sport-text-classification-ball-ISI-public/logistyczna.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "b'Skipping line 25706: expected 2 fields, saw 3\\nSkipping line 58881: expected 2 fields, saw 3\\nSkipping line 73761: expected 2 fields, saw 3\\n'\n",
      "b'Skipping line 1983: expected 1 fields, saw 2\\nSkipping line 5199: expected 1 fields, saw 2\\n'\n"
     ]
    }
   ],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "import pandas as pd\n",
    "import torch\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "import gensim\n",
    "from gensim.models import KeyedVectors\n",
    "import gensim.downloader\n",
    "import nltk\n",
    "import csv\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "import numpy as np\n",
    "def tokenize_data(data):\n",
    "    data_tokenize = [nltk.word_tokenize(x) for x in data]\n",
    " \n",
    "    for doc in data_tokenize:\n",
    "        i = 0\n",
    "        while i < len(doc):\n",
    "            if doc[i].isalpha():\n",
    "                doc[i] = doc[i].lower()\n",
    "            else:\n",
    "                del doc[i]\n",
    "            i += 1\n",
    "    return data_tokenize\n",
    "\n",
    "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\n",
    "r_in = './train/train.tsv'\n",
    "\n",
    "r_ind_ev = './dev-0/in.tsv'\n",
    "tsv_read = pd.read_table(r_in, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t', header=None)\n",
    "tsv_read_dev = pd.read_table(r_ind_ev, error_bad_lines=False, sep='\\t', quoting=csv.QUOTE_NONE, header=None)\n",
    "tsv_read_test_in =  pd.read_table('./test-A/in.tsv', error_bad_lines=False,quoting=csv.QUOTE_NONE, header= None)\n",
    "\n",
    "y_train = tsv_read[0].values\n",
    "X_train = tsv_read[1].values\n",
    "X_dev = tsv_read_dev[0].values\n",
    "X_test= tsv_read_test_in[0].values\n",
    "\n",
    "X_train = tokenize_data(X_train)\n",
    "X_dev = tokenize_data(X_dev)\n",
    "X_test = tokenize_data(X_test)\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "model = KeyedVectors.load(\"./word2vec/word2vec_100_3_polish.bin\")\n",
    "\n",
    "X_train = [np.mean([model[word] for word in content if word in model] or [np.zeros(100)], axis=0) for content in X_train]\n",
    "x_train_vectors = np.array(X_train, dtype=np.float32)\n",
    "x_train_tensor = torch.tensor(x_train_vectors.astype(np.float32))\n",
    "\n",
    "X_dev = [np.mean([model[word] for word in content if word in model] or [np.zeros(100)], axis=0) for content in X_dev]\n",
    "x_dev_vectors = np.array(X_dev, dtype=np.float32)\n",
    "\n",
    "\n",
    "X_test = [np.mean([model[word] for word in content if word in model] or [np.zeros(100)], axis=0) for content in X_test]\n",
    "x_test_vectors = np.array(X_test, dtype=np.float32)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = NeuralNetwork(100, 200, 1)\n",
    "criterion = torch.nn.BCELoss()\n",
    "optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
    "  \n",
    "batch_size = 12\n",
    "\n",
    " \n",
    "for epoch in range(6):\n",
    "    loss_score = 0\n",
    "    acc_score = 0\n",
    "    items_total = 0\n",
    "    model.train()\n",
    "    for i in range(0, y_train.shape[0], batch_size):\n",
    "        X = x_train_vectors[i:i+batch_size]\n",
    "        X = torch.tensor(X.astype(np.float32))\n",
    "        Y = y_train[i:i+batch_size]\n",
    "        Y = torch.tensor(Y.astype(np.float32)).reshape(-1,1)\n",
    " \n",
    "        Y_predictions = model(X)\n",
    "        acc_score += torch.sum((Y_predictions > 0.5) == Y).item()\n",
    "        items_total += Y.shape[0] \n",
    " \n",
    "        optimizer.zero_grad()\n",
    "        loss = criterion(Y_predictions, Y)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    " \n",
    " \n",
    "        loss_score += loss.item() * Y.shape[0]\n",
    " "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "predictions = model(torch.tensor(x_dev_vectors.astype(np.float32)))\n",
    "predictions = predictions.cpu().detach().numpy() \n",
    "predictions = (predictions > 0.5)\n",
    "predictions = np.asarray(predictions, dtype=np.int32)\n",
    "predictions.tofile('dev-0/out.tsv', sep='\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = model(torch.tensor(x_dev_vectors.astype(np.float32)))\n",
    "predictions = predictions.cpu().detach().numpy() \n",
    "predictions = (predictions > 0.5)\n",
    "predictions = np.asarray(predictions, dtype=np.int32)\n",
    "predictions.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": 1
}