/usr/lib/python3/dist-packages/pandas/core/strings.py is in python3-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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 | import numpy as np
from pandas.compat import zip
from pandas.core.common import isnull, _values_from_object
from pandas.core.series import Series
from pandas.core.frame import DataFrame
import pandas.compat as compat
import re
import pandas.lib as lib
import warnings
def _get_array_list(arr, others):
if isinstance(others[0], (list, np.ndarray)):
arrays = [arr] + list(others)
else:
arrays = [arr, others]
return [np.asarray(x, dtype=object) for x in arrays]
def str_cat(arr, others=None, sep=None, na_rep=None):
"""
Concatenate arrays of strings with given separator
Parameters
----------
arr : list or array-like
others : list or array, or list of arrays
sep : string or None, default None
na_rep : string or None, default None
If None, an NA in any array will propagate
Returns
-------
concat : array
"""
if sep is None:
sep = ''
if others is not None:
arrays = _get_array_list(arr, others)
n = _length_check(arrays)
masks = np.array([isnull(x) for x in arrays])
cats = None
if na_rep is None:
na_mask = np.logical_or.reduce(masks, axis=0)
result = np.empty(n, dtype=object)
np.putmask(result, na_mask, np.nan)
notmask = -na_mask
tuples = zip(*[x[notmask] for x in arrays])
cats = [sep.join(tup) for tup in tuples]
result[notmask] = cats
else:
for i, x in enumerate(arrays):
x = np.where(masks[i], na_rep, x)
if cats is None:
cats = x
else:
cats = cats + sep + x
result = cats
return result
else:
arr = np.asarray(arr, dtype=object)
mask = isnull(arr)
if na_rep is None and mask.any():
return np.nan
return sep.join(np.where(mask, na_rep, arr))
def _length_check(others):
n = None
for x in others:
if n is None:
n = len(x)
elif len(x) != n:
raise ValueError('All arrays must be same length')
return n
def _na_map(f, arr, na_result=np.nan):
# should really _check_ for NA
return _map(f, arr, na_mask=True, na_value=na_result)
def _map(f, arr, na_mask=False, na_value=np.nan):
if isinstance(arr, Series):
arr = arr.values
if not isinstance(arr, np.ndarray):
arr = np.asarray(arr, dtype=object)
if na_mask:
mask = isnull(arr)
try:
result = lib.map_infer_mask(arr, f, mask.view(np.uint8))
except (TypeError, AttributeError):
def g(x):
try:
return f(x)
except (TypeError, AttributeError):
return na_value
return _map(g, arr)
if na_value is not np.nan:
np.putmask(result, mask, na_value)
if result.dtype == object:
result = lib.maybe_convert_objects(result)
return result
else:
return lib.map_infer(arr, f)
def str_title(arr):
"""
Convert strings to titlecased version
Returns
-------
titled : array
"""
return _na_map(lambda x: x.title(), arr)
def str_count(arr, pat, flags=0):
"""
Count occurrences of pattern in each string
Parameters
----------
arr : list or array-like
pat : string, valid regular expression
flags : int, default 0 (no flags)
re module flags, e.g. re.IGNORECASE
Returns
-------
counts : arrays
"""
regex = re.compile(pat, flags=flags)
f = lambda x: len(regex.findall(x))
return _na_map(f, arr)
def str_contains(arr, pat, case=True, flags=0, na=np.nan, regex=True):
"""
Check whether given pattern is contained in each string in the array
Parameters
----------
pat : string
Character sequence or regular expression
case : boolean, default True
If True, case sensitive
flags : int, default 0 (no flags)
re module flags, e.g. re.IGNORECASE
na : default NaN, fill value for missing values.
regex : bool, default True
If True use re.search, otherwise use Python in operator
Returns
-------
Series of boolean values
See Also
--------
match : analagous, but stricter, relying on re.match instead of re.search
"""
if regex:
if not case:
flags |= re.IGNORECASE
regex = re.compile(pat, flags=flags)
if regex.groups > 0:
warnings.warn("This pattern has match groups. To actually get the"
" groups, use str.extract.", UserWarning)
f = lambda x: bool(regex.search(x))
else:
f = lambda x: pat in x
return _na_map(f, arr, na)
def str_startswith(arr, pat, na=np.nan):
"""
Return boolean array indicating whether each string starts with passed
pattern
Parameters
----------
pat : string
Character sequence
na : bool, default NaN
Returns
-------
startswith : array (boolean)
"""
f = lambda x: x.startswith(pat)
return _na_map(f, arr, na)
def str_endswith(arr, pat, na=np.nan):
"""
Return boolean array indicating whether each string ends with passed
pattern
Parameters
----------
pat : string
Character sequence
na : bool, default NaN
Returns
-------
endswith : array (boolean)
"""
f = lambda x: x.endswith(pat)
return _na_map(f, arr, na)
def str_lower(arr):
"""
Convert strings in array to lowercase
Returns
-------
lowercase : array
"""
return _na_map(lambda x: x.lower(), arr)
def str_upper(arr):
"""
Convert strings in array to uppercase
Returns
-------
uppercase : array
"""
return _na_map(lambda x: x.upper(), arr)
def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
"""
Replace
Parameters
----------
pat : string
Character sequence or regular expression
repl : string
Replacement sequence
n : int, default -1 (all)
Number of replacements to make from start
case : boolean, default True
If True, case sensitive
flags : int, default 0 (no flags)
re module flags, e.g. re.IGNORECASE
Returns
-------
replaced : array
"""
use_re = not case or len(pat) > 1 or flags
if use_re:
if not case:
flags |= re.IGNORECASE
regex = re.compile(pat, flags=flags)
n = n if n >= 0 else 0
def f(x):
return regex.sub(repl, x, count=n)
else:
f = lambda x: x.replace(pat, repl, n)
return _na_map(f, arr)
def str_repeat(arr, repeats):
"""
Duplicate each string in the array by indicated number of times
Parameters
----------
repeats : int or array
Same value for all (int) or different value per (array)
Returns
-------
repeated : array
"""
if np.isscalar(repeats):
def rep(x):
try:
return compat.binary_type.__mul__(x, repeats)
except TypeError:
return compat.text_type.__mul__(x, repeats)
return _na_map(rep, arr)
else:
def rep(x, r):
try:
return compat.binary_type.__mul__(x, r)
except TypeError:
return compat.text_type.__mul__(x, r)
repeats = np.asarray(repeats, dtype=object)
result = lib.vec_binop(_values_from_object(arr), repeats, rep)
return result
def str_match(arr, pat, case=True, flags=0, na=np.nan, as_indexer=False):
"""
Deprecated: Find groups in each string using passed regular expression.
If as_indexer=True, determine if each string matches a regular expression.
Parameters
----------
pat : string
Character sequence or regular expression
case : boolean, default True
If True, case sensitive
flags : int, default 0 (no flags)
re module flags, e.g. re.IGNORECASE
na : default NaN, fill value for missing values.
as_indexer : False, by default, gives deprecated behavior better achieved
using str_extract. True return boolean indexer.
Returns
-------
Series of boolean values
if as_indexer=True
Series of tuples
if as_indexer=False, default but deprecated
See Also
--------
contains : analagous, but less strict, relying on re.search instead of
re.match
extract : now preferred to the deprecated usage of match (as_indexer=False)
Notes
-----
To extract matched groups, which is the deprecated behavior of match, use
str.extract.
"""
if not case:
flags |= re.IGNORECASE
regex = re.compile(pat, flags=flags)
if (not as_indexer) and regex.groups > 0:
# Do this first, to make sure it happens even if the re.compile
# raises below.
warnings.warn("In future versions of pandas, match will change to"
" always return a bool indexer.""", UserWarning)
if as_indexer and regex.groups > 0:
warnings.warn("This pattern has match groups. To actually get the"
" groups, use str.extract.""", UserWarning)
# If not as_indexer and regex.groups == 0, this returns empty lists
# and is basically useless, so we will not warn.
if (not as_indexer) and regex.groups > 0:
def f(x):
m = regex.match(x)
if m:
return m.groups()
else:
return []
else:
# This is the new behavior of str_match.
f = lambda x: bool(regex.match(x))
return _na_map(f, arr)
def str_extract(arr, pat, flags=0):
"""
Find groups in each string using passed regular expression
Parameters
----------
pat : string
Pattern or regular expression
flags : int, default 0 (no flags)
re module flags, e.g. re.IGNORECASE
Returns
-------
extracted groups : Series (one group) or DataFrame (multiple groups)
Examples
--------
A pattern with one group will return a Series. Non-matches will be NaN.
>>> Series(['a1', 'b2', 'c3']).str.extract('[ab](\d)')
0 1
1 2
2 NaN
dtype: object
A pattern with more than one group will return a DataFrame.
>>> Series(['a1', 'b2', 'c3']).str.extract('([ab])(\d)')
0 1
0 a 1
1 b 2
2 NaN NaN
A pattern may contain optional groups.
>>> Series(['a1', 'b2', 'c3']).str.extract('([ab])?(\d)')
0 1
0 a 1
1 b 2
2 NaN 3
Named groups will become column names in the result.
>>> Series(['a1', 'b2', 'c3']).str.extract('(?P<letter>[ab])(?P<digit>\d)')
letter digit
0 a 1
1 b 2
2 NaN NaN
"""
regex = re.compile(pat, flags=flags)
# just to be safe, check this
if regex.groups == 0:
raise ValueError("This pattern contains no groups to capture.")
empty_row = [np.nan]*regex.groups
def f(x):
if not isinstance(x, compat.string_types):
return empty_row
m = regex.search(x)
if m:
return [np.nan if item is None else item for item in m.groups()]
else:
return empty_row
if regex.groups == 1:
result = Series([f(val)[0] for val in arr], name=regex.groupindex.get(1))
else:
names = dict(zip(regex.groupindex.values(), regex.groupindex.keys()))
columns = [names.get(1 + i, i) for i in range(regex.groups)]
result = DataFrame([f(val) for val in arr], columns=columns)
return result
def str_get_dummies(arr, sep='|'):
"""
Split each string by sep and return a frame of dummy/indicator variables.
Examples
--------
>>> Series(['a|b', 'a', 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 1 0 0
2 1 0 1
>>> pd.Series(['a|b', np.nan, 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 0 0 0
2 1 0 1
See also ``pd.get_dummies``.
"""
# TODO remove this hack?
arr = arr.fillna('')
try:
arr = sep + arr + sep
except TypeError:
arr = sep + arr.astype(str) + sep
tags = set()
for ts in arr.str.split(sep):
tags.update(ts)
tags = sorted(tags - set([""]))
dummies = np.empty((len(arr), len(tags)), dtype=np.int64)
for i, t in enumerate(tags):
pat = sep + t + sep
dummies[:, i] = lib.map_infer(arr.values, lambda x: pat in x)
return DataFrame(dummies, arr.index, tags)
def str_join(arr, sep):
"""
Join lists contained as elements in array, a la str.join
Parameters
----------
sep : string
Delimiter
Returns
-------
joined : array
"""
return _na_map(sep.join, arr)
def str_len(arr):
"""
Compute length of each string in array.
Returns
-------
lengths : array
"""
return _na_map(len, arr)
def str_findall(arr, pat, flags=0):
"""
Find all occurrences of pattern or regular expression
Parameters
----------
pat : string
Pattern or regular expression
flags : int, default 0 (no flags)
re module flags, e.g. re.IGNORECASE
Returns
-------
matches : array
"""
regex = re.compile(pat, flags=flags)
return _na_map(regex.findall, arr)
def str_pad(arr, width, side='left'):
"""
Pad strings with whitespace
Parameters
----------
arr : list or array-like
width : int
Minimum width of resulting string; additional characters will be filled
with spaces
side : {'left', 'right', 'both'}, default 'left'
Returns
-------
padded : array
"""
if side == 'left':
f = lambda x: x.rjust(width)
elif side == 'right':
f = lambda x: x.ljust(width)
elif side == 'both':
f = lambda x: x.center(width)
else: # pragma: no cover
raise ValueError('Invalid side')
return _na_map(f, arr)
def str_center(arr, width):
"""
"Center" strings, filling left and right side with additional whitespace
Parameters
----------
width : int
Minimum width of resulting string; additional characters will be filled
with spaces
Returns
-------
centered : array
"""
return str_pad(arr, width, side='both')
def str_split(arr, pat=None, n=None):
"""
Split each string (a la re.split) in array by given pattern, propagating NA
values
Parameters
----------
pat : string, default None
String or regular expression to split on. If None, splits on whitespace
n : int, default None (all)
Notes
-----
Both 0 and -1 will be interpreted as return all splits
Returns
-------
split : array
"""
if pat is None:
if n is None or n == 0:
n = -1
f = lambda x: x.split()
else:
if len(pat) == 1:
if n is None or n == 0:
n = -1
f = lambda x: x.split(pat, n)
else:
if n is None or n == -1:
n = 0
regex = re.compile(pat)
f = lambda x: regex.split(x, maxsplit=n)
return _na_map(f, arr)
def str_slice(arr, start=None, stop=None, step=1):
"""
Slice substrings from each element in array
Parameters
----------
start : int or None
stop : int or None
Returns
-------
sliced : array
"""
obj = slice(start, stop, step)
f = lambda x: x[obj]
return _na_map(f, arr)
def str_slice_replace(arr, start=None, stop=None, repl=None):
"""
Parameters
----------
Returns
-------
replaced : array
"""
raise NotImplementedError
def str_strip(arr, to_strip=None):
"""
Strip whitespace (including newlines) from each string in the array
Parameters
----------
to_strip : str or unicode
Returns
-------
stripped : array
"""
return _na_map(lambda x: x.strip(to_strip), arr)
def str_lstrip(arr, to_strip=None):
"""
Strip whitespace (including newlines) from left side of each string in the
array
Parameters
----------
to_strip : str or unicode
Returns
-------
stripped : array
"""
return _na_map(lambda x: x.lstrip(to_strip), arr)
def str_rstrip(arr, to_strip=None):
"""
Strip whitespace (including newlines) from right side of each string in the
array
Parameters
----------
to_strip : str or unicode
Returns
-------
stripped : array
"""
return _na_map(lambda x: x.rstrip(to_strip), arr)
def str_wrap(arr, width=80):
"""
Wrap long strings to be formatted in paragraphs
Parameters
----------
width : int
Maximum line-width
Returns
-------
wrapped : array
"""
raise NotImplementedError
def str_get(arr, i):
"""
Extract element from lists, tuples, or strings in each element in the array
Parameters
----------
i : int
Integer index (location)
Returns
-------
items : array
"""
f = lambda x: x[i] if len(x) > i else np.nan
return _na_map(f, arr)
def str_decode(arr, encoding, errors="strict"):
"""
Decode character string to unicode using indicated encoding
Parameters
----------
encoding : string
errors : string
Returns
-------
decoded : array
"""
f = lambda x: x.decode(encoding, errors)
return _na_map(f, arr)
def str_encode(arr, encoding, errors="strict"):
"""
Encode character string to some other encoding using indicated encoding
Parameters
----------
encoding : string
errors : string
Returns
-------
encoded : array
"""
f = lambda x: x.encode(encoding, errors)
return _na_map(f, arr)
def _noarg_wrapper(f):
def wrapper(self):
result = f(self.series)
return self._wrap_result(result)
wrapper.__name__ = f.__name__
if f.__doc__:
wrapper.__doc__ = f.__doc__
return wrapper
def _pat_wrapper(f, flags=False, na=False, **kwargs):
def wrapper1(self, pat):
result = f(self.series, pat)
return self._wrap_result(result)
def wrapper2(self, pat, flags=0, **kwargs):
result = f(self.series, pat, flags=flags, **kwargs)
return self._wrap_result(result)
def wrapper3(self, pat, na=np.nan):
result = f(self.series, pat, na=na)
return self._wrap_result(result)
wrapper = wrapper3 if na else wrapper2 if flags else wrapper1
wrapper.__name__ = f.__name__
if f.__doc__:
wrapper.__doc__ = f.__doc__
return wrapper
def copy(source):
"Copy a docstring from another source function (if present)"
def do_copy(target):
if source.__doc__:
target.__doc__ = source.__doc__
return target
return do_copy
class StringMethods(object):
"""
Vectorized string functions for Series. NAs stay NA unless handled
otherwise by a particular method. Patterned after Python's string methods,
with some inspiration from R's stringr package.
Examples
--------
>>> s.str.split('_')
>>> s.str.replace('_', '')
"""
def __init__(self, series):
self.series = series
def __getitem__(self, key):
if isinstance(key, slice):
return self.slice(start=key.start, stop=key.stop,
step=key.step)
else:
return self.get(key)
def __iter__(self):
i = 0
g = self.get(i)
while g.notnull().any():
yield g
i += 1
g = self.get(i)
def _wrap_result(self, result):
if not hasattr(result, 'ndim'):
return result
elif result.ndim == 1:
return Series(result, index=self.series.index,
name=self.series.name)
else:
assert result.ndim < 3
return DataFrame(result, index=self.series.index)
@copy(str_cat)
def cat(self, others=None, sep=None, na_rep=None):
result = str_cat(self.series, others=others, sep=sep, na_rep=na_rep)
return self._wrap_result(result)
@copy(str_split)
def split(self, pat=None, n=-1):
result = str_split(self.series, pat, n=n)
return self._wrap_result(result)
@copy(str_get)
def get(self, i):
result = str_get(self.series, i)
return self._wrap_result(result)
@copy(str_join)
def join(self, sep):
result = str_join(self.series, sep)
return self._wrap_result(result)
@copy(str_contains)
def contains(self, pat, case=True, flags=0, na=np.nan, regex=True):
result = str_contains(self.series, pat, case=case, flags=flags,
na=na, regex=regex)
return self._wrap_result(result)
@copy(str_replace)
def replace(self, pat, repl, n=-1, case=True, flags=0):
result = str_replace(self.series, pat, repl, n=n, case=case,
flags=flags)
return self._wrap_result(result)
@copy(str_repeat)
def repeat(self, repeats):
result = str_repeat(self.series, repeats)
return self._wrap_result(result)
@copy(str_pad)
def pad(self, width, side='left'):
result = str_pad(self.series, width, side=side)
return self._wrap_result(result)
@copy(str_center)
def center(self, width):
result = str_center(self.series, width)
return self._wrap_result(result)
@copy(str_slice)
def slice(self, start=None, stop=None, step=1):
result = str_slice(self.series, start, stop)
return self._wrap_result(result)
@copy(str_slice)
def slice_replace(self, i=None, j=None):
raise NotImplementedError
@copy(str_decode)
def decode(self, encoding, errors="strict"):
result = str_decode(self.series, encoding, errors)
return self._wrap_result(result)
@copy(str_encode)
def encode(self, encoding, errors="strict"):
result = str_encode(self.series, encoding, errors)
return self._wrap_result(result)
@copy(str_strip)
def strip(self, to_strip=None):
result = str_strip(self.series, to_strip)
return self._wrap_result(result)
@copy(str_lstrip)
def lstrip(self, to_strip=None):
result = str_lstrip(self.series, to_strip)
return self._wrap_result(result)
@copy(str_rstrip)
def rstrip(self, to_strip=None):
result = str_rstrip(self.series, to_strip)
return self._wrap_result(result)
@copy(str_get_dummies)
def get_dummies(self, sep='|'):
result = str_get_dummies(self.series, sep)
return self._wrap_result(result)
count = _pat_wrapper(str_count, flags=True)
startswith = _pat_wrapper(str_startswith, na=True)
endswith = _pat_wrapper(str_endswith, na=True)
findall = _pat_wrapper(str_findall, flags=True)
match = _pat_wrapper(str_match, flags=True)
extract = _pat_wrapper(str_extract, flags=True)
len = _noarg_wrapper(str_len)
lower = _noarg_wrapper(str_lower)
upper = _noarg_wrapper(str_upper)
title = _noarg_wrapper(str_title)
|