469 lines
19 KiB
Plaintext
469 lines
19 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Importy"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 6,
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": true,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:08:45.407869Z",
|
||
|
|
"end_time": "2024-05-19T18:08:45.510869Z"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import gzip\n",
|
||
|
|
"import math\n",
|
||
|
|
"import re\n",
|
||
|
|
"\n",
|
||
|
|
"import numpy as np\n",
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"from gensim.models import KeyedVectors\n",
|
||
|
|
"from keras.layers import Dense, Dropout\n",
|
||
|
|
"from keras.models import Sequential\n",
|
||
|
|
"from keras.regularizers import l2\n",
|
||
|
|
"from sklearn.model_selection import train_test_split"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Wczytywanie oraz czyszczenie danych"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 7,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def load_and_filter_data(file_path):\n",
|
||
|
|
" texts = []\n",
|
||
|
|
" labels = []\n",
|
||
|
|
" with gzip.open(file_path, 'rt', encoding='utf-8') as f:\n",
|
||
|
|
" for line in f:\n",
|
||
|
|
" parts = line.strip().split('\\t')\n",
|
||
|
|
" if len(parts) == 2:\n",
|
||
|
|
" labels.append(int(parts[0]))\n",
|
||
|
|
" texts.append(parts[1])\n",
|
||
|
|
" data = pd.DataFrame({'label': labels, 'text': texts})\n",
|
||
|
|
" return data\n",
|
||
|
|
"\n",
|
||
|
|
"def load_and_filter_tsv(file_path):\n",
|
||
|
|
" texts = []\n",
|
||
|
|
" with open(file_path, 'r', encoding='utf-8') as f:\n",
|
||
|
|
" for line in f:\n",
|
||
|
|
" parts = line.strip().split('\\t')\n",
|
||
|
|
" if len(parts) == 1:\n",
|
||
|
|
" texts.append(parts[0])\n",
|
||
|
|
" data = pd.DataFrame({'text': texts})\n",
|
||
|
|
" return data\n",
|
||
|
|
"\n",
|
||
|
|
"def clean_text(text):\n",
|
||
|
|
" text = text.lower()\n",
|
||
|
|
" text = re.sub(r'\\d+', '', text)\n",
|
||
|
|
" text = re.sub(r'\\s+', ' ', text)\n",
|
||
|
|
" text = re.sub(r'[^\\w\\s]', '', text)\n",
|
||
|
|
" return text"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:08:45.425869Z",
|
||
|
|
"end_time": "2024-05-19T18:08:45.579869Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Wczytywanie danych treningowych oraz testowych"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 8,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"train_data = load_and_filter_data('train/train.tsv.gz')\n",
|
||
|
|
"train_data['text'] = train_data['text'].apply(clean_text)\n",
|
||
|
|
"dev_data = load_and_filter_tsv('dev-0/in.tsv')\n",
|
||
|
|
"dev_data['text'] = dev_data['text'].apply(clean_text)\n",
|
||
|
|
"test_data = load_and_filter_tsv('test-A/in.tsv')\n",
|
||
|
|
"test_data['text'] = test_data['text'].apply(clean_text)"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:08:45.435869Z",
|
||
|
|
"end_time": "2024-05-19T18:08:48.741093Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Wczytywanie modelu word2vec"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 9,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"word2vec_model = KeyedVectors.load(\"word2vec_100_3_polish.bin\")"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:08:48.743093Z",
|
||
|
|
"end_time": "2024-05-19T18:09:04.607384Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Przekształcenie danych na wektory"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 10,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def text_to_vector(text, model):\n",
|
||
|
|
" words = text.split()\n",
|
||
|
|
" word_vecs = [model[word] for word in words if word in model]\n",
|
||
|
|
" return np.mean(word_vecs, axis=0) if len(word_vecs) > 0 else np.zeros(model.vector_size)"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:09:04.609383Z",
|
||
|
|
"end_time": "2024-05-19T18:09:04.621383Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 11,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"X = np.array([text_to_vector(text, word2vec_model) for text in train_data['text']])\n",
|
||
|
|
"y = np.array(train_data['label'])"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:09:04.623384Z",
|
||
|
|
"end_time": "2024-05-19T18:09:12.703303Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Dodatkowy podział danych na zbiór treningowy oraz walidacyjny"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 12,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:09:12.705305Z",
|
||
|
|
"end_time": "2024-05-19T18:09:12.749303Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Model"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 13,
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"C:\\Users\\adamw\\PycharmProjects\\pythonProject\\venv\\lib\\site-packages\\keras\\src\\layers\\core\\dense.py:86: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
|
||
|
|
" super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"model = Sequential()\n",
|
||
|
|
"model.add(Dense(256, input_dim=X_train.shape[1], activation='relu', kernel_regularizer=l2(0.001)))\n",
|
||
|
|
"model.add(Dropout(0.5))\n",
|
||
|
|
"model.add(Dense(128, activation='relu', kernel_regularizer=l2(0.001)))\n",
|
||
|
|
"model.add(Dropout(0.5))\n",
|
||
|
|
"model.add(Dense(1, activation='sigmoid'))"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:09:12.750302Z",
|
||
|
|
"end_time": "2024-05-19T18:09:12.954821Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 14,
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Epoch 1/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.8631 - loss: 0.4892 - val_accuracy: 0.9238 - val_loss: 0.2468\n",
|
||
|
|
"Epoch 2/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9240 - loss: 0.2481 - val_accuracy: 0.9367 - val_loss: 0.2040\n",
|
||
|
|
"Epoch 3/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9289 - loss: 0.2213 - val_accuracy: 0.9377 - val_loss: 0.1938\n",
|
||
|
|
"Epoch 4/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9293 - loss: 0.2195 - val_accuracy: 0.9417 - val_loss: 0.1869\n",
|
||
|
|
"Epoch 5/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9328 - loss: 0.2120 - val_accuracy: 0.9364 - val_loss: 0.1930\n",
|
||
|
|
"Epoch 6/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9302 - loss: 0.2114 - val_accuracy: 0.9384 - val_loss: 0.1898\n",
|
||
|
|
"Epoch 7/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9312 - loss: 0.2134 - val_accuracy: 0.9438 - val_loss: 0.1803\n",
|
||
|
|
"Epoch 8/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9316 - loss: 0.2091 - val_accuracy: 0.9413 - val_loss: 0.1822\n",
|
||
|
|
"Epoch 9/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9330 - loss: 0.2104 - val_accuracy: 0.9228 - val_loss: 0.2174\n",
|
||
|
|
"Epoch 10/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9325 - loss: 0.2093 - val_accuracy: 0.9402 - val_loss: 0.1839\n",
|
||
|
|
"Epoch 11/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9298 - loss: 0.2123 - val_accuracy: 0.9411 - val_loss: 0.1834\n",
|
||
|
|
"Epoch 12/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9323 - loss: 0.2071 - val_accuracy: 0.9445 - val_loss: 0.1774\n",
|
||
|
|
"Epoch 13/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9326 - loss: 0.2089 - val_accuracy: 0.9439 - val_loss: 0.1786\n",
|
||
|
|
"Epoch 14/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9329 - loss: 0.2050 - val_accuracy: 0.9387 - val_loss: 0.1866\n",
|
||
|
|
"Epoch 15/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9331 - loss: 0.2035 - val_accuracy: 0.9447 - val_loss: 0.1815\n",
|
||
|
|
"Epoch 16/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9326 - loss: 0.2078 - val_accuracy: 0.9352 - val_loss: 0.1954\n",
|
||
|
|
"Epoch 17/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9331 - loss: 0.2059 - val_accuracy: 0.9436 - val_loss: 0.1762\n",
|
||
|
|
"Epoch 18/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9332 - loss: 0.2050 - val_accuracy: 0.9437 - val_loss: 0.1765\n",
|
||
|
|
"Epoch 19/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9343 - loss: 0.2038 - val_accuracy: 0.9452 - val_loss: 0.1788\n",
|
||
|
|
"Epoch 20/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9343 - loss: 0.2037 - val_accuracy: 0.9368 - val_loss: 0.1887\n",
|
||
|
|
"Epoch 21/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9326 - loss: 0.2054 - val_accuracy: 0.9435 - val_loss: 0.1773\n",
|
||
|
|
"Epoch 22/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9327 - loss: 0.2059 - val_accuracy: 0.9417 - val_loss: 0.1813\n",
|
||
|
|
"Epoch 23/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9333 - loss: 0.2041 - val_accuracy: 0.9405 - val_loss: 0.1809\n",
|
||
|
|
"Epoch 24/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9340 - loss: 0.2045 - val_accuracy: 0.9393 - val_loss: 0.1840\n",
|
||
|
|
"Epoch 25/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9324 - loss: 0.2046 - val_accuracy: 0.9405 - val_loss: 0.1833\n",
|
||
|
|
"Epoch 26/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9338 - loss: 0.2030 - val_accuracy: 0.9404 - val_loss: 0.1825\n",
|
||
|
|
"Epoch 27/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9346 - loss: 0.2051 - val_accuracy: 0.9385 - val_loss: 0.1875\n",
|
||
|
|
"Epoch 28/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9306 - loss: 0.2091 - val_accuracy: 0.9431 - val_loss: 0.1784\n",
|
||
|
|
"Epoch 29/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9352 - loss: 0.2033 - val_accuracy: 0.9396 - val_loss: 0.1877\n",
|
||
|
|
"Epoch 30/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 2ms/step - accuracy: 0.9333 - loss: 0.2037 - val_accuracy: 0.9403 - val_loss: 0.1808\n",
|
||
|
|
"Epoch 31/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9313 - loss: 0.2090 - val_accuracy: 0.9413 - val_loss: 0.1783\n",
|
||
|
|
"Epoch 32/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9340 - loss: 0.2063 - val_accuracy: 0.9428 - val_loss: 0.1815\n",
|
||
|
|
"Epoch 33/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9324 - loss: 0.2029 - val_accuracy: 0.9405 - val_loss: 0.1822\n",
|
||
|
|
"Epoch 34/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9328 - loss: 0.2046 - val_accuracy: 0.9411 - val_loss: 0.1824\n",
|
||
|
|
"Epoch 35/35\n",
|
||
|
|
"\u001B[1m2454/2454\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m3s\u001B[0m 1ms/step - accuracy: 0.9322 - loss: 0.2063 - val_accuracy: 0.9414 - val_loss: 0.1820\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": "<keras.src.callbacks.history.History at 0x2809ceeab60>"
|
||
|
|
},
|
||
|
|
"execution_count": 14,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
|
||
|
|
"model.fit(X_train, y_train, epochs=35, batch_size=32, validation_data=(X_val, y_val))"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:09:12.957822Z",
|
||
|
|
"end_time": "2024-05-19T18:11:23.248486Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Ewaluacja modelu na zbiorze walidacyjnym"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 15,
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\u001B[1m614/614\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 766us/step - accuracy: 0.9409 - loss: 0.1851\n",
|
||
|
|
"Accuracy on validation set: 0.9413533210754395\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"loss, accuracy = model.evaluate(X_val, y_val)\n",
|
||
|
|
"print(f'Accuracy on validation set: {accuracy}')"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:11:23.208454Z",
|
||
|
|
"end_time": "2024-05-19T18:11:23.753363Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Predykcja na danych walidacyjnych oraz testowych"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 16,
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\u001B[1m171/171\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 882us/step\n",
|
||
|
|
"\u001B[1m171/171\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 700us/step\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"X_dev = np.array([text_to_vector(text, word2vec_model) for text in dev_data['text']])\n",
|
||
|
|
"X_test = np.array([text_to_vector(text, word2vec_model) for text in test_data['text']])\n",
|
||
|
|
"\n",
|
||
|
|
"dev_predictions = model.predict(X_dev)\n",
|
||
|
|
"test_predictions = model.predict(X_test)"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:11:23.754367Z",
|
||
|
|
"end_time": "2024-05-19T18:11:25.114539Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"source": [
|
||
|
|
"### Zapis wyników"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 17,
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"dev_predictions = (dev_predictions > 0.5).astype(int)\n",
|
||
|
|
"test_predictions = (test_predictions > 0.5).astype(int)\n",
|
||
|
|
"\n",
|
||
|
|
"pd.DataFrame(dev_predictions).to_csv('dev-0/out.tsv', sep='\\t', header=False, index=False)\n",
|
||
|
|
"pd.DataFrame(test_predictions).to_csv('test-A/out.tsv', sep='\\t', header=False, index=False)"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"collapsed": false,
|
||
|
|
"ExecuteTime": {
|
||
|
|
"start_time": "2024-05-19T18:11:25.117540Z",
|
||
|
|
"end_time": "2024-05-19T18:11:25.149572Z"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python 3",
|
||
|
|
"language": "python",
|
||
|
|
"name": "python3"
|
||
|
|
},
|
||
|
|
"language_info": {
|
||
|
|
"codemirror_mode": {
|
||
|
|
"name": "ipython",
|
||
|
|
"version": 2
|
||
|
|
},
|
||
|
|
"file_extension": ".py",
|
||
|
|
"mimetype": "text/x-python",
|
||
|
|
"name": "python",
|
||
|
|
"nbconvert_exporter": "python",
|
||
|
|
"pygments_lexer": "ipython2",
|
||
|
|
"version": "2.7.6"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 0
|
||
|
|
}
|