How to create a resuable functions in python to get the required columns and apply conditions in que-CodePudding

Sample dataframe

ticket_start_time   ticket_end_time status customer_type ticket_type customer_type
0   None    None    None    None    None    None
1   None    None    None    None    None    None
2   None    None    None    None    None    None
3   None    None    None    None    None    None
8   2021-10-22 16:26:50 2021-10-22 19:16:28 Por Acción  R   INSTALLATION    R
9   2021-10-22 16:26:50 2021-10-22 16:38:23 Por Acción  R   INSTALLATION    R
10  2021-10-22 16:26:50 2021-10-22 19:16:28 Por Acción  R   INSTALLATION    R

I'm using the below code but it is hardcoded.Create a reusabe fntns for the above dataframe

import pyarrow
import pandas as pd
df = read_df()
columns_list = [req_cols]
filter_conditions =  ["status = 'closed'" and "customer_type = 'R'"]
df.query()
def select_filter_df(df, columns_list, filter_conditions):
# apply the filters, and query
return df

CodePudding user response：

Use function parameters?

def select_filter_df(filename, columns, querystring):
    try:
        df = pd.read_parquet(filename, columns=columns, engine='pyarrow')
        df = df.query(querystring)
    except Exception as error:
        logger.error(error)
    return df

# How to use it:
file_path = "D:\Project_centriam"
filename = os.path.join(file_path, "merged_result.parquet")

cols = ["ticket_start_time","ticket_end_time","status","customer_type","ticket_type","customer_type"]
qs = 'status == "Rechazado" and ticket_type =="INSTALLATION" and customer_type =="R"'

df = select_filter_df(filename, cols, qs)

CodePudding user response：

required_cols = ["install_ticket_start_time","install_ticket_end_time","install_status","install_customer_type","install_ticket_type"]
filter_condition = 'install_status == "Rechazado" and install_ticket_type =="INSTALLATION" and install_customer_type =="R"'
def filter_df(df, column_list, filtered_df): 
    try:
        df = pd.read_parquet(filename, engine='pyarrow') 
        column_list = df.filter(required_cols)
        filtered_df = column_list.query(filter_condition)
        print(filtered_df)
    except Exception as error:
        logger.error(error)
  

filter_df(df, column_list, filtered_df)