def read_row_group(self,
i,
columns=None,
nthreads=None,
use_threads=True,
use_pandas_metadata=False):
"""
Read a single row group from a Parquet file
Parameters
----------
columns: list
If not None, only these columns will be read from the row group. A
column name may be a prefix of a nested field, e.g. 'a' will select
'a.b', 'a.c', and 'a.d.e'
use_threads : boolean, default True
Perform multi-threaded column reads
use_pandas_metadata : boolean, default False
If True and file has custom pandas schema metadata, ensure that
index columns are also loaded
Returns
-------
pyarrow.table.Table
Content of the row group as a table (of columns)
"""
use_threads = _deprecate_nthreads(use_threads, nthreads)
column_indices = self._get_column_indices(
columns, use_pandas_metadata=use_pandas_metadata)
return self.reader.read_row_group(i,
column_indices=column_indices,
use_threads=use_threads)
def read_table(source,
columns=None,
use_threads=True,
metadata=None,
use_pandas_metadata=False,
nthreads=None):
use_threads = _deprecate_nthreads(use_threads, nthreads)
if _is_path_like(source):
fs = _get_fs_from_path(source)
return fs.read_parquet(source,
columns=columns,
use_threads=use_threads,
metadata=metadata,
use_pandas_metadata=use_pandas_metadata)
pf = ParquetFile(source, metadata=metadata)
return pf.read(columns=columns,
use_threads=use_threads,
use_pandas_metadata=use_pandas_metadata)