Update app.py

app.py

@@ -1,5 +1,160 @@
+import gradio as gr
+import joblib
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Load model and scaler
+model = joblib.load('rsf_tuned.pkl')
+scaler = joblib.load('scaler.pkl')
+
+# --- ORDINAL MAPPINGS ---
+wealth_map = {
+    "poorest": 0, "poorer": 1, "middle": 2, "richer": 3, "richest": 4
+}
+
+mat_edu_map = {
+    "no education": 0, "primary": 1, "secondary": 2, "higher": 3
+}
+
+# --- FEATURE NAMES (same as training) ---
+numeric_cols = [
+    'birth_order', 'mat_age', 'mat_height_cm', 'mat_weight_kg',
+    'wealth_ordinal', 'mat_edu_ordinal', 'multiple_birth_binary'
+]
+
+categorical_cols = [
+    'child_sex', 'religion', 'water_improved', 'sanitation_improved',
+    'partner_edu', 'region', 'residence'
+]
+
+cat_feature_names = [
+    'child_sex_female', 'child_sex_male',
+    'religion_catholic', 'religion_islam', 'religion_Not asked/Missing',
+    'religion_other', 'religion_other christian', 'religion_traditionalist',
+    'water_improved_Improved', 'water_improved_Not asked/Missing', 'water_improved_Unimproved',
+    'sanitation_improved_Improved', 'sanitation_improved_Not asked/Missing', 'sanitation_improved_Unimproved',
+    'partner_edu_don\'t know', 'partner_edu_higher', 'partner_edu_no education',
+    'partner_edu_Not asked/Missing', 'partner_edu_primary', 'partner_edu_secondary',
+    'region_North Central', 'region_North East', 'region_North West',
+    'region_South East', 'region_South South', 'region_South West',
+    'residence_rural', 'residence_urban'
+]
+
+def create_inputs():
+    return [
+        gr.Number(label="Birth Order", value=1, minimum=1, maximum=20),
+        gr.Number(label="Maternal Age (years)", value=25, minimum=12, maximum=49),
+        gr.Number(label="Maternal Height (cm)", value=160, minimum=100, maximum=200),
+        gr.Number(label="Maternal Weight (kg)", value=60, minimum=30, maximum=120),
+        gr.Dropdown(
+            choices=[("Poorest", "poorest"), ("Poorer", "poorer"), ("Middle", "middle"),
+                     ("Richer", "richer"), ("Richest", "richest")],
+            label="Wealth Index",
+            value="middle"
+        ),
+        gr.Dropdown(
+            choices=[("No Education", "no education"), ("Primary", "primary"),
+                     ("Secondary", "secondary"), ("Higher", "higher")],
+            label="Maternal Education",
+            value="primary"
+        ),
+        gr.Dropdown(choices=[("No", 0), ("Yes", 1)], label="Multiple Birth", value=0),
+        gr.Dropdown(choices=["male", "female"], label="Child Sex", value="male"),
+        gr.Dropdown(
+            choices=["islam", "catholic", "other christian", "traditionalist", "other"],
+            label="Religion",
+            value="islam"
+        ),
+        gr.Dropdown(
+            choices=["Improved", "Unimproved"],
+            label="Water Source",
+            value="Improved"
+        ),
+        gr.Dropdown(
+            choices=["Improved", "Unimproved"],
+            label="Sanitation",
+            value="Improved"
+        ),
+        gr.Dropdown(
+            choices=["no education", "primary", "secondary", "higher"],
+            label="Partner Education",
+            value="primary"
+        ),
+        gr.Dropdown(
+            choices=["North West", "North East", "North Central", "South West", "South East", "South South"],
+            label="Region",
+            value="North West"
+        ),
+        gr.Dropdown(choices=["rural", "urban"], label="Residence", value="rural")
+    ]
+
+def predict_stunting(birth_order, mat_age, mat_height_cm, mat_weight_kg,
+                     wealth_label, mat_edu_label, multiple_birth_binary,
+                     child_sex, religion, water_improved, sanitation_improved,
+                     partner_edu, region, residence):
+    
+    wealth_ordinal = wealth_map[wealth_label]
+    mat_edu_ordinal = mat_edu_map[mat_edu_label]
+    
+    # Build raw input (14 features)
+    input_data = pd.DataFrame([[
+        birth_order, mat_age, mat_height_cm, mat_weight_kg,
+        wealth_ordinal, mat_edu_ordinal, multiple_birth_binary,
+        child_sex, religion, water_improved, sanitation_improved,
+        partner_edu, region, residence
+    ]], columns=numeric_cols + categorical_cols)
+    
+    # One-hot encoding
+    one_hot_data = pd.DataFrame(0, index=input_data.index, columns=cat_feature_names)
+    for col in categorical_cols:
+        val = input_data[col].iloc[0]
+        if pd.isna(val) or val in ["Not asked/Missing", "don't know"]:
+            col_name = f"{col}_Not asked/Missing"
+        else:
+            col_name = f"{col}_{val}"
+        if col_name in one_hot_data.columns:
+            one_hot_data[col_name] = 1
+    
+    # Combine → 35 features (EXACTLY like notebook's X_sksurv)
+    X_sksurv = pd.concat([input_data[numeric_cols], one_hot_data], axis=1)
+    
+    # Scale ALL 35 features (this is what the notebook does)
+    X_scaled = pd.DataFrame(
+        scaler.transform(X_sksurv),
+        columns=X_sksurv.columns,
+        index=X_sksurv.index
+    )
+    
+    # Predict
+    risk = model.predict(X_scaled)[0]
+    
+    # Survival probabilities
+    surv_funcs = model.predict_survival_function(X_scaled)
+    times = np.array([6, 12, 18, 24, 36, 48])
+    surv_probs = surv_funcs[0](times)
+    stunting_risks = 1 - surv_probs
+    
+    # Plot
+    fig, ax = plt.subplots(figsize=(8, 4))
+    ax.plot(times, stunting_risks, marker='o', linestyle='-', color='steelblue', linewidth=2, markersize=8)
+    ax.axhline(y=0.20, color='red', linestyle='--', label='20% Risk Threshold')
+    ax.set_xlabel('Age (months)')
+    ax.set_ylabel('Stunting Risk')
+    ax.set_title('Stunting Risk by Age')
+    ax.set_ylim(0, 1)
+    ax.grid(True, linestyle=':', alpha=0.7)
+    ax.legend()
+    ax.set_xticks(times)
+    
+    return f"## Risk Score: {risk:.4f}", fig
+
+inputs = create_inputs()
 demo = gr.Interface(
-    ...
+    fn=predict_stunting,
+    inputs=inputs,
+    outputs=[gr.Markdown(label="Risk Score"), gr.Plot(label="Stunting Risk Curve")],
+    title="Stunting Risk Predictor",
     description="""
     ⚠️ **DISCLAIMER**: This is a **research prototype** developed using DHS data. 
     **External validation has not been performed**. This tool is for 
@@ -8,6 +163,14 @@ demo = gr.Interface(
     
     Predicts stunting risk at ages 6, 12, 18, 24, 36, and 48 months using a 
     Random Survival Forest model.
-    """
+    """,
+    examples=[
+        [1, 25, 160, 60, "middle", "primary", 0, "male", "islam", "Improved", "Improved", "primary", "North West", "rural"],
+        [4, 18, 150, 55, "poorest", "no education", 0, "female", "catholic", "Unimproved", "Unimproved", "no education", "South East", "rural"],
+        [2, 35, 170, 70, "richest", "higher", 1, "male", "other christian", "Improved", "Improved", "secondary", "South West", "urban"]
+    ],
+    allow_flagging="never"
 )
 
+if __name__ == "__main__":
+    demo.launch()