File size: 16,548 Bytes
f802df1 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "976841dc",
"metadata": {},
"source": [
"## Preparación de un dataset\n",
"\n",
"Descargamos el dataset y lo preparamos para el entrenamiento. En el caso de ejemplo, usaremos toxic-teenage-relationships, que son frases que describen si un comporamiento es tóxico o sano. Tienen una campo de texto y un campo de etiqueta, que vale 1 si es tóxico y 0 si no lo es. Acumula 267 ejemplos de entrenamiento y 66 para testear."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "b9a1f255",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'label': 1,\n",
" 'text': 'Mi amiga no puede subir videos a tik tok porque su pareja no le deja'}"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from datasets import load_dataset\n",
"data_files = {\"train\": \"train.csv\", \"test\": \"test.csv\"}\n",
"dataset = load_dataset(\"toxic-teenage-relationships\", data_files=data_files, sep=\";\")\n",
"dataset['train'][100]"
]
},
{
"cell_type": "markdown",
"id": "6d0c740a",
"metadata": {},
"source": [
"Una vez cargado el dataset, se crea un tokenizador para procesar el texto e incluir una estrategia para el padding y el truncamiento. Para poder procesar el dataset en un solo paso, se utiliza el método dataset.map para preprocesar todo el dataset."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "01673605",
"metadata": {},
"outputs": [],
"source": [
"#en este ejemplo, utilizamos el AutoTokenizer\n",
"from transformers import AutoTokenizer\n",
"#from transformers import RobertaTokenizer\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\"PlanTL-GOB-ES/roberta-base-bne\")\n",
"\n",
"\n",
"def tokenize_function(examples):\n",
" return tokenizer(examples[\"text\"], padding=\"max_length\", truncation=True)\n",
"\n",
"\n",
"tokenized_datasets = dataset.map(tokenize_function, batched=True)"
]
},
{
"cell_type": "markdown",
"id": "08aacc14",
"metadata": {},
"source": [
"Ahora vamos a convertir el dataset en formator de TensorFlow. Para eso usamos DefaultDataCollator, que junta los tensores en un batch para que el modelo se entrene en él. Debemos especificar el argumento return_tensors=\"tf\". \n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "4a854ead",
"metadata": {},
"outputs": [],
"source": [
"from transformers import DefaultDataCollator\n",
"data_collator = DefaultDataCollator(return_tensors=\"tf\")"
]
},
{
"cell_type": "markdown",
"id": "06346bc5",
"metadata": {},
"source": [
"guardamos los dataset de train y de test\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "698a98ca",
"metadata": {},
"outputs": [],
"source": [
"train_dataset = tokenized_datasets[\"train\"]\n",
"eval_dataset = tokenized_datasets[\"test\"]"
]
},
{
"cell_type": "markdown",
"id": "38a6c521",
"metadata": {},
"source": [
"\n",
"\n",
"En primer lugar, vamos a crear el modelo\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "843f218d",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2023-08-29 20:57:53.276031: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n",
"2023-08-29 20:57:53.624006: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n",
"2023-08-29 20:57:53.683150: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n",
"2023-08-29 20:58:02.251496: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n",
"2023-08-29 20:58:02.566086: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n",
"Some weights of the PyTorch model were not used when initializing the TF 2.0 model TFRobertaForSequenceClassification: ['roberta.embeddings.position_ids']\n",
"- This IS expected if you are initializing TFRobertaForSequenceClassification from a PyTorch model trained on another task or with another architecture (e.g. initializing a TFBertForSequenceClassification model from a BertForPreTraining model).\n",
"- This IS NOT expected if you are initializing TFRobertaForSequenceClassification from a PyTorch model that you expect to be exactly identical (e.g. initializing a TFBertForSequenceClassification model from a BertForSequenceClassification model).\n",
"Some weights or buffers of the TF 2.0 model TFRobertaForSequenceClassification were not initialized from the PyTorch model and are newly initialized: ['classifier.dense.weight', 'classifier.dense.bias', 'classifier.out_proj.weight', 'classifier.out_proj.bias']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
]
}
],
"source": [
"import tensorflow as tf\n",
"from transformers import TFAutoModelForSequenceClassification\n",
"#también tiene una clase propia para el cabezal de clasificación, en este cogemos el general\n",
"#from transformers import TFRobertaForSequenceClassification\n",
"#Hay dos categorías, así que ponemos 2 etiquetas (0 sano 1 tóxico)\n",
"model = TFAutoModelForSequenceClassification.from_pretrained(\"PlanTL-GOB-ES/roberta-base-bne\", num_labels=2, from_pt=\"True\") "
]
},
{
"cell_type": "markdown",
"id": "54d206b4",
"metadata": {},
"source": [
"A hora vamos a convertir los datasets tokenizados en datasets de TensorFlow con el método .to_tf_dataset. Las entradas están en columns y la etiqueta en label_cols. El bach size es el número de ejemplos que se introducen en la red para que se entrene cada vez."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2ac843c2",
"metadata": {},
"outputs": [],
"source": [
"tf_train_dataset= train_dataset.to_tf_dataset(\n",
"columns=[\"attention_mask\", \"input_ids\"],\n",
"label_cols=\"labels\",\n",
"shuffle=True,\n",
"collate_fn=data_collator,\n",
"batch_size=8,\n",
")\n",
"tf_validation_dataset= eval_dataset.to_tf_dataset(\n",
"columns=[\"attention_mask\", \"input_ids\"],\n",
"label_cols=\"labels\",\n",
"shuffle=False,\n",
"collate_fn=data_collator,\n",
"batch_size=8,\n",
")\n"
]
},
{
"cell_type": "markdown",
"id": "d07f651a",
"metadata": {},
"source": [
"Compilamos"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "72e85cab",
"metadata": {},
"outputs": [],
"source": [
"model.compile(\n",
"optimizer=tf.keras.optimizers.Adam(learning_rate=5e-5),\n",
"loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
"metrics=tf.metrics.SparseCategoricalAccuracy(),\n",
")"
]
},
{
"cell_type": "markdown",
"id": "f103f0de",
"metadata": {},
"source": [
"## Cross-validation\n",
"Se definen los parámetros de K-flod cross valdation en primer lugar. Al ser un dataset pequeño el nmero de \n",
"splits será de 3."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "924886a1",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import KFold\n",
"from keras.callbacks import EarlyStopping\n",
"num_splits = 3\n",
"kf = KFold(num_splits, shuffle= True, random_state=42)\n"
]
},
{
"cell_type": "markdown",
"id": "651afcdb",
"metadata": {},
"source": [
"\n",
"Ahora definimos el ciclo de validación cruzada"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f96f6bae",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Fold 1\n",
"Epoch 1/10\n",
"23/23 [==============================] - 1316s 52s/step - loss: 0.6939 - sparse_categorical_accuracy: 0.5506 - val_loss: 0.6605 - val_sparse_categorical_accuracy: 0.7333\n",
"Epoch 2/10\n",
"23/23 [==============================] - 1170s 51s/step - loss: 0.5338 - sparse_categorical_accuracy: 0.7809 - val_loss: 0.6009 - val_sparse_categorical_accuracy: 0.7222\n",
"Epoch 3/10\n",
"23/23 [==============================] - 1088s 47s/step - loss: 0.2613 - sparse_categorical_accuracy: 0.9101 - val_loss: 0.7153 - val_sparse_categorical_accuracy: 0.7556\n",
"Epoch 4/10\n",
"23/23 [==============================] - 1214s 53s/step - loss: 0.1266 - sparse_categorical_accuracy: 0.9663 - val_loss: 1.1409 - val_sparse_categorical_accuracy: 0.6111\n",
"Train\n",
"Fold 1 - Loss: 0.224392369389534, Accuracy: 0.9269663095474243\n",
"Val\n",
"Fold 1 - Loss: 0.6009274125099182, Accuracy: 0.7222222089767456\n",
"Fold 2\n",
"Epoch 1/10\n",
"23/23 [==============================] - 1202s 52s/step - loss: 0.3649 - sparse_categorical_accuracy: 0.8547 - val_loss: 0.3039 - val_sparse_categorical_accuracy: 0.8989\n",
"Epoch 2/10\n",
"23/23 [==============================] - 1202s 53s/step - loss: 0.2095 - sparse_categorical_accuracy: 0.9385 - val_loss: 0.1956 - val_sparse_categorical_accuracy: 0.9326\n",
"Epoch 3/10\n",
"23/23 [==============================] - 1183s 52s/step - loss: 0.1031 - sparse_categorical_accuracy: 0.9665 - val_loss: 0.1776 - val_sparse_categorical_accuracy: 0.9213\n",
"Epoch 4/10\n",
"23/23 [==============================] - 1230s 54s/step - loss: 0.0676 - sparse_categorical_accuracy: 0.9832 - val_loss: 0.1551 - val_sparse_categorical_accuracy: 0.9326\n",
"Epoch 5/10\n",
"23/23 [==============================] - 1094s 48s/step - loss: 0.0161 - sparse_categorical_accuracy: 0.9944 - val_loss: 0.1954 - val_sparse_categorical_accuracy: 0.9438\n",
"Epoch 6/10\n",
"23/23 [==============================] - 925s 40s/step - loss: 0.0053 - sparse_categorical_accuracy: 1.0000 - val_loss: 0.2280 - val_sparse_categorical_accuracy: 0.9326\n",
"Train\n",
"Fold 2 - Loss: 0.01458701491355896, Accuracy: 0.994413435459137\n",
"Val\n",
"Fold 2 - Loss: 0.15508417785167694, Accuracy: 0.932584285736084\n",
"Fold 3\n",
"Epoch 1/10\n",
"23/23 [==============================] - 830s 36s/step - loss: 0.1665 - sparse_categorical_accuracy: 0.9441 - val_loss: 0.0837 - val_sparse_categorical_accuracy: 0.9888\n",
"Epoch 2/10\n",
"23/23 [==============================] - 665s 29s/step - loss: 0.0383 - sparse_categorical_accuracy: 0.9888 - val_loss: 0.0101 - val_sparse_categorical_accuracy: 1.0000\n",
"Epoch 3/10\n",
"23/23 [==============================] - 674s 29s/step - loss: 0.0777 - sparse_categorical_accuracy: 0.9888 - val_loss: 0.1603 - val_sparse_categorical_accuracy: 0.9551\n",
"Epoch 4/10\n",
"23/23 [==============================] - 623s 27s/step - loss: 0.1500 - sparse_categorical_accuracy: 0.9609 - val_loss: 0.3123 - val_sparse_categorical_accuracy: 0.8764\n",
"Train\n",
"Fold 3 - Loss: 0.07668939232826233, Accuracy: 0.9776536226272583\n",
"Val\n",
"Fold 3 - Loss: 0.010059510357677937, Accuracy: 1.0\n"
]
},
{
"ename": "NameError",
"evalue": "name 'np' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[9], line 52\u001b[0m\n\u001b[1;32m 49\u001b[0m val_accuracies\u001b[38;5;241m.\u001b[39mappend(val_scores[\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m 51\u001b[0m \u001b[38;5;66;03m#Calcular las medidas de las métricas\u001b[39;00m\n\u001b[0;32m---> 52\u001b[0m mean_train_loss \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241m.\u001b[39mmean(train_losses)\n\u001b[1;32m 53\u001b[0m mean_train_accuracy \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mmean(train_accuracies)\n\u001b[1;32m 54\u001b[0m mean_val_loss \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mmean(val_losses)\n",
"\u001b[0;31mNameError\u001b[0m: name 'np' is not defined"
]
}
],
"source": [
"#listas para almacenar las métricas en cada fold\n",
"train_losses=[]\n",
"train_accuracies=[]\n",
"val_losses = []\n",
"val_accuracies=[]\n",
"\n",
"for fold, (train_index, val_index) in enumerate(kf.split(train_dataset)):\n",
" print (f\"Fold {fold + 1}\")\n",
" \n",
" #crear conjuntos de entrenamiento y validación para esta iteración\n",
" train_fold_dataset = train_dataset.select(train_index)\n",
" val_fold_dataset = train_dataset.select(val_index)\n",
" \n",
" #convertir los datasets a Tensorflow\n",
" tf_train_fold_dataset= train_fold_dataset.to_tf_dataset(\n",
" columns=[\"attention_mask\", \"input_ids\"],\n",
" label_cols=\"labels\",\n",
" shuffle=True,\n",
" collate_fn=data_collator,\n",
" batch_size=8,\n",
" )\n",
" \n",
" tf_val_fold_dataset= val_fold_dataset.to_tf_dataset(\n",
" columns=[\"attention_mask\", \"input_ids\"],\n",
" label_cols=\"labels\",\n",
" shuffle=False,\n",
" collate_fn=data_collator,\n",
" batch_size=8,\n",
" )\n",
" \n",
" #early-stop\n",
" early_stop=EarlyStopping(monitor=\"val_loss\",patience=2,mode=\"auto\", restore_best_weights=True)\n",
" \n",
" #entrenar el modelo \n",
" model.fit(tf_train_fold_dataset, validation_data=tf_val_fold_dataset, epochs=10, callbacks=[early_stop])\n",
" \n",
" # Evaluar el modelo \n",
" train_scores = model.evaluate(tf_train_fold_dataset, verbose=0)\n",
" val_scores = model.evaluate(tf_val_fold_dataset, verbose=0)\n",
" print(\"Train\")\n",
" print(f\"Fold {fold + 1} - Loss: {train_scores[0]}, Accuracy: {train_scores[1]}\")\n",
" print(\"Val\")\n",
" print(f\"Fold {fold + 1} - Loss: {val_scores[0]}, Accuracy: {val_scores[1]}\")\n",
" \n",
" # Guardamos las cifras para después hacer la media\n",
" train_losses.append(train_scores[0])\n",
" train_accuracies.append(train_scores[1])\n",
" val_losses.append(val_scores[0])\n",
" val_accuracies.append(val_scores[1])\n",
" \n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "4113ab57",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mean Train Loss: 0.1052229255437851, Mean Train Accuracy: 0.9663444558779398\n",
"Mean Val Loss: 0.25535703357309103, Mean Val Accuracy: 0.8849354982376099\n"
]
}
],
"source": [
"import numpy as np\n",
"#Calcular las medidas de las métricas\n",
"mean_train_loss = np.mean(train_losses)\n",
"mean_train_accuracy = np.mean(train_accuracies)\n",
"mean_val_loss = np.mean(val_losses)\n",
"mean_val_accuracy = np. mean(val_accuracies)\n",
"\n",
"#Imprimir las medias de las métricas\n",
"print(f\"Mean Train Loss: {mean_train_loss}, Mean Train Accuracy: {mean_train_accuracy}\")\n",
"print(f\"Mean Val Loss: {mean_val_loss}, Mean Val Accuracy: {mean_val_accuracy}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0e0dff1a",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.8.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|