forked from apache/arrow
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathfeather.py
More file actions
234 lines (190 loc) · 7.16 KB
/
feather.py
File metadata and controls
234 lines (190 loc) · 7.16 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
# 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.
from __future__ import absolute_import
import os
import six
from pyarrow.pandas_compat import _pandas_api # noqa
from pyarrow.lib import FeatherError # noqa
from pyarrow.lib import Table, concat_tables
import pyarrow.lib as ext
def _check_pandas_version():
if _pandas_api.loose_version < '0.17.0':
raise ImportError("feather requires pandas >= 0.17.0")
class FeatherReader(ext.FeatherReader):
def __init__(self, source):
_check_pandas_version()
self.source = source
self.open(source)
def read_table(self, columns=None):
if columns is None:
return self._read()
column_types = [type(column) for column in columns]
if all(map(lambda t: t == int, column_types)):
return self._read_indices(columns)
elif all(map(lambda t: t == str, column_types)):
return self._read_names(columns)
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))
def read_pandas(self, columns=None, use_threads=True):
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 '{0}' 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 '{0}' of type {1} was chunked on conversion "
"to Arrow and cannot be currently written to "
"Feather format".format(name, str(col.type)))
class FeatherWriter(object):
def __init__(self, dest):
_check_pandas_version()
self.dest = dest
self.writer = ext.FeatherWriter()
self.writer.open(dest)
def write(self, df):
if (_pandas_api.has_sparse
and isinstance(df, _pandas_api.pd.SparseDataFrame)):
df = df.to_dense()
if not df.columns.is_unique:
raise ValueError("cannot serialize duplicate column names")
# TODO(wesm): Remove this length check, see ARROW-1732
if len(df.columns) > 0:
table = Table.from_pandas(df, preserve_index=False)
for i, name in enumerate(table.schema.names):
col = table[i]
check_chunked_overflow(name, col)
self.writer.write_array(name, col.chunk(0))
self.writer.close()
class FeatherDataset(object):
"""
Encapsulates details of reading a list of Feather files.
Parameters
----------
path_or_paths : List[str]
A list of file names
validate_schema : boolean, default True
Check that individual file schemas are all the same / compatible
"""
def __init__(self, path_or_paths, validate_schema=True):
_check_pandas_version()
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 = 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 validate_schemas(self, piece, table):
if not self.schema.equals(table.schema):
raise ValueError('Schema in {0!s} was different. \n'
'{1!s}\n\nvs\n\n{2!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 : boolean, default True
Use multiple threads when converting to pandas
Returns
-------
pandas.DataFrame
Content of the file as a pandas DataFrame (of columns)
"""
return self.read_table(columns=columns).to_pandas(
use_threads=use_threads)
def write_feather(df, dest):
"""
Write a pandas.DataFrame to Feather format
Parameters
----------
df : pandas.DataFrame
dest : string
Local file path
"""
writer = FeatherWriter(dest)
try:
writer.write(df)
except Exception:
# Try to make sure the resource is closed
import gc
writer = None
gc.collect()
if isinstance(dest, six.string_types):
try:
os.remove(dest)
except os.error:
pass
raise
def read_feather(source, columns=None, use_threads=True):
"""
Read a pandas.DataFrame from Feather format
Parameters
----------
source : string 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
Returns
-------
df : pandas.DataFrame
"""
reader = FeatherReader(source)
return reader.read_pandas(columns=columns, use_threads=use_threads)
def read_table(source, columns=None):
"""
Read a pyarrow.Table from Feather format
Parameters
----------
source : string file path, or file-like object
columns : sequence, optional
Only read a specific set of columns. If not provided, all columns are
read
Returns
-------
table : pyarrow.Table
"""
reader = FeatherReader(source)
return reader.read_table(columns=columns)