fix box not found

app.py

@@ -4,7 +4,7 @@ import plotly.graph_objects as go
 import pandas as pd
 
 from src.heart_disease_core import (
-    CLEVELAND_FEATURES_ORDER, TARGET_COL, CATEGORICAL_CHOICES,
+    CLEVELAND_FEATURES_ORDER, TARGET_COL,
     load_cleveland_dataframe, fit_all_models, predict_all, example_patient
 )
 
@@ -18,37 +18,57 @@ STATE = {
     "metrics": None,
 }
 
-def _ensure_models(df: pd.DataFrame):
-    if STATE["models"] is None:
-        models, metrics = fit_all_models(df)
-        STATE["models"] = models
-        STATE["metrics"] = metrics
-
-def load_dataset(file):
-    try:
-        if file is None:
-            return gr.Markdown.update(value="❌ Please upload a Cleveland-format dataset (CSV/XLSX)."), gr.DataFrame.update(value=pd.DataFrame()), gr.Markdown.update(visible=False)
-        if file.name.endswith(".csv"):
-            df = pd.read_csv(file.name)
-        else:
-            df = pd.read_excel(file.name)
-        df = load_cleveland_dataframe(uploaded_df=df)
-        STATE["df"] = df
-        STATE["models"] = None  # reset, will refit lazily
-        STATE["metrics"] = None
-        head = df.head(8)
-        return gr.Markdown.update(value="✅ Dataset loaded successfully."), gr.DataFrame.update(value=head, interactive=False), gr.Markdown.update(visible=False)
-    except Exception as e:
-        return gr.Markdown.update(value=f"❌ Error: {e}"), gr.DataFrame.update(value=pd.DataFrame()), gr.Markdown.update(visible=False)
-
-def fill_example(idx):
+DATA_PATH = "data/cleveland.csv"
+
+
+# -----------------------------
+# Startup / init
+# -----------------------------
+def init_page():
+    """
+    Load dataset from disk, fit models once, and return preview + metrics.
+    """
+    if not os.path.exists(DATA_PATH):
+        msg = f"❌ Dataset not found at '{DATA_PATH}'. Please place Cleveland CSV there."
+        return (
+            gr.Markdown.update(value=msg),
+            gr.DataFrame.update(value=pd.DataFrame()),
+            gr.DataFrame.update(value=pd.DataFrame())
+        )
+
+    df = pd.read_csv(DATA_PATH)
+    df = load_cleveland_dataframe(uploaded_df=df)  # cleans, binarizes target
+
+    models, metrics = fit_all_models(df)
+    STATE["df"] = df
+    STATE["models"] = models
+    STATE["metrics"] = metrics
+
+    head = df.head(8)
+    msg = "✅ **Cleveland dataset loaded** from `data/cleveland.csv` and models trained (80/20 split)."
+    return (
+        gr.Markdown.update(value=msg),
+        gr.DataFrame.update(value=head, interactive=False),
+        gr.DataFrame.update(value=metrics, interactive=False)
+    )
+
+
+# -----------------------------
+# Helpers
+# -----------------------------
+def fill_example(idx_text: str):
+    idx = {
+        "Example 1 (likely negative)": 0,
+        "Example 2 (borderline)": 1,
+        "Example 3 (likely positive)": 2
+    }[idx_text]
     ex = example_patient(idx)
     return [ex[c] for c in CLEVELAND_FEATURES_ORDER]
 
+
 def _bar_for_models(results: dict):
     names = list(results.keys())
     probs = [results[n]["prob_1"] for n in names]
-    labels = ["Disease" if results[n]["label"] == 1 else "No disease" for n in names]
 
     fig = go.Figure()
     fig.add_bar(x=names, y=probs, text=[f"{p:.2f}" for p in probs], textposition="auto")
@@ -61,50 +81,48 @@ def _bar_for_models(results: dict):
         height=420,
         margin=dict(l=30, r=20, t=60, b=40)
     )
-    # color emphasis for ensemble bar (last)
+    # Emphasize ensemble bar (assumes last entry named "Ensemble (Soft Voting)")
     if len(names) >= 1:
-        fig.data[0].marker.color = ["#9BB8D3"] * (len(names) - 1) + [APP_ACCENT]
-    return fig, labels
+        colors = ["#9BB8D3"] * len(names)
+        try:
+            idx = names.index("Ensemble (Soft Voting)")
+            colors[idx] = APP_ACCENT
+        except ValueError:
+            colors[-1] = APP_ACCENT
+        fig.data[0].marker.color = colors
+    return fig
+
 
 def run_predict(*vals):
-    # Ensure dataset
-    if STATE["df"] is None:
+    if STATE["df"] is None or STATE["models"] is None:
         return (
-            gr.Markdown.update(value="❌ No dataset yet. Please upload a Cleveland-format dataset."),
+            gr.Markdown.update(value="❌ Models not initialized. Reload the app."),
             gr.Plot.update(None),
             gr.Markdown.update(visible=False),
             gr.DataFrame.update(visible=False)
         )
 
-    # Build input row as dict with strict order
     input_dict = {col: vals[i] for i, col in enumerate(CLEVELAND_FEATURES_ORDER)}
-
-    # Fit models lazily
-    _ensure_models(STATE["df"])
-
-    # Predict
     results = predict_all(STATE["models"], input_dict)
 
-    # Compose readable summary and plot
-    pred_table = []
-    final_label = results["Ensemble (Soft Voting)"]["label"]
-    final_prob = results["Ensemble (Soft Voting)"]["prob_1"]
+    final = results["Ensemble (Soft Voting)"]
     title_md = (
         f"### 🫀 Cleveland Heart Disease Diagnosis\n"
-        f"**Ensemble Prediction**: **{'Positive' if final_label == 1 else 'Negative'}**  \n"
-        f"**Confidence (P=1)**: `{final_prob:.3f}`"
+        f"**Ensemble Prediction**: **{'Positive' if final['label'] == 1 else 'Negative'}**  \n"
+        f"**Confidence (P=1)**: `{final['prob_1']:.3f}`"
     )
 
+    rows = []
     for name, r in results.items():
-        pred_table.append({
+        rows.append({
             "Model": name,
             "Predicted label": "Positive" if r["label"] == 1 else "Negative",
             "P(No disease)": round(r["prob_0"], 3),
             "P(Heart disease)": round(r["prob_1"], 3),
         })
-    table_df = pd.DataFrame(pred_table)
+    table_df = pd.DataFrame(rows)
 
-    fig, labels = _bar_for_models(results)
+    fig = _bar_for_models(results)
 
     return (
         gr.Markdown.update(value=title_md),
@@ -113,84 +131,78 @@ def run_predict(*vals):
         gr.DataFrame.update(value=table_df, visible=True, interactive=False)
     )
 
+
 # -----------------------------
-# UI
+# UI (no gr.Box to avoid your error)
 # -----------------------------
 with gr.Blocks(theme="soft", css=f"""
 :root {{
   --primary-600: {APP_PRIMARY};
 }}
 .gradio-container {{ background: {APP_BG}; }}
-.footer-note a {{ color: {APP_PRIMARY}; }}
 h1, h2, h3, h4 {{ color: {APP_PRIMARY}; }}
 """) as demo:
     gr.Markdown("# 🫀 Cleveland Heart Disease Diagnosis (Ensemble Demo)")
 
     with gr.Row(equal_height=False):
-        # LEFT: inputs
+        # LEFT: data preview + inputs
         with gr.Column(scale=45):
-            with gr.Box():
-                gr.Markdown("### 📁 Load Dataset")
-                info_md = gr.Markdown("Upload a CSV/XLSX in **Cleveland** format (13 features + `target`).")
-                file_u = gr.File(file_count="single", file_types=[".csv", ".xlsx", ".xls"], label="Upload Cleveland Dataset")
-                preview = gr.DataFrame(label="Data Preview (first rows)", interactive=False)
-                metrics_box = gr.Markdown(visible=False)
-
-            with gr.Box():
-                gr.Markdown("### ✍️ Enter Patient Features")
-                with gr.Row():
-                    age = gr.Number(label="age (years)", value=58)
-                    sex = gr.Dropdown(label="sex (0=female, 1=male)", choices=[0,1], value=1)
-                    cp = gr.Dropdown(label="cp (chest pain type 0..3)", choices=[0,1,2,3], value=2)
-                    trestbps = gr.Number(label="trestbps (resting BP mmHg)", value=130)
-
-                with gr.Row():
-                    chol = gr.Number(label="chol (serum cholestrol mg/dl)", value=250)
-                    fbs = gr.Dropdown(label="fbs (>120 mg/dl? 1/0)", choices=[0,1], value=0)
-                    restecg = gr.Dropdown(label="restecg (0..2)", choices=[0,1,2], value=1)
-                    thalach = gr.Number(label="thalach (max heart rate)", value=150)
-
-                with gr.Row():
-                    exang = gr.Dropdown(label="exang (exercise angina 1/0)", choices=[0,1], value=0)
-                    oldpeak = gr.Number(label="oldpeak (ST depression)", value=1.0)
-                    slope = gr.Dropdown(label="slope (0..2)", choices=[0,1,2], value=1)
-                    ca = gr.Dropdown(label="ca (major vessels 0..3)", choices=[0,1,2,3], value=0)
-
-                thal = gr.Dropdown(label="thal (1=normal,2=fixed,3=reversible)", choices=[1,2,3], value=2)
-
-                with gr.Row():
-                    ex_selector = gr.Dropdown(
-                        label="Fill Example",
-                        choices=["Example 1 (likely negative)", "Example 2 (borderline)", "Example 3 (likely positive)"],
-                        value="Example 2 (borderline)"
-                    )
-                    fill_btn = gr.Button("🧪 Use Example", variant="secondary")
-                    predict_btn = gr.Button("🔍 Predict", variant="primary")
+            gr.Markdown("### 📁 Dataset & Model Status")
+            status_md = gr.Markdown("Loading dataset and training models...")
+            preview = gr.DataFrame(label="Cleveland Preview (first rows)", interactive=False)
+            metrics_df = gr.DataFrame(label="Validation ROC-AUC (80/20 split)", interactive=False)
+
+            gr.Markdown("### ✍️ Enter Patient Features")
+            with gr.Row():
+                age = gr.Number(label="age (years)", value=58)
+                sex = gr.Dropdown(label="sex (0=female, 1=male)", choices=[0, 1], value=1)
+                cp = gr.Dropdown(label="cp (chest pain type 0..3)", choices=[0, 1, 2, 3], value=2)
+                trestbps = gr.Number(label="trestbps (resting BP mmHg)", value=130)
+
+            with gr.Row():
+                chol = gr.Number(label="chol (serum cholesterol mg/dl)", value=250)
+                fbs = gr.Dropdown(label="fbs (>120 mg/dl? 1/0)", choices=[0, 1], value=0)
+                restecg = gr.Dropdown(label="restecg (0..2)", choices=[0, 1, 2], value=1)
+                thalach = gr.Number(label="thalach (max heart rate)", value=150)
+
+            with gr.Row():
+                exang = gr.Dropdown(label="exang (exercise angina 1/0)", choices=[0, 1], value=0)
+                oldpeak = gr.Number(label="oldpeak (ST depression)", value=1.0)
+                slope = gr.Dropdown(label="slope (0..2)", choices=[0, 1, 2], value=1)
+                ca = gr.Dropdown(label="ca (major vessels 0..3)", choices=[0, 1, 2, 3], value=0)
+
+            thal = gr.Dropdown(label="thal (1=normal, 2=fixed, 3=reversible)", choices=[1, 2, 3], value=2)
+
+            with gr.Row():
+                ex_selector = gr.Dropdown(
+                    label="Fill Example",
+                    choices=["Example 1 (likely negative)", "Example 2 (borderline)", "Example 3 (likely positive)"],
+                    value="Example 2 (borderline)"
+                )
+                fill_btn = gr.Button("🧪 Use Example")
+                predict_btn = gr.Button("🔍 Predict", variant="primary")
 
         # RIGHT: outputs
         with gr.Column(scale=55):
-            with gr.Box():
-                title_out = gr.Markdown("### Ensemble Prediction will appear here.")
-                bar_out = gr.Plot(label="Model Confidence")
-                sub_md = gr.Markdown(visible=False)
-                table_out = gr.DataFrame(visible=False)
+            gr.Markdown("### 📈 Predictions")
+            title_out = gr.Markdown("Ensemble Prediction will appear here.")
+            bar_out = gr.Plot(label="Model Confidence")
+            sub_md = gr.Markdown(visible=False)
+            table_out = gr.DataFrame(visible=False)
 
             with gr.Accordion("ℹ️ Notes", open=False):
                 gr.Markdown(
-                    "- This demo **fits models** on your uploaded dataset (80/20 split) the first time you predict.\n"
-                    "- **Target** is automatically binarized (0 = no disease, >0 = disease).\n"
-                    "- Ensemble is **soft voting** over Decision Tree, k-NN, and Naive Bayes.\n"
-                    "- This is **for demo/education**; not medical advice."
+                    "- Models are trained once at launch on `data/cleveland.csv` (80/20 split).\n"
+                    "- `target` is binarized automatically (0 = no disease, >0 = disease).\n"
+                    "- Ensemble uses **soft voting** over Decision Tree, k-NN, and Naive Bayes.\n"
+                    "- Educational demo only; **not medical advice**."
                 )
 
-    # Events
-    file_u.upload(fn=load_dataset, inputs=[file_u], outputs=[info_md, preview, metrics_box])
-
-    def _example_index(choice: str):
-        return {"Example 1 (likely negative)": 0, "Example 2 (borderline)": 1, "Example 3 (likely positive)": 2}[choice]
+    # Bind events
+    demo.load(fn=init_page, inputs=None, outputs=[status_md, preview, metrics_df])
 
     fill_btn.click(
-        fn=lambda choice: tuple(fill_example(_example_index(choice))),
+        fn=fill_example,
         inputs=[ex_selector],
         outputs=[age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, oldpeak, slope, ca, thal]
     )
@@ -202,5 +214,4 @@ h1, h2, h3, h4 {{ color: {APP_PRIMARY}; }}
     )
 
 if __name__ == "__main__":
-    # Optional: allow GraphViz logos etc. from static if you keep them
     demo.launch()