Update app.py

app.py

@@ -1,46 +1,68 @@
 import pickle 
 import pandas as pd
 import shap
-from shap.plots._force_matplotlib import draw_additive_plot
 import gradio as gr
 import numpy as np
 import matplotlib.pyplot as plt
 
-# load the model from disk
+# Load the model
 loaded_model = pickle.load(open("salar_xgb_team.pkl", 'rb'))
 
-# Setup SHAP
-explainer = shap.Explainer(loaded_model) # PLEASE DO NOT CHANGE THIS.
-
-# Create the main function for server
-def main_func(age, education_num, sex, capital_gain, capital_loss, hours_per_week):
+# SHAP setup
+explainer = shap.Explainer(loaded_model)  # DO NOT CHANGE
+
+# Education mapping
+education_map = {
+    "Less than 1st grade": 1,
+    "1st–4th grade": 2,
+    "5th–6th grade": 3,
+    "7th–8th grade": 4,
+    "9th grade": 5,
+    "10th grade": 6,
+    "11th grade": 7,
+    "12th grade (no diploma)": 8,
+    "High School Grad": 9,
+    "Some College": 10,
+    "Associate's Degree (Voc)": 11,
+    "Associate's Degree (Acad)": 12,
+    "Bachelor's Degree": 13,
+    "Master's Degree": 14,
+    "Professional School": 15,
+    "Doctorate": 16
+}
+
+# Main model logic
+def main_func(age, education_level, sex, capital_gain, capital_loss, hours_per_week):
+    education_num = education_map[education_level]
     sex = 1 if sex == "Female" else 0
-    new_row = pd.DataFrame.from_dict({'age':age,
-              'education-num':education_num,'sex':sex,'capital-gain':capital_gain,
-              'capital-loss':capital_loss, 'hours-per-week':hours_per_week}, 
-               orient = 'index').transpose()
-    
+
+    new_row = pd.DataFrame.from_dict({
+        'age': age,
+        'education-num': education_num,
+        'sex': sex,
+        'capital-gain': capital_gain,
+        'capital-loss': capital_loss,
+        'hours-per-week': hours_per_week
+    }, orient='index').transpose()
+
     prob = loaded_model.predict_proba(new_row)
-    
+
     shap_values = explainer(new_row)
-    # plot = shap.force_plot(shap_values[0], matplotlib=True, figsize=(30,30), show=False)
-    # plot = shap.plots.waterfall(shap_values[0], max_display=6, show=False)
     plot = shap.plots.bar(shap_values[0], max_display=6, order=shap.Explanation.abs, show_data='auto', show=False)
 
     plt.tight_layout()
     local_plot = plt.gcf()
     plt.close()
-    
+
     return {
         "Chance of Earning > $50K": float(prob[0][1]),
         "Chance of Earning ≤ $50K": float(prob[0][0])
     }, local_plot
 
-# Create the UI
+# Gradio UI
 title = "**Household Income Predictor** 💰"
-description1 = """This app uses your input to predict whether a household earns more or less than $50K per year"""
-
-description2 = """Adjust the values below and click 'Analyze' to see the prediction and explanation."""
+description1 = """This app uses your input to predict whether a household earns more or less than $50K per year."""
+description2 = """Adjust the values below or select a sample profile, then click 'Analyze' to see the prediction and feature impact."""
 
 with gr.Blocks(title=title) as demo:
     gr.Markdown(f"## {title}")
@@ -49,72 +71,77 @@ with gr.Blocks(title=title) as demo:
     gr.Markdown(description2)
     gr.Markdown("---")
 
-    # 🎛 Preset scenario dropdown
+    # Sample profile dropdown
     scenario = gr.Dropdown(
         ["Select a Sample", 
-     "👨‍💻 Young Tech Worker: 28 yrs, college degree, 45 hrs/week", 
-     "👵 Retired Part-Timer: 65 yrs, no college, 20 hrs/week", 
-     "👩‍🏫 Mid-Career Teacher: 42 yrs, 14 education years, 38 hrs/week", 
-     "👨‍🔧 Manual Laborer: 50 yrs, 9 education years, 60 hrs/week"],
-     label="📋 Choose a Sample Profile (optional — autofills values to explore common cases)"
+         "👨‍💻 Young Tech Worker: 28 yrs, Bachelor's, 45 hrs/week", 
+         "👵 Retired Part-Timer: 65 yrs, no college, 20 hrs/week", 
+         "👩‍🏫 Mid-Career Teacher: 42 yrs, Master's, 38 hrs/week", 
+         "👨‍🔧 Manual Laborer: 50 yrs, High School Grad, 60 hrs/week"],
+        label="📋 Choose a Sample Profile (optional — autofills values to explore common cases)"
     )
 
-    # 🎯 Inputs
+    # Inputs
     with gr.Row():
         age = gr.Number(label="🧓 Age", value=35)
-        education_num = gr.Number(label="🎓 Education Level (numeric)", value=10)
+        education_level = gr.Dropdown(
+            list(education_map.keys()),
+            label="🎓 Education Level",
+            value="Some College"
+        )
     with gr.Row():
         sex = gr.Radio(["Male", "Female"], label="🧍 Sex")
         capital_gain = gr.Number(label="📈 Capital Gain", value=0)
         capital_loss = gr.Number(label="📉 Capital Loss", value=0)
         hours_per_week = gr.Number(label="⏱ Hours per Week", value=40)
 
-    submit_btn = gr.Button("🔎 Analyze")
-
-    # 🔁 Handle preset scenario changes
+    # Handle preset scenario changes
     def fill_scenario(scenario_choice):
-        if scenario_choice == "👨‍💻 Young Tech Worker: 28 yrs, college degree, 45 hrs/week":
-            return [28, 16, "Male", 0, 0, 45]
+        if scenario_choice == "👨‍💻 Young Tech Worker: 28 yrs, Bachelor's, 45 hrs/week":
+            return [28, "Bachelor's Degree", "Male", 0, 0, 45]
         elif scenario_choice == "👵 Retired Part-Timer: 65 yrs, no college, 20 hrs/week":
-            return [65, 8, "Female", 0, 0, 20]
-        elif scenario_choice == "👩‍🏫 Mid-Career Teacher: 42 yrs, 14 education years, 38 hrs/week":
-            return [42, 14, "Female", 0, 0, 38]
-        elif scenario_choice == "👨‍🔧 Manual Laborer: 50 yrs, 9 education years, 60 hrs/week":
-            return [50, 9, "Male", 0, 0, 60]
+            return [65, "9th grade", "Female", 0, 0, 20]
+        elif scenario_choice == "👩‍🏫 Mid-Career Teacher: 42 yrs, Master's, 38 hrs/week":
+            return [42, "Master's Degree", "Female", 0, 0, 38]
+        elif scenario_choice == "👨‍🔧 Manual Laborer: 50 yrs, High School Grad, 60 hrs/week":
+            return [50, "High School Grad", "Male", 0, 0, 60]
         else:
-            return [35, 10, "Male", 0, 0, 40]  # Default values
+            return [35, "Some College", "Male", 0, 0, 40]
 
     scenario.change(
         fn=fill_scenario,
         inputs=[scenario],
-        outputs=[age, education_num, sex, capital_gain, capital_loss, hours_per_week]
+        outputs=[age, education_level, sex, capital_gain, capital_loss, hours_per_week]
     )
 
-    # 🧠 Prediction output
+    # Outputs
     with gr.Column(visible=True) as output_col:
         label = gr.Label(label="🧠 Predicted Income")
         confidence = gr.Slider(0, 100, value=50, label="📊 Confidence in > $50K", interactive=False)
         local_plot = gr.Plot(label="🔍 Top SHAP Features")
 
-    # 🧠 Wrap predict + confidence slider logic
-    def wrapped_main(age, education_num, sex, capital_gain, capital_loss, hours_per_week):
-        result, shap_plot = main_func(age, education_num, sex, capital_gain, capital_loss, hours_per_week)
+    # Wrapped function for UI
+    def wrapped_main(age, education_level, sex, capital_gain, capital_loss, hours_per_week):
+        result, shap_plot = main_func(age, education_level, sex, capital_gain, capital_loss, hours_per_week)
         return result, float(result["Chance of Earning > $50K"]) * 100, shap_plot
 
+    # Button
+    submit_btn = gr.Button("🔎 Analyze")
     submit_btn.click(
         wrapped_main,
-        [age, education_num, sex, capital_gain, capital_loss, hours_per_week],
+        [age, education_level, sex, capital_gain, capital_loss, hours_per_week],
         [label, confidence, local_plot],
         api_name="Salary_Predictor"
     )
 
+    # Examples
     gr.Markdown("### 🧪 Try Some Examples:")
     gr.Examples(
         [
-            [28, 16, "Male", 0, 0, 45],
-            [60, 8, "Female", 0, 0, 25]
+            [28, "Bachelor's Degree", "Male", 0, 0, 45],
+            [60, "9th grade", "Female", 0, 0, 25]
         ],
-        [age, education_num, sex, capital_gain, capital_loss, hours_per_week],
+        [age, education_level, sex, capital_gain, capital_loss, hours_per_week],
         [label, confidence, local_plot],
         wrapped_main,
         cache_examples=True
@@ -122,4 +149,5 @@ with gr.Blocks(title=title) as demo:
 
 demo.launch()
 
+