Update app.py

app.py

@@ -1,56 +1,58 @@
 import gradio as gr
 import pandas as pd
-import plotly.express as px
-
-# Global variable to hold the dataset
-data = pd.DataFrame()
-
-def load_and_show(csv_file):
-    global data
-    if csv_file is None:
-        return "Please upload a CSV file.", None, None
-    data = pd.read_csv(csv_file.name)
-    summary = data.describe().reset_index()
-    
-    return (
-        data.head().to_dict(orient="records"),  # Show first few rows in table
-        summary.to_dict(orient="records"),      # Show summary stats
-        None                                   # Empty plot initially
-    )
-
-def plot_column(col_name):
-    global data
-    if data.empty or col_name not in data.columns:
-        return None
-    if pd.api.types.is_numeric_dtype(data[col_name]):
-        fig = px.histogram(data, x=col_name, nbins=30, title=f"Distribution of {col_name}")
-        return fig
+
+# Global variable to store the dataframe
+df_global = None
+
+def load_data(file):
+    global df_global
+    if file is None:
+        return pd.DataFrame(), "Please upload a CSV file."
+    df_global = pd.read_csv(file.name)
+    preview = df_global.head(10)
+    return preview, f"Loaded {len(df_global)} rows and {len(df_global.columns)} columns."
+
+def filter_data(column, value):
+    global df_global
+    if df_global is None:
+        return pd.DataFrame(), "No data loaded."
+    if column == "" or value == "":
+        filtered = df_global
     else:
-        return None
+        # Filter rows where the column contains the value (case-insensitive)
+        filtered = df_global[df_global[column].astype(str).str.contains(value, case=False, na=False)]
+    preview = filtered.head(10)
+    summary = filtered.describe(include='all').to_string()
+    return preview, summary
 
 with gr.Blocks() as demo:
-    gr.Markdown("# 📊 CSV Viewer with Search, Filter & Stats")
-    
+    gr.Markdown("# CSV Data Explorer\nUpload a CSV, filter data, and see summary stats.")
+
+    with gr.Row():
+        csv_file = gr.File(label="Upload CSV", file_types=['.csv'])
+        load_btn = gr.Button("Load Data")
+
+    table = gr.DataFrame(headers=None, interactive=True, label="Data Preview")
+    status = gr.Textbox(label="Status", interactive=False)
+
     with gr.Row():
-        csv_input = gr.File(label="Upload CSV", file_types=[".csv"])
-    
-    table = gr.DataFrame(headers=None, interactive=True, label="Dataset Preview", max_rows=10)
-    summary_table = gr.DataFrame(headers=None, interactive=False, label="Summary Statistics")
-    plot = gr.Plot()
-    
-    csv_input.change(load_and_show, inputs=csv_input, outputs=[table, summary_table, plot])
-    
-    col_dropdown = gr.Dropdown(choices=[], label="Select column to plot histogram")
-    col_dropdown.change(plot_column, inputs=col_dropdown, outputs=plot)
-    
-    # Update column dropdown choices after CSV load
-    def update_columns(csv_file):
-        if csv_file is None:
+        filter_column = gr.Dropdown(choices=[], label="Filter Column", interactive=True)
+        filter_value = gr.Textbox(placeholder="Filter value", label="Filter Value")
+        filter_btn = gr.Button("Filter Data")
+
+    summary_stats = gr.Textbox(label="Summary Statistics", interactive=False, lines=10)
+
+    load_btn.click(load_data, inputs=csv_file, outputs=[table, status])
+
+    # Update filter_column choices dynamically when data loads
+    def update_columns(file):
+        if file is None:
             return []
-        df = pd.read_csv(csv_file.name)
-        numeric_cols = [c for c in df.columns if pd.api.types.is_numeric_dtype(df[c])]
-        return numeric_cols
-    
-    csv_input.change(update_columns, inputs=csv_input, outputs=col_dropdown)
-    
+        df = pd.read_csv(file.name)
+        return list(df.columns)
+
+    csv_file.change(update_columns, inputs=csv_file, outputs=filter_column)
+
+    filter_btn.click(filter_data, inputs=[filter_column, filter_value], outputs=[table, summary_stats])
+
 demo.launch()