arro3-io

import arro3.io import arro3.core import pyarrow as pa import pandas as pd import io # 1. Create some dummy data using pandas and pyarrow df = pd.DataFrame({"col1": [1, 2, 3], "col2": ["A", "B", "C"]}) pa_table = pa.Table.from_pandas(df) # 2. Write the data to an in-memory buffer as a Parquet file using arro3.io buffer = io.BytesIO() arro3.io.write_parquet(pa_table, buffer) buffer.seek(0) # 3. Read the Parquet data back from the buffer using arro3.io # arro3.io.read_parquet returns a RecordBatchReader (an iterator) reader = arro3.io.read_parquet(buffer) # 4. Materialize the streaming RecordBatchReader into an arro3.core.Table arro3_table = arro3.core.Table(reader) print("Original Pandas DataFrame:") print(df) print("\narro3 Table read back:") print(arro3_table) # 5. Demonstrate interoperability by converting the arro3.core.Table back to PyArrow and Pandas print("\narro3 Table converted to PyArrow Table:") print(arro3_table.to_pyarrow()) print("\narro3 Table converted to Pandas DataFrame:") print(arro3_table.to_pandas())