Merge pull request #107 from golastmile/test-percentage-setting

Allow to specify percentage of test data during intent classification

src/classifiers/sklearn_intent_classifier.py

@@ -42,18 +42,19 @@ def transform_labels_num2str(self, y):
         labels = self.le.inverse_transform(y)
         return labels
 
-    def train(self, X, y):
+    def train(self, X, y, test_split_size=0.1):
         """Train the intent classifier on a data set.
 
+        :param test_split_size: defines the percentage of examples to reserve for testing
         :param X: Train data set
         :param y: Train labels (numeric)"""
 
-        X_train, X_test, y_train, y_test = train_test_split(
-            X, y, test_size=0.1, random_state=0)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_split_size, random_state=0)
         self.clf.fit(X_train, y_train)
 
         # Test the trained model
-        logging.info("Score of intent model on test data: %s " % self.clf.score(X_test, y_test))
+        if test_split_size != 0.0:
+            logging.info("Score of intent model on test data: %s " % self.clf.score(X_test, y_test))
 
     def predict_prob(self, X):
         """Given a bow vector of an input text, predict the intent label. Returns probabilities for all labels.

src/trainers/spacy_sklearn_trainer.py

@@ -24,20 +24,20 @@ def __init__(self, config, language_name):
         self.intent_classifier = SklearnIntentClassifier()
         self.entity_extractor = SpacyEntityExtractor()
 
-    def train(self, data):
+    def train(self, data, test_split_size=0.1):
         self.training_data = data
         self.train_entity_extractor(data.entity_examples)
-        self.train_intent_classifier(data.intent_examples)
+        self.train_intent_classifier(data.intent_examples, test_split_size)
 
     def train_entity_extractor(self, entity_examples):
         self.entity_extractor.train(self.nlp, entity_examples)
 
-    def train_intent_classifier(self, intent_examples):
+    def train_intent_classifier(self, intent_examples, test_split_size=0.1):
         labels = [e["intent"] for e in intent_examples]
         sentences = [e["text"] for e in intent_examples]
         y = self.intent_classifier.transform_labels_str2num(labels)
         X = self.featurizer.create_bow_vecs(sentences)
-        self.intent_classifier.train(X, y)
+        self.intent_classifier.train(X, y, test_split_size)
 
     def persist(self, path, persistor=None, create_unique_subfolder=True):
         timestamp = datetime.datetime.now().strftime('%Y%m%d-%H%M%S')