Last active
August 23, 2021 13:49
-
-
Save zhuchangzhan/75ba824bcec95942ac541fa699b6d541 to your computer and use it in GitHub Desktop.
TPCX Blog Bodo Code
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import bodo | |
import pandas as pd | |
import numpy as np | |
@bodo.jit | |
def tpcx_bb_q26(): | |
store_sales = pd.read_parquet('s3://...') | |
item = pd.read_parquet('s3://...') | |
item2 = item[item['i_category'] == 'Books'] | |
sale_items = pd.merge( | |
store_sales, item2, left_on='ss_item_sk', right_on='i_item_sk' | |
) | |
count1 = sale_items.groupby('ss_customer_sk')['ss_item_sk'].count() | |
gp1 = sale_items.groupby('ss_customer_sk')['i_class_id'] | |
def id1(x): return (x == 1).sum() | |
def id2(x): return (x == 2).sum() | |
... | |
def id15(x): return (x == 15).sum() | |
customer_i_class = gp1.agg((id1, id2, ... id15)) | |
customer_i_class['ss_item_count'] = count1 | |
customer_i_class = customer_i_class[customer_i_class.ss_item_count > 5] | |
customer_i_class = customer_i_class.drop(['ss_item_count'], axis=1) | |
customer_i_class = customer_i_class.sort_values('ss_customer_sk') | |
return customer_i_class |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment