saymrwulf/prophet
1
0
Fork 0
mirror of https://github.com/saymrwulf/prophet.git synced 2026-07-30 20:18:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Clean non-ASCII characters out of generated_holidays

Browse source
This commit is contained in:
Sean J. Taylor 2018-12-04 14:49:44 -08:00
parent c9f1ccaa63
commit a5da086ba0
4 changed files with 70675 additions and 67404 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
R/.Rbuildignore Normal file
View file

@ -0,0 +1 @@
^data-raw$

138056
R/data-raw/generated_holidays.csv
View file

File diff suppressed because it is too large Load diff

BIN
R/data/generated_holidays.rda
View file

Binary file not shown.

22
python/scripts/generate_holidays_file.py
View file

@ -10,12 +10,15 @@ from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
import inspect
import unicodedata
import warnings
import pandas as pd
import numpy as np
import warnings
import holidays as hdays_part1
import fbprophet.hdays as hdays_part2
import inspect
def generate_holidays_file():
@ -54,7 +57,20 @@ def generate_holidays_file():
generated_holidays = pd.concat(all_holidays, axis=0, ignore_index=True)
generated_holidays['year'] = generated_holidays.ds.apply(lambda x: x.year)
generated_holidays.to_csv("../R/data-raw/generated_holidays.csv")
generated_holidays.sort_values(['country', 'ds', 'holiday'], inplace=True)
# The holidays often have utf-8 characters.
# These are not allowed in R package data (they generate a NOTE).
# TODO: revisit whether we want to do this lossy conversion.
def utf8_to_ascii(text):
return (
unicodedata.normalize('NFD', text)
.encode('ascii', 'ignore')
.decode('ascii')
)
generated_holidays['holiday'] = generated_holidays['holiday'].apply(utf8_to_ascii)
generated_holidays.to_csv("../R/data-raw/generated_holidays.csv", index=False)
if __name__ == "__main__":