def write_table(table, where, row_group_size=None, version='1.0',
use_dictionary=True, compression='snappy', **kwargs):
"""
Write a Table to Parquet format
Parameters
----------
table : pyarrow.Table
where: string or pyarrow.io.NativeFile
row_group_size : int, default None
The maximum number of rows in each Parquet RowGroup. As a default,
we will write a single RowGroup per file.
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
use_dictionary : bool or list
Specify if we should use dictionary encoding in general or only for
some columns.
compression : str or dict
Specify the compression codec, either on a general basis or per-column.
"""
row_group_size = kwargs.get('chunk_size', row_group_size)
writer = ParquetWriter(where, table.schema,
use_dictionary=use_dictionary,
compression=compression,
version=version)
writer.write_table(table, row_group_size=row_group_size)
writer.close()
def write_metadata(schema,
where,
version='1.0',
use_deprecated_int96_timestamps=False,
coerce_timestamps=None):
"""
Write metadata-only Parquet file from schema
Parameters
----------
schema : pyarrow.Schema
where: string or pyarrow.io.NativeFile
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
use_deprecated_int96_timestamps : boolean, default False
Write nanosecond resolution timestamps to INT96 Parquet format
coerce_timestamps : string, default None
Cast timestamps a particular resolution.
Valid values: {None, 'ms', 'us'}
"""
options = dict(
version=version,
use_deprecated_int96_timestamps=use_deprecated_int96_timestamps,
coerce_timestamps=coerce_timestamps)
writer = ParquetWriter(where, schema, **options)
writer.close()
def write_table(table,
where,
row_group_size=None,
version='1.0',
use_dictionary=True,
compression='snappy',
**kwargs):
"""
Write a Table to Parquet format
Parameters
----------
table : pyarrow.Table
where: string or pyarrow.io.NativeFile
row_group_size : int, default None
The maximum number of rows in each Parquet RowGroup. As a default,
we will write a single RowGroup per file.
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
use_dictionary : bool or list
Specify if we should use dictionary encoding in general or only for
some columns.
compression : str or dict
Specify the compression codec, either on a general basis or per-column.
"""
row_group_size = kwargs.get('chunk_size', row_group_size)
writer = ParquetWriter(where,
table.schema,
use_dictionary=use_dictionary,
compression=compression,
version=version)
writer.write_table(table, row_group_size=row_group_size)
writer.close()
def write_table(table,
where,
row_group_size=None,
version='1.0',
use_dictionary=True,
compression='snappy',
use_deprecated_int96_timestamps=False,
coerce_timestamps=None,
**kwargs):
"""
Write a Table to Parquet format
Parameters
----------
table : pyarrow.Table
where: string or pyarrow.io.NativeFile
row_group_size : int, default None
The maximum number of rows in each Parquet RowGroup. As a default,
we will write a single RowGroup per file.
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
use_dictionary : bool or list
Specify if we should use dictionary encoding in general or only for
some columns.
use_deprecated_int96_timestamps : boolean, default False
Write nanosecond resolution timestamps to INT96 Parquet format
coerce_timestamps : string, default None
Cast timestamps a particular resolution.
Valid values: {None, 'ms', 'us'}
compression : str or dict
Specify the compression codec, either on a general basis or per-column.
"""
row_group_size = kwargs.get('chunk_size', row_group_size)
options = dict(
use_dictionary=use_dictionary,
compression=compression,
version=version,
use_deprecated_int96_timestamps=use_deprecated_int96_timestamps,
coerce_timestamps=coerce_timestamps)
writer = None
try:
writer = ParquetWriter(where, table.schema, **options)
writer.write_table(table, row_group_size=row_group_size)
except:
if writer is not None:
writer.close()
if isinstance(where, six.string_types):
try:
os.remove(where)
except os.error:
pass
raise
else:
writer.close()
def write_metadata(schema, where, version='1.0'):
"""
Write metadata-only Parquet file from schema
Parameters
----------
schema : pyarrow.Schema
where: string or pyarrow.io.NativeFile
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
"""
writer = ParquetWriter(where, schema, version=version)
writer.close()
def write_metadata(schema, where, version='1.0'):
"""
Write metadata-only Parquet file from schema
Parameters
----------
schema : pyarrow.Schema
where: string or pyarrow.io.NativeFile
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
"""
writer = ParquetWriter(where, schema, version=version)
writer.close()
def write_metadata(schema, where, version='1.0',
use_deprecated_int96_timestamps=False):
"""
Write metadata-only Parquet file from schema
Parameters
----------
schema : pyarrow.Schema
where: string or pyarrow.io.NativeFile
version : {"1.0", "2.0"}, default "1.0"
The Parquet format version, defaults to 1.0
"""
options = dict(
version=version,
use_deprecated_int96_timestamps=use_deprecated_int96_timestamps
)
writer = ParquetWriter(where, schema, **options)
writer.close()