Moneypuck dataset import using python for RapidMiner

moneypuck-pandas.py

# SOURCE (and adapted from): https://stackoverflow.com/a/46676405/155406
import requests, zipfile, io
import pandas

# use requests to get the dataset, get the zipfile, and use pandas to read the csv
# the site blocks certain requests, but ironically allows wget from Google Colab
def rm_main():
  # get the data
  URL = ("https://peter-tanner.com/moneypuck/downloads/shots_2021.zip")
  r = requests.get(URL)
  zf = zipfile.ZipFile(io.BytesIO(r.content))
  # find the first matching csv file in the zip:
  match = [s for s in zf.namelist() if ".csv" in s][0]
  # the first line of the file contains a string - that line shall de ignored, hence skiprows
  df = pandas.read_csv(zf.open(match), low_memory=True)
  return df