Merge branch 'master' into 'branch_dev_vectorizationFeature'

# Conflicts:
#   classifiers.py
#   experimentsClassicClassifiers.py

classifiers.py

@@ -14,15 +14,15 @@ classifiers = [
                 ('bayes', MultinomialNB()),
                 ('lr', LogisticRegression()),
                 ('sgd', SGDClassifier()),
-                ('svm', SVC() ),
-                ('decisionTree',DecisionTreeClassifier()),
+                #('decisionTree',DecisionTreeClassifier()),
                 ('rfc', RandomForestClassifier()),
-                ('knn', KNeighborsClassifier())
+                ('knn', KNeighborsClassifier()),
+                ('svm', SVC() )
                 ]
 
 
-param_grid_svm = {'C':[1,10,100,1000],'gamma':[1,0.1,0.001,0.0001], 'kernel':['linear','rbf']}
-param_grid_decisionTree = { 'criterion' : ['gini', 'entropy'], 'max_depth':range(5,10), 'min_samples_split': range(5,10), 'min_samples_leaf': range(1,5) }
+param_grid_svm = {'C':[1,10,100,1000],'gamma':[0.1,0.001,0.0001], 'kernel':['linear','rbf']}
+#param_grid_decisionTree = { 'criterion' : ['gini', 'entropy'], 'max_depth':range(5,10), 'min_samples_split': range(5,10), 'min_samples_leaf': range(1,5) }
 param_grid_rfc = { 'n_estimators': [200, 500], 'max_features': ['auto', 'sqrt', 'log2'], 'max_depth' : [4,5,6,7,8], 'criterion' :['gini', 'entropy'] }
 param_grid_lr = {"C":np.logspace(-3,3,7), "penalty":['none',"l2"]}
 param_grid_sgd = { "loss" : ["hinge", "log", "squared_hinge", "modified_huber"], "alpha" : [0.0001, 0.001, 0.01, 0.1], "penalty" : ["l2", "l1", "none"], "max_iter" : [500]}

experimentsClassicClassifiers.py

@@ -72,8 +72,8 @@ 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'))
 
-for columnInput in [columnText, 'firstParagraph']:
 
+for columnInput in ['firstParagraph',columnText]:
     print('Process: ' + columnInput)
 
     #prepare data
@@ -108,7 +108,7 @@ for columnInput in [columnText, 'firstParagraph']:
             model_file_name = columnInput + '_' +feature_technique_name + '_' + clf_name+ str(minOfInstancePerClass) + '_' + str(maxOfInstancePerClass) +".pkl"
 
             if clf_name != 'bayes' :
-                clf = GridSearchCV(clf, grid_param, refit = True, verbose = 3)
+                clf = GridSearchCV(clf, grid_param, refit = True, verbose = 3, n_jobs=-1)
             elif feature_technique_name == 'doc2vec':
                     continue