improve

logistic_regression.py

@@ -6,7 +6,7 @@ import numpy as np
 import csv  
 
 class LogisticRegression(torch.nn.Module):
-     def __init__(self):
+     def __init__(self, WORDS_IN_DICTIONARY):
         super(LogisticRegression, self).__init__()
         self.linear = torch.nn.Linear(WORDS_IN_DICTIONARY, 2)
      def forward(self, x):
@@ -20,7 +20,7 @@ def make_vector(sentence, dictionary):
     return vector.view(1, -1)
 
 def read_data(path):
-  line = open(path, 'r').readlines()[0:2000]
+  line = open(path, 'r').readlines()[0:1000]
   data = []
   for word in line:
     data.append(word.split())
@@ -28,13 +28,17 @@ def read_data(path):
 
 def main():
   train_data = read_data("train/in.tsv")
-  temp = open('train/expected.tsv', 'r').readlines()[0:2000]
+  temp = open('train/expected.tsv', 'r').readlines()[0:1000]
   train_data_output = []
   for sent in temp:
     train_data_output.append(int(sent))
 
-  test_data = read_data('test-A/in.tsv')
-  output = open('test-A/out.tsv', 'w')
+
+  lines = open('dev-0/in.tsv', 'r').readlines()
+  test_data = []
+  for line in lines:
+    test_data.append(line.split())
+  output = open('dev-0/out.tsv', 'w')
 
 
   dictionary = {}
@@ -45,7 +49,7 @@ def main():
 
   WORDS_IN_DICTIONARY = len(dictionary)
 
-  model = LogisticRegression()
+  model = LogisticRegression(WORDS_IN_DICTIONARY)
 
   criterion = nn.NLLLoss()
   optimizer = optim.SGD(model.parameters(), lr=0.1)