Update app.py

app.py

@@ -24,11 +24,14 @@ def preprocess_data(df: pd.DataFrame, target_column: str, k_best: int = None):
     X.replace([np.inf, -np.inf], np.nan, inplace=True)
     X = X.fillna(X.median())
     y = y.fillna(y.median())
+
+    # Optionally select top k features
     if k_best is not None and k_best < X.shape[1]:
         selector = SelectKBest(score_func=f_regression, k=k_best)
         X_selected = selector.fit_transform(X, y)
         selected_indices = selector.get_support(indices=True)
         X = X.iloc[:, selected_indices]
+
     return X, y
 
 def apply_pca(X: pd.DataFrame, n_components: int = 5):
@@ -38,7 +41,8 @@ def apply_pca(X: pd.DataFrame, n_components: int = 5):
     X_pca = pca.fit_transform(X_scaled)
     return X_pca, pca
 
-def visualize_pca(X_pca: np.ndarray, y: pd.Series, pca, target_label: str = 'Median Income Household'):
+def visualize_pca(X_pca: np.ndarray, y: pd.Series, pca, target_label: str):
+    # 1) Scatter plot of PC1 vs PC2
     scatter_plot_file = 'pca_scatter.png'
     plt.figure(figsize=(10, 6))
     plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', edgecolor='k', s=50)
@@ -50,7 +54,7 @@ def visualize_pca(X_pca: np.ndarray, y: pd.Series, pca, target_label: str = 'Med
     plt.savefig(scatter_plot_file, dpi=100, bbox_inches='tight')
     plt.close()
 
-    # Pair plot
+    # 2) Pair plot of the first few components
     pair_plot_file = 'pca_pairplot.png'
     num_components = min(X_pca.shape[1], 5)
     pca_df = pd.DataFrame(X_pca[:, :num_components],
@@ -62,7 +66,7 @@ def visualize_pca(X_pca: np.ndarray, y: pd.Series, pca, target_label: str = 'Med
     plt.savefig(pair_plot_file, dpi=100, bbox_inches='tight')
     plt.close()
 
-    # Scree plot
+    # 3) Scree plot
     scree_plot_file = 'pca_scree.png'
     plt.figure(figsize=(8, 5))
     plt.bar(range(1, pca.n_components_ + 1), pca.explained_variance_ratio_, alpha=0.7, color='red')
@@ -82,9 +86,6 @@ def gradio_interface(target_column: str, n_components: int = 5, k_best: int = 0)
     scatter_plot, pair_plot, scree_plot = visualize_pca(X_pca, y, pca_model, target_label=target_column)
     return scatter_plot, pair_plot, scree_plot
 
-# ------------------------------------------------------------------------------
-# HERE is the updated Gradio interface with direct component calls (no .inputs)
-# ------------------------------------------------------------------------------
 iface = gr.Interface(
     fn=gradio_interface,
     inputs=[
@@ -92,10 +93,11 @@ iface = gr.Interface(
         gr.Slider(label="Number of PCA Components", minimum=2, maximum=20, step=1, value=5),
         gr.Slider(label="SelectKBest (0 to skip)", minimum=0, maximum=50, step=1, value=0)
     ],
+    # Use 'filepath' instead of 'file' so Gradio knows you're returning local image paths
     outputs=[
-        gr.Image(type="file", label="PCA Scatter Plot"),
-        gr.Image(type="file", label="PCA Pair Plot"),
-        gr.Image(type="file", label="Scree Plot")
+        gr.Image(type="filepath", label="PCA Scatter Plot"),
+        gr.Image(type="filepath", label="PCA Pair Plot"),
+        gr.Image(type="filepath", label="Scree Plot")
     ],
     title="PCA Visualization with DuckDB and Gradio",
     description=(