1
0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-12-21 11:42:20 +01:00

Switch to pandas 2.0.0rc1

Seems to work fine with the new PyArrow datatypes.
This commit is contained in:
Alan Orth 2023-03-22 12:16:56 +03:00
parent 20a2cce34b
commit d4aed378cf
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9
2 changed files with 2 additions and 3 deletions

View File

@ -73,8 +73,7 @@ def run(argv):
# set the signal handler for SIGINT (^C)
signal.signal(signal.SIGINT, signal_handler)
# Read all fields as strings so dates don't get converted from 1998 to 1998.0
df = pd.read_csv(args.input_file, dtype=str)
df = pd.read_csv(args.input_file, dtype_backend="pyarrow")
# Check if the user requested to skip any fields
if args.exclude_fields:

View File

@ -12,7 +12,7 @@ csv-metadata-quality = 'csv_metadata_quality.__main__:main'
[tool.poetry.dependencies]
python = "^3.9"
pandas = "^1.5.2"
pandas = "2.0.0rc1"
python-stdnum = "^1.18"
requests = "^2.28.2"
requests-cache = "^0.9.8"