complete Main.pu

BigramModel.py

@@ -155,6 +155,7 @@ def calculate_sentence_probability(self, sentence, dataset_mode):
 
     # start learning and create unary and binary words dictionary
     def learning(self):
+
         self.create_unary_words_dict()
         self.create_binary_words_dict()
 

main.py → Main.py

@@ -2,6 +2,16 @@
 from BigramModel import *
 
 
+def do_test(test_set, label, model):
+    correct_answer_count = 0
+    for sentence in test_set:
+        model_response = model.recognize_sentence(sentence)
+        if model_response == label or model_response == "equal":
+            correct_answer_count += 1
+
+    return correct_answer_count/len(test_set)
+
+
 if __name__ == "__main__":
 
     # read datasets
@@ -17,19 +27,20 @@
     epsilon = 0.2
     cut_down = 2
     cut_above= 10
-    bigram_model = BigramModel(positive_train_set, negative_train_set, lambda_arr, epsilon)
+    bigram_model = BigramModel(positive_train_set, negative_train_set, lambda_arr, epsilon, cut_down, cut_above)
     bigram_model.learning()     # start learning
 
 
     # analyse
-    for i
+    accuracy_pos_test = do_test(positive_test_set, "positive", bigram_model)
+    print("Accuracy in positive test set : ".format(accuracy_pos_test * 100))
+    accuracy_neg_test = do_test(negative_test_set, "negative", bigram_model)
+    print("Accuracy in negative test set : ".format(accuracy_neg_test * 100))
 
 
 
 
 
-    # TODO create unigram model object
 
-    # TODO analyse and compare models
 
-    pass
+    # TODO create unigram model object