452 lines
19 KiB
Plaintext
452 lines
19 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Importy"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"metadata": {
|
|
"collapsed": true,
|
|
"ExecuteTime": {
|
|
"start_time": "2024-05-19T18:21:27.211216Z",
|
|
"end_time": "2024-05-19T18:21:27.318205Z"
|
|
}
|
|
},
|
|
"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": 19,
|
|
"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 load_labels(file_path):\n",
|
|
" labels = []\n",
|
|
" with open(file_path, 'r', encoding='utf-8') as f:\n",
|
|
" for line in f:\n",
|
|
" labels.append(int(line.strip()))\n",
|
|
" return np.array(labels)\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": "2024-05-19T18:21:27.231204Z",
|
|
"end_time": "2024-05-19T18:21:27.377342Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Wczytywanie danych treningowych oraz testowych"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 20,
|
|
"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",
|
|
"dev_labels = load_labels('dev-0/expected.tsv')\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": "2024-05-19T18:21:27.241222Z",
|
|
"end_time": "2024-05-19T18:21:31.160229Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Wczytywanie modelu word2vec"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 21,
|
|
"outputs": [],
|
|
"source": [
|
|
"word2vec_model = KeyedVectors.load(\"word2vec_100_3_polish.bin\")"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false,
|
|
"ExecuteTime": {
|
|
"start_time": "2024-05-19T18:21:31.161230Z",
|
|
"end_time": "2024-05-19T18:21:54.895038Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Przekształcenie danych na wektory"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 22,
|
|
"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": "2024-05-19T18:21:54.900047Z",
|
|
"end_time": "2024-05-19T18:21:54.909040Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 23,
|
|
"outputs": [],
|
|
"source": [
|
|
"X_train = np.array([text_to_vector(text, word2vec_model) for text in train_data['text']])\n",
|
|
"y_train = np.array(train_data['label'])\n",
|
|
"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']])"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false,
|
|
"ExecuteTime": {
|
|
"start_time": "2024-05-19T18:21:54.913039Z",
|
|
"end_time": "2024-05-19T18:22:03.870813Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Model"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 24,
|
|
"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": "2024-05-19T18:22:03.872859Z",
|
|
"end_time": "2024-05-19T18:22:04.122687Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 25,
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Epoch 1/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m6s\u001B[0m 2ms/step - accuracy: 0.8769 - loss: 0.4540 - val_accuracy: 0.9310 - val_loss: 0.2222\n",
|
|
"Epoch 2/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9270 - loss: 0.2362 - val_accuracy: 0.9303 - val_loss: 0.2106\n",
|
|
"Epoch 3/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9320 - loss: 0.2191 - val_accuracy: 0.9415 - val_loss: 0.1890\n",
|
|
"Epoch 4/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9306 - loss: 0.2139 - val_accuracy: 0.9406 - val_loss: 0.1850\n",
|
|
"Epoch 5/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9322 - loss: 0.2098 - val_accuracy: 0.9395 - val_loss: 0.1883\n",
|
|
"Epoch 6/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9325 - loss: 0.2074 - val_accuracy: 0.9404 - val_loss: 0.1814\n",
|
|
"Epoch 7/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9320 - loss: 0.2093 - val_accuracy: 0.9441 - val_loss: 0.1810\n",
|
|
"Epoch 8/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9326 - loss: 0.2094 - val_accuracy: 0.9441 - val_loss: 0.1804\n",
|
|
"Epoch 9/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9327 - loss: 0.2064 - val_accuracy: 0.9400 - val_loss: 0.1807\n",
|
|
"Epoch 10/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9319 - loss: 0.2073 - val_accuracy: 0.9408 - val_loss: 0.1799\n",
|
|
"Epoch 11/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9324 - loss: 0.2061 - val_accuracy: 0.9391 - val_loss: 0.1826\n",
|
|
"Epoch 12/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9320 - loss: 0.2066 - val_accuracy: 0.9433 - val_loss: 0.1814\n",
|
|
"Epoch 13/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9325 - loss: 0.2066 - val_accuracy: 0.9382 - val_loss: 0.1882\n",
|
|
"Epoch 14/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9330 - loss: 0.2045 - val_accuracy: 0.9406 - val_loss: 0.1813\n",
|
|
"Epoch 15/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9316 - loss: 0.2106 - val_accuracy: 0.9408 - val_loss: 0.1831\n",
|
|
"Epoch 16/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9338 - loss: 0.2036 - val_accuracy: 0.9384 - val_loss: 0.1862\n",
|
|
"Epoch 17/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9330 - loss: 0.2063 - val_accuracy: 0.9398 - val_loss: 0.1862\n",
|
|
"Epoch 18/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9320 - loss: 0.2102 - val_accuracy: 0.9408 - val_loss: 0.1802\n",
|
|
"Epoch 19/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9323 - loss: 0.2059 - val_accuracy: 0.9397 - val_loss: 0.1794\n",
|
|
"Epoch 20/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9338 - loss: 0.2039 - val_accuracy: 0.9431 - val_loss: 0.1728\n",
|
|
"Epoch 21/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9319 - loss: 0.2102 - val_accuracy: 0.9415 - val_loss: 0.1787\n",
|
|
"Epoch 22/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9351 - loss: 0.2034 - val_accuracy: 0.9433 - val_loss: 0.1780\n",
|
|
"Epoch 23/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9330 - loss: 0.2059 - val_accuracy: 0.9404 - val_loss: 0.1759\n",
|
|
"Epoch 24/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 2ms/step - accuracy: 0.9335 - loss: 0.2042 - val_accuracy: 0.9409 - val_loss: 0.1789\n",
|
|
"Epoch 25/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9341 - loss: 0.2052 - val_accuracy: 0.9389 - val_loss: 0.1813\n",
|
|
"Epoch 26/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9322 - loss: 0.2078 - val_accuracy: 0.9406 - val_loss: 0.1813\n",
|
|
"Epoch 27/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9319 - loss: 0.2069 - val_accuracy: 0.9283 - val_loss: 0.2017\n",
|
|
"Epoch 28/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9324 - loss: 0.2083 - val_accuracy: 0.9409 - val_loss: 0.1883\n",
|
|
"Epoch 29/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9326 - loss: 0.2054 - val_accuracy: 0.9411 - val_loss: 0.1791\n",
|
|
"Epoch 30/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9333 - loss: 0.2041 - val_accuracy: 0.9419 - val_loss: 0.1769\n",
|
|
"Epoch 31/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9343 - loss: 0.2029 - val_accuracy: 0.9439 - val_loss: 0.1756\n",
|
|
"Epoch 32/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m5s\u001B[0m 1ms/step - accuracy: 0.9330 - loss: 0.2060 - val_accuracy: 0.9384 - val_loss: 0.1805\n",
|
|
"Epoch 33/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9333 - loss: 0.2023 - val_accuracy: 0.9395 - val_loss: 0.1780\n",
|
|
"Epoch 34/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9347 - loss: 0.2025 - val_accuracy: 0.9408 - val_loss: 0.1806\n",
|
|
"Epoch 35/35\n",
|
|
"\u001B[1m3067/3067\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m4s\u001B[0m 1ms/step - accuracy: 0.9315 - loss: 0.2038 - val_accuracy: 0.9419 - val_loss: 0.1762\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": "<keras.src.callbacks.history.History at 0x280fa5dcb80>"
|
|
},
|
|
"execution_count": 25,
|
|
"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_dev, dev_labels))"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false,
|
|
"ExecuteTime": {
|
|
"start_time": "2024-05-19T18:22:04.124694Z",
|
|
"end_time": "2024-05-19T18:24:44.659379Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Ewaluacja modelu na zbiorze walidacyjnym"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 26,
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001B[1m171/171\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 814us/step - accuracy: 0.9413 - loss: 0.1863\n",
|
|
"Accuracy on validation set: 0.9418562054634094\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"loss, accuracy = model.evaluate(X_dev, dev_labels)\n",
|
|
"print(f'Accuracy on validation set: {accuracy}')"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false,
|
|
"ExecuteTime": {
|
|
"start_time": "2024-05-19T18:24:44.661382Z",
|
|
"end_time": "2024-05-19T18:24:44.864668Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Predykcja na danych walidacyjnych oraz testowych"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 27,
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001B[1m171/171\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 900us/step\n",
|
|
"\u001B[1m171/171\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 765us/step\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"dev_predictions = model.predict(X_dev)\n",
|
|
"test_predictions = model.predict(X_test)"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false,
|
|
"ExecuteTime": {
|
|
"start_time": "2024-05-19T18:24:44.863671Z",
|
|
"end_time": "2024-05-19T18:24:45.395043Z"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"### Zapis wyników"
|
|
],
|
|
"metadata": {
|
|
"collapsed": false
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 28,
|
|
"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": "2024-05-19T18:24:45.398007Z",
|
|
"end_time": "2024-05-19T18:24:45.438575Z"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"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
|
|
}
|