270 lines
7.1 KiB
Plaintext
270 lines
7.1 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import torch\n",
|
|
"from nltk.tokenize import word_tokenize\n",
|
|
"import gensim.downloader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#wczytywanie danych\n",
|
|
"x_train = pd.read_table('train/in.tsv', sep='\\t', error_bad_lines=False, quoting=3, header=None, names=['content', 'id'], usecols=['content'])\n",
|
|
"y_train = pd.read_table('train/expected.tsv', sep='\\t', error_bad_lines=False, quoting=3, header=None, names=['label'])\n",
|
|
"x_dev = pd.read_table('dev-0/in.tsv', sep='\\t', error_bad_lines=False, header=None, quoting=3, names=['content', 'id'], usecols=['content'])\n",
|
|
"x_test = pd.read_table('test-A/in.tsv', sep='\\t', error_bad_lines=False, header=None, quoting=3, names=['content', 'id'], usecols=['content'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"x_train = x_train.content.str.lower()\n",
|
|
"x_dev = x_dev.content.str.lower()\n",
|
|
"x_test = x_test.content.str.lower()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[nltk_data] Downloading package punkt to /home/tomasz/nltk_data...\n",
|
|
"[nltk_data] Unzipping tokenizers/punkt.zip.\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"True"
|
|
]
|
|
},
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"import nltk\n",
|
|
"nltk.download('punkt')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"word2vec = gensim.downloader.load(\"word2vec-google-news-300\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def document_vector(doc):\n",
|
|
" \"\"\"Create document vectors by averaging word vectors. Remove out-of-vocabulary words.\"\"\"\n",
|
|
" return np.mean([word2vec[w] for w in doc if w in word2vec] or [np.zeros(300)], axis=0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"x_train = [document_vector(doc) for doc in x_train]\n",
|
|
"x_dev = [document_vector(doc) for doc in x_dev]\n",
|
|
"x_test = [document_vector(doc) for doc in x_test]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class NeuralNetwork(torch.nn.Module): \n",
|
|
" def __init__(self, hidden_size):\n",
|
|
" super(NeuralNetwork, self).__init__()\n",
|
|
" self.l1 = torch.nn.Linear(300, hidden_size)\n",
|
|
" self.l2 = torch.nn.Linear(hidden_size, 1)\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": 10,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"hidden_size = 600\n",
|
|
"epochs = 5\n",
|
|
"batch_size = 15\n",
|
|
"model = NeuralNetwork(hidden_size)\n",
|
|
"criterion = torch.nn.BCELoss()\n",
|
|
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/home/tomasz/.local/lib/python3.8/site-packages/torch/autograd/__init__.py:130: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at /pytorch/c10/cuda/CUDAFunctions.cpp:100.)\n",
|
|
" Variable._execution_engine.run_backward(\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"for epoch in range(epochs):\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": 19,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"y_dev = []\n",
|
|
"y_test = []"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"NeuralNetwork(\n",
|
|
" (l1): Linear(in_features=300, out_features=600, bias=True)\n",
|
|
" (l2): Linear(in_features=600, out_features=1, bias=True)\n",
|
|
")"
|
|
]
|
|
},
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"model.eval()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 21,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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",
|
|
" outputs = model(X.float()) \n",
|
|
" prediction = (outputs > 0.5)\n",
|
|
" y_dev.extend(prediction)\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",
|
|
" outputs = model(X.float())\n",
|
|
" y = (outputs > 0.5)\n",
|
|
" y_test.extend(prediction)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 22,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"y_dev = np.asarray(y_dev, dtype=np.int32)\n",
|
|
"y_test = np.asarray(y_test, dtype=np.int32)\n",
|
|
"\n",
|
|
"y_dev = pd.DataFrame({'label':y_dev})\n",
|
|
"y_test = pd.DataFrame({'label':y_test})\n",
|
|
"\n",
|
|
"y_dev.to_csv(r'dev-0/out.tsv', sep='\\t', index=False, header=False)\n",
|
|
"y_test.to_csv(r'test-A/out.tsv', sep='\\t', index=False, header=False)"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.8.8"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|