solving the task

Logistic-Regression.py

@@ -0,0 +1,94 @@
+import pandas as pd
+import numpy as np
+import torch
+import gensim.downloader as gensim
+from nltk.tokenize import word_tokenize
+
+x_train = pd.read_table('train/in.tsv', sep='\t', header = None, error_bad_lines = False, quoting = 3)
+y_train = pd.read_table('train/expected.tsv', sep='\t', header = None, quoting = 3)
+y_train = y_train[0]
+x_dev = pd.read_table('dev-0/in.tsv', sep='\t', header = None, quoting = 3)
+x_test = pd.read_table('test-A/in.tsv', sep='\t', header = None, quoting = 3)
+
+x_train = x_train[0].str.lower()
+x_dev = x_dev[0].str.lower()
+x_test = x_test[0].str.lower()
+
+x_train = [word_tokenize(x) for x in x_train]
+x_dev = [word_tokenize(x) for x in x_dev]
+x_test = [word_tokenize(x) for x in x_test]
+
+word2vec = gensim.load('glove-wiki-gigaword-50')
+
+def document_vector(doc):
+    return np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(50)], axis=0)
+
+x_train = [document_vector(doc) for doc in x_train]
+x_dev = [document_vector(doc) for doc in x_dev]
+x_test = [document_vector(doc) for doc in x_test]
+
+class NeuralNetworkModel(torch.nn.Module):
+    def __init__(self, features):
+        super(NeuralNetworkModel, self).__init__()
+        self.fc1 = torch.nn.Linear(50, features)
+        self.fc2 = torch.nn.Linear(features, 1)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+    
+nn_model = NeuralNetworkModel(100)
+BATCH_SIZE = 5
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.1)
+
+for epoch in range(5):
+    nn_model.train()
+    for i in range(0, y_train.shape[0], BATCH_SIZE):
+        X = x_train[i:i+BATCH_SIZE]
+        X = torch.tensor(X)
+        y = y_train[i:i+BATCH_SIZE]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)
+
+        outputs = nn_model(X.float())
+        loss = criterion(outputs, y)
+
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+y_dev = []
+y_test = []
+
+nn_model.eval()
+
+with torch.no_grad():
+    for i in range(0, len(x_dev), BATCH_SIZE):
+        X = x_dev[i:i+BATCH_SIZE]
+        X = torch.tensor(X)
+        
+        outputs = nn_model(X.float())
+        
+        y = (outputs > 0.5)
+        y_dev.extend(y)
+
+    for i in range(0, len(x_test), BATCH_SIZE):
+        X = x_test[i:i+BATCH_SIZE]
+        X = torch.tensor(X)
+
+        outputs = nn_model(X.float())
+
+        y = (outputs > 0.5)
+        y_test.extend(y)
+
+y_dev = np.asarray(y_dev, dtype=np.int32)
+y_test = np.asarray(y_test, dtype=np.int32)
+
+Y_dev = pd.DataFrame({'label':y_dev})
+Y_test = pd.DataFrame({'label':y_test})
+
+Y_dev.to_csv(r'dev-0/out.tsv', sep='\t', index=False,  header=False)
+Y_test.to_csv(r'test-A/out.tsv', sep='\t', index=False,  header=False)

geval-results.txt

@@ -0,0 +1,5 @@
+Likelihood	0.0000
+Accuracy	0.7289
+F1.0	0.5594
+Precision	0.6587
+Recall	0.4861