Update app.py

app.py

@@ -4,14 +4,21 @@ import seaborn as sns
 import matplotlib.pyplot as plt
 
 # Load model + metadata + dataset
-model = joblib.load("maternal_rf_model.joblib")
+model = joblib.load("maternal_risk_model.joblib")
 with open("maternal_metadata.json","r",encoding="utf-8") as f:
     meta = json.load(f)
-df_clean = pd.read_csv("maternal_cleaned.csv")
+
+try:
+    df_clean = pd.read_csv("maternal_cleaned.csv")
+except FileNotFoundError:
+    df_clean = None
 
 numeric_features = meta["numeric_features"]
 categorical_features = meta["categorical_features"]
 
+# ---------- Prediction history ----------
+prediction_history = []
+
 # ---------- Prediction function ----------
 def predict_risk(age, gravida, gest_weeks, weight, height_cm,
                  bp_sys, bp_dias, fetal_hr,
@@ -30,22 +37,32 @@ def predict_risk(age, gravida, gest_weeks, weight, height_cm,
     prob = model.predict_proba(X)[:,1][0]
     pred = int(model.predict(X)[0])
     label = "High Risk" if pred==1 else "Not High Risk"
-    return {"Prediction":label,"Probability_high_risk":round(prob,4)}
+
+    # Save to history
+    history_row = row.copy()
+    history_row["Prediction"] = label
+    history_row["Probability"] = round(prob, 4)
+    prediction_history.append(history_row)
+
+    return {"Prediction": label, "Probability_high_risk": round(prob,4)}
 
 # ---------- Plot functions ----------
 def plot_age_distribution():
+    if df_clean is None: return plt.figure()
     fig, ax = plt.subplots(figsize=(6,4))
     sns.histplot(df_clean["Age"], bins=10, kde=True, ax=ax, color="skyblue")
     ax.set_title("Age Distribution")
     return fig
 
 def plot_risk_counts():
+    if df_clean is None: return plt.figure()
     fig, ax = plt.subplots(figsize=(6,4))
     sns.countplot(x="HighRisk", data=df_clean, ax=ax, palette="Set2")
     ax.set_title("High Risk vs Non-Risk Counts")
     return fig
 
 def plot_gestation_box():
+    if df_clean is None: return plt.figure()
     fig, ax = plt.subplots(figsize=(6,4))
     sns.boxplot(x="HighRisk", y="GestationWeeks", data=df_clean, ax=ax, palette="Set2")
     ax.set_title("Gestation Weeks vs Risk")
@@ -64,14 +81,19 @@ def plot_feature_importance():
     return fig
 
 def plot_corr_heatmap():
+    if df_clean is None: return plt.figure()
     fig, ax = plt.subplots(figsize=(8,6))
     corr = df_clean[numeric_features+["HighRisk"]].corr()
     sns.heatmap(corr, annot=True, cmap="coolwarm", fmt=".2f", ax=ax)
     ax.set_title("Correlation Heatmap")
     return fig
 
+# ---------- History update ----------
+def update_history():
+    return pd.DataFrame(prediction_history)
+
 # ---------- Gradio UI ----------
-with gr.Blocks(title="Maternal Risk Prediction") as demo:
+with gr.Blocks(title="Maternal Risk Prediction Dashboard") as demo:
     gr.Markdown("## Maternal Risk Prediction Dashboard")
 
     with gr.Tab("Prediction"):
@@ -102,16 +124,19 @@ with gr.Blocks(title="Maternal Risk Prediction") as demo:
                   outputs=out)
 
     with gr.Tab("Data Insights"):
-        gr.Markdown("### Dataset Overview")
         gr.Plot(plot_age_distribution)
         gr.Plot(plot_risk_counts)
         gr.Plot(plot_gestation_box)
 
     with gr.Tab("Model Insights"):
-        gr.Markdown("### Model Behavior")
         gr.Plot(plot_feature_importance)
         gr.Plot(plot_corr_heatmap)
 
+    with gr.Tab("Prediction History"):
+        history_table = gr.DataFrame(label="Prediction History", interactive=False)
+        refresh_btn = gr.Button("Refresh History")
+        refresh_btn.click(fn=update_history, outputs=history_table)
+
     with gr.Tab("About"):
         gr.Markdown("""
         ### About this App