Snowflake Scripts

Get Distinct Value of All Columns in A Table Using Snowpark Python

import snowflake.snowpark as snowpark
import pandas as pd
from snowflake.snowpark.functions import col

def main(session: snowpark.Session):
    table_name = 'YOUR-TABLE-NAME'
    
    # Get the list of columns in the specified table
    columns = session.table(table_name).columns
    
    # Initialize an empty dictionary to store distinct values for each column
    distinct_values = {}
    
    # Iterate over each column and fetch distinct values
    for column in columns:
        column_name = column
        distinct_df = session.table(table_name).select(col(column_name)).distinct()
        distinct_df = distinct_df.collect()
        comma_separated_values = ",".join([str(value.__getitem__(column_name)) for value in distinct_df if value is not None])
        distinct_values[column_name] = comma_separated_values

    df = pd.DataFrame({
    'Attribute Name': distinct_values.keys(),
    'Distinct Values': distinct_values.values()
    })

    snowpark_df = session.create_dataframe(data=df)
    return  snowpark_df