pyarrow-segfault.py

import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq

fields = [
    pa.field('column1', pa.string()),
    pa.field('column2', pa.int64()),
    pa.field('column3', pa.string()),
]

schema = pa.schema(fields)

rows = [
    {'column1': 'val1', 'column2': 123, 'column3': ''},
    {'column1': 'val2', 'column2': 234, 'column3': ''},
    {'column1': 'val3', 'column2': 345, 'column3': ''},
]

writer = pq.ParquetWriter('table.parquet', schema)

df = pd.DataFrame(rows)
pa_table = pa.Table.from_pandas(df, schema=schema, preserve_index=False)
writer.write_table(pa_table)