pickle.py
6.4 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
""" pickle compat """
import pickle
from typing import Any, Optional
import warnings
from pandas._typing import FilePathOrBuffer
from pandas.compat import pickle_compat as pc
from pandas.io.common import get_filepath_or_buffer, get_handle
def to_pickle(
obj: Any,
filepath_or_buffer: FilePathOrBuffer,
compression: Optional[str] = "infer",
protocol: int = pickle.HIGHEST_PROTOCOL,
):
"""
Pickle (serialize) object to file.
Parameters
----------
obj : any object
Any python object.
filepath_or_buffer : str, path object or file-like object
File path, URL, or buffer where the pickled object will be stored.
.. versionchanged:: 1.0.0
Accept URL. URL has to be of S3 or GCS.
compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer'
If 'infer' and 'path_or_url' is path-like, then detect compression from
the following extensions: '.gz', '.bz2', '.zip', or '.xz' (otherwise no
compression) If 'infer' and 'path_or_url' is not path-like, then use
None (= no decompression).
protocol : int
Int which indicates which protocol should be used by the pickler,
default HIGHEST_PROTOCOL (see [1], paragraph 12.1.2). The possible
values for this parameter depend on the version of Python. For Python
2.x, possible values are 0, 1, 2. For Python>=3.0, 3 is a valid value.
For Python >= 3.4, 4 is a valid value. A negative value for the
protocol parameter is equivalent to setting its value to
HIGHEST_PROTOCOL.
.. [1] https://docs.python.org/3/library/pickle.html
See Also
--------
read_pickle : Load pickled pandas object (or any object) from file.
DataFrame.to_hdf : Write DataFrame to an HDF5 file.
DataFrame.to_sql : Write DataFrame to a SQL database.
DataFrame.to_parquet : Write a DataFrame to the binary parquet format.
Examples
--------
>>> original_df = pd.DataFrame({"foo": range(5), "bar": range(5, 10)})
>>> original_df
foo bar
0 0 5
1 1 6
2 2 7
3 3 8
4 4 9
>>> pd.to_pickle(original_df, "./dummy.pkl")
>>> unpickled_df = pd.read_pickle("./dummy.pkl")
>>> unpickled_df
foo bar
0 0 5
1 1 6
2 2 7
3 3 8
4 4 9
>>> import os
>>> os.remove("./dummy.pkl")
"""
fp_or_buf, _, compression, should_close = get_filepath_or_buffer(
filepath_or_buffer, compression=compression, mode="wb"
)
if not isinstance(fp_or_buf, str) and compression == "infer":
compression = None
f, fh = get_handle(fp_or_buf, "wb", compression=compression, is_text=False)
if protocol < 0:
protocol = pickle.HIGHEST_PROTOCOL
try:
f.write(pickle.dumps(obj, protocol=protocol))
finally:
f.close()
for _f in fh:
_f.close()
if should_close:
try:
fp_or_buf.close()
except ValueError:
pass
def read_pickle(
filepath_or_buffer: FilePathOrBuffer, compression: Optional[str] = "infer"
):
"""
Load pickled pandas object (or any object) from file.
.. warning::
Loading pickled data received from untrusted sources can be
unsafe. See `here <https://docs.python.org/3/library/pickle.html>`__.
Parameters
----------
filepath_or_buffer : str, path object or file-like object
File path, URL, or buffer where the pickled object will be loaded from.
.. versionchanged:: 1.0.0
Accept URL. URL is not limited to S3 and GCS.
compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer'
If 'infer' and 'path_or_url' is path-like, then detect compression from
the following extensions: '.gz', '.bz2', '.zip', or '.xz' (otherwise no
compression) If 'infer' and 'path_or_url' is not path-like, then use
None (= no decompression).
Returns
-------
unpickled : same type as object stored in file
See Also
--------
DataFrame.to_pickle : Pickle (serialize) DataFrame object to file.
Series.to_pickle : Pickle (serialize) Series object to file.
read_hdf : Read HDF5 file into a DataFrame.
read_sql : Read SQL query or database table into a DataFrame.
read_parquet : Load a parquet object, returning a DataFrame.
Notes
-----
read_pickle is only guaranteed to be backwards compatible to pandas 0.20.3.
Examples
--------
>>> original_df = pd.DataFrame({"foo": range(5), "bar": range(5, 10)})
>>> original_df
foo bar
0 0 5
1 1 6
2 2 7
3 3 8
4 4 9
>>> pd.to_pickle(original_df, "./dummy.pkl")
>>> unpickled_df = pd.read_pickle("./dummy.pkl")
>>> unpickled_df
foo bar
0 0 5
1 1 6
2 2 7
3 3 8
4 4 9
>>> import os
>>> os.remove("./dummy.pkl")
"""
fp_or_buf, _, compression, should_close = get_filepath_or_buffer(
filepath_or_buffer, compression=compression
)
if not isinstance(fp_or_buf, str) and compression == "infer":
compression = None
f, fh = get_handle(fp_or_buf, "rb", compression=compression, is_text=False)
# 1) try standard library Pickle
# 2) try pickle_compat (older pandas version) to handle subclass changes
# 3) try pickle_compat with latin-1 encoding upon a UnicodeDecodeError
try:
excs_to_catch = (AttributeError, ImportError, ModuleNotFoundError, TypeError)
# TypeError for Cython complaints about object.__new__ vs Tick.__new__
try:
with warnings.catch_warnings(record=True):
# We want to silence any warnings about, e.g. moved modules.
warnings.simplefilter("ignore", Warning)
return pickle.load(f)
except excs_to_catch:
# e.g.
# "No module named 'pandas.core.sparse.series'"
# "Can't get attribute '__nat_unpickle' on <module 'pandas._libs.tslib"
return pc.load(f, encoding=None)
except UnicodeDecodeError:
# e.g. can occur for files written in py27; see GH#28645 and GH#31988
return pc.load(f, encoding="latin-1")
finally:
f.close()
for _f in fh:
_f.close()
if should_close:
try:
fp_or_buf.close()
except ValueError:
pass