Update app.py

app.py

@@ -21,10 +21,15 @@ course_df = pd.read_csv(os.path.join(DATA_DIR, "coursera_course_dataset_v2_no_nu
 coding_df = pd.read_csv(os.path.join(DATA_DIR, "Software Questions.csv"), encoding="latin1")
 
 # Preprocess datasets
-coding_df.rename(columns={'Question': 'question', 'Answer': 'solutions'}, inplace=True)
+coding_df = coding_df.rename(columns={
+    'Question': 'question',
+    'Answer': 'solutions',
+    'Category': 'category',
+    'Difficulty': 'difficulty'
+})
+coding_df.dropna(subset=['question', 'solutions', 'category', 'difficulty'], inplace=True)
 job_df.rename(columns={'company_name': 'company', 'required_skills': 'skills'}, inplace=True)
 course_df.rename(columns={'Title': 'course_title', 'Skills': 'skills'}, inplace=True)
-coding_df.dropna(subset=['question', 'solutions'], inplace=True)
 job_df["job_description"] = job_df["job_description"].fillna("")
 
 # Load BERT model and vectorizer
@@ -34,7 +39,7 @@ vectorizer = TfidfVectorizer()
 # Pydantic model for request body
 class UserInput(BaseModel):
     name: str
-    skills: List[str]  # Required list of skills
+    skills: List[str]  # Required list of categories (e.g., "General Programming", "Data Structures")
     answers: Optional[Dict[str, Dict[str, str]]] = None  # Optional answers
 
 # Evaluate coding answers
@@ -48,14 +53,16 @@ def evaluate_coding_with_time(user_code, correct_code, start_time):
     return round(max(similarity, 0), 2)
 
 # Get coding challenges
-def get_coding_challenges(skills, num_questions=5):
+def get_coding_challenges(categories: List[str], num_questions=5, difficulty: Optional[str] = None):
     skill_challenges = {}
-    for skill in skills:
-        relevant = coding_df[coding_df["question"].str.contains(skill, case=False, na=False)]
+    for category in categories:
+        relevant = coding_df[coding_df["category"].str.contains(category, case=False, na=False)]
+        if difficulty:
+            relevant = relevant[relevant["difficulty"].str.lower() == difficulty.lower()]
         if not relevant.empty:
-            skill_challenges[skill] = relevant.sample(min(num_questions, len(relevant)))[["question", "solutions"]].to_dict(orient="records")
+            skill_challenges[category] = relevant.sample(min(num_questions, len(relevant)))[["question", "solutions", "difficulty"]].to_dict(orient="records")
         else:
-            skill_challenges[skill] = []
+            skill_challenges[category] = []
     return skill_challenges
 
 # Assign proficiency level
@@ -90,13 +97,19 @@ def read_root():
 
 # New endpoint to provide challenges
 @app.get("/challenges")
-def get_user_challenges(skills: List[str]):
+def get_user_challenges(skills: List[str], difficulty: Optional[str] = None):
     if not skills:
         raise HTTPException(status_code=400, detail="Skills list cannot be empty")
-    challenges = get_coding_challenges(skills)
-    # Return only questions (exclude solutions for the user)
+    challenges = get_coding_challenges(skills, difficulty=difficulty)
+    # Return only questions and difficulty (exclude solutions for the user)
     return {
-        "challenges": {skill: [challenge["question"] for challenge in challenge_list] for skill, challenge_list in challenges.items()}
+        "challenges": {
+            category: [
+                {"question": challenge["question"], "difficulty": challenge["difficulty"]}
+                for challenge in challenge_list
+            ]
+            for category, challenge_list in challenges.items()
+        }
     }
 
 @app.post("/assess")