sparrow.yaml

image:
  - melezhik/sparrow:debian
  
tasks:
  -
   name: example 
   default: true
   language: Python
   code: |
      from pyquokka.df import QuokkaContext
      qc = QuokkaContext()
      lineitem = qc.read_csv("lineitem.tbl.named", sep="|", has_header=True)
      d = lineitem.filter("l_shipdate <= date '1998-12-01' - interval '90' day")
      d = d.with_column("disc_price", lambda x: x["l_extendedprice"] * (1 - x["l_discount"]), required_columns ={"l_extendedprice", "l_discount"})
      d = d.with_column("charge", lambda x: x["l_extendedprice"] * (1 - x["l_discount"]) * (1 + x["l_tax"]), required_columns={"l_extendedprice", "l_discount", "l_tax"})
      f = d.groupby(["l_returnflag", "l_linestatus"], orderby=["l_returnflag","l_linestatus"]).agg({"l_quantity":["sum","avg"], "l_extendedprice":["sum","avg"], "disc_price":"sum", "charge":"sum", "l_discount":"avg","*":"count"})
      print(f.collect())
   depends:
    -
      name: install
  - 
   name: install 
   language: Bash
   code: |
      set -e
      cd source
      pip3 install -e .
   depends:
    -
      name: install-python
  -
   name: install-python
   language: Bash
   code: |
     set -e
     sudo apt-get install -y python3-pip
     sudo apt-get install -y redis-server