mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2024-11-14 01:57:03 +01:00
Alan Orth
232d28e13e
This makes it cleaner for introducing checks, fixes, tests, docs, and tests in the future. Currently can be run like this: python -m csv_metadata_quality CSV input and output paths are still hard coded. See: https://dev.to/codemouse92/dead-simple-python-project-structure-and-imports-38c6
18 lines
582 B
Python
18 lines
582 B
Python
import csv_metadata_quality.fix as fix
|
|
import pandas as pd
|
|
|
|
def run():
|
|
# Read all fields as strings so dates don't get converted from 1998 to 1998.0
|
|
#df = pd.read_csv('/home/aorth/Downloads/2019-07-26-Bioversity-Migration.csv', dtype=str)
|
|
#df = pd.read_csv('/tmp/quality.csv', dtype=str)
|
|
df = pd.read_csv('/tmp/omg.csv', dtype=str)
|
|
|
|
# Fix whitespace in all columns
|
|
for column in df.columns.values.tolist():
|
|
print(f'DEBUG: {column}')
|
|
|
|
df[column] = df[column].apply(fix.whitespace)
|
|
|
|
# Write
|
|
df.to_csv('/tmp/omg.fixed.csv', index=False)
|