publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-23 10:04:18 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add assertions around codebook (#2014)

Browse source 
* Add assertion around codebook (#1505)

* Assert csv and excel have same cols (#1505)
This commit is contained in:
Matt Bowen 2022-10-13 16:20:04 -04:00 • committed by GitHub
parent 8b611edae6
commit 743d3ce37c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
data/data-pipeline/data_pipeline/etl/score/etl_score_post.py
View file

@ -532,6 +532,22 @@ class PostScoreETL(ExtractTransformLoad):
"fields"
],
)
assert codebook_df["csv_label"].equals(codebook_df["excel_label"]), (
"CSV and Excel differ. If that's intentional, "
"remove this assertion. Otherwise, fix it."
)
# Check the codebook to make sure it matches the download files
assert not set(codebook_df["csv_label"].dropna()).difference(
downloadable_df.columns
), "Codebook is missing columns from downloadable files"
assert (
len(
downloadable_df.columns.difference(
set(codebook_df["csv_label"])
)
)
== 0
), "Codebook has columns the downloadable files do not"
# load codebook to disk
codebook_df.to_csv(codebook_path, index=False)