Added model training

main.py

@@ -1,21 +1,49 @@
+from nltk.util import pr
 import pandas as pd
 import numpy as np
+import torch
 from gensim import downloader
 from nltk.tokenize import word_tokenize
 
-x_labels = (pd.read_csv('in-header.tsv', sep='\t')).columns
-y_labels = (pd.read_csv('out-header.tsv', sep='\t')).columns
 
-x_train = pd.read_table('train/in.tsv', error_bad_lines=False,
+class NeuralNetworkModel(torch.nn.Module):
-                        header=None, quoting=3, names=x_labels)
-y_train = pd.read_table('train/expected.tsv', error_bad_lines=False,
-                        header=None, quoting=3, names=y_labels)
-x_dev = pd.read_table('dev-0/in.tsv', error_bad_lines=False,
-                      header=None, quoting=3, names=x_labels)
-x_test = pd.read_table('test-A/in.tsv', error_bad_lines=False,
-                       header=None, quoting=3, names=x_labels)
 
-print(x_train)
+    def __init__(self):
+        dim = 100
+        super(NeuralNetworkModel, self).__init__()
+        self.fc1 = torch.nn.Linear(dim, 500)
+        self.fc2 = torch.nn.Linear(500, 1)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+
+
+def read_data():
+    x_labels = (pd.read_csv('in-header.tsv', sep='\t')).columns
+    y_labels = (pd.read_csv('out-header.tsv', sep='\t')).columns
+
+    x_train = pd.read_table('train/in.tsv', error_bad_lines=False,
+                            header=None, quoting=3, names=x_labels)
+    y_train = pd.read_table('train/expected.tsv', error_bad_lines=False,
+                            header=None, quoting=3, names=y_labels)
+    x_dev = pd.read_table('dev-0/in.tsv', error_bad_lines=False,
+                          header=None, quoting=3, names=x_labels)
+    x_test = pd.read_table('test-A/in.tsv', error_bad_lines=False,
+                           header=None, quoting=3, names=x_labels)
+
+    # remove some rows for faster development
+    remove_n = 200000
+    drop_indices = np.random.choice(x_train.index, remove_n, replace=False)
+    x_train = x_train.drop(drop_indices)
+
+    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()
 
 x_train = x_train[x_labels[0]].str.lower()
 x_dev = x_dev[x_labels[0]].str.lower()
@@ -26,16 +54,33 @@ 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]
 
-print(x_train)
+w2v = downloader.load('glove-wiki-gigaword-200')
 
+x_train = [np.mean([w2v[word] for word in doc if word in w2v] or [
+                   np.zeros(50)], axis=0) for doc in x_train]
+x_dev = [np.mean([w2v[word] for word in doc if word in w2v]
+                 or [np.zeros(50)], axis=0) for doc in x_dev]
+x_test = [np.mean([w2v[word] for word in doc if word in w2v]
+                  or [np.zeros(50)], axis=0) for doc in x_test]
 
-# w2v = downloader.load('glove-wiki-gigaword-200')
+nn_model = NeuralNetworkModel()
+BATCH_SIZE = 5
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.SGD(nn_model.parameters(), lr=0.1)
 
-# def document_vector(doc):
+for epoch in range(5):
-#     return np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(50)], axis=0)
+    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.astype(np.float32).todense())
+        Y = y_train[i:i+BATCH_SIZE]
+        Y = torch.tensor(Y.astype(np.float32)).reshape(-1, 1)
 
-# for doc in x_train:
+        Y_predictions = nn_model(X)
 
-# x_train = [document_vector(doc) for doc in x_train]
+        optimizer.zero_grad()
-# x_dev = [document_vector(doc) for doc in x_dev]
+        loss = criterion(Y_predictions, Y)
-# x_test = [document_vector(doc) for doc in x_test]
+        loss.backward()
+        optimizer.step()
+
+print(Y_predictions)