Update app.py

app.py

@@ -40,31 +40,15 @@ def clean_data(df):
     df = df.fillna(df.mean(numeric_only=True))
     return df
 
-def upload_file(file_path):
-    """
-    file_path comes in as a str because type="filepath".
-    We catch any error and return a tiny DataFrame with the message.
-    """
+def upload_file(file):
     global df_global
-    try:
-        if not file_path:
-            raise ValueError("No file uploaded.")
-        ext = os.path.splitext(file_path)[-1].lower()
-        if ext == ".csv":
-            df = pd.read_csv(file_path)
-        elif ext in {".xls", ".xlsx"}:
-            df = pd.read_excel(file_path)
-        else:
-            raise ValueError(f"Unsupported extension: {ext}")
-
-        df = clean_data(df)
-        df_global = df
-        return df.head()
-
-    except Exception as e:
-        # Return a 1×1 DataFrame so Gradio won’t crash
-        return pd.DataFrame({"Error": [str(e)]})
-
+    if file is None:
+        return pd.DataFrame({"Error": ["No file uploaded."]})
+    ext = os.path.splitext(file.name)[-1]
+    df = pd.read_csv(file.name) if ext == ".csv" else pd.read_excel(file.name)
+    df = clean_data(df)
+    df_global = df
+    return df.head()
 
 def format_analysis_report(raw_output, visuals):
     try:
@@ -268,70 +252,10 @@ def train_model(_):
         print(f"Training Error: {e}")
         return {}, pd.DataFrame()
 
-def ab_test_models():
-    global df_global
-    if df_global is None:
-        return "⚠️ Please upload and preprocess a dataset first.", pd.DataFrame()
-
-    try:
-        # split off last column as target
-        target = df_global.columns[-1]
-        X = df_global.drop(columns=[target])
-        y = df_global[target]
-        if y.dtype == 'object':
-            y = LabelEncoder().fit_transform(y)
-
-        X_train, X_test, y_train, y_test = train_test_split(
-            X, y, test_size=0.3, random_state=42
-        )
-
-        models = {
-            "Random Forest": RandomForestClassifier(n_estimators=100),
-            "Logistic Regression": LogisticRegression(max_iter=1000),
-            "Gradient Boosting": GradientBoostingClassifier()
-        }
-
-        results = []
-        for name, clf in models.items():
-            clf.fit(X_train, y_train)
-            y_pred = clf.predict(X_test)
-            metrics = {
-                "Model": name,
-                "Accuracy": accuracy_score(y_test, y_pred),
-                "Precision": precision_score(y_test, y_pred, average="weighted", zero_division=0),
-                "Recall": recall_score(y_test, y_pred, average="weighted", zero_division=0),
-                "F1 Score": f1_score(y_test, y_pred, average="weighted", zero_division=0)
-            }
-            results.append(metrics)
-
-            # safe WandB logging
-            try:
-                wandb.log({f"{name}_metrics": metrics})
-            except Exception as e:
-                print(f"[WARN] WandB log failed for {name}: {e}")
-
-        result_df = pd.DataFrame(results)
-        best = result_df.sort_values("F1 Score", ascending=False).iloc[0]
-
-        summary = f"""
-        🔍 <b>Best Model:</b> {best['Model']}<br>
-        ✅ <b>F1 Score:</b> {best['F1 Score']:.4f}<br>
-        📊 <b>Accuracy:</b> {best['Accuracy']:.4f}<br>
-        🧠 <b>Precision:</b> {best['Precision']:.4f}<br>
-        🔁 <b>Recall:</b> {best['Recall']:.4f}
-        """
-        return summary, result_df
-
-    except Exception as err:
-        return f"❌ Error during A/B testing:<br>{err}", pd.DataFrame()
-
 
 def explainability(_):
-    global df_global
     import warnings
     warnings.filterwarnings("ignore")
-    if df_global is None:
-        return None, None
 
     target = df_global.columns[-1]
     X = df_global.drop(target, axis=1)
@@ -407,40 +331,29 @@ def explainability(_):
 with gr.Blocks() as demo:
     gr.Markdown("## 📊 AI-Powered Data Analysis with Hyperparameter Optimization")
 
-    # ─────────────────────── Upload & Preview ───────────────────────
     with gr.Row():
         with gr.Column():
             file_input = gr.File(label="Upload CSV or Excel", type="filepath")
-            df_output  = gr.DataFrame(label="Cleaned Data Preview")
-            file_input.change(fn=upload_file, inputs=[file_input], outputs=[dff := df_output])
+            df_output = gr.DataFrame(label="Cleaned Data Preview")
+            file_input.change(fn=upload_file, inputs=file_input, outputs=df_output)
 
         with gr.Column():
-            insights_output = gr.HTML(label="Insights")
-            #visual_output   = gr.Gallery(columns=2, label="Visuals")
-            agent_btn       = gr.Button("Run AI Agent")
+            insights_output = gr.HTML(label="Insights from SmolAgent")
+            visual_output = gr.Gallery(label="Visualizations (Auto-generated by Agent)", columns=2)
+            agent_btn = gr.Button("Run AI Agent (5 Insights + 5 Visualizations)")
 
-    # ─────────────────── Hyperopt + Trials ──��────────────────
     with gr.Row():
-        train_btn      = gr.Button("Train Model")
-        metrics_output = gr.JSON(label="Metrics")
-        trials_output  = gr.DataFrame(label="Top Trials")
+        train_btn = gr.Button("Train Model with Optuna + WandB")
+        metrics_output = gr.JSON(label="Performance Metrics")
+        trials_output = gr.DataFrame(label="Top 7 Hyperparameter Trials")
 
-    # ─────────────────── Explainability ───────────────────
     with gr.Row():
         explain_btn = gr.Button("SHAP + LIME Explainability")
-        shap_img    = gr.Image(label="SHAP Summary")
-        lime_img    = gr.Image(label="LIME Explanation")
-
-    # ─────────────────── A/B Testing ───────────────────
-    with gr.Row():
-        ab_test_button = gr.Button("Run A/B Testing")
-        ab_summary     = gr.HTML(label="A/B Test Summary")
-        ab_results     = gr.DataFrame(label="A/B Test Results")
+        shap_img = gr.Image(label="SHAP Summary Plot")
+        lime_img = gr.Image(label="LIME Explanation")
 
-    # ─────────────────── Hook callbacks ───────────────────
-   # agent_btn.click(fn=analyze_data,  inputs=[file_input], outputs=[insights_output, visual_output])
-   # train_btn.click(fn=train_model,   inputs=[file_input], outputs=[metrics_output, trials_output])
-   # explain_btn.click(fn=explainability, inputs=[], outputs=[shap_img, lime_img])
-    ab_test_button.click(fn=ab_test_models, inputs=[], outputs=[ab_summary, ab_results])
+    agent_btn.click(fn=analyze_data, inputs=[file_input], outputs=[insights_output, visual_output])
+    train_btn.click(fn=train_model, inputs=[file_input], outputs=[metrics_output, trials_output])
+    explain_btn.click(fn=explainability, inputs=[], outputs=[shap_img, lime_img])
 
-    demo.launch(debug=True)
+demo.launch(debug=True)