updated

app.py

@@ -9,6 +9,7 @@ import dash
 import dash_core_components as dcc
 import dash_html_components as html
 import dash_table
+import gradio as gr
 from sklearn.model_selection import train_test_split
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.linear_model import LogisticRegression
@@ -132,7 +133,7 @@ def create_dashboard(df, correlation_data, clustering_data, prediction_results):
 
         html.Div([
             html.H2('Clustering Analysis'),
-            html.P(f'Best Clustering Algorithm: {clustering_data["best_model"]}'),
+            html.P(f"Best Clustering Algorithm: {clustering_data['best_model']}"),
             dcc.Graph(
                 id='clustering_scatter',
                 figure={
@@ -167,23 +168,21 @@ def create_dashboard(df, correlation_data, clustering_data, prediction_results):
 
     app.run_server(debug=True)
 
-# Main execution
-if __name__ == "__main__":
-    # Load dataset
-    df = pd.read_csv('student_data.csv')  # Replace with your CSV file
-
-    # Preprocess the data
+def load_csv(file):
+    df = pd.read_csv(file.name)
     df = enhanced_preprocessing(df)
+    return df
 
-    # Perform correlation analysis
-    correlation_data = calculate_correlations(df)
-
-    # Perform clustering analysis
-    df, best_model = perform_clustering(df)
-    clustering_data = {'best_model': best_model}
+# Main execution
+iface = gr.Interface(
+    fn=load_csv,
+    inputs=gr.inputs.File(label="Upload CSV File"),
+    outputs="dataframe",
+    description="Upload a CSV file to perform comprehensive student data analysis."
+)
 
-    # Perform prediction analysis
-    prediction_results = pd.DataFrame(perform_predictions(df))
+iface.launch()
 
-    # Create and launch the dashboard
-    create_dashboard(df, correlation_data, clustering_data, prediction_results)
+# Note: The data loading is done through Gradio, no need for an additional file parameter.
+if __name__ == "__main__":
+    pass