Update app.py

app.py

@@ -59,7 +59,6 @@ def load_dataset(file_path, required_columns=[]):
         logger.error(f"Dataset not found at {file_path}. Exiting.")
         return None
 
-user_df = load_dataset("Updated_User_Profile_Dataset.csv", ["name", "skills", "level"])
 questions_df = load_dataset("Generated_Skill-Based_Questions.csv", ["Skill", "Question", "Answer"])
 courses_df = load_dataset("coursera_course_dataset_v2_no_null.csv", ["skills", "course_title", "Organization", "level"])
 jobs_df = load_dataset("Updated_Job_Posting_Dataset.csv", ["job_title", "company_name", "location", "required_skills", "job_description"])
@@ -184,8 +183,8 @@ def recommend_courses(skills_to_improve, user_level, upgrade=False):
 
     collab_scores = []
     for skill in skills_to_improve:
-        overlap = sum(1 for user_skills_str in user_df['skills'] if pd.notna(user_skills_str) and skill.lower() in user_skills_str.lower())
-        collab_scores.append(overlap / len(user_df))
+        overlap = 1  # Simplified since user_df is removed
+        collab_scores.append(overlap)
     collab_similarities = np.array([collab_scores]).repeat(len(courses_df), axis=0).T
 
     popularity = courses_df['popularity'].fillna(0.5).to_numpy()
@@ -231,28 +230,34 @@ def assess_skills():
     data = request.get_json()
     logger.info(f"Received request: {data}")
     
-    if not data or 'user_index' not in data or 'answers' not in data:
-        logger.error("Invalid input: Missing 'user_index' or 'answers' in JSON body.")
-        return jsonify({"error": "Invalid input. Provide 'user_index' and 'answers' in JSON body."}), 400
+    # Validate required fields
+    if not data or 'user_name' not in data or 'skills' not in data or 'answers' not in data:
+        logger.error("Invalid input: Missing 'user_name', 'skills', or 'answers' in JSON body.")
+        return jsonify({"error": "Invalid input. Provide 'user_name', 'skills', and 'answers' in JSON body."}), 400
 
-    # Validate answers length immediately
+    user_name = data['user_name']
+    user_skills = data['skills']
     answers = data['answers']
+
+    # Validate inputs
+    if not isinstance(user_name, str) or not user_name.strip():
+        logger.error("Invalid user_name: Must be a non-empty string.")
+        return jsonify({"error": "Invalid user_name. Must be a non-empty string."}), 400
+
+    if not isinstance(user_skills, list) or not user_skills or not all(isinstance(skill, str) and skill.strip() for skill in user_skills):
+        logger.error("Invalid skills: Must be a non-empty list of non-empty strings.")
+        return jsonify({"error": "Invalid skills. Must be a non-empty list of non-empty strings."}), 400
+
     if not isinstance(answers, list):
         logger.error(f"Answers must be a list, got: {type(answers)}")
         return jsonify({"error": "Answers must be a list."}), 400
-    if len(answers) != 4:
-        logger.error(f"Expected exactly 4 answers, but received {len(answers)}.")
-        return jsonify({"error": f"Please provide exactly 4 answers. Received {len(answers)}."}), 400
-
-    user_index = int(data['user_index'])
-    if user_index < 0 or user_index >= len(user_df):
-        logger.error(f"Invalid user index: {user_index}. Must be between 0 and {len(user_df) - 1}.")
-        return jsonify({"error": "Invalid user index."}), 400
-
-    user_text = user_df.loc[user_index, 'skills']
-    user_skills = [skill.strip() for skill in user_text.split(",") if skill.strip()] if isinstance(user_text, str) else ["Python", "SQL"]
-    user_name = user_df.loc[user_index, 'name']
-    user_level = user_df.loc[user_index, 'level'] if 'level' in user_df.columns and pd.notna(user_df.loc[user_index, 'level']) else 'Intermediate'
+
+    # Ensure the number of answers matches the number of skills
+    if len(answers) != len(user_skills):
+        logger.error(f"Number of answers ({len(answers)}) does not match number of skills ({len(user_skills)}).")
+        return jsonify({"error": f"Number of answers ({len(answers)}) must match the number of skills ({len(user_skills)})."}), 400
+
+    user_level = 'Intermediate'  # Default level since user_df is removed
     logger.info(f"User: {user_name}, Skills: {user_skills}, Level: {user_level}")
 
     initialize_resources(user_skills)
@@ -282,9 +287,9 @@ def assess_skills():
     logger.info(f"Selected questions: {user_questions[['Skill', 'Question']].to_dict(orient='records')}")
     logger.info(f"Number of selected questions: {len(user_questions)}")
 
-    if len(user_questions) != 4:
-        logger.error(f"Not enough questions for all skills. Expected 4, got {len(user_questions)}.")
-        return jsonify({"error": f"Not enough questions for all skills! Expected 4, got {len(user_questions)}."}), 500
+    if len(user_questions) != len(user_skills):
+        logger.error(f"Number of selected questions ({len(user_questions)}) does not match number of skills ({len(user_skills)}).")
+        return jsonify({"error": f"Internal error: Number of selected questions ({len(user_questions)}) does not match number of skills ({len(user_skills)})."}), 500
 
     user_responses = []
     for idx, row in user_questions.iterrows():