import tubes
import json, gzip, glob
FILES = glob.glob("../data/*.jsonz")
def py_ver():
py_result = []
for file_name in FILES:
with gzip.open(file_name, "rt") as fp:
for line in fp:
data = json.loads(line)
py_result.append(data.get("country_code"))
return py_result
%time py_result = py_ver()
def tubes_ver():
return list(tubes.Each(FILES)
.read_files()
.gunzip(stream=True)
.split(b'\n')
.chunk(1)
.json()
.get("country_code", "null"))
%time tubes_result = tubes_ver()
py_result == tubes_result
(4*60) + 14
254/19.6