 6 |   replicas: 2
 7 |   selector:
 8 |     matchLabels:
 9 |       app: imageclassifier
10 |   template:
11 |     metadata:
12 |       labels:
13 |         app: imageclassifier
14 |     spec:
15 |       containers:
16 |       - name: cv-app
17 |         image: gcr.io/srivatsan-project/imgclassifier
18 |         ports:
19 |         - containerPort: 8501


--------------------------------------------------------------------------------
/gke_autopilot/imgwebapp.py:
--------------------------------------------------------------------------------
 1 | import warnings
 2 | warnings.simplefilter(action='ignore', category=FutureWarning)
 3 | 
 4 | import tensorflow as tf
 5 | import numpy as np
 6 | import streamlit as st
 7 | from PIL import Image
 8 | import requests
 9 | from io import BytesIO
10 | 
11 | st.set_option('deprecation.showfileUploaderEncoding', False)
12 | st.title("Bean Image Classifier")
13 | st.text("Provide URL of bean Image for image classification")
14 | 
15 | @st.cache(allow_output_mutation=True)
16 | def load_model():
17 |   model = tf.keras.models.load_model('./models')
18 |   return model
19 | 
20 | with st.spinner('Loading Model Into Memory....'):
21 |   model = load_model()
22 | 
23 | classes=['angular_leaf_spot','bean_rust','healthy']
24 | 
25 | def scale(image):
26 |   image = tf.cast(image, tf.float32)
27 |   image /= 255.0
28 | 
29 |   return tf.image.resize(image,[224,224])
30 | 
31 | def decode_img(image):
32 |   img = tf.image.decode_jpeg(image, channels=3)
33 |   img = scale(img)
34 |   return np.expand_dims(img, axis=0)
35 | 
36 | #path = st.text_input('Enter Image URL to Classify.. ','http://barmac.com.au/wp-content/uploads/sites/3/2016/01/Angular-Leaf-Spot-Beans1.jpg')
37 | img_file_buffer = st.file_uploader("Upload Image to Classify....")
38 | 
39 | if img_file_buffer  is not None:
40 |     image = img_file_buffer
41 |     image_out = Image.open(img_file_buffer)
42 |     image = image.getvalue()
43 | else:
44 |     test_image = 'http://barmac.com.au/wp-content/uploads/sites/3/2016/01/Angular-Leaf-Spot-Beans1.jpg'
45 |     image = requests.get(test_image).content
46 |     image_out = Image.open(BytesIO(image))
47 | 
48 | st.write("Predicted Class :")
49 | with st.spinner('classifying.....'):
50 |     label =np.argmax(model.predict(decode_img(image)),axis=1)
51 |     st.write(classes[label[0]])    
52 | st.write("")
53 | st.image(image_out, caption='Classifying Bean Image', use_column_width=True)


--------------------------------------------------------------------------------
/gke_autopilot/models/assets/README.md:
--------------------------------------------------------------------------------
1 | TBF
2 | 


--------------------------------------------------------------------------------
/gke_autopilot/models/saved_model.pb:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/srivatsan88/google_cloud_AI_ML/1ef1fdb2208cb5db66d43a39a46ffb3597255e0c/gke_autopilot/models/saved_model.pb


--------------------------------------------------------------------------------
/gke_autopilot/models/variables/variables.data-00000-of-00002:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/srivatsan88/google_cloud_AI_ML/1ef1fdb2208cb5db66d43a39a46ffb3597255e0c/gke_autopilot/models/variables/variables.data-00000-of-00002


--------------------------------------------------------------------------------
/gke_autopilot/models/variables/variables.data-00001-of-00002:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/srivatsan88/google_cloud_AI_ML/1ef1fdb2208cb5db66d43a39a46ffb3597255e0c/gke_autopilot/models/variables/variables.data-00001-of-00002


--------------------------------------------------------------------------------
/gke_autopilot/models/variables/variables.index:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/srivatsan88/google_cloud_AI_ML/1ef1fdb2208cb5db66d43a39a46ffb3597255e0c/gke_autopilot/models/variables/variables.index


--------------------------------------------------------------------------------
/gke_autopilot/requirements.txt:
--------------------------------------------------------------------------------
1 | tensorflow
2 | streamlit
3 | pillow
4 | numpy
5 | requests
6 | 
7 | #Run this file with - pip3 install -r requirements.txt


--------------------------------------------------------------------------------
/gke_autopilot/service.yaml:
--------------------------------------------------------------------------------
 1 | apiVersion: v1
 2 | kind: Service
 3 | metadata:
 4 |   name: imageclassifier
 5 | spec:
 6 |   type: LoadBalancer
 7 |   selector:
 8 |     app: imageclassifier
 9 |   ports:
10 |   - port: 80
11 |     targetPort: 8501


--------------------------------------------------------------------------------