Skip to content

Instantly share code, notes, and snippets.

@andydude
Created June 25, 2018 15:03
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save andydude/6e4b81929aa129db0fb4fa2e8284522f to your computer and use it in GitHub Desktop.
Save andydude/6e4b81929aa129db0fb4fa2e8284522f to your computer and use it in GitHub Desktop.
import six
import pyarrow as pa
import pandas as pd
adr_schema = pa.schema([
pa.field('pobox', pa.string()),
pa.field('street2', pa.string()),
pa.field('street1', pa.string()),
pa.field('city', pa.string()),
pa.field('state', pa.string()),
pa.field('postal', pa.string()),
pa.field('country', pa.string()),
])
adr_data = """pobox,street2,street1,city,state,postal,country
,,10475 Little Patuxent Pkwy,Columbia,MD,21044,US
"""
df = pd.read_csv(six.StringIO(adr_data))
dt = pa.Table.from_pandas(df, schema=adr_schema)
out = six.StringIO()
dt.to_pandas().to_csv(out)
print(out.getvalue())
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment