Create app.py

app.py

@@ -0,0 +1,147 @@
+import json
+import joblib
+import numpy as np
+import pandas as pd
+import gradio as gr
+
+# ---------- Load artifacts ----------
+MODEL_PATH = "maternal_rf_model.joblib"
+META_PATH = "maternal_metadata.json"
+DATA_PATH = "maternal_cleaned.csv"  # optional, for example defaults or sanity checks
+
+model = joblib.load(MODEL_PATH)
+
+with open(META_PATH, "r", encoding="utf-8") as f:
+    meta = json.load(f)
+
+numeric_features = meta["numeric_features"]
+categorical_features = meta["categorical_features"]
+target_col = meta["target"]
+
+# Optional: load cleaned dataset to compute sensible defaults/ranges
+try:
+    df_clean = pd.read_csv(DATA_PATH)
+except Exception:
+    df_clean = None
+
+# ---------- Define categorical options ----------
+# Ensure these match your training preprocessing categories
+ANAEMIA_OPTS = ["None", "Minimal", "Medium", "Higher"]
+JAUNDICE_OPTS = ["None", "Minimal", "Medium"]
+FETAL_POSITION_OPTS = ["Normal", "Abnormal"]
+FETAL_MOVEMENT_OPTS = ["Yes", "No"]
+URINE_ALBUMIN_OPTS = ["Negative", "Positive"]
+URINE_SUGAR_OPTS = ["Negative", "Positive"]
+
+# ---------- Defaults from dataset (median or most frequent) ----------
+def default_num(name, fallback=0.0):
+    if df_clean is not None and name in df_clean.columns:
+        return float(np.nanmedian(df_clean[name].values))
+    return float(fallback)
+
+def default_cat(name, options, fallback=None):
+    if df_clean is not None and name in df_clean.columns:
+        mode = df_clean[name].dropna().astype(str).mode()
+        if len(mode) > 0 and mode[0] in options:
+            return mode[0]
+    return fallback or options[0]
+
+DEFAULTS = {
+    "Age": default_num("Age", 22),
+    "Gravida": default_num("Gravida", 1),
+    "GestationWeeks": default_num("GestationWeeks", 30),
+    "WeightKg": default_num("WeightKg", 56),
+    "HeightCm": default_num("HeightCm", 160),
+    "BP_Systolic": default_num("BP_Systolic", 100),
+    "BP_Diastolic": default_num("BP_Diastolic", 60),
+    "FetalHR": default_num("FetalHR", 140),
+    "Anaemia": default_cat("Anaemia", ANAEMIA_OPTS, "None"),
+    "Jaundice": default_cat("Jaundice", JAUNDICE_OPTS, "None"),
+    "FetalPosition": default_cat("FetalPosition", FETAL_POSITION_OPTS, "Normal"),
+    "FetalMovement": default_cat("FetalMovement", FETAL_MOVEMENT_OPTS, "Yes"),
+    "UrineAlbumin": default_cat("UrineAlbumin", URINE_ALBUMIN_OPTS, "Negative"),
+    "UrineSugar": default_cat("UrineSugar", URINE_SUGAR_OPTS, "Negative"),
+}
+
+# ---------- Prediction function ----------
+def predict_risk(
+    age, gravida, gest_weeks, weight, height_cm,
+    bp_sys, bp_dias, fetal_hr,
+    anaemia, jaundice, fetal_position, fetal_movement, urine_albumin, urine_sugar
+):
+    # Build a single-row DataFrame with exact column order
+    row = {
+        "Age": age,
+        "Gravida": gravida,
+        "GestationWeeks": gest_weeks,
+        "WeightKg": weight,
+        "HeightCm": height_cm,
+        "BP_Systolic": bp_sys,
+        "BP_Diastolic": bp_dias,
+        "FetalHR": fetal_hr,
+        "Anaemia": anaemia,
+        "Jaundice": jaundice,
+        "FetalPosition": fetal_position,
+        "FetalMovement": fetal_movement,
+        "UrineAlbumin": urine_albumin,
+        "UrineSugar": urine_sugar,
+    }
+    X = pd.DataFrame([row], columns=numeric_features + categorical_features)
+
+    # Predict
+    prob = None
+    try:
+        prob = model.predict_proba(X)[:, 1][0]
+    except Exception:
+        # If model lacks predict_proba (shouldn’t happen for RandomForest), fallback
+        prob = float(model.predict(X)[0])
+
+    pred = int(model.predict(X)[0])
+    label = "High Risk" if pred == 1 else "Not High Risk"
+
+    # Friendly output with rounded probability
+    return {
+        "Prediction": label,
+        "Probability_high_risk": round(float(prob), 4)
+    }
+
+# ---------- Gradio UI ----------
+with gr.Blocks(title="Maternal Risk Prediction") as demo:
+    gr.Markdown(
+        "## Maternal Risk Prediction\n"
+        "Enter clinical inputs to estimate high-risk pregnancy likelihood. "
+        "This tool uses a trained RandomForest model."
+    )
+
+    with gr.Row():
+        with gr.Column():
+            age_in = gr.Number(label="Age (years)", value=DEFAULTS["Age"])
+            gravida_in = gr.Number(label="Gravida (1/2/3)", value=DEFAULTS["Gravida"])
+            gest_in = gr.Number(label="Gestation Weeks", value=DEFAULTS["GestationWeeks"])
+            weight_in = gr.Number(label="Weight (kg)", value=DEFAULTS["WeightKg"])
+            height_in = gr.Number(label="Height (cm)", value=DEFAULTS["HeightCm"])
+        with gr.Column():
+            bp_sys_in = gr.Number(label="BP Systolic (mmHg)", value=DEFAULTS["BP_Systolic"])
+            bp_dias_in = gr.Number(label="BP Diastolic (mmHg)", value=DEFAULTS["BP_Diastolic"])
+            fetal_hr_in = gr.Number(label="Fetal Heart Rate (bpm)", value=DEFAULTS["FetalHR"])
+            anaemia_in = gr.Dropdown(ANAEMIA_OPTS, label="Anaemia", value=DEFAULTS["Anaemia"])
+            jaundice_in = gr.Dropdown(JAUNDICE_OPTS, label="Jaundice", value=DEFAULTS["Jaundice"])
+        with gr.Column():
+            fetal_pos_in = gr.Dropdown(FETAL_POSITION_OPTS, label="Fetal Position", value=DEFAULTS["FetalPosition"])
+            fetal_mov_in = gr.Dropdown(FETAL_MOVEMENT_OPTS, label="Fetal Movement", value=DEFAULTS["FetalMovement"])
+            urine_alb_in = gr.Dropdown(URINE_ALBUMIN_OPTS, label="Urine Albumin", value=DEFAULTS["UrineAlbumin"])
+            urine_sug_in = gr.Dropdown(URINE_SUGAR_OPTS, label="Urine Sugar", value=DEFAULTS["UrineSugar"])
+
+    predict_btn = gr.Button("Predict Risk")
+
+    out_json = gr.JSON(label="Result")
+
+    predict_btn.click(
+        predict_risk,
+        inputs=[age_in, gravida_in, gest_in, weight_in, height_in,
+                bp_sys_in, bp_dias_in, fetal_hr_in,
+                anaemia_in, jaundice_in, fetal_pos_in, fetal_mov_in, urine_alb_in, urine_sug_in],
+        outputs=[out_json]
+    )
+
+demo.launch()