python code modified as per pylint suggestions

app.py

@@ -1,5 +1,8 @@
+"""
+This module contains the main Flask application for the course recommendation system.
+"""
+
 from flask import Flask, render_template, request
-import os
 from data_loader import load_clean_data
 from helper import get_recommendations
 
@@ -27,16 +30,14 @@ def recommend():
     """
     Recommendation page route. Processes the user's input and provides course recommendations.
     
-    This route receives a course name from the form on the home page and uses it to find similar courses. 
+    This route receives a course name from the form and uses it to find similar courses. 
     It then renders the 'recommendations.html' template with the recommendations.
     
     Returns:
     - Rendered HTML template for the recommendations page with the recommended courses.
     """
     course_name = request.form['course_name']
-
     recommendations = get_recommendations(course_name, data, similarity_matrix)
-
     return render_template('recommendations.html', recommendations=recommendations)
 
 if __name__ == '__main__':

data_loader.py

@@ -1,3 +1,7 @@
+"""
+Module to load and clean course data and similarity matrix.
+"""
+
 import os
 import pickle
 import pandas as pd
@@ -8,7 +12,8 @@ def load_clean_data():
     
     This function loads the precomputed similarity matrix and the course data from CSV files.
     It handles any potential errors during file loading and logs them for debugging.
-    It also ensures that the data does not have duplicates and ascii characters in the data are removed.
+    It also ensures that the data does not have duplicates and ascii characters in the data are
+    removed.
     
     Returns:
     - data: Clean DataFrame containing course information.
@@ -18,23 +23,22 @@ def load_clean_data():
     try:
         # Get the absolute path to the current directory (where the script is located)
         current_dir = os.path.dirname(os.path.abspath(__file__))
-
         # Build paths to the necessary files in the 'models' and 'data' directories
         similarity_matrix_path = os.path.join(current_dir, 'models', 'similarity_matrix.pkl')
         data_path = os.path.join(current_dir, 'data', 'coursera.csv')
-
         # Load the files
-        similarity_matrix = pickle.load(open(similarity_matrix_path, 'rb'))
+        with open(similarity_matrix_path, 'rb') as f:
+            similarity_matrix = pickle.load(f)
         data = pd.read_csv(data_path, encoding='utf-8')
-
     except (FileNotFoundError, pickle.UnpicklingError, pd.errors.EmptyDataError) as e:
         # Log the error and raise an exception if loading fails
         print(f"Error loading files: {e}")
         raise Exception(f"Error loading files: {e}")
-    
+
     # Drop duplicates from the course data based on key columns
-    data = data.drop_duplicates(subset=['Course Name', 'University', 'Difficulty Level', 'Course Rating', 'Course URL', 'Course Description'])
-
+    data = data.drop_duplicates(subset=['Course Name', 'University', 'Difficulty Level',
+    'Course Rating', 'Course URL', 'Course Description'])
+
     # Function to remove non-ASCII characters
     def remove_non_ascii(text):
         return text.encode('ascii', 'ignore').decode('ascii') if isinstance(text, str) else text

helper.py

@@ -1,6 +1,7 @@
-import pandas as pd
-import re
-
+"""
+Module for generating course recommendations based on similarity scores.
+"""
+
 def normalize_rating(rating_str):
     """
     Normalize the course rating to a 0-1 scale.
@@ -13,7 +14,8 @@ def normalize_rating(rating_str):
     except ValueError:
         return 0  # Return 0 if the rating is invalid
 
-def get_recommendations(course_name, data, similarity_matrix, top_n=6, threshold=90, rating_weight=0.05):
+def get_recommendations(course_name, data, similarity_matrix, top_n=6,
+                        rating_weight=0.05):
     """
     Get top N course recommendations based on similarity to the given course name.
     
@@ -31,12 +33,12 @@ def get_recommendations(course_name, data, similarity_matrix, top_n=6, threshold
     """
     course_name = data[data['Course Name'] == course_name]  # Filter data for selected course
     course_idx = course_name.index[0]  # Get the index of the selected course
-    similarity_scores = list(enumerate(similarity_matrix[course_idx]))  # Get similarity scores for all courses
-    
+    similarity_scores = list(enumerate(similarity_matrix[course_idx]))  # Get similarity for courses
+
     recommendations = []
     for idx, similarity_score in sorted(similarity_scores, key=lambda x: x[1], reverse=True)[:top_n]:
         course_data = data.iloc[idx]  # Get course data for the current recommendation
-        normalized_rating = normalize_rating(course_data.get('Course Rating', '0'))  # Normalize rating
+        normalized_rating = normalize_rating(course_data.get('Course Rating', '0'))
 
         # Prepare recommendation dictionary with relevant course information
         recommendations.append({
@@ -46,8 +48,8 @@ def get_recommendations(course_name, data, similarity_matrix, top_n=6, threshold
             "institution": course_data.get('University', 'Unknown'),
             "difficulty_level": course_data.get('Difficulty Level', 'Unknown'),
             "similarity": similarity_score,
-            "final_score": similarity_score * (1 - rating_weight) + normalized_rating * rating_weight  # Weighted final score
+            "final_score": similarity_score * (1 - rating_weight) + normalized_rating * rating_weight
         })
 
     # Return sorted recommendations based on the final score
-    return sorted(recommendations, key=lambda x: x['final_score'], reverse=True)
+    return sorted(recommendations, key=lambda x: x['final_score'], reverse=True)