def read(self, columns=None, nthreads=1):
"""
Read multiple Parquet files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
nthreads : int, default 1
Number of columns to read in parallel. Requires that the underlying
file source is threadsafe
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
open_file = self._get_open_file_func()
tables = []
for piece in self.pieces:
table = piece.read(columns=columns, nthreads=nthreads,
partitions=self.partitions,
open_file_func=open_file)
tables.append(table)
all_data = lib.concat_tables(tables)
return all_data
def read(self, columns=None, nthreads=1):
"""
Read multiple Parquet files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
nthreads : int, default 1
Number of columns to read in parallel. Requires that the underlying
file source is threadsafe
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
open_file = self._get_open_file_func()
tables = []
for piece in self.pieces:
table = piece.read(columns=columns,
nthreads=nthreads,
partitions=self.partitions,
open_file_func=open_file)
tables.append(table)
all_data = lib.concat_tables(tables)
return all_data
def read(self, columns=None, nthreads=1, use_pandas_metadata=False):
"""
Read multiple Parquet files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
nthreads : int, default 1
Number of columns to read in parallel. Requires that the underlying
file source is threadsafe
use_pandas_metadata : bool, default False
Passed through to each dataset piece
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
open_file = self._get_open_file_func()
tables = []
for piece in self.pieces:
table = piece.read(columns=columns,
nthreads=nthreads,
partitions=self.partitions,
open_file_func=open_file,
use_pandas_metadata=use_pandas_metadata)
tables.append(table)
all_data = lib.concat_tables(tables)
if use_pandas_metadata:
# We need to ensure that this metadata is set in the Table's schema
# so that Table.to_pandas will construct pandas.DataFrame with the
# right index
common_metadata = self._get_common_pandas_metadata()
current_metadata = all_data.schema.metadata or {}
if common_metadata and b'pandas' not in current_metadata:
all_data = all_data.replace_schema_metadata(
{b'pandas': common_metadata})
return all_data
def read(self, columns=None, nthreads=1, use_pandas_metadata=False):
"""
Read multiple Parquet files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
nthreads : int, default 1
Number of columns to read in parallel. Requires that the underlying
file source is threadsafe
use_pandas_metadata : bool, default False
Passed through to each dataset piece
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
open_file = self._get_open_file_func()
tables = []
for piece in self.pieces:
table = piece.read(columns=columns, nthreads=nthreads,
partitions=self.partitions,
open_file_func=open_file,
use_pandas_metadata=use_pandas_metadata)
tables.append(table)
all_data = lib.concat_tables(tables)
if use_pandas_metadata:
# We need to ensure that this metadata is set in the Table's schema
# so that Table.to_pandas will construct pandas.DataFrame with the
# right index
common_metadata = self._get_common_pandas_metadata()
current_metadata = all_data.schema.metadata or {}
if common_metadata and b'pandas' not in current_metadata:
all_data = all_data.replace_schema_metadata({
b'pandas': common_metadata})
return all_data
def read(self, columns=None, use_threads=True, use_pandas_metadata=False):
"""
Read multiple Parquet files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
use_threads : boolean, default True
Perform multi-threaded column reads
use_pandas_metadata : bool, default False
Passed through to each dataset piece
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
tables = []
for piece in self.pieces:
table = piece.read(columns=columns,
use_threads=use_threads,
partitions=self.partitions,
use_pandas_metadata=use_pandas_metadata)
tables.append(table)
all_data = lib.concat_tables(tables)
if use_pandas_metadata:
# We need to ensure that this metadata is set in the Table's schema
# so that Table.to_pandas will construct pandas.DataFrame with the
# right index
common_metadata = self._get_common_pandas_metadata()
current_metadata = all_data.schema.metadata or {}
if common_metadata and b'pandas' not in current_metadata:
all_data = all_data.replace_schema_metadata(
{b'pandas': common_metadata})
return all_data
def read(self, columns=None, use_threads=True, use_pandas_metadata=False):
"""
Read multiple Parquet files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
use_threads : boolean, default True
Perform multi-threaded column reads
use_pandas_metadata : bool, default False
Passed through to each dataset piece
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
tables = []
for piece in self.pieces:
table = piece.read(columns=columns, use_threads=use_threads,
partitions=self.partitions,
use_pandas_metadata=use_pandas_metadata)
tables.append(table)
all_data = lib.concat_tables(tables)
if use_pandas_metadata:
# We need to ensure that this metadata is set in the Table's schema
# so that Table.to_pandas will construct pandas.DataFrame with the
# right index
common_metadata = self._get_common_pandas_metadata()
current_metadata = all_data.schema.metadata or {}
if common_metadata and b'pandas' not in current_metadata:
all_data = all_data.replace_schema_metadata({
b'pandas': common_metadata})
return all_data
def read_table(self, columns=None):
"""
Read multiple feather files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
_fil = FeatherReader(self.paths[0]).read_table(columns=columns)
self._tables = [_fil]
self.schema = _fil.schema
for fil in self.paths[1:]:
fil_table = FeatherReader(fil).read_table(columns=columns)
if self.validate_schema:
self.validate_schemas(fil, fil_table)
self._tables.append(fil_table)
return concat_tables(self._tables)
def read_table(self, columns=None):
"""
Read multiple feather files as a single pyarrow.Table
Parameters
----------
columns : List[str]
Names of columns to read from the file
Returns
-------
pyarrow.Table
Content of the file as a table (of columns)
"""
_fil = FeatherReader(self.paths[0]).read_table(columns=columns)
self._tables = [_fil]
self.schema = _fil.schema
for fil in self.paths[1:]:
fil_table = FeatherReader(fil).read_table(columns=columns)
if self.validate_schema:
self.validate_schemas(fil, fil_table)
self._tables.append(fil_table)
return concat_tables(self._tables)
