File size: 26,346 Bytes
11a4e74 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import re\n",
"import nltk\n",
"from nltk.corpus import stopwords\n",
"from nltk.stem import WordNetLemmatizer\n",
"import tensorflow as tf\n",
"from tensorflow.keras.preprocessing.text import Tokenizer\n",
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package stopwords to\n",
"[nltk_data] C:\\Users\\gouth\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Unzipping corpora\\stopwords.zip.\n",
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\gouth\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\gouth\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\gouth\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nltk.download('stopwords')\n",
"nltk.download('wordnet')\n",
"nltk.download('omw-1.4')\n",
"nltk.download('punkt')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>review</th>\n",
" <th>sentiment</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>One of the other reviewers has mentioned that ...</td>\n",
" <td>positive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>A wonderful little production. <br /><br />The...</td>\n",
" <td>positive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>I thought this was a wonderful way to spend ti...</td>\n",
" <td>positive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Basically there's a family where a little boy ...</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Petter Mattei's \"Love in the Time of Money\" is...</td>\n",
" <td>positive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49995</th>\n",
" <td>I thought this movie did a down right good job...</td>\n",
" <td>positive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49996</th>\n",
" <td>Bad plot, bad dialogue, bad acting, idiotic di...</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49997</th>\n",
" <td>I am a Catholic taught in parochial elementary...</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49998</th>\n",
" <td>I'm going to have to disagree with the previou...</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49999</th>\n",
" <td>No one expects the Star Trek movies to be high...</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>50000 rows × 2 columns</p>\n",
"</div>"
],
"text/plain": [
" review sentiment\n",
"0 One of the other reviewers has mentioned that ... positive\n",
"1 A wonderful little production. <br /><br />The... positive\n",
"2 I thought this was a wonderful way to spend ti... positive\n",
"3 Basically there's a family where a little boy ... negative\n",
"4 Petter Mattei's \"Love in the Time of Money\" is... positive\n",
"... ... ...\n",
"49995 I thought this movie did a down right good job... positive\n",
"49996 Bad plot, bad dialogue, bad acting, idiotic di... negative\n",
"49997 I am a Catholic taught in parochial elementary... negative\n",
"49998 I'm going to have to disagree with the previou... negative\n",
"49999 No one expects the Star Trek movies to be high... negative\n",
"\n",
"[50000 rows x 2 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"D:/New download/archive (1)/IMDB Dataset.csv\")\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import emoji\n",
"\n",
"def preprocess_text(text):\n",
" text = text.lower()\n",
" text = re.sub(r'<.*?>', '', text)\n",
" text = re.sub(r'http\\S+|www\\S+', '', text)\n",
" text = re.sub(r'[^a-zA-Z\\s]', '', text)\n",
" text = emoji.replace_emoji(text, replace=\"\")\n",
" return text"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"df[\"c_review\"] = df[\"review\"].apply(preprocess_text)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'a wonderful little production the filming technique is very unassuming very oldtimebbc fashion and gives a comforting and sometimes discomforting sense of realism to the entire piece the actors are extremely well chosen michael sheen not only has got all the polari but he has all the voices down pat too you can truly see the seamless editing guided by the references to williams diary entries not only is it well worth the watching but it is a terrificly written and performed piece a masterful production about one of the great masters of comedy and his life the realism really comes home with the little things the fantasy of the guard which rather than use the traditional dream techniques remains solid then disappears it plays on our knowledge and our senses particularly with the scenes concerning orton and halliwell and the sets particularly of their flat with halliwells murals decorating every surface are terribly well done'"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[\"c_review\"][1]"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"le = LabelEncoder()\n",
"df[\"n_sentiment\"] = le.fit_transform(df[\"sentiment\"])"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>review</th>\n",
" <th>sentiment</th>\n",
" <th>c_review</th>\n",
" <th>n_sentiment</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>One of the other reviewers has mentioned that ...</td>\n",
" <td>positive</td>\n",
" <td>one of the other reviewers has mentioned that ...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>A wonderful little production. <br /><br />The...</td>\n",
" <td>positive</td>\n",
" <td>a wonderful little production the filming tech...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>I thought this was a wonderful way to spend ti...</td>\n",
" <td>positive</td>\n",
" <td>i thought this was a wonderful way to spend ti...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Basically there's a family where a little boy ...</td>\n",
" <td>negative</td>\n",
" <td>basically theres a family where a little boy j...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Petter Mattei's \"Love in the Time of Money\" is...</td>\n",
" <td>positive</td>\n",
" <td>petter matteis love in the time of money is a ...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49995</th>\n",
" <td>I thought this movie did a down right good job...</td>\n",
" <td>positive</td>\n",
" <td>i thought this movie did a down right good job...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49996</th>\n",
" <td>Bad plot, bad dialogue, bad acting, idiotic di...</td>\n",
" <td>negative</td>\n",
" <td>bad plot bad dialogue bad acting idiotic direc...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49997</th>\n",
" <td>I am a Catholic taught in parochial elementary...</td>\n",
" <td>negative</td>\n",
" <td>i am a catholic taught in parochial elementary...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49998</th>\n",
" <td>I'm going to have to disagree with the previou...</td>\n",
" <td>negative</td>\n",
" <td>im going to have to disagree with the previous...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49999</th>\n",
" <td>No one expects the Star Trek movies to be high...</td>\n",
" <td>negative</td>\n",
" <td>no one expects the star trek movies to be high...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>50000 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" review sentiment \\\n",
"0 One of the other reviewers has mentioned that ... positive \n",
"1 A wonderful little production. <br /><br />The... positive \n",
"2 I thought this was a wonderful way to spend ti... positive \n",
"3 Basically there's a family where a little boy ... negative \n",
"4 Petter Mattei's \"Love in the Time of Money\" is... positive \n",
"... ... ... \n",
"49995 I thought this movie did a down right good job... positive \n",
"49996 Bad plot, bad dialogue, bad acting, idiotic di... negative \n",
"49997 I am a Catholic taught in parochial elementary... negative \n",
"49998 I'm going to have to disagree with the previou... negative \n",
"49999 No one expects the Star Trek movies to be high... negative \n",
"\n",
" c_review n_sentiment \n",
"0 one of the other reviewers has mentioned that ... 1 \n",
"1 a wonderful little production the filming tech... 1 \n",
"2 i thought this was a wonderful way to spend ti... 1 \n",
"3 basically theres a family where a little boy j... 0 \n",
"4 petter matteis love in the time of money is a ... 1 \n",
"... ... ... \n",
"49995 i thought this movie did a down right good job... 1 \n",
"49996 bad plot bad dialogue bad acting idiotic direc... 0 \n",
"49997 i am a catholic taught in parochial elementary... 0 \n",
"49998 im going to have to disagree with the previous... 0 \n",
"49999 no one expects the star trek movies to be high... 0 \n",
"\n",
"[50000 rows x 4 columns]"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'one of the other reviewers has mentioned that after watching just oz episode youll be hooked they are right as this is exactly what happened with methe first thing that struck me about oz was its brutality and unflinching scenes of violence which set in right from the word go trust me this is not a show for the faint hearted or timid this show pulls no punches with regards to drugs sex or violence its is hardcore in the classic use of the wordit is called oz as that is the nickname given to the oswald maximum security state penitentary it focuses mainly on emerald city an experimental section of the prison where all the cells have glass fronts and face inwards so privacy is not high on the agenda em city is home to manyaryans muslims gangstas latinos christians italians irish and moreso scuffles death stares dodgy dealings and shady agreements are never far awayi would say the main appeal of the show is due to the fact that it goes where other shows wouldnt dare forget pretty pictures painted for mainstream audiences forget charm forget romanceoz doesnt mess around the first episode i ever saw struck me as so nasty it was surreal i couldnt say i was ready for it but as i watched more i developed a taste for oz and got accustomed to the high levels of graphic violence not just violence but injustice crooked guards wholl be sold out for a nickel inmates wholl kill on order and get away with it well mannered middle class inmates being turned into prison bitches due to their lack of street skills or prison experience watching oz you may become comfortable with what is uncomfortable viewingthats if you can get in touch with your darker side'"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['c_review'][0]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"x_train, x_test, y_train, y_test = train_test_split(df[\"c_review\"],df[\"n_sentiment\"], test_size=0.2, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"max_words = 10000\n",
"max_len = 20\n",
"\n",
"token = Tokenizer(num_words=max_words, oov_token= \"<oov>\")\n",
"token.fit_on_texts(x_train)\n",
"x_train_seq = token.texts_to_sequences(x_train)\n",
"x_test_seq = token.texts_to_sequences(x_test)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"x_train_pad = pad_sequences(x_train_seq, maxlen = max_len, padding = 'post', truncating = 'post')\n",
"x_test_pad = pad_sequences(x_test_seq, maxlen = max_len, padding = 'post', truncating = 'post')"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"X_train_pad = np.array(x_train_pad, dtype=np.int32)\n",
"X_test_pad = np.array(x_test_pad, dtype=np.int32)\n",
"y_train = np.array(y_train, dtype=np.float32)\n",
"y_test = np.array(y_test, dtype=np.float32)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"X_train_pad dtype: int32, shape: (40000, 20)\n",
"X_test_pad dtype: int32, shape: (10000, 20)\n",
"y_train dtype: float32, shape: (40000,)\n",
"y_test dtype: float32, shape: (10000,)\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
"X_train_pad = np.array(X_train_pad, dtype=np.int32)\n",
"X_test_pad = np.array(X_test_pad, dtype=np.int32)\n",
"y_train = np.array(y_train, dtype=np.float32)\n",
"y_test = np.array(y_test, dtype=np.float32)\n",
"\n",
"print(f\"X_train_pad dtype: {X_train_pad.dtype}, shape: {X_train_pad.shape}\")\n",
"print(f\"X_test_pad dtype: {X_test_pad.dtype}, shape: {X_test_pad.shape}\")\n",
"print(f\"y_train dtype: {y_train.dtype}, shape: {y_train.shape}\")\n",
"print(f\"y_test dtype: {y_test.dtype}, shape: {y_test.shape}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\gouth\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\keras\\src\\layers\\core\\embedding.py:90: UserWarning: Argument `input_length` is deprecated. Just remove it.\n",
" warnings.warn(\n"
]
}
],
"source": [
"model = Sequential([\n",
" Embedding(input_dim=max_words, output_dim=128, input_length= max_len), \n",
" LSTM(128, return_sequences=True),\n",
" Dropout(0.3),\n",
" LSTM(64),\n",
" Dropout(0.3),\n",
" Dense(64, activation='relu'),\n",
" Dense(1, activation='sigmoid')])\n",
"\n",
"model.compile(loss= 'binary_crossentropy', optimizer='adam',metrics = ['accuracy'])"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/5\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step - accuracy: 0.6499 - loss: 0.6137\n",
"Epoch 1: val_accuracy improved from -inf to 0.72350, saving model to imdb-001.keras\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m50s\u001b[0m 71ms/step - accuracy: 0.6500 - loss: 0.6136 - val_accuracy: 0.7235 - val_loss: 0.5364\n",
"Epoch 2/5\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step - accuracy: 0.7795 - loss: 0.4639\n",
"Epoch 2: val_accuracy improved from 0.72350 to 0.72690, saving model to imdb-002.keras\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m45s\u001b[0m 71ms/step - accuracy: 0.7795 - loss: 0.4639 - val_accuracy: 0.7269 - val_loss: 0.5347\n",
"Epoch 3/5\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step - accuracy: 0.8218 - loss: 0.3898\n",
"Epoch 3: val_accuracy did not improve from 0.72690\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m45s\u001b[0m 72ms/step - accuracy: 0.8218 - loss: 0.3898 - val_accuracy: 0.7197 - val_loss: 0.5766\n",
"Epoch 4/5\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 69ms/step - accuracy: 0.8574 - loss: 0.3142\n",
"Epoch 4: val_accuracy did not improve from 0.72690\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m46s\u001b[0m 73ms/step - accuracy: 0.8573 - loss: 0.3143 - val_accuracy: 0.7087 - val_loss: 0.6811\n",
"Epoch 5/5\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 71ms/step - accuracy: 0.8940 - loss: 0.2464\n",
"Epoch 5: val_accuracy did not improve from 0.72690\n",
"\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 75ms/step - accuracy: 0.8940 - loss: 0.2464 - val_accuracy: 0.7032 - val_loss: 0.7815\n"
]
},
{
"data": {
"text/plain": [
"<keras.src.callbacks.history.History at 0x21dac69a560>"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from tensorflow.keras.callbacks import ModelCheckpoint\n",
"\n",
"checkpoint = ModelCheckpoint(\"imdb-{epoch:03d}.keras\", monitor = 'val_accuracy', save_best_only = True, mode = 'max', verbose = 1)\n",
"model.fit(x_train_pad,y_train, epochs=5, batch_size=64,validation_data=(x_test_pad,y_test), callbacks=[checkpoint])"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 14ms/step - accuracy: 0.7220 - loss: 0.5362\n",
"Accuracy: 0.7269\n"
]
}
],
"source": [
"model.load_weights(\"imdb-002.keras\")\n",
"\n",
"loss, accuracy = model.evaluate(X_test_pad, y_test)\n",
"print(f'Accuracy: {accuracy:.4f}')"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 99ms/step\n",
"Predicted Sentiment: Positive (Confidence: 0.9227)\n",
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 86ms/step\n",
"Predicted Sentiment: Positive (Confidence: 0.9227)\n",
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 86ms/step\n",
"Predicted Sentiment: Negative (Confidence: 0.0638)\n"
]
}
],
"source": [
"def predict_sentiment(review):\n",
" processed_review = preprocess_text(review)\n",
" sequence = token.texts_to_sequences([processed_review])\n",
" padded_sequence = pad_sequences(sequence, maxlen=max_len, padding='post', truncating='post')\n",
" prediction = model.predict(padded_sequence)[0][0]\n",
" sentiment = 'Positive' if prediction > 0.5 else 'Negative'\n",
" return sentiment, prediction\n",
"\n",
"while True:\n",
" user_input = input(\"Enter a review (or type 'exit' to quit): \")\n",
" if user_input.lower() == 'exit':\n",
" break\n",
" sentiment, confidence = predict_sentiment(user_input)\n",
" print(f\"Predicted Sentiment: {sentiment} (Confidence: {confidence:.4f})\")"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
"tokenizer_json = token.to_json()\n",
"with open(\"imdb.json\", \"w\") as file:\n",
" file.write(tokenizer_json)\n",
"\n",
"model.save(\"imdb-002.keras\")\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|