s444380/paranormal-or-skeptic-ISI-public
1
0
Fork 0
forked from kubapok/paranormal-or-skeptic-ISI-public
Code Issues Pull Requests Projects Releases Wiki Activity

Neural network with word2vec

Browse Source
This commit is contained in:
Kamil Guttmann 2022-05-23 21:30:07 +02:00
parent b217d37450
commit 7f75f2e2e2
3 changed files with 1660 additions and 1441 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1470
dev-0/out.tsv
View File

File diff suppressed because it is too large Load Diff

219
pytorch_classifier.ipynb Normal file
View File

@ -0,0 +1,219 @@
{
"metadata": {
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.5-final"
},
"orig_nbformat": 2,
"kernelspec": {
"name": "python3",
"display_name": "Python 3.9.5 64-bit",
"metadata": {
"interpreter": {
"hash": "ac59ebe37160ed0dfa835113d9b8498d9f09ceb179beaac4002f036b9467c963"
}
}
}
},
"nbformat": 4,
"nbformat_minor": 2,
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import lzma\n",
"import torch\n",
"import numpy as np\n",
"from gensim import downloader"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"BATCH_SIZE = 10\n",
"EPOCHS = 10\n",
"FEATURES = 200"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"class NeuralNetworkModel(torch.nn.Module):\n",
"\n",
" def __init__(self):\n",
" super(NeuralNetworkModel, self).__init__()\n",
" self.fc1 = torch.nn.Linear(FEATURES, 1000)\n",
" self.fc2 = torch.nn.Linear(1000, 500)\n",
" self.fc3 = torch.nn.Linear(500, 1)\n",
"\n",
" def forward(self, x):\n",
" x = self.fc1(x)\n",
" x = torch.relu(x)\n",
" x = self.fc2(x)\n",
" x = torch.relu(x)\n",
" x = self.fc3(x)\n",
" x = torch.sigmoid(x)\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Read train files\n",
"with lzma.open(\"train/in.tsv.xz\", \"rt\", encoding=\"utf-8\") as train_file:\n",
" x_train = [x.strip().lower() for x in train_file.readlines()]\n",
"\n",
"with open(\"train/expected.tsv\", \"r\", encoding=\"utf-8\") as train_file:\n",
" y_train = np.array([int(x.strip()) for x in train_file.readlines()])\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"word2vec = downloader.load(\"glove-twitter-200\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"x_train_w2v = [np.mean([word2vec[word.lower()] for word in doc.split() if word.lower() in word2vec]\n",
" or [np.zeros(FEATURES)], axis=0) for doc in x_train]"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"model = NeuralNetworkModel()\n",
"\n",
"criterion = torch.nn.BCELoss()\n",
"optimizer = torch.optim.ASGD(model.parameters(), lr=0.05)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"0\n",
"0.5444966091123856 0.7128072132302411\n",
"1\n",
"0.5187017436751196 0.7303153888921503\n",
"2\n",
"0.5117590330604093 0.7348944502191112\n",
"3\n",
"0.5075270808198805 0.7376916143781145\n",
"4\n",
"0.5043017516287736 0.7403230206610286\n",
"5\n",
"0.5016950109024928 0.7418977204838748\n",
"6\n",
"0.49942716640870777 0.7432134236253319\n",
"7\n",
"0.49766424133924386 0.7448606425189672\n",
"8\n",
"0.49617289846816215 0.745534033890579\n",
"9\n",
"0.49471875689137873 0.7467116054686286\n"
]
}
],
"source": [
"for epoch in range(EPOCHS):\n",
" print(epoch)\n",
" loss_score = 0\n",
" acc_score = 0\n",
" items_total = 0\n",
" for i in range(0, y_train.shape[0], BATCH_SIZE):\n",
" x = x_train_w2v[i:i+BATCH_SIZE]\n",
" x = torch.tensor(np.array(x).astype(np.float32))\n",
" y = y_train[i:i+BATCH_SIZE]\n",
" y = torch.tensor(y.astype(np.float32)).reshape(-1, 1)\n",
" y_pred = model(x)\n",
" acc_score += torch.sum((y_pred > 0.5) == y).item()\n",
" items_total += y.shape[0]\n",
"\n",
" optimizer.zero_grad()\n",
" loss = criterion(y_pred, y)\n",
" loss.backward()\n",
" optimizer.step()\n",
"\n",
" loss_score += loss.item() * y.shape[0]\n",
" \n",
" print((loss_score / items_total), (acc_score / items_total))"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# Read dev files\n",
"with lzma.open(\"dev-0/in.tsv.xz\", \"rt\", encoding=\"utf-8\") as dev_file:\n",
" x_dev = [x.strip().lower() for x in dev_file.readlines()]"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"x_dev_w2v = [np.mean([word2vec[word.lower()] for word in doc.split() if word.lower() in word2vec]\n",
" or [np.zeros(FEATURES)], axis=0) for doc in x_train]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"y_dev = []\n",
"with torch.no_grad():\n",
" for i in range(0, len(x_dev_w2v), BATCH_SIZE):\n",
" x = x_dev_w2v[i:i+BATCH_SIZE]\n",
" x = torch.tensor(np.array(x).astype(np.float32))\n",
" \n",
" outputs = model(x\n",
" \n",
" y = (outputs > 0.5)\n",
" y_dev.extend(y)"
]
}
]
}

1412
test-A/out.tsv
View File

File diff suppressed because it is too large Load Diff