Update app.py

app.py

@@ -1,3 +1,4 @@
+import gradio as gr
 import pandas as pd
 import matplotlib.pyplot as plt
 import io
@@ -6,12 +7,6 @@ from PIL import Image, ImageDraw
 import google.generativeai as genai
 import traceback
 import os
-from pywebio import start_server
-from pywebio.input import file_upload, input
-from pywebio.output import put_text, put_image, put_row, put_column, use_scope, put_buttons
-from pywebio.session import run_js, set_env
-import base64
-import threading
 
 def process_file(file, instructions):
     try:
@@ -21,11 +16,8 @@ def process_file(file, instructions):
         model = genai.GenerativeModel('gemini-2.5-pro-preview-03-25')
         
         # Read uploaded file
-        content = file['content']
-        if file['filename'].endswith('.csv'):
-            df = pd.read_csv(io.BytesIO(content))
-        else:
-            df = pd.read_excel(io.BytesIO(content))
+        file_path = file.name
+        df = pd.read_csv(file_path) if file_path.endswith('.csv') else pd.read_excel(file_path)
         
         # Generate visualization code
         response = model.generate_content(f"""
@@ -40,7 +32,6 @@ def process_file(file, instructions):
             2. Determine appropriate data aggregation (e.g., top 5 categories, yearly averages)
             3. Select relevant columns for x-axis, y-axis, and any additional dimensions (color, size)
             4. Provide a clear, concise title that explains the insight
-
             Consider data density and choose visualizations that simplify and clarify the information.
             Limit the number of data points displayed to ensure readability (e.g., top 5, top 10, yearly).
             
@@ -123,42 +114,22 @@ def process_file(file, instructions):
         draw.text((10, 10), error_message, fill=(255, 0, 0))
         return [error_image] * 3
 
-def data_analysis_dashboard():
-    set_env(title="Data Analysis Dashboard")
-    put_text("# Data Analysis Dashboard")
-    
-    with use_scope('form'):
-        put_row([
-            put_column([
-                file_upload("Upload Dataset", accept=[".csv", ".xlsx"], name="file"),
-                input("Analysis Instructions", type="text", placeholder="Describe the analysis you want...", name="instructions"),
-                put_buttons(['Generate Insights'], onclick=[lambda: generate_insights()])
-            ])
-        ])
-    
-    with use_scope('output'):
-        for i in range(3):
-            put_scope(f'visualization_{i+1}')
-
-def generate_insights():
-    file = file_upload.files.get('file')
-    instructions = input.inputs.get('instructions')
+with gr.Blocks(theme=gr.themes.Default()) as demo:
+    gr.Markdown("# Data Analysis Dashboard")
     
-    if not file or not instructions:
-        put_text("Please upload a file and provide instructions.")
-        return
+    with gr.Row():
+        file = gr.File(label="Upload Dataset", file_types=[".csv", ".xlsx"])
+        instructions = gr.Textbox(label="Analysis Instructions", placeholder="Describe the analysis you want...")
     
-    images = process_file(file, instructions)
+    submit = gr.Button("Generate Insights", variant="primary")
     
-    for i, img in enumerate(images):
-        buffered = io.BytesIO()
-        img.save(buffered, format="PNG")
-        img_str = base64.b64encode(buffered.getvalue()).decode()
-        with use_scope(f'visualization_{i+1}', clear=True):
-            put_image(img_str, width='100%')
+    output_images = [gr.Image(label=f"Visualization {i+1}") for i in range(3)]
 
-def main():
-    data_analysis_dashboard()
+    submit.click(
+        process_file,
+        inputs=[file, instructions],
+        outputs=output_images
+    )
 
-if __name__ == '__main__':
-    start_server(main, host='0.0.0.0', port=7860, debug=True, cdn=False, auto_open_webbrowser=True)
+if __name__ == "__main__":
+    demo.launch()