mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2025-05-08 06:06:00 +02:00
Refactor as package with subpackages
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
This commit is contained in:
0
csv_metadata_quality/__init__.py
Normal file
0
csv_metadata_quality/__init__.py
Normal file
4
csv_metadata_quality/__main__.py
Normal file
4
csv_metadata_quality/__main__.py
Normal file
@ -0,0 +1,4 @@
|
||||
from csv_metadata_quality import app
|
||||
|
||||
if __name__ == '__main__':
|
||||
app.run()
|
17
csv_metadata_quality/app.py
Normal file
17
csv_metadata_quality/app.py
Normal file
@ -0,0 +1,17 @@
|
||||
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)
|
42
csv_metadata_quality/fix.py
Executable file
42
csv_metadata_quality/fix.py
Executable file
@ -0,0 +1,42 @@
|
||||
import pandas as pd
|
||||
import re
|
||||
|
||||
def alan():
|
||||
print('Alan')
|
||||
|
||||
|
||||
def whitespace(field):
|
||||
"""Fix whitespace issues.
|
||||
|
||||
Return string with leading, trailing, and consecutive whitespace trimmed.
|
||||
"""
|
||||
|
||||
|
||||
# Skip fields with missing values
|
||||
if pd.isna(field):
|
||||
return
|
||||
|
||||
# Initialize an empty list to hold the cleaned values
|
||||
values = list()
|
||||
|
||||
# Try to split multi-value field on "||" separator
|
||||
for value in field.split('||'):
|
||||
# Strip leading and trailing whitespace
|
||||
value = value.strip()
|
||||
|
||||
# Replace excessive whitespace (>2) with one space
|
||||
pattern = re.compile(r'\s{2,}')
|
||||
match = re.findall(pattern, value)
|
||||
|
||||
if len(match) > 0:
|
||||
print('DEBUG: Excessive whitespace')
|
||||
value = re.sub(pattern, ' ', value)
|
||||
|
||||
# Save cleaned value
|
||||
values.append(value)
|
||||
|
||||
# Create a new field consisting of all values joined with "||"
|
||||
new_field = '||'.join(values)
|
||||
|
||||
return new_field
|
||||
|
Reference in New Issue
Block a user