/usr/lib/python2.7/dist-packages/pandas/core/algorithms.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 | """
Generic data algorithms. This module is experimental at the moment and not
intended for public consumption
"""
from __future__ import division
from warnings import warn
import numpy as np
import pandas.core.common as com
import pandas.algos as algos
import pandas.hashtable as htable
import pandas.compat as compat
from pandas.compat import filter, string_types
def match(to_match, values, na_sentinel=-1):
"""
Compute locations of to_match into values
Parameters
----------
to_match : array-like
values to find positions of
values : array-like
Unique set of values
na_sentinel : int, default -1
Value to mark "not found"
Examples
--------
Returns
-------
match : ndarray of integers
"""
values = com._asarray_tuplesafe(values)
if issubclass(values.dtype.type, string_types):
values = np.array(values, dtype='O')
f = lambda htype, caster: _match_generic(to_match, values, htype, caster)
result = _hashtable_algo(f, values.dtype)
if na_sentinel != -1:
# replace but return a numpy array
# use a Series because it handles dtype conversions properly
from pandas.core.series import Series
result = Series(result.ravel()).replace(-1,na_sentinel).values.reshape(result.shape)
return result
def unique(values):
"""
Compute unique values (not necessarily sorted) efficiently from input array
of values
Parameters
----------
values : array-like
Returns
-------
uniques
"""
values = com._asarray_tuplesafe(values)
f = lambda htype, caster: _unique_generic(values, htype, caster)
return _hashtable_algo(f, values.dtype)
# def count(values, uniques=None):
# f = lambda htype, caster: _count_generic(values, htype, caster)
# if uniques is not None:
# raise NotImplementedError
# else:
# return _hashtable_algo(f, values.dtype)
def _hashtable_algo(f, dtype):
"""
f(HashTable, type_caster) -> result
"""
if com.is_float_dtype(dtype):
return f(htable.Float64HashTable, com._ensure_float64)
elif com.is_integer_dtype(dtype):
return f(htable.Int64HashTable, com._ensure_int64)
else:
return f(htable.PyObjectHashTable, com._ensure_object)
def _count_generic(values, table_type, type_caster):
from pandas.core.series import Series
values = type_caster(values)
table = table_type(min(len(values), 1000000))
uniques, labels = table.factorize(values)
return Series(counts, index=uniques)
def _match_generic(values, index, table_type, type_caster):
values = type_caster(values)
index = type_caster(index)
table = table_type(min(len(index), 1000000))
table.map_locations(index)
return table.lookup(values)
def _unique_generic(values, table_type, type_caster):
values = type_caster(values)
table = table_type(min(len(values), 1000000))
uniques = table.unique(values)
return type_caster(uniques)
def factorize(values, sort=False, order=None, na_sentinel=-1):
"""
Encode input values as an enumerated type or categorical variable
Parameters
----------
values : ndarray (1-d)
Sequence
sort : boolean, default False
Sort by values
order :
na_sentinel: int, default -1
Value to mark "not found"
Returns
-------
labels : the indexer to the original array
uniques : the unique values
note: an array of Periods will ignore sort as it returns an always sorted PeriodIndex
"""
from pandas.tseries.period import PeriodIndex
vals = np.asarray(values)
is_datetime = com.is_datetime64_dtype(vals)
(hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
table = hash_klass(len(vals))
uniques = vec_klass()
labels = table.get_labels(vals, uniques, 0, na_sentinel)
labels = com._ensure_platform_int(labels)
uniques = uniques.to_array()
if sort and len(uniques) > 0:
try:
sorter = uniques.argsort()
except:
# unorderable in py3 if mixed str/int
t = hash_klass(len(uniques))
t.map_locations(com._ensure_object(uniques))
# order ints before strings
ordered = np.concatenate([
np.sort(np.array([ e for i, e in enumerate(uniques) if f(e) ],dtype=object)) for f in [ lambda x: not isinstance(x,string_types),
lambda x: isinstance(x,string_types) ]
])
sorter = com._ensure_platform_int(t.lookup(com._ensure_object(ordered)))
reverse_indexer = np.empty(len(sorter), dtype=np.int_)
reverse_indexer.put(sorter, np.arange(len(sorter)))
mask = labels < 0
labels = reverse_indexer.take(labels)
np.putmask(labels, mask, -1)
uniques = uniques.take(sorter)
if is_datetime:
uniques = uniques.astype('M8[ns]')
if isinstance(values, PeriodIndex):
uniques = PeriodIndex(ordinal=uniques, freq=values.freq)
return labels, uniques
def value_counts(values, sort=True, ascending=False, normalize=False,
bins=None):
"""
Compute a histogram of the counts of non-null values
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
values = Series(values).values
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.labels
if com.is_integer_dtype(values.dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
elif issubclass(values.dtype.type, (np.datetime64, np.timedelta64)):
dtype = values.dtype
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
# convert the keys back to the dtype we came in
keys = Series(keys, dtype=dtype)
else:
mask = com.isnull(values)
values = com._ensure_object(values)
keys, counts = htable.value_count_object(values, mask)
result = Series(counts, index=com._values_from_object(keys))
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.levels)), fill_value=0)
result.index = bins[:-1]
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result
def mode(values):
"""Returns the mode or mode(s) of the passed Series or ndarray (sorted)"""
# must sort because hash order isn't necessarily defined.
from pandas.core.series import Series
if isinstance(values, Series):
constructor = values._constructor
values = values.values
else:
values = np.asanyarray(values)
constructor = Series
dtype = values.dtype
if com.is_integer_dtype(values.dtype):
values = com._ensure_int64(values)
result = constructor(sorted(htable.mode_int64(values)), dtype=dtype)
elif issubclass(values.dtype.type, (np.datetime64, np.timedelta64)):
dtype = values.dtype
values = values.view(np.int64)
result = constructor(sorted(htable.mode_int64(values)), dtype=dtype)
else:
mask = com.isnull(values)
values = com._ensure_object(values)
res = htable.mode_object(values, mask)
try:
res = sorted(res)
except TypeError as e:
warn("Unable to sort modes: %s" % e)
result = constructor(res, dtype=dtype)
return result
def rank(values, axis=0, method='average', na_option='keep',
ascending=True):
"""
"""
if values.ndim == 1:
f, values = _get_data_algo(values, _rank1d_functions)
ranks = f(values, ties_method=method, ascending=ascending,
na_option=na_option)
elif values.ndim == 2:
f, values = _get_data_algo(values, _rank2d_functions)
ranks = f(values, axis=axis, ties_method=method,
ascending=ascending, na_option=na_option)
return ranks
def quantile(x, q, interpolation_method='fraction'):
"""
Compute sample quantile or quantiles of the input array. For example, q=0.5
computes the median.
The `interpolation_method` parameter supports three values, namely
`fraction` (default), `lower` and `higher`. Interpolation is done only,
if the desired quantile lies between two data points `i` and `j`. For
`fraction`, the result is an interpolated value between `i` and `j`;
for `lower`, the result is `i`, for `higher` the result is `j`.
Parameters
----------
x : ndarray
Values from which to extract score.
q : scalar or array
Percentile at which to extract score.
interpolation_method : {'fraction', 'lower', 'higher'}, optional
This optional parameter specifies the interpolation method to use,
when the desired quantile lies between two data points `i` and `j`:
- fraction: `i + (j - i)*fraction`, where `fraction` is the
fractional part of the index surrounded by `i` and `j`.
-lower: `i`.
- higher: `j`.
Returns
-------
score : float
Score at percentile.
Examples
--------
>>> from scipy import stats
>>> a = np.arange(100)
>>> stats.scoreatpercentile(a, 50)
49.5
"""
x = np.asarray(x)
mask = com.isnull(x)
x = x[-mask]
values = np.sort(x)
def _get_score(at):
if len(values) == 0:
return np.nan
idx = at * (len(values) - 1)
if idx % 1 == 0:
score = values[idx]
else:
if interpolation_method == 'fraction':
score = _interpolate(values[int(idx)], values[int(idx) + 1],
idx % 1)
elif interpolation_method == 'lower':
score = values[np.floor(idx)]
elif interpolation_method == 'higher':
score = values[np.ceil(idx)]
else:
raise ValueError("interpolation_method can only be 'fraction' "
", 'lower' or 'higher'")
return score
if np.isscalar(q):
return _get_score(q)
else:
q = np.asarray(q, np.float64)
return algos.arrmap_float64(q, _get_score)
def _interpolate(a, b, fraction):
"""Returns the point at the given fraction between a and b, where
'fraction' must be between 0 and 1.
"""
return a + (b - a) * fraction
def _get_data_algo(values, func_map):
mask = None
if com.is_float_dtype(values):
f = func_map['float64']
values = com._ensure_float64(values)
elif com.is_datetime64_dtype(values):
# if we have NaT, punt to object dtype
mask = com.isnull(values)
if mask.ravel().any():
f = func_map['generic']
values = com._ensure_object(values)
values[mask] = np.nan
else:
f = func_map['int64']
values = values.view('i8')
elif com.is_integer_dtype(values):
f = func_map['int64']
values = com._ensure_int64(values)
else:
f = func_map['generic']
values = com._ensure_object(values)
return f, values
def group_position(*args):
"""
Get group position
"""
from collections import defaultdict
table = defaultdict(int)
result = []
for tup in zip(*args):
result.append(table[tup])
table[tup] += 1
return result
_rank1d_functions = {
'float64': algos.rank_1d_float64,
'int64': algos.rank_1d_int64,
'generic': algos.rank_1d_generic
}
_rank2d_functions = {
'float64': algos.rank_2d_float64,
'int64': algos.rank_2d_int64,
'generic': algos.rank_2d_generic
}
_hashtables = {
'float64': (htable.Float64HashTable, htable.Float64Vector),
'int64': (htable.Int64HashTable, htable.Int64Vector),
'generic': (htable.PyObjectHashTable, htable.ObjectVector)
}
|