ibrahimsharaf#14 Relevant file paths

models/classifier_builder.py

@@ -1,14 +1,18 @@
 import logging
 import numpy as np
 import os
+import inspect
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score, f1_score
 from sklearn.externals import joblib
 from .model_builder import ModelBuilder
 from .doc2vec_builder import doc2VecBuilder
 
 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
-
+base_file_path = inspect.getframeinfo(inspect.currentframe()).filename
+base_path = os.path.dirname(os.path.abspath(base_file_path))
+project_dir_path = os.path.dirname(os.path.abspath(base_path))
+classifiers_path = os.path.join(project_dir_path, 'classifiers')
 
 class classifierBuilder(ModelBuilder):
     def __init__(self):
@@ -29,12 +33,14 @@ def train_model(self, d2v, training_vectors, training_labels):
 
     def save_model(self, filename):
         logging.info("Saving trained classification model")
-        joblib.dump(self.model, "./classifiers/" + filename)
+        filename = os.path.join(classifiers_path, filename)
+        joblib.dump(self.model, filename)
 
     def load_model(self, filename):
         logging.info("Loading trained classification model")
-        if (os.path.isfile('./classifiers/' + filename)):
-            loaded_model = joblib.load('./classifiers/' + filename)
+        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

models/doc2vec_builder.py

@@ -1,14 +1,18 @@
 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_builder import ModelBuilder
 
 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
-
+base_file_path = inspect.getframeinfo(inspect.currentframe()).filename
+base_path = os.path.dirname(os.path.abspath(base_file_path))
+project_dir_path = os.path.dirname(os.path.abspath(base_path))
+classifiers_path = os.path.join(project_dir_path, 'classifiers')
 
 class doc2VecBuilder(ModelBuilder):
 
@@ -45,12 +49,14 @@ def train_model(self):
 
     def save_model(self, filename):
         logging.info("Saving trained Doc2Vec model")
-        self.model.save("./classifiers/" + filename)
+        filename = os.path.join(classifiers_path, filename)
+        self.model.save(filename)
 
     def load_model(self, filename):
         logging.info("Loading trained Doc2Vec model")
-        if (os.path.isfile('./classifiers/' + filename)):
-            d2v = Doc2Vec.load("./classifiers/" + filename)
+        filename = os.path.join(classifiers_path, filename)
+        if (os.path.isfile(filename)):
+            d2v = Doc2Vec.load(filename)
             self.model = d2v
         else:
             self.model = None

models/model_builder.py

@@ -22,3 +22,5 @@ def save_model(self):
     @abstractmethod
     def load_model(self):
         pass
+
+

text_classifier.py

@@ -1,12 +1,16 @@
 import pandas as pd
 import logging
 import sys, getopt
+import os, inspect
 from sklearn.model_selection import train_test_split
 from models.doc2vec_builder import doc2VecBuilder
 from models.classifier_builder import classifierBuilder
 
 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
-
+base_file_path = inspect.getframeinfo(inspect.currentframe()).filename
+base_path = os.path.dirname(os.path.abspath(base_file_path))
+project_dir_path = os.path.dirname(os.path.abspath(base_path))
+data_path = os.path.join(project_dir_path, 'data')
 
 class TextClassifier():
 
@@ -16,8 +20,9 @@ def __init__(self):
         self.classifier = classifierBuilder()
         self.dataset = None
 
-    def read_data(self, path):
-        self.dataset = pd.read_csv(path, header=0, delimiter="\t")
+    def read_data(self, filename):
+        filename = os.path.join(data_path, filename)
+        self.dataset = pd.read_csv(filename, header=0, delimiter="\t")
 
     def prepare_all_data(self):
         x_train, x_test, y_train, y_test = train_test_split(self.dataset.review, self.dataset.sentiment, random_state=0,
@@ -53,15 +58,15 @@ def test_classifier(self, d2v_file, classifier_file):
             self.classifier.test_model(self.d2v, x_test, y_test)
 
 
-def run(mode, d2v_file, classifier_file):
+def run(mode,dataset_file, d2v_file, classifier_file):
     tc = TextClassifier()
-    tc.read_data('./data/dataset.csv')
+    tc.read_data(dataset_file)
     if mode == 'Test':
         tc.test_classifier(d2v_file, classifier_file)
     else:
         tc.train_classifier(d2v_file, classifier_file)
 
 
 if __name__ == "__main__":
-    run("Train", "d2v.model", "joblib_model.pkl")
+    run("Train","dataset.csv", "d2v.model", "joblib_model.pkl")
     # run("Test", "d2v.model", "joblib_model.pkl")