logreg first attempt

log-reg.py

@@ -0,0 +1,98 @@
+import pandas as pd
+import numpy as np
+import torch
+from nltk.tokenize import word_tokenize
+import gensim.downloader
+from csv import QUOTE_NONE
+
+
+print('initialization')
+word2vec = gensim.downloader.load('word2vec-google-news-300')
+
+
+def get_word2vec(document):
+    return np.mean([word2vec[token] for token in document if token in word2vec] or [np.zeros(300)], axis=0)
+
+
+class MyNeuralNetwork(torch.nn.Module):
+
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(MyNeuralNetwork, self).__init__()
+        self.fc1 = torch.nn.Linear(input_size, hidden_size)
+        self.fc2 = torch.nn.Linear(hidden_size, num_classes)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+
+
+# wczytanie danych
+print('loading data')
+train_x = pd.read_table('train/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE,
+                        names=['content', 'id'])
+train_y = pd.read_table('train/expected.tsv', error_bad_lines=False, header=None, quoting=QUOTE_NONE,
+                        names=['label'])['label']
+dev_x = pd.read_table('dev-0/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE,
+                      names=['content', 'id'])
+test_x = pd.read_table('test-A/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE,
+                       names=['content', 'id'])
+
+# preprocessing danych
+print('word tokenize')
+train_x = [word_tokenize(row) for row in train_x['content'].str.lower()]
+dev_x = [word_tokenize(row) for row in dev_x['content'].str.lower()]
+test_x = [word_tokenize(row) for row in test_x['content'].str.lower()]
+
+print('word2vec')
+train_x = [get_word2vec(document) for document in train_x]
+dev_x = [get_word2vec(document) for document in dev_x]
+test_x = [get_word2vec(document) for document in test_x]
+
+# trenowanie
+print('model training')
+network = MyNeuralNetwork(300, 600, 1)
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.SGD(network.parameters(), lr=0.1)
+epochs = 5
+batch_size = 5
+
+for epoch in range(epochs):
+    network.train()
+    for i in range(0, train_y.shape[0], batch_size):
+        x = train_x[i:i + batch_size]
+        x = torch.tensor(x)
+        y = train_y[i:i + batch_size]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+        outputs = network(x.float())
+        loss = criterion(outputs, y)
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+# ewaluacja
+print('evaluation')
+dev_y_prediction = []
+test_y_prediction = []
+with torch.no_grad():
+    for i in range(0, len(dev_x), batch_size):
+        x = dev_x[i:i + batch_size]
+        x = torch.tensor(x)
+        outputs = network(x.float())
+        prediction = outputs > 0.5
+        dev_y_prediction += prediction.tolist()
+    for i in range(0, len(test_x), batch_size):
+        x = test_x[i:i + batch_size]
+        x = torch.tensor(x)
+        outputs = network(x.float())
+        prediction = outputs > 0.5
+        test_y_prediction += prediction.tolist()
+
+# zapisanie danych
+print('saving data')
+np.asarray(dev_y_prediction, dtype=np.int32).tofile('./dev-0/out.tsv', sep='\n')
+np.asarray(test_y_prediction, dtype=np.int32).tofile('./test-A/out.tsv', sep='\n')
+
+print('done')