cleanup code

main.py

@@ -6,6 +6,8 @@ from gensim import downloader
 from nltk.tokenize import word_tokenize
 import csv
 
+BATCH_SIZE = 5
+
 
 class NeuralNetworkModel(torch.nn.Module):
 
@@ -45,8 +47,7 @@ def read_data():
     return x_labels, y_labels, x_train, y_train, x_dev, x_test
 
 
-x_labels, y_labels, x_train, y_train, x_dev, x_test = read_data()
+def process_data(x_labels, y_labels, x_train, y_train, x_dev, x_test):
-
     x_train = x_train[x_labels[0]].str.lower()
     x_dev = x_dev[x_labels[0]].str.lower()
     x_test = x_test[x_labels[0]].str.lower()
@@ -58,20 +59,47 @@ x_test = [word_tokenize(x) for x in x_test]
 
     w2v = downloader.load('glove-wiki-gigaword-200')
 
-x_train = [np.mean([w2v[word] for word in doc if word in w2v] or [
+    x_train = [np.mean([w2v[w] for w in d if w in w2v] or [
-                   np.zeros(200)], axis=0) for doc in x_train]
+        np.zeros(200)], axis=0) for d in x_train]
-x_dev = [np.mean([w2v[word] for word in doc if word in w2v]
+    x_dev = [np.mean([w2v[w] for w in d if w in w2v]
-                 or [np.zeros(200)], axis=0) for doc in x_dev]
+                     or [np.zeros(200)], axis=0) for d in x_dev]
-x_test = [np.mean([w2v[word] for word in doc if word in w2v]
+    x_test = [np.mean([w2v[w] for w in d if w in w2v]
-                  or [np.zeros(200)], axis=0) for doc in x_test]
+                      or [np.zeros(200)], axis=0) for d in x_test]
+
+    return x_train, y_train, x_dev, x_test
+
+
+def predict(model, x_data, out_path):
+    y_out = []
+    model.eval()
+    with torch.no_grad():
+        for i in range(0, len(x_data), BATCH_SIZE):
+
+            x = x_data[i:i+BATCH_SIZE]
+            x = torch.tensor(x)
+            pred = nn_model(x.float())
+
+            y_pred = (pred > 0.5)
+            y_out.extend(y_pred)
+
+    y_data = np.asarray(y_out, dtype=np.int32)
+    pd.DataFrame(y_data).to_csv(out_path, sep='\t', index=False,  header=False)
+
+
+if __name__ == "__main__":
+
+    x_labels, y_labels, x_train, y_train, x_dev, x_test = read_data()
+
+    x_train, y_train, x_dev, x_test = process_data(
+        x_labels, y_labels, x_train, y_train, x_dev, x_test)
 
     nn_model = NeuralNetworkModel()
-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)
@@ -85,35 +113,5 @@ for epoch in range(5):
             loss.backward()
             optimizer.step()
 
-y_dev = []
+    predict(nn_model, x_dev, 'dev-0/out.tsv')
-y_test = []
+    predict(nn_model, x_test, 'test-A/out.tsv')
-
-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)