Update experimentsClassicClassifiers.py

experimentsClassicClassifiers.py

@@ -52,7 +52,7 @@ if not os.path.exists('models'):
 # Reading data and preprocessings steps
 preprocessor = Preprocessor()
 
-df = pd.read_csv(dataPath)
+df = pd.read_csv(dataPath, sep="\t")
 
 df = remove_weak_classes(df, columnClass, minOfInstancePerClass)
 df = resample_classes(df, columnClass, maxOfInstancePerClass)
@@ -72,32 +72,40 @@ doc2vec_min_count = int(config.get('vectorizers','doc2vec_min_count'))
 doc2vec_dm = int(config.get('vectorizers','doc2vec_dm')) # If dm=1, ‘distributed memory’ (PV-DM) is used. Otherwise, distributed bag of words (PV-DBOW) is employed.
 doc2vec_workers = int(config.get('vectorizers','doc2vec_workers'))
 
+print("size after resampling, ",len(df))
 
-for columnInput in [columnText]:
-    print('Process: ' + columnInput)
+#prepare data
+df = df[df[columnClass] != 'unclassified']
+y  = df[columnClass]
+
+print(df.head())
+
+train_x, test_x, train_y, test_y = train_test_split(df, y, test_size=0.33, random_state=42, stratify = y )
+encoder = preprocessing.LabelEncoder()
+train_y = encoder.fit_transform(train_y)
+valid_y = encoder.fit_transform(test_y)
 
-    #prepare data
-    df = df[df[columnClass] != 'unclassified']
-    y  = df[columnClass]
+print("size training set, ",len(train_x))
+print("size validation set, ",len(test_x))
 
-    train_x, test_x, train_y, test_y = train_test_split(df, y, test_size=0.33, random_state=42, stratify = y )
-    encoder = preprocessing.LabelEncoder()
-    train_y = encoder.fit_transform(train_y)
-    valid_y = encoder.fit_transform(test_y)
 
+for columnInput in [columnText, 'firstParagraph']:
+
+    print('Process: ' + columnInput)
 
     extractor = feature_extractor(train_x, test_x, columnInput, columnClass)
 
     features_techniques = [
     ('counter',  extractor.count_vect(max_df = vectorization_max_df, min_df = vectorization_min_df, numberOfFeatures = vectorization_numberOfFeatures )),
     ('tf_idf',  extractor.tf_idf(max_df = vectorization_max_df, min_df = vectorization_min_df, numberOfFeatures = vectorization_numberOfFeatures)),
-    ('doc2vec',  extractor.doc2vec(max_epochs, doc2vec_vec_size, doc2vec_min_count ,  doc2vec_dm, doc2vec_workers))]
+    ('doc2vec',  extractor.doc2vec(max_epochs, doc2vec_vec_size, doc2vec_min_count ,  doc2vec_dm))]
 
 
 
     #case of full text
     for feature_technique_name, features in features_techniques:
 
+        print("**** Classifier :", feature_technique_name)
         # features has the train_x and the test_x after vectorization
         train_x, test_x = features
 
@@ -115,10 +123,11 @@ for columnInput in [columnText]:
             t_begin = time.time()
 
             if os.path.isfile(os.path.join('./models', model_file_name)):
-                with open(os.path.join('./models', model_file_name), 'rb') as file:
+                report, accuracy, weighted_avg = evaluate_model(clf, test_x, valid_y, y_pred, valid_y, [str(e) for e in encoder.transform(encoder.classes_)],  encoder.classes_, os.path.join('reports', columnClass, dir_name_report, file_name_report)+'.pdf')
+                with open(os.path.join('./models',columnClass, model_file_name), 'rb') as file:
                     clf = pickle.load(file)
             else:
-                with open(os.path.join('./models', model_file_name), 'wb') as file:
+                with open(os.path.join('./models',columnClass, model_file_name), 'wb') as file:
                     clf.fit(train_x, train_y)
                     pickle.dump(clf, file)
 
@@ -143,5 +152,10 @@ for columnInput in [columnText]:
                 print('weighted_Support   : {}'.format(weighted_avg['support']))
                 print(dict(zip(encoder.classes_, encoder.transform(encoder.classes_))))
                 print('training time   : {}'.format(training_time))
+                try:
+                    print('best parameters   : {}'.format(clf.best_params_))
+                except AttributeError:
+                    pass
+
                 #sys.stdout = sys.stdout # Reset the standard output to its original value
                 sys.stdout = sys.__stdout__