Created
July 19, 2024 12:47
-
-
Save edsu/f3231a5b2d6540aae4b6f9113659ef0d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import sys | |
from itertools import batched | |
import pyarrow | |
from pyarrow.parquet import ParquetWriter | |
csv.field_size_limit(sys.maxsize) | |
def csv_to_parquet(csv_file, parquet_file, batch_size=10_000): | |
csv_input = open(csv_file) | |
reader = csv.DictReader(csv_input) | |
# naively assume all columns are strings | |
schema = pyarrow.schema([(name, pyarrow.string()) for name in reader.fieldnames]) | |
with ParquetWriter(open(parquet_file, 'wb'), schema, compression='SNAPPY') as writer: | |
for rows in batched(reader, batch_size): | |
table = pyarrow.Table.from_pylist(rows, schema) | |
writer.write_table(table) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment