Requested Changes

.gitignore

@@ -155,9 +155,5 @@ crashlytics.properties
 crashlytics-build.properties
 fabric.properties
 
-# .idea and models
+# .idea
 .idea/
-classifiers/*.model
-classifiers/*.model.*
-classifiers/*.pkl
-data/*.csv

.travis.yml

@@ -5,4 +5,4 @@
   - sudo rm -f /etc/boto.cfg
   - pip install -r requirements.txt
  script:
-   - python3 text_classifier.py Test dataset.csv d2v.model joblib_model.pkl
+   - python3 text_classifier.py

models/classifier_model.py

@@ -1,11 +1,14 @@
+from .model import Model
+from .doc2vec_model import doc2VecModel
+
 import logging
-import numpy as np
 import os
 import inspect
+
+import numpy as np
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score, f1_score
-from .model import Model
-from .doc2vec_model import doc2VecModel
+
 
 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
 base_file_path = inspect.getframeinfo(inspect.currentframe()).filename
@@ -30,12 +33,6 @@ def train_model(self, d2v, training_vectors, training_labels):
         logging.info(
             'Training F1 score: {}'.format(f1_score(training_labels, training_predictions, average='weighted')))
 
-    def save_model(self, filename):
-        logging.info("Saving trained classification model")
-
-    def load_model(self, filename):
-        logging.info("Loading trained classification model")
-
     def test_model(self, d2v, testing_vectors, testing_labels):
         logging.info("Classifier testing")
         test_vectors = doc2VecModel.get_vectors(d2v, len(testing_vectors), 300, 'Test')

models/doc2vec_model.py

@@ -1,12 +1,14 @@
+from .model import Model
+
 import logging
 import random
 import os
 import inspect
+
 import numpy as np
 from gensim.models import doc2vec
-from gensim.models.doc2vec import Doc2Vec
 
-from .model import Model
+
 
 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
 base_file_path = inspect.getframeinfo(inspect.currentframe()).filename
@@ -47,20 +49,6 @@ def train_model(self):
             # fix the learning rate, no decay
             self.model.min_alpha = self.model.alpha
 
-    def save_model(self, filename):
-        logging.info("Saving trained Doc2Vec model")
-        filename = os.path.join(classifiers_path, filename)
-        self.model.save(filename)
-
-    def load_model(self, filename):
-        logging.info("Loading trained Doc2Vec model")
-        filename = os.path.join(classifiers_path, filename)
-        if (os.path.isfile(filename)):
-            d2v = Doc2Vec.load(filename)
-            self.model = d2v
-        else:
-            self.model = None
-
     def get_vectors(self, corpus_size, vectors_size, vectors_type):
         """
         Get vectors from trained doc2vec model

models/model.py

@@ -15,12 +15,5 @@ def initialize_model(self):
     def train_model(self):
         pass
 
-    @abstractmethod
-    def save_model(self):
-        pass
-
-    @abstractmethod
-    def load_model(self):
-        pass
 
 

text_classifier.py

@@ -1,17 +1,19 @@
-import pandas as pd
-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
 
+import os
+import logging
+import inspect
+
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+
 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
 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_classifier = os.path.join(project_dir_path, 'classifiers','logreg_model.pkl')
 default_doc2vec= os.path.join(project_dir_path, 'classifiers','d2v.model')
 default_dataset= os.path.join(data_path, 'dataset.csv')
 
@@ -49,24 +51,17 @@ def train_classifier(self):
         return self.d2v, self.classifier
 
     def test_classifier(self):
-        x_train, x_test, y_train, y_test, all_data = self.prepare_all_data()
+        _, x_test, _, y_test, _ = self.prepare_all_data()
         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)==1):
-        dataset_file = argv[0]
-
-        tc = TextClassifier()
-        tc.read_data(dataset_file)
-        tc.test_classifier()
-        tc.train_classifier()
-
-    else:
-        print('Please use the following Commands to use text_classifier for training/testing/predicting:')
-        print ('To Run: python text_classifier.py <dataset_file>')
+def run(dataset_file):
+    tc = TextClassifier()
+    tc.read_data(dataset_file)
+    tc.test_classifier()
+    tc.train_classifier()
 
 if __name__ == "__main__":
-    main(sys.argv[1:])
+    run("dataset.csv")