Update app.py

app.py

@@ -5,232 +5,173 @@ from openpyxl.utils.dataframe import dataframe_to_rows
 import tempfile
 
 def process_file(file):
-    # Read the uploaded Excel file into a DataFrame
     df = pd.read_excel(file.name)
-    
-    # Replace 0s with NaN
     df.replace(0, pd.NA, inplace=True)
-    
-    # Save the intermediate Excel file
+
     with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as tmp:
         intermediate_file_path = tmp.name
         df.to_excel(intermediate_file_path, index=False)
     
-    # Load the workbook
     wb = load_workbook(intermediate_file_path)
     
-    # Iterate through each sheet in the workbook
     for sheet_name in wb.sheetnames:
         ws = wb[sheet_name]
-        
-        # Convert the sheet to a DataFrame
         data = ws.values
         columns = next(data)[0:]
         df = pd.DataFrame(data, columns=columns)
         
-        # Get unique states
         unique_states = df['Name of State'].unique()
         
         for state in unique_states:
             state_str = str(state)
-            # Filter data for the current state
             state_data = df[df['Name of State'] == state]
-            
-            # Get unique channels within the state
             unique_channels = state_data['Outlet Channel'].unique()
-            
-            # Initialize a list to hold mode data for each channel
             mode_data = []
             
             for channel in unique_channels:
                 channel_str = str(channel)
-                # Filter data for the current channel within the state
                 channel_data = state_data[state_data['Outlet Channel'] == channel]
-                
-                # Calculate the count of non-null values for each column
                 count_series = channel_data.count()
-
-            
-                # Find the mode for each column
                 mode_series = channel_data.mode().iloc[0]
                 
-
-                combined_series = pd.concat([count_series.rename('COUNT'), mode_series.rename('MODE')], axis=1).T
-
-                # Add the state and channel information to the mode data
+                numeric_columns = channel_data.select_dtypes(include='number').columns
+                max_series = channel_data[numeric_columns].max()
+                min_series = channel_data[numeric_columns].min()
+                
+                combined_series = pd.concat([
+                    count_series.rename('COUNT'), 
+                    mode_series.rename('MODE'), 
+                    max_series.rename('MAX'), 
+                    min_series.rename('MIN')
+                ], axis=1).T
+                
                 combined_series.loc[:,'STATE'] = state_str
                 combined_series.loc[:,'CHANNEL'] = channel_str
-                #mode_series['COUNT'] = record_count
                 mode_data.append(combined_series)
             
-            # Convert the mode data list to a DataFrame
             mode_df = pd.concat(mode_data)
-            
-            # Create a new sheet for the state
             new_ws = wb.create_sheet(title=state_str)
             
-            # Write the mode data to the new sheet
             for r in dataframe_to_rows(mode_df, index=False, header=True):
                 new_ws.append(r)
     
-    # Save the workbook to a new file
     output_file_path = 'state_and_channel_modes.xlsx'
     wb.save(output_file_path)
     
     return output_file_path
 
 def process_regional(file):
-    # Read the uploaded Excel file into a DataFrame
     df = pd.read_excel(file.name)
-    
-    # Replace 0s with NaN
     df.replace(0, pd.NA, inplace=True)
-    
-    # Save the intermediate Excel file
+
     with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as tmp:
         intermediate_file_path = tmp.name
         df.to_excel(intermediate_file_path, index=False)
     
-    # Load the workbook
     wb = load_workbook(intermediate_file_path)
     
-    # Iterate through each sheet in the workbook
     for sheet_name in wb.sheetnames:
         ws = wb[sheet_name]
-        
-        # Convert the sheet to a DataFrame
         data = ws.values
         columns = next(data)[0:]
         df = pd.DataFrame(data, columns=columns)
         
-        # Get unique states
         unique_states = df['Region'].unique()
         
         for state in unique_states:
             state_str = str(state)
-            # Filter data for the current state
             state_data = df[df['Region'] == state]
-            
-            # Get unique channels within the state
             unique_channels = state_data['Outlet Channel'].unique()
-            
-            # Initialize a list to hold mode data for each channel
             mode_data = []
             
             for channel in unique_channels:
                 channel_str = str(channel)
-                # Filter data for the current channel within the state
                 channel_data = state_data[state_data['Outlet Channel'] == channel]
-                
-                # Calculate the count of non-null values for each column
                 count_series = channel_data.count()
-
-            
-                # Find the mode for each column
                 mode_series = channel_data.mode().iloc[0]
                 
-
-                combined_series = pd.concat([count_series.rename('COUNT'), mode_series.rename('MODE')], axis=1).T
-
-                # Add the state and channel information to the mode data
+                numeric_columns = channel_data.select_dtypes(include='number').columns
+                max_series = channel_data[numeric_columns].max()
+                min_series = channel_data[numeric_columns].min()
+                
+                combined_series = pd.concat([
+                    count_series.rename('COUNT'), 
+                    mode_series.rename('MODE'), 
+                    max_series.rename('MAX'), 
+                    min_series.rename('MIN')
+                ], axis=1).T
+                
                 combined_series.loc[:,'STATE'] = state_str
                 combined_series.loc[:,'CHANNEL'] = channel_str
-                #mode_series['COUNT'] = record_count
                 mode_data.append(combined_series)
             
-            # Convert the mode data list to a DataFrame
             mode_df = pd.concat(mode_data)
-            
-            # Create a new sheet for the state
             new_ws = wb.create_sheet(title=state_str)
             
-            # Write the mode data to the new sheet
             for r in dataframe_to_rows(mode_df, index=False, header=True):
                 new_ws.append(r)
     
-    # Save the workbook to a new file
     output_file_path = 'regional.xlsx'
     wb.save(output_file_path)
     
     return output_file_path
 
 def process_national(file):
-    # Read the uploaded Excel file into a DataFrame
     df = pd.read_excel(file.name)
-    
-    # Replace 0s with NaN
     df.replace(0, pd.NA, inplace=True)
-    
-    # Save the intermediate Excel file
+
     with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as tmp:
         intermediate_file_path = tmp.name
         df.to_excel(intermediate_file_path, index=False)
     
-    # Load the workbook
     wb = load_workbook(intermediate_file_path)
     
-    # Iterate through each sheet in the workbook
     for sheet_name in wb.sheetnames:
         ws = wb[sheet_name]
-        
-        # Convert the sheet to a DataFrame
         data = ws.values
         columns = next(data)[0:]
         df = pd.DataFrame(data, columns=columns)
         
-        # Get unique states
         unique_states = df['Nation'].unique()
         
         for state in unique_states:
             state_str = str(state)
-            # Filter data for the current state
             state_data = df[df['Nation'] == state]
-            
-            # Get unique channels within the state
             unique_channels = state_data['Outlet Channel'].unique()
-            
-            # Initialize a list to hold mode data for each channel
             mode_data = []
             
             for channel in unique_channels:
                 channel_str = str(channel)
-                # Filter data for the current channel within the state
                 channel_data = state_data[state_data['Outlet Channel'] == channel]
-                
-                # Calculate the count of non-null values for each column
                 count_series = channel_data.count()
-
-            
-                # Find the mode for each column
                 mode_series = channel_data.mode().iloc[0]
                 
-
-                combined_series = pd.concat([count_series.rename('COUNT'), mode_series.rename('MODE')], axis=1).T
-
-                # Add the state and channel information to the mode data
+                numeric_columns = channel_data.select_dtypes(include='number').columns
+                max_series = channel_data[numeric_columns].max()
+                min_series = channel_data[numeric_columns].min()
+                
+                combined_series = pd.concat([
+                    count_series.rename('COUNT'), 
+                    mode_series.rename('MODE'), 
+                    max_series.rename('MAX'), 
+                    min_series.rename('MIN')
+                ], axis=1).T
+                
                 combined_series.loc[:,'STATE'] = state_str
                 combined_series.loc[:,'CHANNEL'] = channel_str
-                #mode_series['COUNT'] = record_count
                 mode_data.append(combined_series)
             
-            # Convert the mode data list to a DataFrame
             mode_df = pd.concat(mode_data)
-            
-            # Create a new sheet for the state
             new_ws = wb.create_sheet(title=state_str)
             
-            # Write the mode data to the new sheet
             for r in dataframe_to_rows(mode_df, index=False, header=True):
                 new_ws.append(r)
     
-    # Save the workbook to a new file
     output_file_path = 'national.xlsx'
     wb.save(output_file_path)
     
     return output_file_path
 
-
-# Set up the Gradio interface
 iface = gr.Interface(
     fn=process_file,
     inputs=gr.File(file_types=[".xlsx"]),
@@ -244,16 +185,15 @@ iface2 = gr.Interface(
     inputs=gr.File(file_types=[".xlsx"]),
     outputs=gr.File(),
     title="Excel File Processor",
-    description="Upload an Excel file to process it and generate a new file with state and channel modes."
+    description="Upload an Excel file to process it and generate a new file with regional and channel modes."
 )
 
-iface3= gr.Interface(
+iface3 = gr.Interface(
     fn=process_national,
     inputs=gr.File(file_types=[".xlsx"]),
     outputs=gr.File(),
     title="Excel File Processor",
-    description="Upload an Excel file to process it and generate a new file with state and channel modes."
+    description="Upload an Excel file to process it and generate a new file with national and channel modes."
 )
 
-# Launch the Gradio interface
-gr.TabbedInterface([iface3,iface2,iface],tab_names=['National','Region','State']).launch()
+gr.TabbedInterface([iface3, iface2, iface], tab_names=['National', 'Region', 'State']).launch()