main.py

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+import pandas as pd
+import openai  # For LLM integration
+import matplotlib.pyplot as plt
+import seaborn as sns
+import io
+
+# OpenAI API Key (Replace with env variable in production)
+openai.api_key = "YOUR_OPENAI_API_KEY"
+
+def analyze_dataset(file):
+    # Load dataset
+    df = pd.read_csv(file.name)
+    
+    # Generate summary statistics
+    summary = df.describe().to_string()
+    missing_values = df.isnull().sum().to_string()
+    duplicates = df.duplicated().sum()
+    
+    # Prompt LLM for insights
+    prompt = f"""
+    Given the following dataset summary:
+    {summary}
+    Missing Values:
+    {missing_values}
+    Duplicate Entries: {duplicates}
+    
+    Provide a structured analysis, visualization suggestions, and cleaning strategies.
+    """
+    response = openai.ChatCompletion.create(
+        model="gpt-4",
+        messages=[{"role": "system", "content": "You are a data science expert."},
+                  {"role": "user", "content": prompt}]
+    )
+    insights = response["choices"][0]["message"]["content"]
+    
+    # Generate visualizations
+    fig, ax = plt.subplots(figsize=(6, 4))
+    sns.heatmap(df.corr(), annot=True, cmap='coolwarm', ax=ax)
+    buf = io.BytesIO()
+    plt.savefig(buf, format='png')
+    buf.seek(0)
+    
+    return insights, buf
+
+# Gradio UI
+demo = gr.Interface(
+    fn=analyze_dataset,
+    inputs=gr.File(type="file"),
+    outputs=[gr.Textbox(label="Analysis"), gr.Image(label="Correlation Heatmap")],
+    title="LLM-Powered Data Analyzer",
+    description="Upload a dataset and get automatic insights, visualizations, and cleaning suggestions."
+)
+
+demo.launch()