[FIX] update number of jobs in GridSearchCV

classifiers.py

@@ -14,26 +14,26 @@ 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":["l1","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]}
+param_grid_sgd = { "loss" : ["hinge", "log", "squared_hinge", "modified_huber"], "alpha" : [0.0001, 0.001, 0.01, 0.1], "penalty" : ["l2", "l1"], "max_iter" : [500]}
 param_grid_knn = {'n_neighbors' : list(range(3,20)), 'weights' : ['uniform', 'distance'], 'metric' : ['euclidean', 'manhattan'] }
 
 grid_params = [
                 ('bayes', None),
-                ('svm', param_grid_svm),
-                ('decisionTree', param_grid_decisionTree),
-                ('rfc', param_grid_rfc ),
                 ('lr', param_grid_lr),
                 ('sgd', param_grid_sgd ),
+                #('decisionTree', param_grid_decisionTree),
+                ('rfc', param_grid_rfc ),
                 ('knn', param_grid_knn),
+                ('svm', param_grid_svm),
                 ]

experimentsClassicClassifiers.py

@@ -68,8 +68,8 @@ doc2vec_vec_size = int(config.get('vectorizers','doc2vec_vec_size'))
 doc2vec_epochs = int(config.get('vectorizers','doc2vec_epochs'))
 doc2vec_lr = float(config.get('vectorizers','doc2vec_lr'))
 
-for columnInput in [columnText, 'firstParagraph']:
 
+for columnInput in ['firstParagraph',columnText]:
     print('Process: ' + columnInput)
 
     extractor = feature_extractor(df, columnInput, columnClass)
@@ -77,7 +77,8 @@ for columnInput in [columnText, 'firstParagraph']:
     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(doc2vec_epochs, doc2vec_vec_size, doc2vec_lr))]
+    ('doc2vec',  extractor.doc2vec(doc2vec_epochs, doc2vec_vec_size, doc2vec_lr))
+    ]
 
     #prepare data
     df = df[df[columnClass] != 'unclassified']
@@ -97,7 +98,7 @@ 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