Update app.py

app.py

@@ -12,95 +12,125 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import io
 
-def analyze_csv(file, label_col, n_clusters):
+def update_dropdown(file):
+    """Update the dropdown choices with column names from the uploaded file."""
+    if file is None:
+        return gr.Dropdown.update(choices=[], value=None)
     try:
-        df = pd.read_csv(file.name if hasattr(file, "name") else file)
+        if file.name.endswith('.csv'):
+            df = pd.read_csv(file.name)
+        elif file.name.endswith('.xlsx'):
+            df = pd.read_excel(file.name)
+        else:
+            return gr.Dropdown.update(choices=[], value=None)
+        return gr.Dropdown.update(choices=list(df.columns), value=None)
+    except Exception:
+        return gr.Dropdown.update(choices=[], value=None)
+
+def analyze_file(file, label_col, n_clusters):
+    """Analyze the uploaded file with ML techniques and return results and plots."""
+    # Read the file based on its extension
+    try:
+        if file.name.endswith('.csv'):
+            df = pd.read_csv(file.name)
+        elif file.name.endswith('.xlsx'):
+            df = pd.read_excel(file.name)
+        else:
+            return ("Unsupported file type. Please upload a CSV or XLSX file.", None, None, None, None, None)
     except Exception as e:
-        return (None,)*6 + (f"error reading csv: {e}",)
-    
+        return (f"Error reading file: {e}", None, None, None, None, None)
+
+    # Validate label column
     if label_col not in df.columns:
-        return (None,)*6 + (f"label column '{label_col}' not in data",)
-    
+        return (f"Label column '{label_col}' not found. Please select a valid column.", None, None, None, None, None)
+
+    # Clean data and validate size
     df = df.dropna()
-    # separate target and features
+    if df.shape[0] < 10:
+        return ("Not enough data rows (less than 10) after removing missing values.", None, None, None, None, None)
+    if df.shape[1] < 2:
+        return ("Need at least one feature and one label column.", None, None, None, None, None)
+
+    # Separate features and target
     y = df[label_col]
     X = df.drop(columns=[label_col])
-    # create one-hot encodings for non-numeric columns
-    X_processed = pd.get_dummies(X)
-    
-    # scale features for clustering methods
+    X_processed = pd.get_dummies(X)  # One-hot encode categorical features
     scaler = StandardScaler()
     X_scaled = scaler.fit_transform(X_processed)
-    
+
     results_text = ""
     model_img = None
 
-    # model training & evaluation: regression if y numeric, classification otherwise
+    # Prediction: regression or classification based on target type
     if pd.api.types.is_numeric_dtype(y):
-        # regression
+        # Regression
         X_train, X_test, y_train, y_test = train_test_split(X_processed, y, test_size=0.3, random_state=42)
         model = RandomForestRegressor(random_state=42)
         model.fit(X_train, y_train)
         y_pred = model.predict(X_test)
         mse = mean_squared_error(y_test, y_pred)
         r2 = r2_score(y_test, y_pred)
-        results_text += f"regression results:\nmse: {mse:.3f}\nr2: {r2:.3f}\n"
-        # scatter plot: true vs predicted with y=x line
-        plt.figure(figsize=(6,4))
+        results_text += (
+            "Regression Results (predicting numeric values):\n"
+            f"- Mean Squared Error (MSE): {mse:.3f} (lower is better)\n"
+            f"- R² Score: {r2:.3f} (0 to 1, higher is better)\n"
+        )
+        plt.figure(figsize=(8, 6))
         plt.scatter(y_test, y_pred, alpha=0.7)
         plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')
-        plt.xlabel("true values")
-        plt.ylabel("predicted values")
-        plt.title("regression: true vs predicted")
+        plt.xlabel("True Values")
+        plt.ylabel("Predicted Values")
+        plt.title("Regression: True vs Predicted")
         buf = io.BytesIO()
         plt.savefig(buf, format="png", bbox_inches="tight")
         plt.close()
         buf.seek(0)
         model_img = buf
     else:
-        # classification
+        # Classification
         y_encoded, uniques = pd.factorize(y)
         X_train, X_test, y_train, y_test = train_test_split(X_processed, y_encoded, test_size=0.3, random_state=42)
         model = RandomForestClassifier(random_state=42)
         model.fit(X_train, y_train)
         y_pred = model.predict(X_test)
         cm = confusion_matrix(y_test, y_pred)
-        cr = classification_report(y_test, y_pred)
-        results_text += f"classification results:\n{cr}\n"
-        plt.figure(figsize=(6,4))
-        sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
-        plt.xlabel("predicted")
-        plt.ylabel("true")
-        plt.title("confusion matrix")
+        cr = classification_report(y_test, y_pred, target_names=[str(u) for u in uniques])
+        results_text += "Classification Results (predicting categories):\n" + cr + "\n"
+        plt.figure(figsize=(8, 6))
+        sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", xticklabels=uniques, yticklabels=uniques)
+        plt.xlabel("Predicted")
+        plt.ylabel("True")
+        plt.title("Confusion Matrix")
         buf = io.BytesIO()
         plt.savefig(buf, format="png", bbox_inches="tight")
         plt.close()
         buf.seek(0)
         model_img = buf
 
-    # feature importance plot (from the model)
-    fi = pd.Series(model.feature_importances_, index=X_processed.columns).sort_values(ascending=False)
-    plt.figure(figsize=(8,4))
+    # Feature importance (top 10)
+    fi = pd.Series(model.feature_importances_, index=X_processed.columns).sort_values(ascending=False).head(10)
+    plt.figure(figsize=(10, 6))
     sns.barplot(x=fi.values, y=fi.index)
-    plt.title("feature importances")
-    plt.xlabel("importance")
-    plt.ylabel("feature")
+    plt.title("Top 10 Feature Importances")
+    plt.xlabel("Importance")
+    plt.ylabel("Feature")
     buf = io.BytesIO()
     plt.savefig(buf, format="png", bbox_inches="tight")
     plt.close()
     buf.seek(0)
     fi_img = buf
 
-    # clustering with kmeans
+    # KMeans clustering
     kmeans = KMeans(n_clusters=n_clusters, random_state=42)
     clusters_kmeans = kmeans.fit_predict(X_scaled)
     pca = PCA(n_components=2, random_state=42)
     X_pca = pca.fit_transform(X_scaled)
-    plt.figure(figsize=(6,4))
-    scatter = plt.scatter(X_pca[:,0], X_pca[:,1], c=clusters_kmeans, cmap="viridis", alpha=0.7)
-    plt.xlabel("pca 1")
-    plt.ylabel("pca 2")
-    plt.title(f"kmeans clustering (k={n_clusters})")
+    explained_var = sum(pca.explained_variance_ratio_)
+    plt.figure(figsize=(8, 6))
+    scatter = plt.scatter(X_pca[:, 0], X_pca[:, 1], c=clusters_kmeans, cmap="viridis", alpha=0.7)
+    plt.xlabel("PCA 1")
+    plt.ylabel("PCA 2")
+    plt.title(f"KMeans Clustering (PCA, {explained_var:.2%} variance explained)")
     plt.colorbar(scatter, ticks=range(n_clusters))
     buf = io.BytesIO()
     plt.savefig(buf, format="png", bbox_inches="tight")
@@ -108,14 +138,14 @@ def analyze_csv(file, label_col, n_clusters):
     buf.seek(0)
     kmeans_img = buf
 
-    # clustering with agglomerative clustering
+    # Agglomerative clustering
     agg = AgglomerativeClustering(n_clusters=n_clusters)
     clusters_agg = agg.fit_predict(X_scaled)
-    plt.figure(figsize=(6,4))
-    scatter = plt.scatter(X_pca[:,0], X_pca[:,1], c=clusters_agg, cmap="plasma", alpha=0.7)
-    plt.xlabel("pca 1")
-    plt.ylabel("pca 2")
-    plt.title(f"agglomerative clustering (k={n_clusters})")
+    plt.figure(figsize=(8, 6))
+    scatter = plt.scatter(X_pca[:, 0], X_pca[:, 1], c=clusters_agg, cmap="plasma", alpha=0.7)
+    plt.xlabel("PCA 1")
+    plt.ylabel("PCA 2")
+    plt.title(f"Agglomerative Clustering (PCA, {explained_var:.2%} variance explained)")
     plt.colorbar(scatter, ticks=range(n_clusters))
     buf = io.BytesIO()
     plt.savefig(buf, format="png", bbox_inches="tight")
@@ -123,15 +153,14 @@ def analyze_csv(file, label_col, n_clusters):
     buf.seek(0)
     agg_img = buf
 
-    # differentiating features among clusters (using kmeans clusters)
-    f_scores, p_vals = f_classif(X_processed, clusters_kmeans)
-    f_series = pd.Series(f_scores, index=X_processed.columns).sort_values(ascending=False)
-    top_features = f_series.head(10)
-    plt.figure(figsize=(8,4))
-    sns.barplot(x=top_features.values, y=top_features.index, palette="mako")
-    plt.title("top differentiating features (anova f-scores)")
-    plt.xlabel("f-score")
-    plt.ylabel("feature")
+    # Differentiating features (top 10)
+    f_scores, _ = f_classif(X_processed, clusters_kmeans)
+    f_series = pd.Series(f_scores, index=X_processed.columns).sort_values(ascending=False).head(10)
+    plt.figure(figsize=(10, 6))
+    sns.barplot(x=f_series.values, y=f_series.index, palette="mako")
+    plt.title("Top 10 Differentiating Features (ANOVA F-scores)")
+    plt.xlabel("F-score")
+    plt.ylabel("Feature")
     buf = io.BytesIO()
     plt.savefig(buf, format="png", bbox_inches="tight")
     plt.close()
@@ -140,45 +169,6 @@ def analyze_csv(file, label_col, n_clusters):
 
     return results_text, model_img, fi_img, kmeans_img, agg_img, diff_img
 
-def update_dropdown(file):
-    if file is None:
-        return gr.Dropdown.update(choices=[], value=None)
-    try:
-        df = pd.read_csv(file.name if hasattr(file, "name") else file)
-        return gr.Dropdown.update(choices=list(df.columns), value=None)
-    except:
-        return gr.Dropdown.update(choices=[], value=None)
-
 with gr.Blocks() as demo:
-    gr.Markdown("## csv analysis app")
-    with gr.Row():
-        file_input = gr.File(label="upload csv", file_types=[".csv"])
-        label_dropdown = gr.Dropdown(label="select label column", interactive=True)
-    
-        file_input.change(
-            fn=update_dropdown, 
-            inputs=file_input, 
-            outputs=label_dropdown
-        )
-        clusters_slider = gr.Slider(minimum=2, maximum=10, step=1, value=3, label="number of clusters")
-    
-    
-    analyze_btn = gr.Button("analyze")
-    with gr.Tabs():
-        with gr.TabItem("results"):
-            results_textbox = gr.Textbox(label="metrics & descriptions", lines=10)
-        with gr.TabItem("model visualization"):
-            model_img_output = gr.Image(label="model output (confusion matrix or regression scatter)")
-        with gr.TabItem("feature importances"):
-            fi_output = gr.Image(label="feature importances")
-        with gr.TabItem("kmeans clustering"):
-            kmeans_output = gr.Image(label="kmeans clustering (pca projection)")
-        with gr.TabItem("agglomerative clustering"):
-            agg_output = gr.Image(label="agglomerative clustering (pca projection)")
-        with gr.TabItem("cluster differentiation"):
-            diff_output = gr.Image(label="differentiating features among clusters")
-    
-    analyze_btn.click(fn=analyze_csv, inputs=[file_input, label_dropdown, clusters_slider],
-                      outputs=[results_textbox, model_img_output, fi_output, kmeans_output, agg_output, diff_output])
-
-demo.launch()
+    gr.Markdown("## Data Analysis Explorer")
+    gr.Markdown("Upload a CSV or XLSX file to explore classification, regression, and clustering. Select a column to predict and the number of