Update app.py

app.py

@@ -1,206 +1,6 @@
 
 
 
-# import gradio as gr
-# import pandas as pd 
-# import numpy as np 
-# import pickle
-# import sklearn
-# from datasets import load_dataset
-# import joblib
-
-
-# # 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)
-#     elif model_choice == "Sequential Model":
-#         try:
-#             # Try loading the Sequential model saved using joblib
-#             with open('my_seq_model_second.pkl', 'rb') as pickleFile:
-#                 return joblib.load(pickleFile)
-#         except:
-#             # If joblib loading fails, fallback to TensorFlow loading
-#             return load_model('my_seq_model (1)')
-#     else:
-#         raise ValueError("Invalid model selection")
-
-# # Prepare categorical data (same as original code)
-# categorical_cols = data[[
-#     'certifications',
-#     'workshops',
-#     'Interested subjects',
-#     'interested career area ',
-#     'Type of company want to settle in?',
-#     'Interested Type of Books'
-# ]]
-
-# # Assign category codes
-# 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)
-# 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],
-#             "hackathon_attend": [hackathon_attend],
-#             "coding_skills": [coding_skills],
-#             "public_speaking_skills": [public_speaking_skills],
-#             "self_learning": [self_learning],
-#             "extra_course": [extra_course],
-#             "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)
-#                 ],
-#             "memory_capability": [
-#                     (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],
-#             "senior_elder_advise": [senior_elder_advise],
-#             "book_interest": [book_interest],
-#             "introvert_extro": [introvert_extro],
-#             "team_player": [team_player],
-#             "management_technical":[management_technical],
-#             "smart_hardworker": [smart_hardworker]
-#         }
-#     )
-    
-#     # 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 (same as original code)
-#     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"
-
-#     # 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"
-
-#     # Prediction
-#     prediction_result_all = rfmodel.predict_proba(userdata_list)
-    
-#     # 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"]
-# 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"]
-# book_list = ["Action and Adventure", "Anthology", "Art", "Autobiographies", "Biographies", "Childrens", "Comics","Cookbooks","Diaries","Dictionaries","Drama","Encyclopedias","Fantasy","Guide","Health","History","Horror","Journals","Math","Mystery","Poetry","Prayer books","Religion-Spirituality","Romance","Satire","Science","Science fiction","Self help","Series","Travel","Trilogy"]
-# Choice_list = ["Management", "Technical"]
-# worker_list = ["hard worker", "smart worker"]
-
-# # Create Gradio interface (modified to include model selection)
-# demo = gr.Interface(
-#     fn=rfprediction, 
-#     inputs=[
-#         gr.Dropdown(["Random Forest", "Decision Tree","Sequential Model"], 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 
@@ -208,7 +8,7 @@ import pickle
 import sklearn
 from datasets import load_dataset
 import joblib
-import tensorflow as tf
+
 
 # Read the data
 data = pd.read_csv("mldata.csv")
@@ -221,18 +21,11 @@ def load_model(model_choice):
     elif model_choice == "Decision Tree":
         with open('dtreeweights.pkl', 'rb') as pickleFile:
             return pickle.load(pickleFile)
-    elif model_choice == "Sequential Model":
-        try:
-            # Try loading the Sequential model saved using joblib
-            model = joblib.load('my_seq_model_second.pkl')
-        except:
-            # If joblib loading fails, fallback to TensorFlow loading
-            model = tf.keras.models.load_model('my_seq_model (1)')
-        return model
+   
     else:
         raise ValueError("Invalid model selection")
 
-# Prepare categorical data
+# Prepare categorical data (same as original code)
 categorical_cols = data[[
     'certifications',
     'workshops',
@@ -247,7 +40,7 @@ for i in categorical_cols:
     data[i] = data[i].astype('category')
     data[i] = data[i].cat.codes
 
-# Create reference dictionaries for embeddings
+# 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())
@@ -260,7 +53,7 @@ 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
+# 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,
@@ -268,7 +61,7 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
     # Load the selected model
     rfmodel = load_model(model_choice)
     
-    # Create DataFrame
+    # Create DataFrame (same as original code)
     df = pd.DataFrame.from_dict(
         {
             "logical_thinking": [logical_thinking],
@@ -307,7 +100,7 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
         "book_interest": book_interest_references
     })
     
-    # Dummy encoding
+    # Dummy encoding (same as original code)
     userdata_list = df.values.tolist()
     
     # Management-Technical dummy encoding
@@ -334,29 +127,27 @@ def rfprediction(model_choice, name, logical_thinking, hackathon_attend, coding_
     else: 
         return "Error in Smart-Hard worker encoding"
 
-    # Prediction handling for different model types
-    if model_choice in ["Random Forest", "Decision Tree"]:
-        prediction_result_all = rfmodel.predict_proba(userdata_list)
-    else:  # Sequential Model (Keras)
-        prediction_result_all = rfmodel.predict(userdata_list)
+    # Prediction
+    prediction_result_all = rfmodel.predict_proba(userdata_list)
     
     # Create result dictionary
-    careers = [
-        "Applications Developer", "CRM Technical Developer", "Database Developer", 
-        "Mobile Applications Developer", "Network Security Engineer", "Software Developer", 
-        "Software Engineer", "Software Quality Assurance (QA)/ Testing", 
-        "Systems Security Administrator", "Technical Support", "UX Designer", "Web Developer"
-    ]
-    
-    # Handle probability extraction based on model type
-    if model_choice in ["Random Forest", "Decision Tree"]:
-        result_list = {career: float(prediction_result_all[0][i]) for i, career in enumerate(careers)}
-    else:  # Sequential Model
-        result_list = {career: float(prediction_result_all[0][i]) for i, career in enumerate(careers)}
-    
+    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
+# 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"]
@@ -367,11 +158,11 @@ book_list = ["Action and Adventure", "Anthology", "Art", "Autobiographies", "Bio
 Choice_list = ["Management", "Technical"]
 worker_list = ["hard worker", "smart worker"]
 
-# Create Gradio interface
+# Create Gradio interface (modified to include model selection)
 demo = gr.Interface(
     fn=rfprediction, 
     inputs=[
-        gr.Dropdown(["Random Forest", "Decision Tree","Sequential Model"], label="Select Machine Learning Model"),
+        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"),
@@ -401,3 +192,5 @@ demo = gr.Interface(
 # Main execution
 if __name__ == "__main__":
     demo.launch(share=True)
+
+