Update app.py

app.py

@@ -1,4 +1,6 @@
 
+
+
 # import gradio as gr
 # import pandas as pd 
 # import numpy as np 
@@ -6,16 +8,21 @@
 # import sklearn
 # from datasets import load_dataset
 
+# # Read the data
 # data = pd.read_csv("mldata.csv")
 
+# # Function to load model based on selection
+# def load_model(model_choice):
+#     if model_choice == "Random Forest":
+#         with open('rfweights (1).pkl', 'rb') as pickleFile:
+#             return pickle.load(pickleFile)
+#     elif model_choice == "Decision Tree":
+#         with open('dtreeweights.pkl', 'rb') as pickleFile:
+#             return pickle.load(pickleFile)
+#     else:
+#         raise ValueError("Invalid model selection")
 
-# #load prediction model from notebook
-# # pickleFile = open('rfweights (1).pkl','rb')
-# pickelFile=open('dtreeweights.pkl','rb')
-# rfmodel = pickle.load(pickelFile)
-
-# #Obtain the categorical/nominal data because it is not coded according (but based on the first occurence, first come first assign number)
-# #Therefore, need to read from the file to obtain the number.
+# # Prepare categorical data (same as original code)
 # categorical_cols = data[[
 #     'certifications',
 #     'workshops',
@@ -23,63 +30,35 @@
 #     'interested career area ',
 #     'Type of company want to settle in?',
 #     'Interested Type of Books'
-#                         ]]
-# #assign the datatype and automated assigned code
+# ]]
+
+# # Assign category codes
 # for i in categorical_cols:
 #     data[i] = data[i].astype('category')
 #     data[i] = data[i].cat.codes
 
-# #embedded nominal/ categorical values for certicates
-# certificates_name = list(categorical_cols['certifications'].unique())
-# certificates_code = list(data['certifications'].unique())
-# certificates_references = dict(zip(certificates_name,certificates_code))
-
-# #embedding for workshops
-# workshop_name = list(categorical_cols['workshops'].unique())
-# workshop_code = list(data['workshops'].unique())
-# workshop_references = dict(zip(workshop_name, workshop_code))
-
-# #embedding for subjects_interests
-# subjects_interest_name = list(categorical_cols['Interested subjects'].unique())
-# subjects_interest_code = list(data['Interested subjects'].unique())
-# subjects_interest_references = dict(zip(subjects_interest_name, subjects_interest_code))
-
-# #embedding for career_interests
-# career_interest_name = list(categorical_cols['interested career area '].unique())
-# career_interest_code = list(data['interested career area '].unique())
-# career_interest_references = dict(zip(career_interest_name, career_interest_code))
-
-# #embedding for company_intends
-# company_intends_name = list(categorical_cols['Type of company want to settle in?'].unique())
-# company_intends_code = list(data['Type of company want to settle in?'].unique())
-# company_intends_references = dict(zip(company_intends_name, company_intends_code))
-
-# #embedding for book_interests
-# book_interest_name = list(categorical_cols['Interested Type of Books'].unique())
-# book_interest_code = list(data['Interested Type of Books'].unique())
-# book_interest_references = dict(zip(book_interest_name, book_interest_code))
-
-
-# def greet(name):
-#     return f"Hello, {name}!"
-
-# '''#dummy encode
-# def dummy_encode(df):
-#     if input == "Management":
-#         return [1, 0]
-#     elif input == "Technical":
-#         return [0, 1]
-#     elif input == "smart worker":
-#         return [1, 0]
-#     elif input == "hard worker":
-#         return [0, 1]
-#     else:
-#         return "Invalid choice"'''
-
-# def rfprediction(name, logical_thinking, hackathon_attend, coding_skills, public_speaking_skills,
-#                  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,
+# # Create reference dictionaries for embeddings (same as original code)
+# def create_embedding_dict(column):
+#     unique_names = list(categorical_cols[column].unique())
+#     unique_codes = list(data[column].unique())
+#     return dict(zip(unique_names, unique_codes))
+
+# certificates_references = create_embedding_dict('certifications')
+# workshop_references = create_embedding_dict('workshops')
+# subjects_interest_references = create_embedding_dict('Interested subjects')
+# career_interest_references = create_embedding_dict('interested career area ')
+# company_intends_references = create_embedding_dict('Type of company want to settle in?')
+# book_interest_references = create_embedding_dict('Interested Type of Books')
+
+# # Prediction function (modified to accept model choice)
+# def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_skills, public_speaking_skills,
+#                  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 (same as original code)
 #     df = pd.DataFrame.from_dict(
 #         {
 #             "logical_thinking": [logical_thinking],
@@ -108,18 +87,20 @@
 #         }
 #     )
     
-#     #replace str to numeric representation, dtype chged to int8
-#     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})
+#     # 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
-#     #first we convert into list from df
+#     # Dummy encoding (same as original code)
 #     userdata_list = df.values.tolist()
-#     #now we append boolean based conditions
+    
+#     # Management-Technical dummy encoding
 #     if(df["management_technical"].values == "Management"):
 #         userdata_list[0].extend([1])
 #         userdata_list[0].extend([0])
@@ -128,8 +109,10 @@
 #         userdata_list[0].extend([0])
 #         userdata_list[0].extend([1])
 #         userdata_list[0].remove('Technical')
-#     else: return "Err"
+#     else: 
+#         return "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])
@@ -138,30 +121,33 @@
 #         userdata_list[0].extend([0])
 #         userdata_list[0].extend([1])
 #         userdata_list[0].remove('hard worker')
-#     else: return "Err"
+#     else: 
+#         return "Error in Smart-Hard worker encoding"
 
-#     prediction_result = rfmodel.predict(userdata_list)
+#     # Prediction
 #     prediction_result_all = rfmodel.predict_proba(userdata_list)
-#     print(prediction_result_all)
-#     #create a list for output 
-#     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]),
-#                    }
+    
+#     # Create result dictionary
+#     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]),
+#     }
 #     return result_list
 
+# # Lists for dropdown menus (same as original code)
 # cert_list = ["app development", "distro making", "full stack", "hadoop", "information security", "machine learning", "python", "r programming", "shell programming"]
 # workshop_list = ["cloud computing", "data science", "database security", "game development", "hacking", "system designing", "testing", "web technologies"]
-# skill = ["excellent", "medium", "poor"] #can be used in this section and memory capability section
+# skill = ["excellent", "medium", "poor"]
 # subject_list = ["cloud computing", "Computer Architecture", "data engineering", "hacking", "IOT", "Management", "networks", "parallel computing", "programming", "Software Engineering"]
 # career_list = ["Business process analyst", "cloud computing", "developer", "security", "system developer", "testing"]
 # company_list = ["BPA", "Cloud Services", "Finance", "Product based", "product development", "SAaS services", "Sales and Marketing", "Service Based", "Testing and Maintainance Services", "Web Services"]
@@ -169,44 +155,47 @@
 # Choice_list = ["Management", "Technical"]
 # worker_list = ["hard worker", "smart worker"]
 
-# demo =gr.Interface(fn = rfprediction, inputs=[
-#                 gr.Textbox(placeholder="What is your name?", label="Name"),
-#                 gr.Slider(minimum=1,maximum=9,value=3,step=1,label="Are you a logical thinking person?", info="Scale: 1 - 9"),
-#                 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.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"),
-#                 gr.Dropdown(skill, label="Is your memory capability good?"),
-#                 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.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.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=gr.Label(num_top_classes=5), 
-#                 title="IT-Career Recommendation System: TMI4033 Colletive Intelligence, Group 12",
-#                 description="Members: Derrick Lim Kin Yeap 74597, Jason Jong Sheng Tat 75125, Jason Ng Yong Xing 75127, Muhamad Hazrie Bin Suhkery 73555 "
-#                 )
-
-
-# #main
+# # Create Gradio interface (modified to include model selection)
+# demo = gr.Interface(
+#     fn=rfprediction, 
+#     inputs=[
+#         gr.Dropdown(["Random Forest", "Decision Tree"], label="Select Machine Learning Model"),
+#         gr.Textbox(placeholder="What is your name?", label="Name"),
+#         gr.Slider(minimum=1, maximum=9, value=3, step=1, label="Are you a logical thinking person?", info="Scale: 1 - 9"),
+#         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.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"),
+#         gr.Dropdown(skill, label="Is your memory capability good?"),
+#         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.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.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=gr.Label(num_top_classes=5), 
+#     title="IT-Career Recommendation System: TMI4033 Colletive Intelligence, Group 12",
+#     description="Members: Derrick Lim Kin Yeap 74597, Jason Jong Sheng Tat 75125, Jason Ng Yong Xing 75127, Muhamad Hazrie Bin Suhkery 73555 "
+# )
+
+# # Main execution
 # if __name__ == "__main__":
 #     demo.launch(share=True)
 
-
 import gradio as gr
 import pandas as pd 
 import numpy as np 
 import pickle
 import sklearn
+import requests
 from datasets import load_dataset
 
 # Read the data
@@ -223,7 +212,7 @@ def load_model(model_choice):
     else:
         raise ValueError("Invalid model selection")
 
-# Prepare categorical data (same as original code)
+# Prepare categorical data
 categorical_cols = data[[
     'certifications',
     'workshops',
@@ -238,7 +227,7 @@ for i in categorical_cols:
     data[i] = data[i].astype('category')
     data[i] = data[i].cat.codes
 
-# Create reference dictionaries for embeddings (same as original code)
+# Create reference dictionaries for embeddings
 def create_embedding_dict(column):
     unique_names = list(categorical_cols[column].unique())
     unique_codes = list(data[column].unique())
@@ -251,7 +240,7 @@ career_interest_references = create_embedding_dict('interested career area ')
 company_intends_references = create_embedding_dict('Type of company want to settle in?')
 book_interest_references = create_embedding_dict('Interested Type of Books')
 
-# Prediction function (modified to accept model choice)
+# Prediction function (modified to fetch job details)
 def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_skills, public_speaking_skills,
                  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,
@@ -259,7 +248,7 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
     # Load the selected model
     rfmodel = load_model(model_choice)
     
-    # Create DataFrame (same as original code)
+    # Create DataFrame
     df = pd.DataFrame.from_dict(
         {
             "logical_thinking": [logical_thinking],
@@ -298,7 +287,7 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
         "book_interest": book_interest_references
     })
     
-    # Dummy encoding (same as original code)
+    # Dummy encoding
     userdata_list = df.values.tolist()
     
     # Management-Technical dummy encoding
@@ -343,9 +332,35 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
         "UX Designer": float(prediction_result_all[0][10]),
         "Web Developer": float(prediction_result_all[0][11]),
     }
+    
+    # Get the top predicted job
+    job_pre = max(result_list, key=result_list.get)
+    
+    # Fetch job details using RapidAPI
+    url = "https://jobs-api14.p.rapidapi.com/v2/list"
+    querystring = {
+        "query": job_pre,
+        "location": "India",
+        "autoTranslateLocation": "false",
+        "remoteOnly": "false",
+        "employmentTypes": "fulltime;parttime;intern;contractor"
+    }
+    headers = {
+        "x-rapidapi-key": "714f5a2539msh798d996c3243876p19c71ajsnfcd7ce481cb9",
+        "x-rapidapi-host": "jobs-api14.p.rapidapi.com"
+    }
+    
+    try:
+        response = requests.get(url, headers=headers, params=querystring)
+        job_response = response.json()
+        print(job_response)  # Print the response for debugging
+    except Exception as e:
+        print(f"Error fetching job details: {e}")
+        job_response = {}
+    
     return result_list
 
-# Lists for dropdown menus (same as original code)
+# Lists for dropdown menus
 cert_list = ["app development", "distro making", "full stack", "hadoop", "information security", "machine learning", "python", "r programming", "shell programming"]
 workshop_list = ["cloud computing", "data science", "database security", "game development", "hacking", "system designing", "testing", "web technologies"]
 skill = ["excellent", "medium", "poor"]
@@ -356,7 +371,7 @@ book_list = ["Action and Adventure", "Anthology", "Art", "Autobiographies", "Bio
 Choice_list = ["Management", "Technical"]
 worker_list = ["hard worker", "smart worker"]
 
-# Create Gradio interface (modified to include model selection)
+# Create Gradio interface
 demo = gr.Interface(
     fn=rfprediction, 
     inputs=[