Create TenTenDistrib.py

TenTenDistrib.py

@@ -0,0 +1,54 @@
+import pandas as pd
+import streamlit as st
+
+# Load the XLSX file using pandas
+data = pd.read_excel('your_file.xlsx')
+
+# Perform EDA on the data
+# ...
+
+# Function to create the top ten ordered distribution
+def create_top_ten_distribution(data, column):
+    # Count the unique values and blanks in the specified column
+    value_counts = data[column].value_counts(dropna=False)
+    
+    # Create a DataFrame with the top ten values and their counts
+    top_ten_df = pd.DataFrame({'Value': value_counts.index, 'Count': value_counts.values})
+    top_ten_df['Rank'] = range(1, len(top_ten_df) + 1)
+    
+    return top_ten_df.head(10)
+
+# Function to display the filtered dataframe based on rank
+def display_filtered_dataframe(data, column, rank):
+    # Get the value corresponding to the specified rank
+    value = top_ten_df[top_ten_df['Rank'] == rank]['Value'].values[0]
+    
+    # Filter the dataframe based on the value
+    filtered_df = data[data[column] == value]
+    
+    return filtered_df
+
+# Streamlit app
+def main():
+    st.title('Top Ten Distribution and Filtered Dataframe')
+    
+    # Specify the column for creating the top ten distribution
+    column = 'your_column_name'
+    
+    # Create the top ten ordered distribution
+    top_ten_df = create_top_ten_distribution(data, column)
+    
+    # Display the top ten distribution as a markdown table
+    st.markdown('### Top Ten Distribution')
+    st.markdown(top_ten_df.to_markdown(index=False))
+    
+    # Get the user input for the rank
+    rank = st.number_input('Enter the rank to filter the dataframe', min_value=1, max_value=10, value=1, step=1)
+    
+    # Display the filtered dataframe based on the rank
+    filtered_df = display_filtered_dataframe(data, column, rank)
+    st.markdown(f'### Filtered Dataframe (Rank: {rank})')
+    st.dataframe(filtered_df)
+
+if __name__ == '__main__':
+    main()