Spaces:
Paused
Paused
File size: 31,834 Bytes
dc2106c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 |
"""A collection of functions designed to help I/O with ascii files.
"""
__docformat__ = "restructuredtext en"
import numpy as np
import numpy.core.numeric as nx
from numpy.compat import asbytes, asunicode
def _decode_line(line, encoding=None):
"""Decode bytes from binary input streams.
Defaults to decoding from 'latin1'. That differs from the behavior of
np.compat.asunicode that decodes from 'ascii'.
Parameters
----------
line : str or bytes
Line to be decoded.
encoding : str
Encoding used to decode `line`.
Returns
-------
decoded_line : unicode
Unicode in Python 2, a str (unicode) in Python 3.
"""
if type(line) is bytes:
if encoding is None:
encoding = "latin1"
line = line.decode(encoding)
return line
def _is_string_like(obj):
"""
Check whether obj behaves like a string.
"""
try:
obj + ''
except (TypeError, ValueError):
return False
return True
def _is_bytes_like(obj):
"""
Check whether obj behaves like a bytes object.
"""
try:
obj + b''
except (TypeError, ValueError):
return False
return True
def has_nested_fields(ndtype):
"""
Returns whether one or several fields of a dtype are nested.
Parameters
----------
ndtype : dtype
Data-type of a structured array.
Raises
------
AttributeError
If `ndtype` does not have a `names` attribute.
Examples
--------
>>> dt = np.dtype([('name', 'S4'), ('x', float), ('y', float)])
>>> np.lib._iotools.has_nested_fields(dt)
False
"""
for name in ndtype.names or ():
if ndtype[name].names is not None:
return True
return False
def flatten_dtype(ndtype, flatten_base=False):
"""
Unpack a structured data-type by collapsing nested fields and/or fields
with a shape.
Note that the field names are lost.
Parameters
----------
ndtype : dtype
The datatype to collapse
flatten_base : bool, optional
If True, transform a field with a shape into several fields. Default is
False.
Examples
--------
>>> dt = np.dtype([('name', 'S4'), ('x', float), ('y', float),
... ('block', int, (2, 3))])
>>> np.lib._iotools.flatten_dtype(dt)
[dtype('S4'), dtype('float64'), dtype('float64'), dtype('int64')]
>>> np.lib._iotools.flatten_dtype(dt, flatten_base=True)
[dtype('S4'),
dtype('float64'),
dtype('float64'),
dtype('int64'),
dtype('int64'),
dtype('int64'),
dtype('int64'),
dtype('int64'),
dtype('int64')]
"""
names = ndtype.names
if names is None:
if flatten_base:
return [ndtype.base] * int(np.prod(ndtype.shape))
return [ndtype.base]
else:
types = []
for field in names:
info = ndtype.fields[field]
flat_dt = flatten_dtype(info[0], flatten_base)
types.extend(flat_dt)
return types
class LineSplitter:
"""
Object to split a string at a given delimiter or at given places.
Parameters
----------
delimiter : str, int, or sequence of ints, optional
If a string, character used to delimit consecutive fields.
If an integer or a sequence of integers, width(s) of each field.
comments : str, optional
Character used to mark the beginning of a comment. Default is '#'.
autostrip : bool, optional
Whether to strip each individual field. Default is True.
"""
def autostrip(self, method):
"""
Wrapper to strip each member of the output of `method`.
Parameters
----------
method : function
Function that takes a single argument and returns a sequence of
strings.
Returns
-------
wrapped : function
The result of wrapping `method`. `wrapped` takes a single input
argument and returns a list of strings that are stripped of
white-space.
"""
return lambda input: [_.strip() for _ in method(input)]
def __init__(self, delimiter=None, comments='#', autostrip=True,
encoding=None):
delimiter = _decode_line(delimiter)
comments = _decode_line(comments)
self.comments = comments
# Delimiter is a character
if (delimiter is None) or isinstance(delimiter, str):
delimiter = delimiter or None
_handyman = self._delimited_splitter
# Delimiter is a list of field widths
elif hasattr(delimiter, '__iter__'):
_handyman = self._variablewidth_splitter
idx = np.cumsum([0] + list(delimiter))
delimiter = [slice(i, j) for (i, j) in zip(idx[:-1], idx[1:])]
# Delimiter is a single integer
elif int(delimiter):
(_handyman, delimiter) = (
self._fixedwidth_splitter, int(delimiter))
else:
(_handyman, delimiter) = (self._delimited_splitter, None)
self.delimiter = delimiter
if autostrip:
self._handyman = self.autostrip(_handyman)
else:
self._handyman = _handyman
self.encoding = encoding
def _delimited_splitter(self, line):
"""Chop off comments, strip, and split at delimiter. """
if self.comments is not None:
line = line.split(self.comments)[0]
line = line.strip(" \r\n")
if not line:
return []
return line.split(self.delimiter)
def _fixedwidth_splitter(self, line):
if self.comments is not None:
line = line.split(self.comments)[0]
line = line.strip("\r\n")
if not line:
return []
fixed = self.delimiter
slices = [slice(i, i + fixed) for i in range(0, len(line), fixed)]
return [line[s] for s in slices]
def _variablewidth_splitter(self, line):
if self.comments is not None:
line = line.split(self.comments)[0]
if not line:
return []
slices = self.delimiter
return [line[s] for s in slices]
def __call__(self, line):
return self._handyman(_decode_line(line, self.encoding))
class NameValidator:
"""
Object to validate a list of strings to use as field names.
The strings are stripped of any non alphanumeric character, and spaces
are replaced by '_'. During instantiation, the user can define a list
of names to exclude, as well as a list of invalid characters. Names in
the exclusion list are appended a '_' character.
Once an instance has been created, it can be called with a list of
names, and a list of valid names will be created. The `__call__`
method accepts an optional keyword "default" that sets the default name
in case of ambiguity. By default this is 'f', so that names will
default to `f0`, `f1`, etc.
Parameters
----------
excludelist : sequence, optional
A list of names to exclude. This list is appended to the default
list ['return', 'file', 'print']. Excluded names are appended an
underscore: for example, `file` becomes `file_` if supplied.
deletechars : str, optional
A string combining invalid characters that must be deleted from the
names.
case_sensitive : {True, False, 'upper', 'lower'}, optional
* If True, field names are case-sensitive.
* If False or 'upper', field names are converted to upper case.
* If 'lower', field names are converted to lower case.
The default value is True.
replace_space : '_', optional
Character(s) used in replacement of white spaces.
Notes
-----
Calling an instance of `NameValidator` is the same as calling its
method `validate`.
Examples
--------
>>> validator = np.lib._iotools.NameValidator()
>>> validator(['file', 'field2', 'with space', 'CaSe'])
('file_', 'field2', 'with_space', 'CaSe')
>>> validator = np.lib._iotools.NameValidator(excludelist=['excl'],
... deletechars='q',
... case_sensitive=False)
>>> validator(['excl', 'field2', 'no_q', 'with space', 'CaSe'])
('EXCL', 'FIELD2', 'NO_Q', 'WITH_SPACE', 'CASE')
"""
defaultexcludelist = ['return', 'file', 'print']
defaultdeletechars = set(r"""~!@#$%^&*()-=+~\|]}[{';: /?.>,<""")
def __init__(self, excludelist=None, deletechars=None,
case_sensitive=None, replace_space='_'):
# Process the exclusion list ..
if excludelist is None:
excludelist = []
excludelist.extend(self.defaultexcludelist)
self.excludelist = excludelist
# Process the list of characters to delete
if deletechars is None:
delete = self.defaultdeletechars
else:
delete = set(deletechars)
delete.add('"')
self.deletechars = delete
# Process the case option .....
if (case_sensitive is None) or (case_sensitive is True):
self.case_converter = lambda x: x
elif (case_sensitive is False) or case_sensitive.startswith('u'):
self.case_converter = lambda x: x.upper()
elif case_sensitive.startswith('l'):
self.case_converter = lambda x: x.lower()
else:
msg = 'unrecognized case_sensitive value %s.' % case_sensitive
raise ValueError(msg)
self.replace_space = replace_space
def validate(self, names, defaultfmt="f%i", nbfields=None):
"""
Validate a list of strings as field names for a structured array.
Parameters
----------
names : sequence of str
Strings to be validated.
defaultfmt : str, optional
Default format string, used if validating a given string
reduces its length to zero.
nbfields : integer, optional
Final number of validated names, used to expand or shrink the
initial list of names.
Returns
-------
validatednames : list of str
The list of validated field names.
Notes
-----
A `NameValidator` instance can be called directly, which is the
same as calling `validate`. For examples, see `NameValidator`.
"""
# Initial checks ..............
if (names is None):
if (nbfields is None):
return None
names = []
if isinstance(names, str):
names = [names, ]
if nbfields is not None:
nbnames = len(names)
if (nbnames < nbfields):
names = list(names) + [''] * (nbfields - nbnames)
elif (nbnames > nbfields):
names = names[:nbfields]
# Set some shortcuts ...........
deletechars = self.deletechars
excludelist = self.excludelist
case_converter = self.case_converter
replace_space = self.replace_space
# Initializes some variables ...
validatednames = []
seen = dict()
nbempty = 0
for item in names:
item = case_converter(item).strip()
if replace_space:
item = item.replace(' ', replace_space)
item = ''.join([c for c in item if c not in deletechars])
if item == '':
item = defaultfmt % nbempty
while item in names:
nbempty += 1
item = defaultfmt % nbempty
nbempty += 1
elif item in excludelist:
item += '_'
cnt = seen.get(item, 0)
if cnt > 0:
validatednames.append(item + '_%d' % cnt)
else:
validatednames.append(item)
seen[item] = cnt + 1
return tuple(validatednames)
def __call__(self, names, defaultfmt="f%i", nbfields=None):
return self.validate(names, defaultfmt=defaultfmt, nbfields=nbfields)
def str2bool(value):
"""
Tries to transform a string supposed to represent a boolean to a boolean.
Parameters
----------
value : str
The string that is transformed to a boolean.
Returns
-------
boolval : bool
The boolean representation of `value`.
Raises
------
ValueError
If the string is not 'True' or 'False' (case independent)
Examples
--------
>>> np.lib._iotools.str2bool('TRUE')
True
>>> np.lib._iotools.str2bool('false')
False
"""
value = value.upper()
if value == 'TRUE':
return True
elif value == 'FALSE':
return False
else:
raise ValueError("Invalid boolean")
class ConverterError(Exception):
"""
Exception raised when an error occurs in a converter for string values.
"""
pass
class ConverterLockError(ConverterError):
"""
Exception raised when an attempt is made to upgrade a locked converter.
"""
pass
class ConversionWarning(UserWarning):
"""
Warning issued when a string converter has a problem.
Notes
-----
In `genfromtxt` a `ConversionWarning` is issued if raising exceptions
is explicitly suppressed with the "invalid_raise" keyword.
"""
pass
class StringConverter:
"""
Factory class for function transforming a string into another object
(int, float).
After initialization, an instance can be called to transform a string
into another object. If the string is recognized as representing a
missing value, a default value is returned.
Attributes
----------
func : function
Function used for the conversion.
default : any
Default value to return when the input corresponds to a missing
value.
type : type
Type of the output.
_status : int
Integer representing the order of the conversion.
_mapper : sequence of tuples
Sequence of tuples (dtype, function, default value) to evaluate in
order.
_locked : bool
Holds `locked` parameter.
Parameters
----------
dtype_or_func : {None, dtype, function}, optional
If a `dtype`, specifies the input data type, used to define a basic
function and a default value for missing data. For example, when
`dtype` is float, the `func` attribute is set to `float` and the
default value to `np.nan`. If a function, this function is used to
convert a string to another object. In this case, it is recommended
to give an associated default value as input.
default : any, optional
Value to return by default, that is, when the string to be
converted is flagged as missing. If not given, `StringConverter`
tries to supply a reasonable default value.
missing_values : {None, sequence of str}, optional
``None`` or sequence of strings indicating a missing value. If ``None``
then missing values are indicated by empty entries. The default is
``None``.
locked : bool, optional
Whether the StringConverter should be locked to prevent automatic
upgrade or not. Default is False.
"""
_mapper = [(nx.bool_, str2bool, False),
(nx.int_, int, -1),]
# On 32-bit systems, we need to make sure that we explicitly include
# nx.int64 since ns.int_ is nx.int32.
if nx.dtype(nx.int_).itemsize < nx.dtype(nx.int64).itemsize:
_mapper.append((nx.int64, int, -1))
_mapper.extend([(nx.float64, float, nx.nan),
(nx.complex128, complex, nx.nan + 0j),
(nx.longdouble, nx.longdouble, nx.nan),
# If a non-default dtype is passed, fall back to generic
# ones (should only be used for the converter)
(nx.integer, int, -1),
(nx.floating, float, nx.nan),
(nx.complexfloating, complex, nx.nan + 0j),
# Last, try with the string types (must be last, because
# `_mapper[-1]` is used as default in some cases)
(nx.unicode_, asunicode, '???'),
(nx.string_, asbytes, '???'),
])
@classmethod
def _getdtype(cls, val):
"""Returns the dtype of the input variable."""
return np.array(val).dtype
@classmethod
def _getsubdtype(cls, val):
"""Returns the type of the dtype of the input variable."""
return np.array(val).dtype.type
@classmethod
def _dtypeortype(cls, dtype):
"""Returns dtype for datetime64 and type of dtype otherwise."""
# This is a bit annoying. We want to return the "general" type in most
# cases (ie. "string" rather than "S10"), but we want to return the
# specific type for datetime64 (ie. "datetime64[us]" rather than
# "datetime64").
if dtype.type == np.datetime64:
return dtype
return dtype.type
@classmethod
def upgrade_mapper(cls, func, default=None):
"""
Upgrade the mapper of a StringConverter by adding a new function and
its corresponding default.
The input function (or sequence of functions) and its associated
default value (if any) is inserted in penultimate position of the
mapper. The corresponding type is estimated from the dtype of the
default value.
Parameters
----------
func : var
Function, or sequence of functions
Examples
--------
>>> import dateutil.parser
>>> import datetime
>>> dateparser = dateutil.parser.parse
>>> defaultdate = datetime.date(2000, 1, 1)
>>> StringConverter.upgrade_mapper(dateparser, default=defaultdate)
"""
# Func is a single functions
if hasattr(func, '__call__'):
cls._mapper.insert(-1, (cls._getsubdtype(default), func, default))
return
elif hasattr(func, '__iter__'):
if isinstance(func[0], (tuple, list)):
for _ in func:
cls._mapper.insert(-1, _)
return
if default is None:
default = [None] * len(func)
else:
default = list(default)
default.append([None] * (len(func) - len(default)))
for fct, dft in zip(func, default):
cls._mapper.insert(-1, (cls._getsubdtype(dft), fct, dft))
@classmethod
def _find_map_entry(cls, dtype):
# if a converter for the specific dtype is available use that
for i, (deftype, func, default_def) in enumerate(cls._mapper):
if dtype.type == deftype:
return i, (deftype, func, default_def)
# otherwise find an inexact match
for i, (deftype, func, default_def) in enumerate(cls._mapper):
if np.issubdtype(dtype.type, deftype):
return i, (deftype, func, default_def)
raise LookupError
def __init__(self, dtype_or_func=None, default=None, missing_values=None,
locked=False):
# Defines a lock for upgrade
self._locked = bool(locked)
# No input dtype: minimal initialization
if dtype_or_func is None:
self.func = str2bool
self._status = 0
self.default = default or False
dtype = np.dtype('bool')
else:
# Is the input a np.dtype ?
try:
self.func = None
dtype = np.dtype(dtype_or_func)
except TypeError:
# dtype_or_func must be a function, then
if not hasattr(dtype_or_func, '__call__'):
errmsg = ("The input argument `dtype` is neither a"
" function nor a dtype (got '%s' instead)")
raise TypeError(errmsg % type(dtype_or_func))
# Set the function
self.func = dtype_or_func
# If we don't have a default, try to guess it or set it to
# None
if default is None:
try:
default = self.func('0')
except ValueError:
default = None
dtype = self._getdtype(default)
# find the best match in our mapper
try:
self._status, (_, func, default_def) = self._find_map_entry(dtype)
except LookupError:
# no match
self.default = default
_, func, _ = self._mapper[-1]
self._status = 0
else:
# use the found default only if we did not already have one
if default is None:
self.default = default_def
else:
self.default = default
# If the input was a dtype, set the function to the last we saw
if self.func is None:
self.func = func
# If the status is 1 (int), change the function to
# something more robust.
if self.func == self._mapper[1][1]:
if issubclass(dtype.type, np.uint64):
self.func = np.uint64
elif issubclass(dtype.type, np.int64):
self.func = np.int64
else:
self.func = lambda x: int(float(x))
# Store the list of strings corresponding to missing values.
if missing_values is None:
self.missing_values = {''}
else:
if isinstance(missing_values, str):
missing_values = missing_values.split(",")
self.missing_values = set(list(missing_values) + [''])
self._callingfunction = self._strict_call
self.type = self._dtypeortype(dtype)
self._checked = False
self._initial_default = default
def _loose_call(self, value):
try:
return self.func(value)
except ValueError:
return self.default
def _strict_call(self, value):
try:
# We check if we can convert the value using the current function
new_value = self.func(value)
# In addition to having to check whether func can convert the
# value, we also have to make sure that we don't get overflow
# errors for integers.
if self.func is int:
try:
np.array(value, dtype=self.type)
except OverflowError:
raise ValueError
# We're still here so we can now return the new value
return new_value
except ValueError:
if value.strip() in self.missing_values:
if not self._status:
self._checked = False
return self.default
raise ValueError("Cannot convert string '%s'" % value)
def __call__(self, value):
return self._callingfunction(value)
def _do_upgrade(self):
# Raise an exception if we locked the converter...
if self._locked:
errmsg = "Converter is locked and cannot be upgraded"
raise ConverterLockError(errmsg)
_statusmax = len(self._mapper)
# Complains if we try to upgrade by the maximum
_status = self._status
if _status == _statusmax:
errmsg = "Could not find a valid conversion function"
raise ConverterError(errmsg)
elif _status < _statusmax - 1:
_status += 1
self.type, self.func, default = self._mapper[_status]
self._status = _status
if self._initial_default is not None:
self.default = self._initial_default
else:
self.default = default
def upgrade(self, value):
"""
Find the best converter for a given string, and return the result.
The supplied string `value` is converted by testing different
converters in order. First the `func` method of the
`StringConverter` instance is tried, if this fails other available
converters are tried. The order in which these other converters
are tried is determined by the `_status` attribute of the instance.
Parameters
----------
value : str
The string to convert.
Returns
-------
out : any
The result of converting `value` with the appropriate converter.
"""
self._checked = True
try:
return self._strict_call(value)
except ValueError:
self._do_upgrade()
return self.upgrade(value)
def iterupgrade(self, value):
self._checked = True
if not hasattr(value, '__iter__'):
value = (value,)
_strict_call = self._strict_call
try:
for _m in value:
_strict_call(_m)
except ValueError:
self._do_upgrade()
self.iterupgrade(value)
def update(self, func, default=None, testing_value=None,
missing_values='', locked=False):
"""
Set StringConverter attributes directly.
Parameters
----------
func : function
Conversion function.
default : any, optional
Value to return by default, that is, when the string to be
converted is flagged as missing. If not given,
`StringConverter` tries to supply a reasonable default value.
testing_value : str, optional
A string representing a standard input value of the converter.
This string is used to help defining a reasonable default
value.
missing_values : {sequence of str, None}, optional
Sequence of strings indicating a missing value. If ``None``, then
the existing `missing_values` are cleared. The default is `''`.
locked : bool, optional
Whether the StringConverter should be locked to prevent
automatic upgrade or not. Default is False.
Notes
-----
`update` takes the same parameters as the constructor of
`StringConverter`, except that `func` does not accept a `dtype`
whereas `dtype_or_func` in the constructor does.
"""
self.func = func
self._locked = locked
# Don't reset the default to None if we can avoid it
if default is not None:
self.default = default
self.type = self._dtypeortype(self._getdtype(default))
else:
try:
tester = func(testing_value or '1')
except (TypeError, ValueError):
tester = None
self.type = self._dtypeortype(self._getdtype(tester))
# Add the missing values to the existing set or clear it.
if missing_values is None:
# Clear all missing values even though the ctor initializes it to
# set(['']) when the argument is None.
self.missing_values = set()
else:
if not np.iterable(missing_values):
missing_values = [missing_values]
if not all(isinstance(v, str) for v in missing_values):
raise TypeError("missing_values must be strings or unicode")
self.missing_values.update(missing_values)
def easy_dtype(ndtype, names=None, defaultfmt="f%i", **validationargs):
"""
Convenience function to create a `np.dtype` object.
The function processes the input `dtype` and matches it with the given
names.
Parameters
----------
ndtype : var
Definition of the dtype. Can be any string or dictionary recognized
by the `np.dtype` function, or a sequence of types.
names : str or sequence, optional
Sequence of strings to use as field names for a structured dtype.
For convenience, `names` can be a string of a comma-separated list
of names.
defaultfmt : str, optional
Format string used to define missing names, such as ``"f%i"``
(default) or ``"fields_%02i"``.
validationargs : optional
A series of optional arguments used to initialize a
`NameValidator`.
Examples
--------
>>> np.lib._iotools.easy_dtype(float)
dtype('float64')
>>> np.lib._iotools.easy_dtype("i4, f8")
dtype([('f0', '<i4'), ('f1', '<f8')])
>>> np.lib._iotools.easy_dtype("i4, f8", defaultfmt="field_%03i")
dtype([('field_000', '<i4'), ('field_001', '<f8')])
>>> np.lib._iotools.easy_dtype((int, float, float), names="a,b,c")
dtype([('a', '<i8'), ('b', '<f8'), ('c', '<f8')])
>>> np.lib._iotools.easy_dtype(float, names="a,b,c")
dtype([('a', '<f8'), ('b', '<f8'), ('c', '<f8')])
"""
try:
ndtype = np.dtype(ndtype)
except TypeError:
validate = NameValidator(**validationargs)
nbfields = len(ndtype)
if names is None:
names = [''] * len(ndtype)
elif isinstance(names, str):
names = names.split(",")
names = validate(names, nbfields=nbfields, defaultfmt=defaultfmt)
ndtype = np.dtype(dict(formats=ndtype, names=names))
else:
# Explicit names
if names is not None:
validate = NameValidator(**validationargs)
if isinstance(names, str):
names = names.split(",")
# Simple dtype: repeat to match the nb of names
if ndtype.names is None:
formats = tuple([ndtype.type] * len(names))
names = validate(names, defaultfmt=defaultfmt)
ndtype = np.dtype(list(zip(names, formats)))
# Structured dtype: just validate the names as needed
else:
ndtype.names = validate(names, nbfields=len(ndtype.names),
defaultfmt=defaultfmt)
# No implicit names
elif ndtype.names is not None:
validate = NameValidator(**validationargs)
# Default initial names : should we change the format ?
numbered_names = tuple("f%i" % i for i in range(len(ndtype.names)))
if ((ndtype.names == numbered_names) and (defaultfmt != "f%i")):
ndtype.names = validate([''] * len(ndtype.names),
defaultfmt=defaultfmt)
# Explicit initial names : just validate
else:
ndtype.names = validate(ndtype.names, defaultfmt=defaultfmt)
return ndtype
|