vectorizer
Browse files- sms_vectorizer.pkl +3 -0
- spam-detector-Mathis-AI.ipynb +43 -18
sms_vectorizer.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e78e5596ceaf5a0c1f4100235ce1d528801a34a57732e86c4857a2e5ead0f9d2
|
| 3 |
+
size 106218
|
spam-detector-Mathis-AI.ipynb
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"cell_type": "code",
|
| 21 |
-
"execution_count":
|
| 22 |
"id": "8a313f24",
|
| 23 |
"metadata": {},
|
| 24 |
"outputs": [],
|
|
@@ -36,7 +36,7 @@
|
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"cell_type": "code",
|
| 39 |
-
"execution_count":
|
| 40 |
"id": "e530b713",
|
| 41 |
"metadata": {},
|
| 42 |
"outputs": [
|
|
@@ -104,7 +104,7 @@
|
|
| 104 |
"4 ham Nah I don't think he goes to usf, he lives aro..."
|
| 105 |
]
|
| 106 |
},
|
| 107 |
-
"execution_count":
|
| 108 |
"metadata": {},
|
| 109 |
"output_type": "execute_result"
|
| 110 |
}
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"cell_type": "code",
|
| 130 |
-
"execution_count":
|
| 131 |
"id": "fb533887",
|
| 132 |
"metadata": {},
|
| 133 |
"outputs": [
|
|
@@ -195,7 +195,7 @@
|
|
| 195 |
"4 0 Nah I don't think he goes to usf, he lives aro..."
|
| 196 |
]
|
| 197 |
},
|
| 198 |
-
"execution_count":
|
| 199 |
"metadata": {},
|
| 200 |
"output_type": "execute_result"
|
| 201 |
}
|
|
@@ -210,7 +210,7 @@
|
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"cell_type": "code",
|
| 213 |
-
"execution_count":
|
| 214 |
"id": "c4ea8a09",
|
| 215 |
"metadata": {},
|
| 216 |
"outputs": [
|
|
@@ -220,7 +220,7 @@
|
|
| 220 |
"((5572, 8713), (5572,))"
|
| 221 |
]
|
| 222 |
},
|
| 223 |
-
"execution_count":
|
| 224 |
"metadata": {},
|
| 225 |
"output_type": "execute_result"
|
| 226 |
}
|
|
@@ -255,7 +255,7 @@
|
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"cell_type": "code",
|
| 258 |
-
"execution_count":
|
| 259 |
"id": "aea723b8",
|
| 260 |
"metadata": {},
|
| 261 |
"outputs": [
|
|
@@ -293,7 +293,7 @@
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"cell_type": "code",
|
| 296 |
-
"execution_count":
|
| 297 |
"id": "2d01ce1c",
|
| 298 |
"metadata": {},
|
| 299 |
"outputs": [
|
|
@@ -320,7 +320,7 @@
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"cell_type": "code",
|
| 323 |
-
"execution_count":
|
| 324 |
"id": "7e014dbc",
|
| 325 |
"metadata": {},
|
| 326 |
"outputs": [
|
|
@@ -340,7 +340,7 @@
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"cell_type": "code",
|
| 343 |
-
"execution_count":
|
| 344 |
"id": "c61d8311",
|
| 345 |
"metadata": {},
|
| 346 |
"outputs": [
|
|
@@ -358,7 +358,7 @@
|
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"cell_type": "code",
|
| 361 |
-
"execution_count":
|
| 362 |
"id": "ef960679",
|
| 363 |
"metadata": {},
|
| 364 |
"outputs": [
|
|
@@ -376,7 +376,7 @@
|
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"cell_type": "code",
|
| 379 |
-
"execution_count":
|
| 380 |
"id": "58f88820",
|
| 381 |
"metadata": {},
|
| 382 |
"outputs": [
|
|
@@ -394,7 +394,7 @@
|
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"cell_type": "code",
|
| 397 |
-
"execution_count":
|
| 398 |
"id": "8f4f505b",
|
| 399 |
"metadata": {},
|
| 400 |
"outputs": [
|
|
@@ -404,7 +404,7 @@
|
|
| 404 |
"<Axes: xlabel='label', ylabel='count'>"
|
| 405 |
]
|
| 406 |
},
|
| 407 |
-
"execution_count":
|
| 408 |
"metadata": {},
|
| 409 |
"output_type": "execute_result"
|
| 410 |
},
|
|
@@ -433,7 +433,19 @@
|
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"cell_type": "code",
|
| 436 |
-
"execution_count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 437 |
"id": "dba57e87",
|
| 438 |
"metadata": {},
|
| 439 |
"outputs": [],
|
|
@@ -458,9 +470,22 @@
|
|
| 458 |
"execution_count": null,
|
| 459 |
"id": "6ebccf7a",
|
| 460 |
"metadata": {},
|
| 461 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 462 |
"source": [
|
| 463 |
-
"with open('
|
| 464 |
" model=pickle.load(file)"
|
| 465 |
]
|
| 466 |
}
|
|
|
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"cell_type": "code",
|
| 21 |
+
"execution_count": 14,
|
| 22 |
"id": "8a313f24",
|
| 23 |
"metadata": {},
|
| 24 |
"outputs": [],
|
|
|
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"cell_type": "code",
|
| 39 |
+
"execution_count": 15,
|
| 40 |
"id": "e530b713",
|
| 41 |
"metadata": {},
|
| 42 |
"outputs": [
|
|
|
|
| 104 |
"4 ham Nah I don't think he goes to usf, he lives aro..."
|
| 105 |
]
|
| 106 |
},
|
| 107 |
+
"execution_count": 15,
|
| 108 |
"metadata": {},
|
| 109 |
"output_type": "execute_result"
|
| 110 |
}
|
|
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"cell_type": "code",
|
| 130 |
+
"execution_count": 16,
|
| 131 |
"id": "fb533887",
|
| 132 |
"metadata": {},
|
| 133 |
"outputs": [
|
|
|
|
| 195 |
"4 0 Nah I don't think he goes to usf, he lives aro..."
|
| 196 |
]
|
| 197 |
},
|
| 198 |
+
"execution_count": 16,
|
| 199 |
"metadata": {},
|
| 200 |
"output_type": "execute_result"
|
| 201 |
}
|
|
|
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"cell_type": "code",
|
| 213 |
+
"execution_count": 17,
|
| 214 |
"id": "c4ea8a09",
|
| 215 |
"metadata": {},
|
| 216 |
"outputs": [
|
|
|
|
| 220 |
"((5572, 8713), (5572,))"
|
| 221 |
]
|
| 222 |
},
|
| 223 |
+
"execution_count": 17,
|
| 224 |
"metadata": {},
|
| 225 |
"output_type": "execute_result"
|
| 226 |
}
|
|
|
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"cell_type": "code",
|
| 258 |
+
"execution_count": 18,
|
| 259 |
"id": "aea723b8",
|
| 260 |
"metadata": {},
|
| 261 |
"outputs": [
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"cell_type": "code",
|
| 296 |
+
"execution_count": 19,
|
| 297 |
"id": "2d01ce1c",
|
| 298 |
"metadata": {},
|
| 299 |
"outputs": [
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"cell_type": "code",
|
| 323 |
+
"execution_count": 20,
|
| 324 |
"id": "7e014dbc",
|
| 325 |
"metadata": {},
|
| 326 |
"outputs": [
|
|
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"cell_type": "code",
|
| 343 |
+
"execution_count": 21,
|
| 344 |
"id": "c61d8311",
|
| 345 |
"metadata": {},
|
| 346 |
"outputs": [
|
|
|
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"cell_type": "code",
|
| 361 |
+
"execution_count": 22,
|
| 362 |
"id": "ef960679",
|
| 363 |
"metadata": {},
|
| 364 |
"outputs": [
|
|
|
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"cell_type": "code",
|
| 379 |
+
"execution_count": 23,
|
| 380 |
"id": "58f88820",
|
| 381 |
"metadata": {},
|
| 382 |
"outputs": [
|
|
|
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"cell_type": "code",
|
| 397 |
+
"execution_count": 24,
|
| 398 |
"id": "8f4f505b",
|
| 399 |
"metadata": {},
|
| 400 |
"outputs": [
|
|
|
|
| 404 |
"<Axes: xlabel='label', ylabel='count'>"
|
| 405 |
]
|
| 406 |
},
|
| 407 |
+
"execution_count": 24,
|
| 408 |
"metadata": {},
|
| 409 |
"output_type": "execute_result"
|
| 410 |
},
|
|
|
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"cell_type": "code",
|
| 436 |
+
"execution_count": 27,
|
| 437 |
+
"id": "faf22bf2",
|
| 438 |
+
"metadata": {},
|
| 439 |
+
"outputs": [],
|
| 440 |
+
"source": [
|
| 441 |
+
"# Sauvegarder le vectorizer\n",
|
| 442 |
+
"with open('sms_vectorizer.pkl', 'wb') as file:\n",
|
| 443 |
+
" pickle.dump(vectorizer, file)"
|
| 444 |
+
]
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"cell_type": "code",
|
| 448 |
+
"execution_count": 25,
|
| 449 |
"id": "dba57e87",
|
| 450 |
"metadata": {},
|
| 451 |
"outputs": [],
|
|
|
|
| 470 |
"execution_count": null,
|
| 471 |
"id": "6ebccf7a",
|
| 472 |
"metadata": {},
|
| 473 |
+
"outputs": [
|
| 474 |
+
{
|
| 475 |
+
"ename": "FileNotFoundError",
|
| 476 |
+
"evalue": "[Errno 2] No such file or directory: 'dht11_model.pkl'",
|
| 477 |
+
"output_type": "error",
|
| 478 |
+
"traceback": [
|
| 479 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 480 |
+
"\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
|
| 481 |
+
"Cell \u001b[0;32mIn[26], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdht11_model.pkl\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m file: \n\u001b[1;32m 2\u001b[0m model\u001b[38;5;241m=\u001b[39mpickle\u001b[38;5;241m.\u001b[39mload(file)\n",
|
| 482 |
+
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/IPython/core/interactiveshell.py:324\u001b[0m, in \u001b[0;36m_modified_open\u001b[0;34m(file, *args, **kwargs)\u001b[0m\n\u001b[1;32m 317\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m {\u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m2\u001b[39m}:\n\u001b[1;32m 318\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 319\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIPython won\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt let you open fd=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfile\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m by default \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 320\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mas it is likely to crash IPython. If you know what you are doing, \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 321\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myou can use builtins\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m open.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 322\u001b[0m )\n\u001b[0;32m--> 324\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m io_open(file, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
|
| 483 |
+
"\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'dht11_model.pkl'"
|
| 484 |
+
]
|
| 485 |
+
}
|
| 486 |
+
],
|
| 487 |
"source": [
|
| 488 |
+
"with open('sms_spam_detector_model.pkl','rb') as file: \n",
|
| 489 |
" model=pickle.load(file)"
|
| 490 |
]
|
| 491 |
}
|