/usr/lib/python2.7/dist-packages/pandas/io/packers.py is in python-pandas 0.13.1-2ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 | """
Msgpack serializer support for reading and writing pandas data structures
to disk
"""
# portions of msgpack_numpy package, by Lev Givon were incorporated
# into this module (and tests_packers.py)
"""
License
=======
Copyright (c) 2013, Lev Givon.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
* Neither the name of Lev Givon nor the names of any
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
"""
import os
from datetime import datetime, date, timedelta
from dateutil.parser import parse
import numpy as np
from pandas import compat
from pandas.compat import u, PY3
from pandas import (
Timestamp, Period, Series, DataFrame, Panel, Panel4D,
Index, MultiIndex, Int64Index, PeriodIndex, DatetimeIndex, Float64Index,
NaT
)
from pandas.sparse.api import SparseSeries, SparseDataFrame, SparsePanel
from pandas.sparse.array import BlockIndex, IntIndex
from pandas.core.generic import NDFrame
from pandas.core.common import needs_i8_conversion
from pandas.io.common import get_filepath_or_buffer
from pandas.core.internals import BlockManager, make_block
import pandas.core.internals as internals
from pandas.msgpack import Unpacker as _Unpacker, Packer as _Packer
import zlib
try:
import blosc
_BLOSC = True
except:
_BLOSC = False
# until we can pass this into our conversion functions,
# this is pretty hacky
compressor = None
def to_msgpack(path_or_buf, *args, **kwargs):
"""
msgpack (serialize) object to input file path
THIS IS AN EXPERIMENTAL LIBRARY and the storage format
may not be stable until a future release.
Parameters
----------
path_or_buf : string File path, buffer-like, or None
if None, return generated string
args : an object or objects to serialize
append : boolean whether to append to an existing msgpack
(default is False)
compress : type of compressor (zlib or blosc), default to None (no
compression)
"""
global compressor
compressor = kwargs.pop('compress', None)
append = kwargs.pop('append', None)
if append:
mode = 'a+b'
else:
mode = 'wb'
def writer(fh):
for a in args:
fh.write(pack(a, **kwargs))
if isinstance(path_or_buf, compat.string_types):
with open(path_or_buf, mode) as fh:
writer(fh)
elif path_or_buf is None:
buf = compat.BytesIO()
writer(buf)
return buf.getvalue()
else:
writer(path_or_buf)
def read_msgpack(path_or_buf, iterator=False, **kwargs):
"""
Load msgpack pandas object from the specified
file path
THIS IS AN EXPERIMENTAL LIBRARY and the storage format
may not be stable until a future release.
Parameters
----------
path_or_buf : string File path, BytesIO like or string
iterator : boolean, if True, return an iterator to the unpacker
(default is False)
Returns
-------
obj : type of object stored in file
"""
path_or_buf, _ = get_filepath_or_buffer(path_or_buf)
if iterator:
return Iterator(path_or_buf)
def read(fh):
l = list(unpack(fh))
if len(l) == 1:
return l[0]
return l
# see if we have an actual file
if isinstance(path_or_buf, compat.string_types):
try:
exists = os.path.exists(path_or_buf)
except (TypeError,ValueError):
exists = False
if exists:
with open(path_or_buf, 'rb') as fh:
return read(fh)
# treat as a string-like
if not hasattr(path_or_buf, 'read'):
try:
fh = compat.BytesIO(path_or_buf)
return read(fh)
finally:
fh.close()
# a buffer like
return read(path_or_buf)
dtype_dict = {21: np.dtype('M8[ns]'),
u('datetime64[ns]'): np.dtype('M8[ns]'),
u('datetime64[us]'): np.dtype('M8[us]'),
22: np.dtype('m8[ns]'),
u('timedelta64[ns]'): np.dtype('m8[ns]'),
u('timedelta64[us]'): np.dtype('m8[us]')}
def dtype_for(t):
if t in dtype_dict:
return dtype_dict[t]
return np.typeDict[t]
c2f_dict = {'complex': np.float64,
'complex128': np.float64,
'complex64': np.float32}
# numpy 1.6.1 compat
if hasattr(np, 'float128'):
c2f_dict['complex256'] = np.float128
def c2f(r, i, ctype_name):
"""
Convert strings to complex number instance with specified numpy type.
"""
ftype = c2f_dict[ctype_name]
return np.typeDict[ctype_name](ftype(r) + 1j * ftype(i))
def convert(values):
""" convert the numpy values to a list """
dtype = values.dtype
if needs_i8_conversion(dtype):
values = values.view('i8')
v = values.ravel()
# convert object
if dtype == np.object_:
return v.tolist()
if compressor == 'zlib':
# return string arrays like they are
if dtype == np.object_:
return v.tolist()
# convert to a bytes array
v = v.tostring()
return zlib.compress(v)
elif compressor == 'blosc' and _BLOSC:
# return string arrays like they are
if dtype == np.object_:
return v.tolist()
# convert to a bytes array
v = v.tostring()
return blosc.compress(v, typesize=dtype.itemsize)
# ndarray (on original dtype)
return v.tostring()
def unconvert(values, dtype, compress=None):
if dtype == np.object_:
return np.array(values, dtype=object)
if compress == 'zlib':
values = zlib.decompress(values)
return np.frombuffer(values, dtype=dtype)
elif compress == 'blosc':
if not _BLOSC:
raise Exception("cannot uncompress w/o blosc")
# decompress
values = blosc.decompress(values)
return np.frombuffer(values, dtype=dtype)
# from a string
return np.fromstring(values.encode('latin1'), dtype=dtype)
def encode(obj):
"""
Data encoder
"""
tobj = type(obj)
if isinstance(obj, Index):
if isinstance(obj, PeriodIndex):
return {'typ': 'period_index',
'klass': obj.__class__.__name__,
'name': getattr(obj, 'name', None),
'freq': getattr(obj, 'freqstr', None),
'dtype': obj.dtype.num,
'data': convert(obj.asi8)}
elif isinstance(obj, DatetimeIndex):
tz = getattr(obj, 'tz', None)
# store tz info and data as UTC
if tz is not None:
tz = tz.zone
obj = obj.tz_convert('UTC')
return {'typ': 'datetime_index',
'klass': obj.__class__.__name__,
'name': getattr(obj, 'name', None),
'dtype': obj.dtype.num,
'data': convert(obj.asi8),
'freq': getattr(obj, 'freqstr', None),
'tz': tz}
elif isinstance(obj, MultiIndex):
return {'typ': 'multi_index',
'klass': obj.__class__.__name__,
'names': getattr(obj, 'names', None),
'dtype': obj.dtype.num,
'data': convert(obj.values)}
else:
return {'typ': 'index',
'klass': obj.__class__.__name__,
'name': getattr(obj, 'name', None),
'dtype': obj.dtype.num,
'data': convert(obj.values)}
elif isinstance(obj, Series):
if isinstance(obj, SparseSeries):
raise NotImplementedError(
'msgpack sparse series is not implemented'
)
#d = {'typ': 'sparse_series',
# 'klass': obj.__class__.__name__,
# 'dtype': obj.dtype.num,
# 'index': obj.index,
# 'sp_index': obj.sp_index,
# 'sp_values': convert(obj.sp_values),
# 'compress': compressor}
#for f in ['name', 'fill_value', 'kind']:
# d[f] = getattr(obj, f, None)
#return d
else:
return {'typ': 'series',
'klass': obj.__class__.__name__,
'name': getattr(obj, 'name', None),
'index': obj.index,
'dtype': obj.dtype.num,
'data': convert(obj.values),
'compress': compressor}
elif issubclass(tobj, NDFrame):
if isinstance(obj, SparseDataFrame):
raise NotImplementedError(
'msgpack sparse frame is not implemented'
)
#d = {'typ': 'sparse_dataframe',
# 'klass': obj.__class__.__name__,
# 'columns': obj.columns}
#for f in ['default_fill_value', 'default_kind']:
# d[f] = getattr(obj, f, None)
#d['data'] = dict([(name, ss)
# for name, ss in compat.iteritems(obj)])
#return d
elif isinstance(obj, SparsePanel):
raise NotImplementedError(
'msgpack sparse frame is not implemented'
)
#d = {'typ': 'sparse_panel',
# 'klass': obj.__class__.__name__,
# 'items': obj.items}
#for f in ['default_fill_value', 'default_kind']:
# d[f] = getattr(obj, f, None)
#d['data'] = dict([(name, df)
# for name, df in compat.iteritems(obj)])
#return d
else:
data = obj._data
if not data.is_consolidated():
data = data.consolidate()
# the block manager
return {'typ': 'block_manager',
'klass': obj.__class__.__name__,
'axes': data.axes,
'blocks': [{'items': b.items,
'values': convert(b.values),
'shape': b.values.shape,
'dtype': b.dtype.num,
'klass': b.__class__.__name__,
'compress': compressor
} for b in data.blocks]}
elif isinstance(obj, (datetime, date, np.datetime64, timedelta,
np.timedelta64)):
if isinstance(obj, Timestamp):
tz = obj.tzinfo
if tz is not None:
tz = tz.zone
offset = obj.offset
if offset is not None:
offset = offset.freqstr
return {'typ': 'timestamp',
'value': obj.value,
'offset': offset,
'tz': tz}
elif isinstance(obj, np.timedelta64):
return {'typ': 'timedelta64',
'data': obj.view('i8')}
elif isinstance(obj, timedelta):
return {'typ': 'timedelta',
'data': (obj.days, obj.seconds, obj.microseconds)}
elif isinstance(obj, np.datetime64):
return {'typ': 'datetime64',
'data': str(obj)}
elif isinstance(obj, datetime):
return {'typ': 'datetime',
'data': obj.isoformat()}
elif isinstance(obj, date):
return {'typ': 'date',
'data': obj.isoformat()}
raise Exception("cannot encode this datetimelike object: %s" % obj)
elif isinstance(obj, Period):
return {'typ': 'period',
'ordinal': obj.ordinal,
'freq': obj.freq}
elif isinstance(obj, BlockIndex):
return {'typ': 'block_index',
'klass': obj.__class__.__name__,
'blocs': obj.blocs,
'blengths': obj.blengths,
'length': obj.length}
elif isinstance(obj, IntIndex):
return {'typ': 'int_index',
'klass': obj.__class__.__name__,
'indices': obj.indices,
'length': obj.length}
elif isinstance(obj, np.ndarray):
return {'typ': 'ndarray',
'shape': obj.shape,
'ndim': obj.ndim,
'dtype': obj.dtype.num,
'data': convert(obj),
'compress': compressor}
elif isinstance(obj, np.number):
if np.iscomplexobj(obj):
return {'typ': 'np_scalar',
'sub_typ': 'np_complex',
'dtype': obj.dtype.name,
'real': obj.real.__repr__(),
'imag': obj.imag.__repr__()}
else:
return {'typ': 'np_scalar',
'dtype': obj.dtype.name,
'data': obj.__repr__()}
elif isinstance(obj, complex):
return {'typ': 'np_complex',
'real': obj.real.__repr__(),
'imag': obj.imag.__repr__()}
return obj
def decode(obj):
"""
Decoder for deserializing numpy data types.
"""
typ = obj.get('typ')
if typ is None:
return obj
elif typ == 'timestamp':
return Timestamp(obj['value'], tz=obj['tz'], offset=obj['offset'])
elif typ == 'period':
return Period(ordinal=obj['ordinal'], freq=obj['freq'])
elif typ == 'index':
dtype = dtype_for(obj['dtype'])
data = unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress'))
return globals()[obj['klass']](data, dtype=dtype, name=obj['name'])
elif typ == 'multi_index':
data = unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress'))
data = [tuple(x) for x in data]
return globals()[obj['klass']].from_tuples(data, names=obj['names'])
elif typ == 'period_index':
data = unconvert(obj['data'], np.int64, obj.get('compress'))
d = dict(name=obj['name'], freq=obj['freq'])
return globals()[obj['klass']](data, **d)
elif typ == 'datetime_index':
data = unconvert(obj['data'], np.int64, obj.get('compress'))
d = dict(name=obj['name'], freq=obj['freq'], verify_integrity=False)
result = globals()[obj['klass']](data, **d)
tz = obj['tz']
# reverse tz conversion
if tz is not None:
result = result.tz_localize('UTC').tz_convert(tz)
return result
elif typ == 'series':
dtype = dtype_for(obj['dtype'])
index = obj['index']
return globals()[obj['klass']](unconvert(obj['data'], dtype,
obj['compress']),
index=index, name=obj['name'])
elif typ == 'block_manager':
axes = obj['axes']
def create_block(b):
dtype = dtype_for(b['dtype'])
return make_block(unconvert(b['values'], dtype, b['compress'])
.reshape(b['shape']), b['items'], axes[0],
klass=getattr(internals, b['klass']))
blocks = [create_block(b) for b in obj['blocks']]
return globals()[obj['klass']](BlockManager(blocks, axes))
elif typ == 'datetime':
return parse(obj['data'])
elif typ == 'datetime64':
return np.datetime64(parse(obj['data']))
elif typ == 'date':
return parse(obj['data']).date()
elif typ == 'timedelta':
return timedelta(*obj['data'])
elif typ == 'timedelta64':
return np.timedelta64(int(obj['data']))
#elif typ == 'sparse_series':
# dtype = dtype_for(obj['dtype'])
# return globals()[obj['klass']](
# unconvert(obj['sp_values'], dtype, obj['compress']),
# sparse_index=obj['sp_index'], index=obj['index'],
# fill_value=obj['fill_value'], kind=obj['kind'], name=obj['name'])
#elif typ == 'sparse_dataframe':
# return globals()[obj['klass']](
# obj['data'], columns=obj['columns'],
# default_fill_value=obj['default_fill_value'],
# default_kind=obj['default_kind']
# )
#elif typ == 'sparse_panel':
# return globals()[obj['klass']](
# obj['data'], items=obj['items'],
# default_fill_value=obj['default_fill_value'],
# default_kind=obj['default_kind'])
elif typ == 'block_index':
return globals()[obj['klass']](obj['length'], obj['blocs'],
obj['blengths'])
elif typ == 'int_index':
return globals()[obj['klass']](obj['length'], obj['indices'])
elif typ == 'ndarray':
return unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress')).reshape(obj['shape'])
elif typ == 'np_scalar':
if obj.get('sub_typ') == 'np_complex':
return c2f(obj['real'], obj['imag'], obj['dtype'])
else:
dtype = dtype_for(obj['dtype'])
try:
return dtype(obj['data'])
except:
return dtype.type(obj['data'])
elif typ == 'np_complex':
return complex(obj['real'] + '+' + obj['imag'] + 'j')
elif isinstance(obj, (dict, list, set)):
return obj
else:
return obj
def pack(o, default=encode,
encoding='latin1', unicode_errors='strict', use_single_float=False):
"""
Pack an object and return the packed bytes.
"""
return Packer(default=default, encoding=encoding,
unicode_errors=unicode_errors,
use_single_float=use_single_float).pack(o)
def unpack(packed, object_hook=decode,
list_hook=None, use_list=False, encoding='latin1',
unicode_errors='strict', object_pairs_hook=None):
"""
Unpack a packed object, return an iterator
Note: packed lists will be returned as tuples
"""
return Unpacker(packed, object_hook=object_hook,
list_hook=list_hook,
use_list=use_list, encoding=encoding,
unicode_errors=unicode_errors,
object_pairs_hook=object_pairs_hook)
class Packer(_Packer):
def __init__(self, default=encode,
encoding='latin1',
unicode_errors='strict',
use_single_float=False):
super(Packer, self).__init__(default=default,
encoding=encoding,
unicode_errors=unicode_errors,
use_single_float=use_single_float)
class Unpacker(_Unpacker):
def __init__(self, file_like=None, read_size=0, use_list=False,
object_hook=decode,
object_pairs_hook=None, list_hook=None, encoding='latin1',
unicode_errors='strict', max_buffer_size=0):
super(Unpacker, self).__init__(file_like=file_like,
read_size=read_size,
use_list=use_list,
object_hook=object_hook,
object_pairs_hook=object_pairs_hook,
list_hook=list_hook,
encoding=encoding,
unicode_errors=unicode_errors,
max_buffer_size=max_buffer_size)
class Iterator(object):
""" manage the unpacking iteration,
close the file on completion """
def __init__(self, path, **kwargs):
self.path = path
self.kwargs = kwargs
def __iter__(self):
needs_closing = True
try:
# see if we have an actual file
if isinstance(self.path, compat.string_types):
try:
path_exists = os.path.exists(self.path)
except TypeError:
path_exists = False
if path_exists:
fh = open(self.path, 'rb')
else:
fh = compat.BytesIO(self.path)
else:
if not hasattr(self.path, 'read'):
fh = compat.BytesIO(self.path)
else:
# a file-like
needs_closing = False
fh = self.path
unpacker = unpack(fh)
for o in unpacker:
yield o
finally:
if needs_closing:
fh.close()
|