Update app.py

app.py

@@ -6,7 +6,7 @@ import matplotlib.pyplot as plt
 from io import BytesIO
 from sklearn.model_selection import train_test_split
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import classification_report
+from sklearn.metrics import classification_report, accuracy_score
 from PIL import Image
 
 original_df = None
@@ -22,8 +22,9 @@ def load_data(file):
         else:
             original_df = pd.read_excel(file)
         help_text = (
-            "Step 1: Data loaded successfully! Here you see a preview of the first 10 rows.\n"
-            "Next, click 'Process Data' to discretize numeric columns and add word counts."
+            "Step 1: Data loaded successfully!\n"
+            "- Preview shows first 10 rows.\n"
+            "- Next: Click 'Process Data' to discretize numeric columns and add word counts for text."
         )
         return original_df.head(10), "✅ File loaded successfully.", help_text
     except Exception as e:
@@ -34,19 +35,19 @@ def process_data():
     if original_df is None:
         return pd.DataFrame(), gr.update(choices=[]), gr.update(choices=[]), "⚠️ Please load a dataset first.", ""
     df = original_df.copy()
-    # Quartiles
+    # Quartiles discretization
     for col in df.select_dtypes(include=np.number).columns:
         try:
             df[col + "_qbin"] = pd.qcut(df[col], 4, labels=False, duplicates='drop')
         except Exception:
             pass
-    # Deciles
+    # Deciles discretization
     for col in df.select_dtypes(include=np.number).columns:
         try:
             df[col + "_decil"] = pd.qcut(df[col], 10, labels=False, duplicates='drop')
         except Exception:
             pass
-    # Word counts
+    # Word counts for text columns
     for col in df.select_dtypes(include='object').columns:
         df[col + "_wordcount"] = df[col].astype(str).apply(lambda x: len(x.split()))
     processed_df = df.copy()
@@ -55,35 +56,44 @@ def process_data():
         "Step 2: Data processed!\n"
         "- Numeric columns discretized into quartiles and deciles.\n"
         "- Word counts added for text columns.\n"
-        "You can now select your target and feature columns."
+        "- You can now select your target and feature columns."
     )
     return df.head(10), gr.update(choices=all_columns), gr.update(choices=all_columns), "✅ Data processed.", help_text
 
 def train_model(target_col, feature_cols):
     global processed_df, trained_model, processed_X_columns
     if processed_df is None:
-        return "⚠️ Please process your data first.", None, "Load and process your data before training."
+        return "⚠️ Please process your data first.", None, ""
     if not target_col or not feature_cols:
-        return "⚠️ Please select a target and at least one feature.", None, "Select a target variable and features to train the model."
+        return "⚠️ Please select a target and at least one feature.", None, ""
 
     try:
         X = processed_df[feature_cols]
         y = processed_df[target_col]
+
+        # One-hot encoding categorical features if any
         X = pd.get_dummies(X)
         processed_X_columns = X.columns.tolist()
+
+        # Train/test split
         X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+        # Train Random Forest Classifier
         clf = RandomForestClassifier(random_state=42)
         clf.fit(X_train, y_train)
         trained_model = clf
+
+        # Predict & evaluate
         y_pred = clf.predict(X_test)
+        accuracy = accuracy_score(y_test, y_pred)
         report = classification_report(y_test, y_pred)
 
-        # Prepare feature importance heatmap
+        # Feature importances
         fi = clf.feature_importances_
         fi_df = pd.DataFrame({'Feature': processed_X_columns, 'Importance': fi})
         fi_df = fi_df.sort_values(by='Importance', ascending=False).head(20)
 
-        plt.figure(figsize=(8,6))
+        plt.figure(figsize=(10, 6))
         sns.heatmap(fi_df.set_index('Feature').T, annot=True, cmap="YlGnBu", cbar_kws={'label': 'Feature Importance'})
         plt.title("Feature Importances Heatmap (Top 20)")
         plt.tight_layout()
@@ -94,16 +104,20 @@ def train_model(target_col, feature_cols):
         buf.seek(0)
         img = Image.open(buf)
 
-        # Dynamic explanatory help text
+        # Detailed help text
         help_text = (
-            "📋 **Classification Report Help:**\n"
-            "- Precision: Of all predicted positive cases, how many are actually positive?\n"
-            "- Recall: Of all actual positive cases, how many did the model identify?\n"
-            "- F1-Score: Balance between precision and recall.\n\n"
-            "🌟 **Heatmap Help:**\n"
-            "- Shows top 20 features by importance.\n"
-            "- Darker color = more influence on model's decisions.\n"
-            "- Use this to understand which variables drive predictions most."
+            f"📊 Model type: Random Forest Classifier\n"
+            f"🎯 Target: '{target_col}'\n"
+            f"���� Features used: {len(feature_cols)}\n"
+            f"✅ Accuracy on test set: {accuracy:.2%}\n\n"
+            "📋 Classification Report Explanation:\n"
+            "- Precision: Of predicted positives, how many are correct?\n"
+            "- Recall: Of actual positives, how many were found?\n"
+            "- F1-Score: Harmonic mean of precision & recall.\n\n"
+            "🌡️ Heatmap Explanation:\n"
+            "- Shows top 20 most important features by model.\n"
+            "- Darker cells = higher influence on predictions.\n"
+            "- Use this to understand which variables drive decisions."
         )
 
         return report, img, help_text
@@ -111,7 +125,6 @@ def train_model(target_col, feature_cols):
     except Exception as e:
         return f"❌ Model training failed: {e}", None, ""
 
-
 with gr.Blocks(title="Step-by-Step Model Trainer with Help and Heatmap") as app:
     gr.Markdown("## 🧠 Step-by-Step Model Trainer\nUpload your data, process it, train a model, and get help at each step!")
 
@@ -131,11 +144,9 @@ with gr.Blocks(title="Step-by-Step Model Trainer with Help and Heatmap") as app:
     feature_selector = gr.CheckboxGroup(label="📊 Select Feature Columns", choices=[])
 
     train_button = gr.Button("🚀 Train Model")
-    train_output = gr.Textbox(label="📈 Classification Report", lines=10)
+    train_output = gr.Textbox(label="📈 Classification Report", lines=15)
     heatmap_output = gr.Image(label="🌡️ Feature Importance Heatmap")
-    train_help = gr.Textbox(label="📝 Help to read results", interactive=False, lines=10)
-    train_help = gr.Textbox(label="📖 Step 3 Help", interactive=False)
-    heatmap_img = gr.Image(label="🔥 Feature Importances Heatmap")
+    train_help = gr.Textbox(label="📝 Help to read results", interactive=False, lines=12)
 
     # Callbacks
     file_input.change(
@@ -151,9 +162,9 @@ with gr.Blocks(title="Step-by-Step Model Trainer with Help and Heatmap") as app:
     )
 
     train_button.click(
-    fn=train_model,
-    inputs=[target_selector, feature_selector],
-    outputs=[train_output, heatmap_output, train_help]
+        fn=train_model,
+        inputs=[target_selector, feature_selector],
+        outputs=[train_output, heatmap_output, train_help]
     )
 
 app.launch()