FM / pyarrow

/usr/local/lib64/python3.6/site-packages/pyarrow/

/usr/local/lib64/python3.6/site-packages/pyarrow

Name	Size	Mode	Actions
include/	-	0755	rm
includes/	-	0755	rm
tensorflow/	-	0755	rm
tests/	-	0755	rm
vendored/	-	0755	rm
__pycache__/	-	0755	rm
array.pxi	79609	0644	edit dl rm
benchmark.pxi	869	0644	edit dl rm
benchmark.py	856	0644	edit dl rm
builder.pxi	2688	0644	edit dl rm
cffi.py	2178	0644	edit dl rm
compat.pxi	1810	0644	edit dl rm
compat.py	1076	0644	edit dl rm
compute.py	22837	0644	edit dl rm
config.pxi	2613	0644	edit dl rm
csv.py	962	0644	edit dl rm
cuda.py	1087	0644	edit dl rm
dataset.py	33333	0644	edit dl rm
error.pxi	7807	0644	edit dl rm
feather.py	9258	0644	edit dl rm
filesystem.py	14468	0644	edit dl rm
flight.py	1794	0644	edit dl rm
fs.py	13444	0644	edit dl rm
gandiva.pyx	18447	0644	edit dl rm
hdfs.py	7527	0644	edit dl rm
io.pxi	64495	0644	edit dl rm
ipc.pxi	28821	0644	edit dl rm
ipc.py	8029	0644	edit dl rm
json.py	858	0644	edit dl rm
jvm.py	9593	0644	edit dl rm
lib.cpython-36m-x86_64-linux-gnu.so	3760528	0755	edit dl rm
lib.pxd	14442	0644	edit dl rm
lib.pyx	4373	0644	edit dl rm
libarrow.so.600	48162600	0755	edit dl rm
libarrow_dataset.so.600	2541120	0755	edit dl rm
libarrow_flight.so.600	12999784	0755	edit dl rm
libarrow_python.so.600	1848920	0755	edit dl rm
libarrow_python_flight.so.600	112728	0755	edit dl rm
libparquet.so.600	4458552	0755	edit dl rm
libplasma.so.600	251296	0755	edit dl rm
lib_api.h	19153	0644	edit dl rm
memory.pxi	7451	0644	edit dl rm
orc.py	5269	0644	edit dl rm
pandas-shim.pxi	7987	0644	edit dl rm
pandas_compat.py	42243	0644	edit dl rm
parquet.py	86844	0644	edit dl rm
plasma-store-server	482776	0755	edit dl rm
plasma.py	6075	0644	edit dl rm
public-api.pxi	12814	0644	edit dl rm
scalar.pxi	29182	0644	edit dl rm
serialization.pxi	19086	0644	edit dl rm
serialization.py	18202	0644	edit dl rm
table.pxi	72277	0644	edit dl rm
tensor.pxi	34311	0644	edit dl rm
types.pxi	79432	0644	edit dl rm
types.py	10381	0644	edit dl rm
util.py	5001	0644	edit dl rm
_compute.cpython-36m-x86_64-linux-gnu.so	717312	0755	edit dl rm
_compute.pxd	1149	0644	edit dl rm
_compute.pyx	41759	0644	edit dl rm
_csv.cpython-36m-x86_64-linux-gnu.so	312168	0755	edit dl rm
_csv.pxd	1602	0644	edit dl rm
_csv.pyx	39297	0644	edit dl rm
_cuda.pxd	1922	0644	edit dl rm
_cuda.pyx	34731	0644	edit dl rm
_dataset.cpython-36m-x86_64-linux-gnu.so	1080168	0755	edit dl rm
_dataset.pxd	1644	0644	edit dl rm
_dataset.pyx	120054	0644	edit dl rm
_dataset_orc.cpython-36m-x86_64-linux-gnu.so	52536	0755	edit dl rm
_dataset_orc.pyx	1345	0644	edit dl rm
_feather.cpython-36m-x86_64-linux-gnu.so	94280	0755	edit dl rm
_feather.pyx	3623	0644	edit dl rm
_flight.cpython-36m-x86_64-linux-gnu.so	1124664	0755	edit dl rm
_flight.pyx	93532	0644	edit dl rm
_fs.cpython-36m-x86_64-linux-gnu.so	469992	0755	edit dl rm
_fs.pxd	2484	0644	edit dl rm
_fs.pyx	40017	0644	edit dl rm
_generated_version.py	142	0644	edit dl rm
_hdfs.cpython-36m-x86_64-linux-gnu.so	127352	0755	edit dl rm
_hdfs.pyx	5471	0644	edit dl rm
_hdfsio.cpython-36m-x86_64-linux-gnu.so	208096	0755	edit dl rm
_hdfsio.pyx	13681	0644	edit dl rm
_json.cpython-36m-x86_64-linux-gnu.so	90616	0755	edit dl rm
_json.pyx	8406	0644	edit dl rm
_orc.cpython-36m-x86_64-linux-gnu.so	109776	0755	edit dl rm
_orc.pxd	2350	0644	edit dl rm
_orc.pyx	5151	0644	edit dl rm
_parquet.cpython-36m-x86_64-linux-gnu.so	507792	0755	edit dl rm
_parquet.pxd	22084	0644	edit dl rm
_parquet.pyx	47997	0644	edit dl rm
_plasma.cpython-36m-x86_64-linux-gnu.so	259168	0755	edit dl rm
_plasma.pyx	29495	0644	edit dl rm
_s3fs.cpython-36m-x86_64-linux-gnu.so	199496	0755	edit dl rm
_s3fs.pyx	11662	0644	edit dl rm
__init__.pxd	2195	0644	edit dl rm
__init__.py	21263	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/pyarrow/feather.py (9258B)

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

import os

from pyarrow.pandas_compat import _pandas_api  # noqa
from pyarrow.lib import (Codec, Table,  # noqa
                         concat_tables, schema)
import pyarrow.lib as ext
from pyarrow import _feather
from pyarrow._feather import FeatherError  # noqa: F401
from pyarrow.vendored.version import Version

def _check_pandas_version():
    if _pandas_api.loose_version < Version('0.17.0'):
        raise ImportError("feather requires pandas >= 0.17.0")

class FeatherDataset:
    """
    Encapsulates details of reading a list of Feather files.

Parameters
    ----------
    path_or_paths : List[str]
        A list of file names
    validate_schema : bool, default True
        Check that individual file schemas are all the same / compatible
    """

def __init__(self, path_or_paths, validate_schema=True):
        self.paths = path_or_paths
        self.validate_schema = validate_schema

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 = read_table(self.paths[0], columns=columns)
        self._tables = [_fil]
        self.schema = _fil.schema

for path in self.paths[1:]:
            table = read_table(path, columns=columns)
            if self.validate_schema:
                self.validate_schemas(path, table)
            self._tables.append(table)
        return concat_tables(self._tables)

def validate_schemas(self, piece, table):
        if not self.schema.equals(table.schema):
            raise ValueError('Schema in {!s} was different. \n'
                             '{!s}\n\nvs\n\n{!s}'
                             .format(piece, self.schema,
                                     table.schema))

def read_pandas(self, columns=None, use_threads=True):
        """
        Read multiple Parquet files as a single pandas DataFrame

Parameters
        ----------
        columns : List[str]
            Names of columns to read from the file
        use_threads : bool, default True
            Use multiple threads when converting to pandas

Returns
        -------
        pandas.DataFrame
            Content of the file as a pandas DataFrame (of columns)
        """
        _check_pandas_version()
        return self.read_table(columns=columns).to_pandas(
            use_threads=use_threads)

def check_chunked_overflow(name, col):
    if col.num_chunks == 1:
        return

if col.type in (ext.binary(), ext.string()):
        raise ValueError("Column '{}' exceeds 2GB maximum capacity of "
                         "a Feather binary column. This restriction may be "
                         "lifted in the future".format(name))
    else:
        # TODO(wesm): Not sure when else this might be reached
        raise ValueError("Column '{}' of type {} was chunked on conversion "
                         "to Arrow and cannot be currently written to "
                         "Feather format".format(name, str(col.type)))

_FEATHER_SUPPORTED_CODECS = {'lz4', 'zstd', 'uncompressed'}

def write_feather(df, dest, compression=None, compression_level=None,
                  chunksize=None, version=2):
    """
    Write a pandas.DataFrame to Feather format.

Parameters
    ----------
    df : pandas.DataFrame or pyarrow.Table
        Data to write out as Feather format.
    dest : str
        Local destination path.
    compression : string, default None
        Can be one of {"zstd", "lz4", "uncompressed"}. The default of None uses
        LZ4 for V2 files if it is available, otherwise uncompressed.
    compression_level : int, default None
        Use a compression level particular to the chosen compressor. If None
        use the default compression level
    chunksize : int, default None
        For V2 files, the internal maximum size of Arrow RecordBatch chunks
        when writing the Arrow IPC file format. None means use the default,
        which is currently 64K
    version : int, default 2
        Feather file version. Version 2 is the current. Version 1 is the more
        limited legacy format
    """
    if _pandas_api.have_pandas:
        _check_pandas_version()
        if (_pandas_api.has_sparse and
                isinstance(df, _pandas_api.pd.SparseDataFrame)):
            df = df.to_dense()

if _pandas_api.is_data_frame(df):
        table = Table.from_pandas(df, preserve_index=False)

if version == 1:
            # Version 1 does not chunking
            for i, name in enumerate(table.schema.names):
                col = table[i]
                check_chunked_overflow(name, col)
    else:
        table = df

if version == 1:
        if len(table.column_names) > len(set(table.column_names)):
            raise ValueError("cannot serialize duplicate column names")

if compression is not None:
            raise ValueError("Feather V1 files do not support compression "
                             "option")

if chunksize is not None:
            raise ValueError("Feather V1 files do not support chunksize "
                             "option")
    else:
        if compression is None and Codec.is_available('lz4_frame'):
            compression = 'lz4'
        elif (compression is not None and
              compression not in _FEATHER_SUPPORTED_CODECS):
            raise ValueError('compression="{}" not supported, must be '
                             'one of {}'.format(compression,
                                                _FEATHER_SUPPORTED_CODECS))

try:
        _feather.write_feather(table, dest, compression=compression,
                               compression_level=compression_level,
                               chunksize=chunksize, version=version)
    except Exception:
        if isinstance(dest, str):
            try:
                os.remove(dest)
            except os.error:
                pass
        raise

def read_feather(source, columns=None, use_threads=True, memory_map=True):
    """
    Read a pandas.DataFrame from Feather format. To read as pyarrow.Table use
    feather.read_table.

Parameters
    ----------
    source : str file path, or file-like object
    columns : sequence, optional
        Only read a specific set of columns. If not provided, all columns are
        read.
    use_threads : bool, default True
        Whether to parallelize reading using multiple threads. If false the
        restriction is only used in the conversion to Pandas and not in the
        reading from Feather format.
    memory_map : boolean, default True
        Use memory mapping when opening file on disk

Returns
    -------
    df : pandas.DataFrame
    """
    _check_pandas_version()
    return (read_table(source, columns=columns, memory_map=memory_map)
            .to_pandas(use_threads=use_threads))

def read_table(source, columns=None, memory_map=True):
    """
    Read a pyarrow.Table from Feather format

Parameters
    ----------
    source : str file path, or file-like object
    columns : sequence, optional
        Only read a specific set of columns. If not provided, all columns are
        read.
    memory_map : boolean, default True
        Use memory mapping when opening file on disk

Returns
    -------
    table : pyarrow.Table
    """
    reader = _feather.FeatherReader(source, use_memory_map=memory_map)

if columns is None:
        return reader.read()

column_types = [type(column) for column in columns]
    if all(map(lambda t: t == int, column_types)):
        table = reader.read_indices(columns)
    elif all(map(lambda t: t == str, column_types)):
        table = reader.read_names(columns)
    else:
        column_type_names = [t.__name__ for t in column_types]
        raise TypeError("Columns must be indices or names. "
                        "Got columns {} of types {}"
                        .format(columns, column_type_names))

# Feather v1 already respects the column selection
    if reader.version < 3:
        return table
    # Feather v2 reads with sorted / deduplicated selection
    elif sorted(set(columns)) == columns:
        return table
    else:
        # follow exact order / selection of names
        return table.select(columns)

cmd: