Update app.py

app.py

@@ -5,7 +5,8 @@ import pickle
 import sklearn
 from datasets import load_dataset
 import joblib
-import requests  
+import requests
+import os
 
 # Read the data
 data = pd.read_csv("mldata.csv")
@@ -18,7 +19,6 @@ def load_model(model_choice):
     elif model_choice == "Decision Tree":
         with open('dtreeweights.pkl', 'rb') as pickleFile:
             return pickle.load(pickleFile)
-   
     else:
         raise ValueError("Invalid model selection")
 
@@ -30,7 +30,7 @@ categorical_cols = data[[
     'interested career area ',
     'Type of company want to settle in?',
     'Interested Type of Books'
-]]
+]].copy()
 
 # Assign category codes
 for i in categorical_cols:
@@ -52,6 +52,9 @@ book_interest_references = create_embedding_dict('Interested Type of Books')
 
 # Function to fetch job listings
 def fetch_job_listings(job_title):
+    # Use environment variable for API key (more secure)
+    api_key = os.environ.get('RAPIDAPI_KEY', '714f5a2539msh798d996c3243876p19c71ajsnfcd7ce481cb9')
+    
     url = "https://jobs-api14.p.rapidapi.com/v2/list"
     querystring = {
         "query": job_title,
@@ -61,12 +64,13 @@ def fetch_job_listings(job_title):
         "employmentTypes": "fulltime;parttime;intern;contractor"
     }
     headers = {
-        "x-rapidapi-key": "714f5a2539msh798d996c3243876p19c71ajsnfcd7ce481cb9",
+        "x-rapidapi-key": api_key,
         "x-rapidapi-host": "jobs-api14.p.rapidapi.com"
     }
 
     try:
-        response = requests.get(url, headers=headers, params=querystring)
+        response = requests.get(url, headers=headers, params=querystring, timeout=10)
+        response.raise_for_status()
         job_data = response.json()
         
         # Process and format job listings
@@ -91,12 +95,13 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
                  self_learning, extra_course, certificate_code, worskhop_code, read_writing_skill, memory_capability,
                  subject_interest, career_interest, company_intend, senior_elder_advise, book_interest, introvert_extro,
                  team_player, management_technical, smart_hardworker):
-    # Load the selected model
-    rfmodel = load_model(model_choice)
     
-    # Create DataFrame 
-    df = pd.DataFrame.from_dict(
-        {
+    try:
+        # Load the selected model
+        rfmodel = load_model(model_choice)
+        
+        # Create DataFrame 
+        df = pd.DataFrame({
             "logical_thinking": [logical_thinking],
             "hackathon_attend": [hackathon_attend],
             "coding_skills": [coding_skills],
@@ -106,11 +111,11 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
             "certificate": [certificate_code],
             "workshop": [worskhop_code],
             "read_writing_skills": [
-                    (0 if "poor" in read_writing_skill else 1 if "medium" in read_writing_skill else 2)
-                ],
+                (0 if "poor" in read_writing_skill else 1 if "medium" in read_writing_skill else 2)
+            ],
             "memory_capability": [
-                    (0 if "poor" in memory_capability else 1 if "medium" in memory_capability else 2)   
-                ],
+                (0 if "poor" in memory_capability else 1 if "medium" in memory_capability else 2)   
+            ],
             "subject_interest": [subject_interest],
             "career_interest": [career_interest],
             "company_intend": [company_intend],
@@ -118,74 +123,80 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
             "book_interest": [book_interest],
             "introvert_extro": [introvert_extro],
             "team_player": [team_player],
-            "management_technical":[management_technical],
+            "management_technical": [management_technical],
             "smart_hardworker": [smart_hardworker]
+        })
+        
+        # Replace string values with numeric representations - FIX for FutureWarning
+        replacement_dict = {
+            "certificate": certificates_references, 
+            "workshop": workshop_references,
+            "subject_interest": subjects_interest_references,
+            "career_interest": career_interest_references,
+            "company_intend": company_intends_references,
+            "book_interest": book_interest_references
         }
-    )
-    
-    # Replace string values with numeric representations
-    df = df.replace({
-        "certificate": certificates_references, 
-        "workshop": workshop_references,
-        "subject_interest": subjects_interest_references,
-        "career_interest": career_interest_references,
-        "company_intend": company_intends_references,
-        "book_interest": book_interest_references
-    })
-    
-    # Dummy encoding 
-    userdata_list = df.values.tolist()
-    
-    # Management-Technical dummy encoding
-    if(df["management_technical"].values == "Management"):
-        userdata_list[0].extend([1])
-        userdata_list[0].extend([0])
-        userdata_list[0].remove('Management')
-    elif(df["management_technical"].values == "Technical"):
-        userdata_list[0].extend([0])
-        userdata_list[0].extend([1])
-        userdata_list[0].remove('Technical')
-    else: 
-        return "Error in Management-Technical encoding"
+        
+        for col, mapping in replacement_dict.items():
+            if col in df.columns:
+                df[col] = df[col].map(mapping)
+        
+        # Dummy encoding 
+        userdata_list = df.values.tolist()
+        
+        # Management-Technical dummy encoding
+        if df["management_technical"].values[0] == "Management":
+            userdata_list[0].extend([1, 0])
+            userdata_list[0].remove('Management')
+        elif df["management_technical"].values[0] == "Technical":
+            userdata_list[0].extend([0, 1])
+            userdata_list[0].remove('Technical')
+        else: 
+            return {"Error": 1.0}, [["Error in Management-Technical encoding", "", "", ""]]
 
-    # Smart-Hard worker dummy encoding
-    if(df["smart_hardworker"].values == "smart worker"):
-        userdata_list[0].extend([1])
-        userdata_list[0].extend([0])
-        userdata_list[0].remove('smart worker')
-    elif(df["smart_hardworker"].values == "hard worker"):
-        userdata_list[0].extend([0])
-        userdata_list[0].extend([1])
-        userdata_list[0].remove('hard worker')
-    else: 
-        return "Error in Smart-Hard worker encoding"
+        # Smart-Hard worker dummy encoding
+        if df["smart_hardworker"].values[0] == "smart worker":
+            userdata_list[0].extend([1, 0])
+            userdata_list[0].remove('smart worker')
+        elif df["smart_hardworker"].values[0] == "hard worker":
+            userdata_list[0].extend([0, 1])
+            userdata_list[0].remove('hard worker')
+        else: 
+            return {"Error": 1.0}, [["Error in Smart-Hard worker encoding", "", "", ""]]
 
-    # Prediction
-    prediction_result_all = rfmodel.predict_proba(userdata_list)
-    
-    # Create result dictionary with probabilities
-    result_list = {
-        "Applications Developer": float(prediction_result_all[0][0]),
-        "CRM Technical Developer": float(prediction_result_all[0][1]),
-        "Database Developer": float(prediction_result_all[0][2]),
-        "Mobile Applications Developer": float(prediction_result_all[0][3]),
-        "Network Security Engineer": float(prediction_result_all[0][4]),
-        "Software Developer": float(prediction_result_all[0][5]),
-        "Software Engineer": float(prediction_result_all[0][6]),
-        "Software Quality Assurance (QA)/ Testing": float(prediction_result_all[0][7]),
-        "Systems Security Administrator": float(prediction_result_all[0][8]),
-        "Technical Support": float(prediction_result_all[0][9]),
-        "UX Designer": float(prediction_result_all[0][10]),
-        "Web Developer": float(prediction_result_all[0][11]),
-    }
-    
-    # Find the top predicted career
-    top_career = max(result_list, key=result_list.get)
-    
-    # Fetch job listings for the top predicted career
-    job_suggestions = fetch_job_listings(top_career)
+        # Convert to numpy array for prediction
+        userdata_array = np.array(userdata_list)
+        
+        # Prediction
+        prediction_result_all = rfmodel.predict_proba(userdata_array)
+        
+        # Create result dictionary with probabilities
+        result_list = {
+            "Applications Developer": float(prediction_result_all[0][0]),
+            "CRM Technical Developer": float(prediction_result_all[0][1]),
+            "Database Developer": float(prediction_result_all[0][2]),
+            "Mobile Applications Developer": float(prediction_result_all[0][3]),
+            "Network Security Engineer": float(prediction_result_all[0][4]),
+            "Software Developer": float(prediction_result_all[0][5]),
+            "Software Engineer": float(prediction_result_all[0][6]),
+            "Software Quality Assurance (QA)/ Testing": float(prediction_result_all[0][7]),
+            "Systems Security Administrator": float(prediction_result_all[0][8]),
+            "Technical Support": float(prediction_result_all[0][9]),
+            "UX Designer": float(prediction_result_all[0][10]),
+            "Web Developer": float(prediction_result_all[0][11]),
+        }
+        
+        # Find the top predicted career
+        top_career = max(result_list, key=result_list.get)
+        
+        # Fetch job listings for the top predicted career
+        job_suggestions = fetch_job_listings(top_career)
+        
+        return result_list, job_suggestions
     
-    return result_list, job_suggestions
+    except Exception as e:
+        error_msg = f"Error during prediction: {str(e)}"
+        return {"Error": 1.0}, [[error_msg, "", "", ""]]
 
 # Lists for dropdown menus
 cert_list = ["app development", "distro making", "full stack", "hadoop", "information security", "machine learning", "python", "r programming", "shell programming"]
@@ -217,8 +228,8 @@ demo = gr.Interface(
         gr.Slider(minimum=0, maximum=6, value=0, step=1, label="Do you attend any Hackathons?", info="Scale: 0 - 6 | 0 - if not attended any"),
         gr.Slider(minimum=1, maximum=9, value=5, step=1, label="How do you rate your coding skills?", info="Scale: 1 - 9"),
         gr.Slider(minimum=1, maximum=9, value=3, step=1, label="How do you rate your public speaking skills/confidency?", info="Scale: 1 - 9"),
-        gr.Radio({"Yes", "No"}, type="index", label="Are you a self-learning person? *"),
-        gr.Radio({"Yes", "No"}, type="index", label="Do you take extra courses in uni (other than IT)? *"),
+        gr.Radio(["Yes", "No"], type="index", label="Are you a self-learning person? *"),
+        gr.Radio(["Yes", "No"], type="index", label="Do you take extra courses in uni (other than IT)? *"),
         gr.Dropdown(cert_list, label="Select a certificate you took!"),
         gr.Dropdown(workshop_list, label="Select a workshop you attended!"),
         gr.Dropdown(skill, label="Select your read and writing skill"),
@@ -226,17 +237,17 @@ demo = gr.Interface(
         gr.Dropdown(subject_list, label="What subject you are interested in?"),
         gr.Dropdown(career_list, label="Which IT-Career do you have interests in?"),
         gr.Dropdown(company_list, label="Do you have any interested company that you intend to settle in?"),
-        gr.Radio({"Yes", "No"}, type="index", label="Do you ever seek any advices from senior or elders? *"),
+        gr.Radio(["Yes", "No"], type="index", label="Do you ever seek any advices from senior or elders? *"),
         gr.Dropdown(book_list, label="Select your interested genre of book!"),
-        gr.Radio({"Yes", "No"}, type="index", label="Are you an Introvert?| No - extrovert *"),
-        gr.Radio({"Yes", "No"}, type="index", label="Ever worked in a team? *"),
+        gr.Radio(["Yes", "No"], type="index", label="Are you an Introvert?| No - extrovert *"),
+        gr.Radio(["Yes", "No"], type="index", label="Ever worked in a team? *"),
         gr.Dropdown(Choice_list, label="Which area do you prefer: Management or Technical?"),
         gr.Dropdown(worker_list, label="Are you a Smart worker or Hard worker?")
     ],
     outputs=create_output_component(), 
-    title="Ai-Enhanced career guidance system"
+    title="AI-Enhanced Career Guidance System"
 )
 
 # Main execution
 if __name__ == "__main__":
-    demo.launch(share=True)
+    demo.launch(share=False)  # share=True not supported on HF Spaces