removing all code not related to ibrahimsharaf#14

models/classifier_model.py

@@ -4,7 +4,6 @@
 import inspect
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score, f1_score
-from sklearn.externals import joblib
 from .model import Model
 from .doc2vec_model import doc2VecModel
 
@@ -33,17 +32,9 @@ def train_model(self, d2v, training_vectors, training_labels):
 
     def save_model(self, filename):
         logging.info("Saving trained classification model")
-        filename = os.path.join(classifiers_path, filename)
-        joblib.dump(self.model, filename)
 
     def load_model(self, filename):
         logging.info("Loading trained classification model")
-        filename = os.path.join(classifiers_path, filename)
-        if (os.path.isfile(filename)):
-            loaded_model = joblib.load(filename)
-            self.model = loaded_model
-        else:
-            self.model = None
 
     def test_model(self, d2v, testing_vectors, testing_labels):
         logging.info("Classifier testing")
@@ -52,3 +43,9 @@ def test_model(self, d2v, testing_vectors, testing_labels):
         logging.info('Testing predicted classes: {}'.format(np.unique(testing_predictions)))
         logging.info('Testing accuracy: {}'.format(accuracy_score(testing_labels, testing_predictions)))
         logging.info('Testing F1 score: {}'.format(f1_score(testing_labels, testing_predictions, average='weighted')))
+
+    def predict(self, d2v, testing_vectors):
+        logging.info("Classifier Predicting")
+        test_vectors = doc2VecModel.get_vectors(d2v, len(testing_vectors), 300, 'Test')
+        testing_predictions = self.model.predict(test_vectors)
+        logging.info(testing_predictions)

text_classifier.py

@@ -2,6 +2,7 @@
 import logging
 import sys, getopt
 import os, inspect
+import numpy as np
 from sklearn.model_selection import train_test_split
 from models.doc2vec_model import doc2VecModel
 from models.classifier_model import classifierModel
@@ -10,6 +11,9 @@
 base_file_path = inspect.getframeinfo(inspect.currentframe()).filename
 project_dir_path = os.path.dirname(os.path.abspath(base_file_path))
 data_path = os.path.join(project_dir_path, 'data')
+default_classifier = os.path.join(project_dir_path, 'classifiers','joblib_model.pkl')
+default_doc2vec= os.path.join(project_dir_path, 'classifiers','d2v.model')
+default_dataset= os.path.join(data_path, 'dataset.csv')
 
 class TextClassifier():
 
@@ -31,48 +35,38 @@ def prepare_all_data(self):
         all_data = x_train + x_test
         return x_train, x_test, y_train, y_test, all_data
 
-    # def prepare_test_data(self):
-    #    x_test = doc2VecBuilder.label_sentences(self.dataset.review, 'Test')
-    #    y_test = self.dataset.sentiment
-    #    return x_test, y_test
+    def prepare_test_data(self,sentence):
+        x_test = doc2VecModel.label_sentences(sentence, 'Test')
+        return x_test
 
-    def train_classifier(self, d2v_file, classifier_file):
+    def train_classifier(self):
         x_train, x_test, y_train, y_test, all_data = self.prepare_all_data()
         self.d2v.initialize_model(all_data)
         self.d2v.train_model()
-        self.d2v.save_model(d2v_file)
         self.classifier.initialize_model()
         self.classifier.train_model(self.d2v, x_train, y_train)
-        self.classifier.save_model(classifier_file)
         self.classifier.test_model(self.d2v, x_test, y_test)
+        return self.d2v, self.classifier
 
-    def test_classifier(self, d2v_file, classifier_file):
-        # x_test, y_test = self.prepare_test_data()
+    def test_classifier(self):
         x_train, x_test, y_train, y_test, all_data = self.prepare_all_data()
-        self.d2v.load_model(d2v_file)
-        self.classifier.load_model(classifier_file)
         if (self.d2v.model is None or self.classifier.model is None):
             logging.info("No Trained Models Found, Train First or Use Correct Model Names")
         else:
             self.classifier.test_model(self.d2v, x_test, y_test)
 
-
 def main(argv):
-    if(len(argv)==4):
-        mode = argv[0]
-        dataset_file = argv[1]
-        d2v_file = argv[2]
-        classifier_file = argv[3]
+    if(len(argv)==1):
+        dataset_file = argv[0]
 
         tc = TextClassifier()
         tc.read_data(dataset_file)
-        if mode.lower() == 'test':
-            tc.test_classifier(d2v_file, classifier_file)
-        else:
-            tc.train_classifier(d2v_file, classifier_file)
-    else:
-        print ('python text_classifier.py <mode> <dataset_file> <doc2vec_file> <classifier_file>')
+        tc.test_classifier()
+        tc.train_classifier()
 
+    else:
+        print('Please use any of the following Commands to use text_classifier for training/testing/predicting:')
+        print ('To Run: python text_classifier.py <dataset_file>')
 
 if __name__ == "__main__":
     main(sys.argv[1:])