File size: 17,206 Bytes
b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 6bee2db b2898f0 |
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 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Airline Sentiment Prediction using BERT\n",
"\n",
"### Approach\n",
"First I analysed the data and I found that there was a huge imbalance in the dataset, to resolve this I used Textattack for augumentation of data.\n",
"Before the augumenting the dataset I used the following techniques to clean the data & reduce the noise:\n",
"- Removed the @usernames\n",
"- Removed the URLs\n",
"- Removed hashtags\n",
"- Replacement of emojis with their meaning\n",
"\n",
"After cleaning the data I used EasyDataAugment of Textattack to augment the data, augmenting the data helped me to increase the accuracy of the model by more than 3%. I also tried using Clare(It replaces the words with their synonyms) but that was very resource intensive & it was taking very long to get output.\n",
"\n",
"### Model\n",
"Since, this was a binary classification task I used BERT for training the model. I used the pretrained BERT model from Huggingface transformers library. I used the BERT model with the following parameters:\n",
"- BERT-base-uncased\n",
"- Max length of the input sequence: 128\n",
"- Learning rate: 3e-5\n",
"- Batch size: 32\n",
"\n",
"### Results\n",
"The dataset was split into 80:20 ratio for training & validation.\n",
"I got the following results after training the model:\n",
"Training loss: 0.0137\n",
"Validation loss: 0.1209\n",
"Training accuracy: 0.9955\n",
"Validation accuracy: 0.9794\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"========================================================================================================================================"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Install the required libraries"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "nwuC7017BwyD"
},
"outputs": [],
"source": [
"%pip install transformers\n",
"%pip install emoji\n",
"%pip install numpy pandas\n",
"%pip install scikit-learn\n",
"%pip install textattack"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Importing the libraries"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "iM2I9UEjm_pE"
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from pprint import pprint"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Reading the data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 676
},
"id": "mrnzcvkzm_pF",
"outputId": "61550835-27fc-4049-f3a3-f9ab9e1ba1bb"
},
"outputs": [],
"source": [
"df = pd.read_csv(\"airline_sentiment_analysis.csv\")\n",
"df.head(20)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Assigning 1 to positive sentiment and 0 to negative sentiment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 676
},
"id": "Jbl-wjpWm_pG",
"outputId": "19c8b0ca-4506-4960-d588-505feecf678e"
},
"outputs": [],
"source": [
"for label in df['airline_sentiment']:\n",
" if label == 'positive':\n",
" df['airline_sentiment'].replace(label, 1, inplace=True)\n",
" elif label == 'negative':\n",
" df['airline_sentiment'].replace(label, 0, inplace=True)\n",
"df.head(20)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Remove the @usernames, URLs, hashtags & Replace the emojis with their meaning"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 676
},
"id": "ApZHkGw2m_pG",
"outputId": "330f44ff-3314-4392-eef4-69f2994b1cae"
},
"outputs": [],
"source": [
"\n",
"import emoji\n",
"for i,r in df.iterrows():\n",
" \n",
" df.loc[i,\"text\"] = emoji.demojize(df.loc[i,\"text\"])\n",
" df.loc[i,\"text\"] = df.loc[i,\"text\"].replace(\":\",\" \")\n",
" df.loc[i,\"text\"] = ' '.join(df.loc[i,\"text\"].split())\n",
"\n",
"df['text'] = df['text'].str.replace(\"@[A-Za-z0-9]+\", \"\",regex=True)\n",
"df['text'] = df['text'].str.replace(\"#\", \"\",regex=True)\n",
"df['text'] = df['text'].str.replace(\"https?://[A-Za-z0-9./]+\", \"\",regex=True)\n",
"df['text'] = df['text'].str.replace(\"[^a-zA-Z.!?']\", \" \",regex=True)\n",
"\n",
"\n",
"df.head(20)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Augumenting Positive Sentiment using EasyDataAugment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lNr4OWDaGYww"
},
"outputs": [],
"source": [
"positive_feedback = (df.loc[df[\"airline_sentiment\"] == 1])[\"text\"]\n",
"positive_feedback = positive_feedback.tolist()\n",
"# pprint(positive_feedback)\n",
"\n",
"from textattack.augmentation import EasyDataAugmenter\n",
"esy_aug = EasyDataAugmenter()\n",
"aug_list = []\n",
"for sen in positive_feedback:\n",
" aug_list.append(esy_aug.augment(sen))\n",
"serial_list = []\n",
"for l in aug_list:\n",
" for sen in l:\n",
" serial_list.append(sen)\n",
"df = df.drop(df.columns[[0]],axis=1)\n",
"\n",
"df2 = pd.DataFrame(list(zip([1]*len(serial_list),serial_list)),columns=[\"airline_sentiment\",\"text\"])\n",
"\n",
"df = pd.concat([df,df2])\n",
"\n",
"df.to_csv(\"modified.csv\") #save the modified dataset\n",
"df.head()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Split dataset into train & validation in 80:20 ratio"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "MrynUQ9Xm_pG"
},
"outputs": [],
"source": [
"# split the data into train and test\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"train, test = train_test_split(df, test_size=0.2, random_state=42)\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Initalise the BERT model & tokenizer"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "MambfTNXm_pG",
"outputId": "f0e11223-8e74-445a-8cdc-cc8492f26b14"
},
"outputs": [],
"source": [
"from transformers import BertTokenizer, TFBertForSequenceClassification\n",
"from transformers import InputExample, InputFeatures\n",
"import tensorflow as tf\n",
"\n",
"model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased')\n",
"tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Utility function to convert the data into the format required by BERT"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "uxgZ7GsEm_pH"
},
"outputs": [],
"source": [
"def convert_data_to_examples(train, test, DATA_COLUMN, LABEL_COLUMN): \n",
" train_InputExamples = train.apply(lambda x: InputExample(guid=None, # Globally unique ID for bookkeeping, unused in this case\n",
" text_a = x[DATA_COLUMN], \n",
" text_b = None,\n",
" label = x[LABEL_COLUMN]), axis = 1)\n",
"\n",
" validation_InputExamples = test.apply(lambda x: InputExample(guid=None, # Globally unique ID for bookkeeping, unused in this case\n",
" text_a = x[DATA_COLUMN], \n",
" text_b = None,\n",
" label = x[LABEL_COLUMN]), axis = 1)\n",
" \n",
" return train_InputExamples, validation_InputExamples\n",
"\n",
" \n",
"def convert_examples_to_tf_dataset(examples, tokenizer, max_length=128):\n",
" features = [] # -> will hold InputFeatures to be converted later\n",
"\n",
" for e in examples:\n",
" # Documentation is really strong for this method, so please take a look at it\n",
" input_dict = tokenizer.encode_plus(\n",
" e.text_a,\n",
" add_special_tokens=True,\n",
" max_length=max_length, # truncates if len(s) > max_length\n",
" return_token_type_ids=True,\n",
" return_attention_mask=True,\n",
" pad_to_max_length=True, # pads to the right by default # CHECK THIS for pad_to_max_length\n",
" truncation=True\n",
" )\n",
"\n",
" input_ids, token_type_ids, attention_mask = (input_dict[\"input_ids\"],\n",
" input_dict[\"token_type_ids\"], input_dict['attention_mask'])\n",
"\n",
" features.append(\n",
" InputFeatures(\n",
" input_ids=input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids, label=e.label\n",
" )\n",
" )\n",
"\n",
" def gen():\n",
" for f in features:\n",
" yield (\n",
" {\n",
" \"input_ids\": f.input_ids,\n",
" \"attention_mask\": f.attention_mask,\n",
" \"token_type_ids\": f.token_type_ids,\n",
" },\n",
" f.label,\n",
" )\n",
"\n",
" return tf.data.Dataset.from_generator(\n",
" gen,\n",
" ({\"input_ids\": tf.int32, \"attention_mask\": tf.int32, \"token_type_ids\": tf.int32}, tf.int64),\n",
" (\n",
" {\n",
" \"input_ids\": tf.TensorShape([None]),\n",
" \"attention_mask\": tf.TensorShape([None]),\n",
" \"token_type_ids\": tf.TensorShape([None]),\n",
" },\n",
" tf.TensorShape([]),\n",
" ),\n",
" )\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"BERT model for training"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "tPsHpWhJm_pH",
"outputId": "a9f7b2b8-d0bb-474b-d91a-25f0c8a40905"
},
"outputs": [],
"source": [
"DATA_COLUMN = 'text'\n",
"LABEL_COLUMN = 'airline_sentiment'\n",
"\n",
"\n",
"train_InputExamples, validation_InputExamples = convert_data_to_examples(train, test, DATA_COLUMN, LABEL_COLUMN)\n",
"\n",
"train_data = convert_examples_to_tf_dataset(list(train_InputExamples), tokenizer)\n",
"train_data = train_data.shuffle(100).batch(32).repeat(2)\n",
"\n",
"validation_data = convert_examples_to_tf_dataset(list(validation_InputExamples), tokenizer)\n",
"validation_data = validation_data.batch(32)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GDcgmUOCm_pI",
"outputId": "2f262b78-65f4-4cfc-deb3-a51d2b499eab"
},
"outputs": [],
"source": [
"model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=3e-5, epsilon=1e-08, clipnorm=1.0), \n",
" loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), \n",
" metrics=[tf.keras.metrics.SparseCategoricalAccuracy('accuracy')])\n",
"\n",
"model.fit(train_data, epochs=2, validation_data=validation_data)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Saving the trained weights"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "K3pzOJS8R1dx"
},
"outputs": [],
"source": [
"model.save_weights(\"weights.h5\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Inference: Predicting the sentiment of the tweet"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "BLcz_yKOr38C",
"outputId": "a56245b6-395a-4ff1-aeba-ab30c98cedb1"
},
"outputs": [],
"source": [
"pred_data = [\"@abc The flight was great\", \"@abc ☹️\",\"🎊 it was bad experience\"]\n",
"pred_data = pd.DataFrame(pred_data)\n",
"\n",
"\n",
"for i,r in pred_data.iterrows():\n",
" pred_data.loc[i,0] = emoji.demojize(r[0])\n",
" pred_data.loc[i,0] = r[0].replace(\":\",\" \")\n",
" pred_data.loc[i,0] = ' '.join(r[0].split())\n",
"\n",
"\n",
"pred_data[0] = pred_data[0].str.replace(\"@[A-Za-z0-9]+\", \"\",regex=True)\n",
"pred_data[0] = pred_data[0].str.replace(\"#\", \"\",regex=True)\n",
"pred_data[0] = pred_data[0].str.replace(\"https?://[A-Za-z0-9./]+\", \"\",regex=True)\n",
"pred_data[0] = pred_data[0].str.replace(\"[^a-zA-Z.!?']\", \" \",regex=True)\n",
"\n",
"pred_data.head()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "lrTfXZzLsKd6",
"outputId": "0f2c6e24-bc62-45a6-bc71-9b6918ab961e"
},
"outputs": [],
"source": [
"pred_data = pred_data[0].values.tolist()\n",
"print(pred_data)\n",
"tf_batch = tokenizer(pred_data, max_length=128, padding=True, truncation=True, return_tensors='tf')\n",
"tf_outputs = model(tf_batch)\n",
"tf_predictions = tf.nn.softmax(tf_outputs[0], axis=-1)\n",
"labels = ['Negative','Positive']\n",
"label = tf.argmax(tf_predictions, axis=1)\n",
"label = label.numpy()\n",
"for i in range(len(pred_data)):\n",
" print(pred_data[i], \": \\n\", labels[label[i]])"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"provenance": []
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "venv",
"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 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]"
},
"vscode": {
"interpreter": {
"hash": "497fb9213e55408ad8b1ca9a37e341ac93888d86a532670599a03e0c8054f45a"
}
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|