Create app.py

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import pandas as pd
+import os
+from omnibin import generate_binary_classification_report
+import tempfile
+
+def process_csv(csv_file):
+    # Read the CSV file
+    df = pd.read_csv(csv_file.name)
+    
+    # Check if required columns exist
+    required_columns = ['y_true', 'y_pred']
+    if not all(col in df.columns for col in required_columns):
+        raise ValueError("CSV file must contain 'y_true' and 'y_pred' columns")
+    
+    # Create a temporary directory for the output
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Generate the report
+        report_path = generate_binary_classification_report(
+            y_true=df['y_true'].values,
+            y_scores=df['y_pred'].values,
+            output_path=os.path.join(temp_dir, "classification_report.pdf"),
+            n_bootstrap=1000,
+            random_seed=42,
+            dpi=72
+        )
+        
+        # Return the PDF file
+        return report_path
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=process_csv,
+    inputs=gr.File(label="Upload CSV file with 'y_true' and 'y_pred' columns"),
+    outputs=gr.File(label="Classification Report PDF"),
+    title="Binary Classification Report Generator",
+    description="Upload a CSV file containing 'y_true' and 'y_pred' columns to generate a comprehensive classification report with 6 figures.",
+    examples=[],
+    cache_examples=False
+)
+
+if __name__ == "__main__":
+    iface.launch()