Update app.py

app.py

@@ -2,7 +2,6 @@ import pandas as pd
 import gradio as gr
 import plotly.express as px
 import io
-import os
 
 # Helper function for categorization
 def categorize_rank(r):
@@ -17,98 +16,112 @@ def categorize_rank(r):
     elif r <= 100: return "51–100"
     else: return "100+"
 
-def process_and_viz(file):
+def process_data(file):
     if file is None:
-        return None, None, "Please upload a file."
+        return None, None, None
     
     excel = pd.ExcelFile(file.name)
-    processed_sheets = {}
-    charts = []
-
-    # Processing logic
-    def process_sheet(df):
-        df.columns = df.columns.map(lambda x: str(x).strip())
-        non_date_cols = ["Keyword", "Avg. monthly searches"]
-        available_non_date = [c for c in non_date_cols if c in df.columns]
-        base_df = df[available_non_date].copy()
-        potential_date_cols = [col for col in df.columns if col not in non_date_cols and "Unnamed" not in col]
-
-        rename_dict = {}
-        for col in potential_date_cols:
-            try:
-                cleaned = str(col).replace("_", " ").replace(".", " ").strip()
-                d = pd.to_datetime(cleaned, errors="coerce", dayfirst=True)
-                if pd.notna(d):
-                    rename_dict[col] = d.strftime("%d-%m-%Y 00:00")
-            except: pass
-
-        df.rename(columns=rename_dict, inplace=True)
-        date_cols = [col for col in df.columns if col in rename_dict.values()]
-        for col in date_cols:
-            df[col] = pd.to_numeric(df[col], errors="coerce")
-
-        final_df = base_df.copy()
-        for col in date_cols:
-            d = pd.to_datetime(col, dayfirst=True)
-            date_label = d.strftime("%d_%b_%Y")
-            range_col_name = f"{date_label}_Rank Range"
-            rank_numeric_col = f"{date_label}_Rank_Numeric"
-
-            final_df[date_label] = d.strftime("%d-%m-%Y 00:00")
-            final_df[rank_numeric_col] = df[col].fillna(0).astype(int)
-            final_df[range_col_name] = df[col].apply(categorize_rank)
+    first_sheet = excel.sheet_names[0]
+    df = pd.read_excel(file.name, sheet_name=first_sheet)
+    
+    df.columns = df.columns.map(lambda x: str(x).strip())
+    non_date_cols = ["Keyword", "Avg. monthly searches"]
+    available_non_date = [c for c in non_date_cols if c in df.columns]
+    
+    potential_date_cols = [col for col in df.columns if col not in non_date_cols and "Unnamed" not in col]
+    rename_dict = {}
+    for col in potential_date_cols:
+        try:
+            cleaned = str(col).replace("_", " ").replace(".", " ").strip()
+            d = pd.to_datetime(cleaned, errors="coerce", dayfirst=True)
+            if pd.notna(d):
+                rename_dict[col] = d.strftime("%d_%b_%Y")
+        except: pass
+    
+    df.rename(columns=rename_dict, inplace=True)
+    date_cols = list(rename_dict.values())
+    
+    final_df = df[available_non_date].copy()
+    viz_data = []
 
-        return final_df
+    for col in date_cols:
+        rank_numeric_col = f"{col}_Rank_Numeric"
+        range_col_name = f"{col}_Rank Range"
+        
+        raw_vals = pd.to_numeric(df[col], errors="coerce")
+        final_df[rank_numeric_col] = raw_vals.fillna(0).astype(int)
+        final_df[range_col_name] = raw_vals.apply(categorize_rank)
+        
+        counts = final_df[range_col_name].value_counts().reset_index()
+        counts.columns = ['Range', 'Keyword Count']
+        counts['Month'] = col
+        viz_data.append(counts)
 
-    # Create an Excel file for download
-    output_path = "Processed_Keyword_Ranking_Cleaned.xlsx"
-    with pd.ExcelWriter(output_path, engine="openpyxl") as writer:
-        for sheet_name in excel.sheet_names:
-            df_sheet = pd.read_excel(excel, sheet_name=sheet_name)
-            res_df = process_sheet(df_sheet)
-            res_df.to_excel(writer, index=False, sheet_name=sheet_name)
-            processed_sheets[sheet_name] = res_df
+    full_viz_df = pd.concat(viz_data)
+    sort_order = ["01–03", "04–10", "11–20", "21–30", "31–40", "41–50", "51–100", "100+", "Not Talking (Intent Not Correct)"]
+    full_viz_df['Range'] = pd.Categorical(full_viz_df['Range'], categories=sort_order, ordered=True)
+    
+    fig = px.bar(
+        full_viz_df, x='Range', y='Keyword Count', color='Month',
+        title="Keyword Performance Distribution Across All Months",
+        text_auto=True, barmode='group',
+        labels={'Range': 'Rank Range', 'Keyword Count': 'Number of Keywords'}
+    )
+    
+    fig.update_layout(clickmode='event+select')
+    
+    return final_df, fig, final_df
 
-    # Generate Visualization for the FIRST sheet (as a preview)
-    first_sheet_name = excel.sheet_names[0]
-    viz_df = processed_sheets[first_sheet_name]
+def filter_table(evt: gr.SelectData, full_data):
+    # evt.value is the Rank Range bucket clicked
+    # evt.legend_value is the Month (color) clicked
+    clicked_range = evt.value
+    clicked_month = evt.legend_value
     
-    # Identify Rank Range columns for charts
-    range_cols = [c for c in viz_df.columns if "Rank Range" in c]
+    target_col = f"{clicked_month}_Rank Range"
     
-    fig_list = []
-    for col in range_cols:
-        counts = viz_df[col].value_counts().reset_index()
-        counts.columns = ['Range', 'Keyword Count']
-        # Ensure correct sorting for SEO buckets
-        sort_order = ["01–03", "04–10", "11–20", "21–30", "31–40", "41–50", "51–100", "100+", "Not Talking (Intent Not Correct)"]
-        counts['Range'] = pd.Categorical(counts['Range'], categories=sort_order, ordered=True)
-        counts = counts.sort_values('Range')
-        
-        fig = px.bar(counts, x='Range', y='Keyword Count', title=f"Keywords By {col}", text_auto=True)
-        fig_list.append(fig)
+    if target_col in full_data.columns:
+        filtered_df = full_data[full_data[target_col] == clicked_range]
+        return filtered_df
+    return full_data
 
-    return output_path, viz_df.head(20), fig_list[0] if fig_list else None
+def reset_table(full_data):
+    return full_data
 
-# Gradio Interface
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 📊 SEO Dashboard & Keyword Processor")
+    full_data_state = gr.State()
+
+    gr.Markdown("# 🚀 SEO Market Intelligence Dashboard")
+    gr.Markdown("### How to use: \n1. Upload your Excel. \n2. Click any bar in the chart to see which keywords are in that specific range for that month.")
     
-    with gr.Tab("1. Upload & Process"):
-        file_input = gr.File(label="Upload Excel File", file_types=[".xlsx"])
-        process_btn = gr.Button("Generate Dashboard & File", variant="primary")
-        file_output = gr.File(label="Download Processed Excel")
+    with gr.Row():
+        file_input = gr.File(label="Upload SEO Excel", file_types=[".xlsx"])
+        with gr.Column():
+            process_btn = gr.Button("📊 Build Dashboard", variant="primary")
+            reset_btn = gr.Button("🔄 Reset Table Filters")
 
-    with gr.Tab("2. Visual Analytics"):
-        gr.Markdown("### Data Preview (Top 20 Rows)")
-        table_output = gr.DataFrame()
-        gr.Markdown("### Ranking Distribution (Latest Month)")
-        plot_output = gr.Plot()
+    plot_output = gr.Plot(label="Ranking Distribution (Interactive)")
+    
+    gr.Markdown("### 🔍 Keywords List")
+    table_output = gr.DataFrame(interactive=False)
 
     process_btn.click(
-        fn=process_and_viz, 
-        inputs=file_input, 
-        outputs=[file_output, table_output, plot_output]
+        fn=process_data,
+        inputs=file_input,
+        outputs=[table_output, plot_output, full_data_state]
+    )
+
+    plot_output.select(
+        fn=filter_table,
+        inputs=full_data_state,
+        outputs=table_output
+    )
+
+    reset_btn.click(
+        fn=reset_table,
+        inputs=full_data_state,
+        outputs=table_output
     )
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()