File size: 13,828 Bytes
ad3e56b |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import opendatasets as od"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading mpst-movie-plot-synopses-with-tags.zip to .\\mpst-movie-plot-synopses-with-tags\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 28.8M/28.8M [00:07<00:00, 3.81MB/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"od.download('https://www.kaggle.com/datasets/cryptexcode/mpst-movie-plot-synopses-with-tags')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"df = pd.read_csv('mpst-movie-plot-synopses-with-tags\\mpst_full_data.csv')"
]
},
{
"cell_type": "code",
"execution_count": 7,
"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>imdb_id</th>\n",
" <th>title</th>\n",
" <th>plot_synopsis</th>\n",
" <th>tags</th>\n",
" <th>split</th>\n",
" <th>synopsis_source</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>tt0057603</td>\n",
" <td>I tre volti della paura</td>\n",
" <td>Note: this synopsis is for the orginal Italian...</td>\n",
" <td>cult, horror, gothic, murder, atmospheric</td>\n",
" <td>train</td>\n",
" <td>imdb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>tt1733125</td>\n",
" <td>Dungeons & Dragons: The Book of Vile Darkness</td>\n",
" <td>Two thousand years ago, Nhagruul the Foul, a s...</td>\n",
" <td>violence</td>\n",
" <td>train</td>\n",
" <td>imdb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>tt0033045</td>\n",
" <td>The Shop Around the Corner</td>\n",
" <td>Matuschek's, a gift store in Budapest, is the ...</td>\n",
" <td>romantic</td>\n",
" <td>test</td>\n",
" <td>imdb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>tt0113862</td>\n",
" <td>Mr. Holland's Opus</td>\n",
" <td>Glenn Holland, not a morning person by anyone'...</td>\n",
" <td>inspiring, romantic, stupid, feel-good</td>\n",
" <td>train</td>\n",
" <td>imdb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>tt0086250</td>\n",
" <td>Scarface</td>\n",
" <td>In May 1980, a Cuban man named Tony Montana (A...</td>\n",
" <td>cruelty, murder, dramatic, cult, violence, atm...</td>\n",
" <td>val</td>\n",
" <td>imdb</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" imdb_id title \\\n",
"0 tt0057603 I tre volti della paura \n",
"1 tt1733125 Dungeons & Dragons: The Book of Vile Darkness \n",
"2 tt0033045 The Shop Around the Corner \n",
"3 tt0113862 Mr. Holland's Opus \n",
"4 tt0086250 Scarface \n",
"\n",
" plot_synopsis \\\n",
"0 Note: this synopsis is for the orginal Italian... \n",
"1 Two thousand years ago, Nhagruul the Foul, a s... \n",
"2 Matuschek's, a gift store in Budapest, is the ... \n",
"3 Glenn Holland, not a morning person by anyone'... \n",
"4 In May 1980, a Cuban man named Tony Montana (A... \n",
"\n",
" tags split synopsis_source \n",
"0 cult, horror, gothic, murder, atmospheric train imdb \n",
"1 violence train imdb \n",
"2 romantic test imdb \n",
"3 inspiring, romantic, stupid, feel-good train imdb \n",
"4 cruelty, murder, dramatic, cult, violence, atm... val imdb "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install gpt-2-simple"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['imdb_id', 'title', 'plot_synopsis', 'tags', 'split',\n",
" 'synopsis_source'],\n",
" dtype='object')"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"from sklearn.model_selection import train_test_split\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, Flatten\n",
"from sklearn.preprocessing import MultiLabelBinarizer"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"df = df[['title', 'plot_synopsis', 'tags']]"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [],
"source": [
"tokenizer = Tokenizer()\n",
"tokenizer.fit_on_texts(df['title'])\n",
"title_sequences = tokenizer.texts_to_sequences(df['title'])\n",
"max_title_length = max(len(seq) for seq in title_sequences)\n",
"title_sequences = pad_sequences(title_sequences, maxlen=max_title_length)"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [],
"source": [
"tags = [tag.split(', ') for tag in df['tags']]\n",
"mlb = MultiLabelBinarizer()\n",
"tags = mlb.fit_transform(tags)"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
"tokenizer_json = tokenizer.to_json()\n",
"with open('tokenizer.json', 'w') as json_file:\n",
" json_file.write(tokenizer_json)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(title_sequences, tags, test_size=0.2, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [],
"source": [
"vocab_size = len(tokenizer.word_index) + 1\n",
"embedding_dim = 100"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train on 11862 samples, validate on 2966 samples\n",
"Epoch 1/15\n",
"11862/11862 [==============================] - 10s 826us/sample - loss: 0.1911 - accuracy: 0.9457 - val_loss: 0.1417 - val_accuracy: 0.9569\n",
"Epoch 2/15\n",
"11862/11862 [==============================] - 11s 887us/sample - loss: 0.1390 - accuracy: 0.9583 - val_loss: 0.1416 - val_accuracy: 0.9569\n",
"Epoch 3/15\n",
"11862/11862 [==============================] - 11s 941us/sample - loss: 0.1388 - accuracy: 0.9583 - val_loss: 0.1415 - val_accuracy: 0.9569\n",
"Epoch 4/15\n",
"11862/11862 [==============================] - 11s 916us/sample - loss: 0.1367 - accuracy: 0.9583 - val_loss: 0.1420 - val_accuracy: 0.9568\n",
"Epoch 5/15\n",
"11862/11862 [==============================] - 11s 906us/sample - loss: 0.1310 - accuracy: 0.9595 - val_loss: 0.1433 - val_accuracy: 0.9567\n",
"Epoch 6/15\n",
"11862/11862 [==============================] - 11s 909us/sample - loss: 0.1248 - accuracy: 0.9608 - val_loss: 0.1444 - val_accuracy: 0.9569\n",
"Epoch 7/15\n",
"11862/11862 [==============================] - 11s 911us/sample - loss: 0.1184 - accuracy: 0.9624 - val_loss: 0.1461 - val_accuracy: 0.9564\n",
"Epoch 8/15\n",
"11862/11862 [==============================] - 11s 948us/sample - loss: 0.1123 - accuracy: 0.9649 - val_loss: 0.1484 - val_accuracy: 0.9562\n",
"Epoch 9/15\n",
"11862/11862 [==============================] - 11s 916us/sample - loss: 0.1069 - accuracy: 0.9668 - val_loss: 0.1509 - val_accuracy: 0.9552\n",
"Epoch 10/15\n",
"11862/11862 [==============================] - 11s 921us/sample - loss: 0.1021 - accuracy: 0.9682 - val_loss: 0.1537 - val_accuracy: 0.9550\n",
"Epoch 11/15\n",
"11862/11862 [==============================] - 11s 932us/sample - loss: 0.0978 - accuracy: 0.9692 - val_loss: 0.1566 - val_accuracy: 0.9541\n",
"Epoch 12/15\n",
"11862/11862 [==============================] - 11s 927us/sample - loss: 0.0937 - accuracy: 0.9700 - val_loss: 0.1591 - val_accuracy: 0.9540\n",
"Epoch 13/15\n",
"11862/11862 [==============================] - 11s 927us/sample - loss: 0.0896 - accuracy: 0.9710 - val_loss: 0.1621 - val_accuracy: 0.9536\n",
"Epoch 14/15\n",
"11862/11862 [==============================] - 11s 954us/sample - loss: 0.0857 - accuracy: 0.9719 - val_loss: 0.1660 - val_accuracy: 0.9536\n",
"Epoch 15/15\n",
"11862/11862 [==============================] - 12s 1ms/sample - loss: 0.0820 - accuracy: 0.9729 - val_loss: 0.1690 - val_accuracy: 0.9538\n"
]
},
{
"data": {
"text/plain": [
"<keras.callbacks.History at 0x1cc31c0b250>"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"model = Sequential()\n",
"model.add(Embedding(vocab_size, embedding_dim, input_length=max_title_length))\n",
"model.add(LSTM(100))\n",
"model.add(Dense(tags.shape[1], activation='sigmoid'))\n",
"\n",
"model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
"\n",
"\n",
"model.fit(X_train, y_train, batch_size=64, epochs=15, validation_data=(X_test, y_test))\n"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
"model.save('story_gen.h5')"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [],
"source": [
"title = \"A oversized t-shirt\"\n"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [],
"source": [
"title_sequences = tokenizer.texts_to_sequences(title)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"predictions = model.predict(title_sequences)"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Input Title: Spider Man\n",
"Predicted Tags: [('murder',)]\n"
]
}
],
"source": [
"from tensorflow.keras.models import load_model\n",
"with open('tokenizer.json', 'r') as f:\n",
" tokenizer = tokenizer_from_json(f.read())\n",
"\n",
"model = load_model('story_gen.h5') \n",
"\n",
"example_title = \"Spider Man\"\n",
"\n",
"example_sequence = tokenizer.texts_to_sequences([example_title])\n",
"example_sequence = pad_sequences(example_sequence, maxlen=max_title_length)\n",
"\n",
"predictions = model.predict(example_sequence)\n",
"\n",
"predicted_tags = mlb.inverse_transform((predictions > 0.5).astype(int))\n",
"\n",
"print(\"Input Title:\", example_title)\n",
"print(\"Predicted Tags:\", predicted_tags)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.10.9"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|