More linting

Author: KingAkeem

src/nlp/gather_data.py

@@ -4,7 +4,8 @@
 
 def write_data():
     """
-    Writes the training data from the csv file to a directory based on the scikit-learn.datasets `load_files` specification.
+    Writes the training data from the csv file to a directory based on the
+    scikit-learn.datasets `load_files` specification.
 
     dataset source: https://www.kaggle.com/hetulmehta/website-classification
 
@@ -15,15 +16,18 @@ def write_data():
             category_2_folder/
                     file_43.txt file_44.txt ...
     """
+
     with open('website_classification.csv') as csvfile:
         website_reader = csv.reader(csvfile, delimiter=',')
         for row in website_reader:
             [id, website, content, category] = row
             if category != 'category':
                 category = category.replace('/', '+')
-                Path(f"training_data/{category}").mkdir(parents=True, exist_ok=True)
-                with open(f'training_data/{category}/{id}.txt', mode='w+') as txtfile:
+		dir_name = f"training_data/{category}"
+                Path(dir_name).mkdir(parents=True, exist_ok=True)
+                with open(f'{dir_name}/{id}.txt', mode='w+') as txtfile:
                     txtfile.write(content)
 
+
 if __name__ == "__main__":
     write_data()

src/nlp/main.py

@@ -24,18 +24,21 @@
     ('clf', SGDClassifier())
 ])
 dataset = load_files('training_data')
-x_train, x_test, y_train, y_test = train_test_split(dataset.data, dataset.target)
+x_train, x_test, y_train, y_test = train_test_split(
+						dataset.data,
+						dataset.target
+					)
 clf.fit(x_train, y_train)
 
-# returns an array of target_name indices
-predicted = clf.predict([html])
 
 website = 'Unknown'
 if soup.title:
     website = soup.title.text
-print(f'The category of {website} is {dataset.target_names[predicted[0]]}');
+
+# returns an array of target_name values
+predicted = clf.predict([html])
+print(f'The category of {website} is {dataset.target_names[predicted[0]]}')
 
 if args.accuracy:
     accuracy = np.mean(predicted == y_test)
     print(f'Accuracy: {accuracy}%')
-