252 lines
6.6 KiB
Plaintext
252 lines
6.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import torch\n",
|
|
"import csv\n",
|
|
"from nltk.tokenize import word_tokenize\n",
|
|
"from gensim.models import Word2Vec\n",
|
|
"import gensim.downloader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class NeuralNetwork(torch.nn.Module):\n",
|
|
" def __init__(self, input_size, hidden_size, num_classes):\n",
|
|
" super(NeuralNetwork, self).__init__()\n",
|
|
" self.l1 = torch.nn.Linear(input_size, hidden_size)\n",
|
|
" self.l2 = torch.nn.Linear(hidden_size, num_classes)\n",
|
|
"\n",
|
|
" def forward(self, x):\n",
|
|
" x = self.l1(x)\n",
|
|
" x = torch.relu(x)\n",
|
|
" x = self.l2(x)\n",
|
|
" x = torch.sigmoid(x)\n",
|
|
" return x"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"col_names = ['content', 'id', 'label']\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Wczytanie danych...\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print('Wczytanie danych...')\n",
|
|
"# loading dataset\n",
|
|
"train_set_features = pd.read_table('train/in.tsv.xz', error_bad_lines=False, quoting=csv.QUOTE_NONE, header=None, names=col_names[:2])\n",
|
|
"train_set_labels = pd.read_table('train/expected.tsv', error_bad_lines=False, quoting=csv.QUOTE_NONE, header=None, names=col_names[2:])\n",
|
|
"dev_set = pd.read_table('dev-0/in.tsv.xz', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=col_names[:2])\n",
|
|
"test_set = pd.read_table('test-A/in.tsv.xz', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=col_names[:2])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Preprocessing danych...\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print('Preprocessing danych...')\n",
|
|
"# lowercase\n",
|
|
"X_train = train_set_features['content'].str.lower()\n",
|
|
"y_train = train_set_labels['label']"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"X_dev = dev_set['content'].str.lower()\n",
|
|
"X_test = test_set['content'].str.lower()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# tokenize\n",
|
|
"X_train = [word_tokenize(content) for content in X_train]\n",
|
|
"X_dev = [word_tokenize(content) for content in X_dev]\n",
|
|
"X_test = [word_tokenize(content) for content in X_test]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[==================================================] 100.0% 1662.8/1662.8MB downloaded\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# word2vec\n",
|
|
"word2vec = gensim.downloader.load('word2vec-google-news-300')\n",
|
|
"X_train = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_train]\n",
|
|
"X_dev = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_dev]\n",
|
|
"X_test = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_test]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"model = NeuralNetwork(300, 600, 1)\n",
|
|
"\n",
|
|
"criterion = torch.nn.BCELoss()\n",
|
|
"optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)\n",
|
|
"\n",
|
|
"batch_size = 10"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Trenowanie modelu...\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print('Trenowanie modelu...')\n",
|
|
"for epoch in range(6):\n",
|
|
" model.train()\n",
|
|
" for i in range(0, y_train.shape[0], batch_size):\n",
|
|
" X = X_train[i:i+batch_size]\n",
|
|
" X = torch.tensor(X)\n",
|
|
" y = y_train[i:i+batch_size]\n",
|
|
" y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)\n",
|
|
"\n",
|
|
" outputs = model(X.float())\n",
|
|
" loss = criterion(outputs, y)\n",
|
|
"\n",
|
|
" optimizer.zero_grad()\n",
|
|
" loss.backward()\n",
|
|
" optimizer.step()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Predykcje...\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print('Predykcje...')\n",
|
|
"dev_prediction = []\n",
|
|
"test_prediction = []\n",
|
|
"\n",
|
|
"model.eval()\n",
|
|
"with torch.no_grad():\n",
|
|
" for i in range(0, len(X_dev), batch_size):\n",
|
|
" X = X_dev[i:i+batch_size]\n",
|
|
" X = torch.tensor(X)\n",
|
|
"\n",
|
|
" outputs = model(X.float())\n",
|
|
"\n",
|
|
" prediction = (outputs > 0.5)\n",
|
|
" dev_prediction = dev_prediction + prediction.tolist()\n",
|
|
"\n",
|
|
" for i in range(0, len(X_test), batch_size):\n",
|
|
" X = X_test[i:i+batch_size]\n",
|
|
" X = torch.tensor(X)\n",
|
|
"\n",
|
|
" outputs = model(X.float())\n",
|
|
"\n",
|
|
" prediction = (outputs > 0.5)\n",
|
|
" test_prediction = test_prediction + prediction.tolist()\n",
|
|
"\n",
|
|
"dev_prediction = np.asarray(dev_prediction, dtype=np.int32)\n",
|
|
"test_prediction = np.asarray(test_prediction, dtype=np.int32)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"dev_prediction.tofile('./dev-0/out.tsv', sep='\\n')\n",
|
|
"test_prediction.tofile('./test-A/out.tsv', sep='\\n')"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"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": "3.8.5"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|