{ "cells": [ { "cell_type": "code", "execution_count": 2, "id": "308eb052", "metadata": {}, "outputs": [], "source": [ "import torch\n", "import gensim.downloader as downloader\n", "import pandas as pd\n", "import csv\n", "from nltk.tokenize import word_tokenize as tokenize\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 7, "id": "212c0f2c", "metadata": {}, "outputs": [], "source": [ "class NeuralNetworkModel(torch.nn.Module):\n", " \n", " def __init__(self, input_size, hidden_size, num_classes):\n", " super(NeuralNetworkModel, self).__init__()\n", " self.fc1 = torch.nn.Linear(input_size,hidden_size)\n", " self.fc2 = torch.nn.Linear(hidden_size,num_classes)\n", " \n", " def forward(self,x):\n", " x = self.fc1(x)\n", " x = torch.relu(x)\n", " x = self.fc2(x)\n", " x = torch.sigmoid(x)\n", " return x" ] }, { "cell_type": "code", "execution_count": 4, "id": "afd13d8c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[==================================================] 100.0% 1662.8/1662.8MB downloaded\n" ] } ], "source": [ "w2v = downloader.load('word2vec-google-news-300')" ] }, { "cell_type": "code", "execution_count": 9, "id": "f68b0a7c", "metadata": {}, "outputs": [], "source": [ "#model + settings\n", "\n", "nn = NeuralNetworkModel(300,300,1)\n", "crit = torch.nn.BCELoss()\n", "opti = torch.optim.SGD(nn.parameters(), lr=0.08)\n", "BATCH_SIZE = 5\n", "epochs = 5" ] }, { "cell_type": "code", "execution_count": 12, "id": "f0713eab", "metadata": { "scrolled": true }, "outputs": [], "source": [ "#trening\n", "\n", "#wczytanie danych\n", "train_data_in = pd.read_csv('train/in.tsv.xz', compression='xz', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t', nrows=3000)\n", "train_data_ex = pd.read_csv('train/expected.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t', nrows=3000)\n", "\n", "#preprocessing\n", "train_in = train_data_in[0].str.lower()\n", "train_in = [tokenize(line) for line in train_in]\n", "train_in = [np.mean([w2v[x] for x in data if x in w2v] or [np.zeros(300)], axis=0) for data in train_in]\n", "train_ex = train_data_ex[0]\n", "\n", "for epoch in range(epochs):\n", " nn.train()\n", " for i in range(0,train_data_ex.shape[0],BATCH_SIZE):\n", " x = train_in[i:i + BATCH_SIZE]\n", " x = torch.tensor(x)\n", " y = train_ex[i:i + BATCH_SIZE]\n", " y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)\n", " \n", " opti.zero_grad()\n", " y_pred = nn(x.float())\n", " loss = crit(y_pred,y)\n", " loss.backward()\n", " opti.step()" ] }, { "cell_type": "code", "execution_count": 27, "id": "1ab1dce0", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":21: FutureWarning: The input object of type 'Tensor' is an array-like implementing one of the corresponding protocols (`__array__`, `__array_interface__` or `__array_struct__`); but not a sequence (or 0-D). In the future, this object will be coerced as if it was first converted using `np.array(obj)`. To retain the old behaviour, you have to either modify the type 'Tensor', or assign to an empty array created with `np.empty(correct_shape, dtype=object)`.\n", " np.asarray(dev0_y, dtype=np.int32).tofile('dev-0/out.tsv', sep='\\n')\n", ":21: DeprecationWarning: setting an array element with a sequence. This was supported in some cases where the elements are arrays with a single element. For example `np.array([1, np.array([2])], dtype=int)`. In the future this will raise the same ValueError as `np.array([1, [2]], dtype=int)`.\n", " np.asarray(dev0_y, dtype=np.int32).tofile('dev-0/out.tsv', sep='\\n')\n" ] } ], "source": [ "#dev-0 predict\n", "\n", "#wczytanie danych\n", "dev0_data = pd.read_csv('dev-0/in.tsv.xz', compression='xz', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t')\n", "dev0_data = dev0_data[0].str.lower()\n", "dev0_data = [tokenize(line) for line in dev0_data]\n", "dev0_data = [np.mean([w2v[x] for x in data if x in w2v] or [np.zeros(300)], axis=0) for data in dev0_data]\n", "\n", "dev0_y=[]\n", "nn.eval()\n", "with torch.no_grad():\n", " for i in range(0, len(dev0_data), BATCH_SIZE):\n", " x = dev0_data[i:i + BATCH_SIZE]\n", " x = torch.tensor(x)\n", " dev0_y_pred = nn(x.float())\n", "\n", " dev0_y_prediction = (dev0_y_pred > 0.5)\n", " dev0_y.extend(dev0_y_prediction)\n", " \n", "#zapis wyników\n", "np.asarray(dev0_y, dtype=np.int32).tofile('dev-0/out.tsv', sep='\\n')" ] }, { "cell_type": "code", "execution_count": 28, "id": "22941828", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":21: FutureWarning: The input object of type 'Tensor' is an array-like implementing one of the corresponding protocols (`__array__`, `__array_interface__` or `__array_struct__`); but not a sequence (or 0-D). In the future, this object will be coerced as if it was first converted using `np.array(obj)`. To retain the old behaviour, you have to either modify the type 'Tensor', or assign to an empty array created with `np.empty(correct_shape, dtype=object)`.\n", " np.asarray(testA_y, dtype=np.int32).tofile('test-A/out.tsv', sep='\\n')\n", ":21: DeprecationWarning: setting an array element with a sequence. This was supported in some cases where the elements are arrays with a single element. For example `np.array([1, np.array([2])], dtype=int)`. In the future this will raise the same ValueError as `np.array([1, [2]], dtype=int)`.\n", " np.asarray(testA_y, dtype=np.int32).tofile('test-A/out.tsv', sep='\\n')\n" ] } ], "source": [ "#test-A predict\n", "\n", "#wczytanie danych\n", "testA_data = pd.read_csv('test-A/in.tsv.xz', compression='xz', header=None, quoting=csv.QUOTE_NONE, sep='\\t')\n", "testA_data = testA_data[0].str.lower()\n", "testA_data = [tokenize(line) for line in testA_data]\n", "testA_data = [np.mean([w2v[x] for x in data if x in w2v] or [np.zeros(300)], axis=0) for data in testA_data]\n", "\n", "testA_y=[]\n", "nn.eval()\n", "with torch.no_grad():\n", " for i in range(0, len(testA_data), BATCH_SIZE):\n", " x = testA_data[i:i + BATCH_SIZE]\n", " x = torch.tensor(x)\n", " testA_y_pred = nn(x.float())\n", "\n", " testA_y_prediction = (testA_y_pred > 0.5)\n", " testA_y.extend(testA_y_prediction)\n", " \n", "#zapis wyników\n", "np.asarray(testA_y, dtype=np.int32).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": "3.8.8" } }, "nbformat": 4, "nbformat_minor": 5 }