reran mixed features with list of features lr 0.5 n est 100

AIclassifier.py

@@ -123,8 +123,8 @@ def create_vectors_list(sents, conversion_dict):
         mixed_vector.append(sent_mixed_vector)
 
     #return vectors_list # unigrams
-    return bigrams_vector
-    #return mixed_vector
+    #return bigrams_vector
+    return mixed_vector
 
 # def create_word_embedding(partition):
 
@@ -184,7 +184,8 @@ def create_vectors_list(sents, conversion_dict):
 bigrams_to_numbers = create_dict(bigrams_filtered_lexicon)
 
 # Mixed dictionary
-with open('features.txt', 'r') as file:
+with open('featureslr0.5nEst100.txt', 'r') as file:
+#with open('features.txt', 'r') as file:
     features_list = file.read()
 features_list = features_list.split('\n')
 mixed_to_numbers = create_dict(features_list)
@@ -198,8 +199,8 @@ def create_vectors_list(sents, conversion_dict):
 #dev_word_embedding_features = create_word_embedding(sents_dev)
 #test_word_embedding_features = numpy.asarray(create_word_embedding(sents_test))
 #print("Length of the dictionary of word representations:",len(words_to_numbers))
-print("Length of the dictionary of word representations:",len(bigrams_to_numbers))
-#print("Length of the dictionary of word representations:",len(mixed_to_numbers))
+#print("Length of the dictionary of word representations:",len(bigrams_to_numbers))
+print("Length of the dictionary of word representations:",len(mixed_to_numbers))
 
 # FLAG - CHECK IF DICTIONARY IS BUILT CORRECTLY
 #               SHOULD PUNCTUATION BE UNKNOWN? BECAUSE RIGHT NOW IT IS -NOPE, FIXED
@@ -211,13 +212,13 @@ def create_vectors_list(sents, conversion_dict):
 # dev_vectors_list = create_vectors_list(sents_dev, words_to_numbers)
 # test_vectors_list = create_vectors_list(sents_test, words_to_numbers)
 
-train_vectors_list = create_vectors_list(sents_train, bigrams_to_numbers)
-dev_vectors_list = create_vectors_list(sents_dev, bigrams_to_numbers)
-test_vectors_list = create_vectors_list(sents_test, bigrams_to_numbers)
+# train_vectors_list = create_vectors_list(sents_train, bigrams_to_numbers)
+# dev_vectors_list = create_vectors_list(sents_dev, bigrams_to_numbers)
+# test_vectors_list = create_vectors_list(sents_test, bigrams_to_numbers)
 
-# train_vectors_list = create_vectors_list(sents_train, mixed_to_numbers)
-# dev_vectors_list = create_vectors_list(sents_dev, mixed_to_numbers)
-# test_vectors_list = create_vectors_list(sents_test, mixed_to_numbers)
+train_vectors_list = create_vectors_list(sents_train, mixed_to_numbers)
+dev_vectors_list = create_vectors_list(sents_dev, mixed_to_numbers)
+test_vectors_list = create_vectors_list(sents_test, mixed_to_numbers)
 
 # COUNT STATISTICS - HOW MANY WORDS WERE CONSIDERED UNK, AND HOW MANY OF EACH WORD
 
@@ -227,13 +228,13 @@ def create_vectors_list(sents, conversion_dict):
 # dev_matrix_array = format_sentVector_to_SparseMatrix(dev_vectors_list, words_to_numbers)
 # test_matrix_array = format_sentVector_to_SparseMatrix(test_vectors_list, words_to_numbers)
 
-train_matrix_array = format_sentVector_to_SparseMatrix(train_vectors_list, bigrams_to_numbers)
-dev_matrix_array = format_sentVector_to_SparseMatrix(dev_vectors_list, bigrams_to_numbers)
-test_matrix_array = format_sentVector_to_SparseMatrix(test_vectors_list, bigrams_to_numbers)
+# train_matrix_array = format_sentVector_to_SparseMatrix(train_vectors_list, bigrams_to_numbers)
+# dev_matrix_array = format_sentVector_to_SparseMatrix(dev_vectors_list, bigrams_to_numbers)
+# test_matrix_array = format_sentVector_to_SparseMatrix(test_vectors_list, bigrams_to_numbers)
 
-# train_matrix_array = format_sentVector_to_SparseMatrix(train_vectors_list, mixed_to_numbers)
-# dev_matrix_array = format_sentVector_to_SparseMatrix(dev_vectors_list, mixed_to_numbers)
-# test_matrix_array = format_sentVector_to_SparseMatrix(test_vectors_list, mixed_to_numbers)
+train_matrix_array = format_sentVector_to_SparseMatrix(train_vectors_list, mixed_to_numbers)
+dev_matrix_array = format_sentVector_to_SparseMatrix(dev_vectors_list, mixed_to_numbers)
+test_matrix_array = format_sentVector_to_SparseMatrix(test_vectors_list, mixed_to_numbers)
 
 # FLAG - CHECK IF SPARSE MATRIX REPRESENTATION WAS DONE CORRECTLY
 
@@ -286,8 +287,8 @@ def create_vectors_list(sents, conversion_dict):
 
 features = {}
 #for i,(token,value) in enumerate(zip(words_to_numbers, importances)):
-#for i,(token,value) in enumerate(zip(mixed_to_numbers, importances)):
-for i,(token,value) in enumerate(zip(bigrams_to_numbers, importances)): # IMPORTANTO TO CHANGE TO ADEQUATE DICT
+for i,(token,value) in enumerate(zip(mixed_to_numbers, importances)):
+#for i,(token,value) in enumerate(zip(bigrams_to_numbers, importances)): # IMPORTANTO TO CHANGE TO ADEQUATE DICT
    if (value != 0):
        features[token] = value
 features = sorted([(value, key) for (key, value) in features.items()], reverse=True)
@@ -326,7 +327,7 @@ def create_vectors_list(sents, conversion_dict):
 os.makedirs(os.path.dirname(path), exist_ok=True)
 with open(path, 'w') as file:
     #print("Performance measures - Unigram Dictionary - MLP Word Embeddings\n", file=file)
-    print("Performance measures - Bigram Dictionary - Adaboost\n", file=file)
+    print("Performance measures - Mixed Dictionary - Adaboost\n", file=file)
 #write_output_stats_file(path, "Dev", dev_labels_primary, predictions, labels)
 write_output_stats_file(path, "Test", test_labels_primary, predictions, labels)
 

output/AI Classifier/1labelPredictionsStatsTest.txt

@@ -1,14 +1,14 @@
-Performance measures - Bigram Dictionary - Adaboost
+Performance measures - Mixed Dictionary - Adaboost
 
 Test set:
 
-Precision macro: 0.275
-Precision Individually: [0.857 0.    0.517 0.    0.   ]
-Recall macro: 0.279
-Recall Individually: [0.429 0.    0.968 0.    0.   ]
-F1 Score micro: 0.537
-F1 Score macro: 0.249
-F1 Score weighted: 0.431
-F1 Score Individually: [0.571 0.    0.674 0.    0.   ]
+Precision macro: 0.425
+Precision Individually: [0.8   0.    0.574 0.25  0.5  ]
+Recall macro: 0.315
+Recall Individually: [0.286 0.    1.    0.091 0.2  ]
+F1 Score micro: 0.567
+F1 Score macro: 0.314
+F1 Score weighted: 0.49
+F1 Score Individually: [0.421 0.    0.729 0.133 0.286]