Create app.py

app.py

@@ -0,0 +1,85 @@
+import gradio as gr
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import io
+from docx import Document
+from docx.shared import Inches
+
+def generate_report(df):
+    # Create Word Document
+    doc = Document()
+    doc.add_heading('Amrita Manthan: Preprocessing Report', 0)
+    doc.add_paragraph(f"Author: Prof. B. Santhi, SRC, SASTRA")
+    
+    # Data Description
+    doc.add_heading('1. Data Description', level=1)
+    description = df.describe().to_string()
+    doc.add_paragraph(description)
+    
+    # Missing Values
+    doc.add_heading('2. Preprocessing: Missing Values', level=1)
+    null_data = df.isnull().sum().to_string()
+    doc.add_paragraph(null_data)
+    
+    report_path = "preprocessing_report.docx"
+    doc.save(report_path)
+    return report_path
+
+def process_data(file):
+    if file is None:
+        return None, "Please upload a CSV file.", None, None
+    
+    # Load Data
+    df = pd.read_csv(file.name)
+    
+    # 1. EDA: Basic Stats
+    desc = df.describe(include='all').reset_index()
+    
+    # 2. EDA: Correlation Plot
+    plt.figure(figsize=(10, 6))
+    sns.heatmap(df.corr(numeric_only=True), annot=True, cmap='coolwarm')
+    plt.tight_layout()
+    plot_path = "eda_plot.png"
+    plt.savefig(plot_path)
+    plt.close()
+    
+    # 3. Generate Docx
+    report = generate_report(df)
+    
+    return df.head(10), desc, plot_path, report
+
+# --- Gradio UI Design ---
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    # Header Section
+    with gr.Column(elem_id="header"):
+        gr.Image("sastra_logo.jpg", width=150, container=False) # Ensure file exists
+        gr.Markdown("<h1 style='text-align: center;'>Amrita Manthan</h1>")
+        gr.Markdown("<h3 style='text-align: center;'>Preprocessing & Data Mining Portal</h3>")
+        gr.Markdown("<p style='text-align: center;'><i>Prof. B. Santhi, SRC, SASTRA</i></p>")
+
+    with gr.Tabs():
+        with gr.TabItem("Step 1: Upload & Process"):
+            file_input = gr.File(label="Upload CSV Dataset", file_types=[".csv"])
+            process_btn = gr.Button("Analyze Data", variant="primary")
+            
+        with gr.TabItem("Step 2: Data View"):
+            with gr.Row():
+                out_raw = gr.DataFrame(label="Raw Data (First 10 Rows)")
+                out_desc = gr.DataFrame(label="Statistical Summary")
+                
+        with gr.TabItem("Step 3: Visual EDA"):
+            out_plot = gr.Image(label="Correlation Heatmap")
+            
+        with gr.TabItem("Step 4: Download Report"):
+            gr.Markdown("Click below to download the full preprocessing documentation.")
+            out_file = gr.File(label="Download DOCX Report")
+
+    # Click Logic
+    process_btn.click(
+        fn=process_data,
+        inputs=[file_input],
+        outputs=[out_raw, out_desc, out_plot, out_file]
+    )
+
+demo.launch()