Converting HDF5 to Parquet without loading into memory
You can use pyarrow for this!
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
def convert_hdf5_to_parquet(h5_file, parquet_file, chunksize=100000):
stream = pd.read_hdf(h5_file, chunksize=chunksize)
for i, chunk in enumerate(stream):
print("Chunk {}".format(i))
if i == 0:
# Infer schema and open parquet file on first chunk
parquet_schema = pa.Table.from_pandas(df=chunk).schema
parquet_writer = pq.ParquetWriter(parquet_file, parquet_schema, compression='snappy')
table = pa.Table.from_pandas(chunk, schema=parquet_schema)
parquet_writer.write_table(table)
parquet_writer.close()
Thanks for your answer, I tried calling the below py script from CLI but it neither shows any error nor I could see converted parquet file.
And h5 files are not empty as well.enter image description here
import pandas as pd import pyarrow as pa import pyarrow.parquet as pq
h5_file = "C:\Users...\tall.h5" parquet_file = "C:\Users...\my.parquet"
def convert_hdf5_to_parquet(h5_file, parquet_file, chunksize=100000):
stream = pd.read_hdf(h5_file, chunksize=chunksize)
for i, chunk in enumerate(stream):
print("Chunk {}".format(i))
print(chunk.head())
if i == 0:
# Infer schema and open parquet file on first chunk
parquet_schema = pa.Table.from_pandas(df=chunk).schema
parquet_writer = pq.ParquetWriter(parquet_file, parquet_schema, compression='snappy')
table = pa.Table.from_pandas(chunk, schema=parquet_schema)
parquet_writer.write_table(table)
parquet_writer.close()