update

main.py

@@ -26,7 +26,7 @@ HIDDEN_D = 600
 OUTPUT_D = 1
 
 
-def main(dirname):
+def main(dirnames):
     check_path(IN_HEADER_FILE_NAME)
     in_cols = (pd.read_csv(IN_HEADER_FILE_NAME, sep=FILE_SEP)).columns
     check_path(OUT_HEADER_FILE_NAME)
@@ -39,7 +39,10 @@ def main(dirname):
         TRAIN_PATH, EXP_FILE_NAME), names=out_cols, compression=None)
 
     print("Reading input data...")
-    in_set = get_tsv_data(os.path.join(dirname, IN_FILE_NAME), names=in_cols)
+    in_sets = []
+    for d in dirnames:
+        in_sets.append(get_tsv_data(
+            os.path.join(d, IN_FILE_NAME), names=in_cols))
 
     print("Preparing training data...")
     X_train_raw = train_set_features[in_cols[0]].str.lower()
@@ -47,14 +50,19 @@ def main(dirname):
     Y_train = train_set_labels[out_cols[0]]
 
     print("Preparing input data...")
-    X_in_raw = in_set[in_cols[0]].str.lower()
+    X_ins_raw = []
+    for s in in_sets:
+        X_ins_raw.append(s[in_cols[0]].str.lower())
 
     print("Loading word 2 vector model...")
     w2v_model = downloader.load(WORD_2_VEC_MODEL_NAME)
 
     print("Vectorizing data...")
     X_train = vectorize(X_train, w2v_model)
-    X_in = vectorize(X_in_raw, w2v_model)
+
+    X_ins = []
+    for r in X_ins_raw:
+        X_ins.append(vectorize(r, w2v_model))
 
     model = Model(input_dim=INPUT_D, hidden_dim=HIDDEN_D, output_dim=OUTPUT_D)
 
@@ -63,10 +71,11 @@ def main(dirname):
 
     model.eval()
 
-    predictions = predict(model, X_in)
+    for i in range(len(X_ins)):
+        predictions = predict(model, X_ins[i])
 
-    out_file_path = os.path.join(dirname, OUT_FILE_NAME)
+        out_file_path = os.path.join(dirnames[i], OUT_FILE_NAME)
-    print(f"Saving predictions to file: {out_file_path}")
+        print(f"Saving predictions to file: {out_file_path}")
     np.asarray(predictions, dtype=np.int32).tofile(out_file_path, sep="\n")
 
 
@@ -113,4 +122,4 @@ def check_path(filename: str):
 if __name__ == "__main__":
     if len(sys.argv) < 2:
         raise Exception("Name of working dir not specified!")
-    main(sys.argv[1])
+    main(sys.argv[1:])

model.py

@@ -19,7 +19,8 @@ class Model(nn.Module):
         self.fc2 = nn.Linear(self.hidden_dim, self.hidden_dim)
         self.fc3 = nn.Linear(self.hidden_dim, self.output_dim)
 
-        self.relu = nn.ReLU()
+        self.r1 = nn.ReLU()
+        self.r2 = nn.ReLU()
 
         self.criterion = nn.BCELoss()
         self.optimizer = torch.optim.SGD(self.parameters(), lr=0.01)
@@ -28,19 +29,16 @@ class Model(nn.Module):
         """Step forward learning fn"""
 
         x = self.fc1(x)
-        x = self.relu(x)
+        x = self.r1(x)
-        x = self.fc2(x)
+        x = self.r2(x)
-        x = self.relu(x)
         x = self.fc3(x)
         x = torch.sigmoid(x)
         return x
 
     def run_training(self, X_train, Y_train, batch_size, epochs_count):
-        for _ in range(epochs_count):
+        for i in range(epochs_count):
             self.train()
-            print(f"{Y_train.shape[0]}, {Y_train.shape[0] == self.input_dim}")
+            print(f"Epochs: {i + 1}/{epochs_count}")
-            print(f"{Y_train.shape[0]}, {Y_train.shape[0] == self.hidden_dim}")
-            print(f"{Y_train.shape[0]}, {Y_train.shape[0] == self.output_dim}")
             for i in range(0, Y_train.shape[0], batch_size):
                 X = X_train[i: i + batch_size]
                 X = torch.tensor(X)