forked from ukosuagwu/scikit-learn
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path_utils.pyx
More file actions
447 lines (362 loc) · 15.7 KB
/
Copy path_utils.pyx
File metadata and controls
447 lines (362 loc) · 15.7 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
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
# Authors: Gilles Louppe <g.louppe@gmail.com>
# Peter Prettenhofer <peter.prettenhofer@gmail.com>
# Arnaud Joly <arnaud.v.joly@gmail.com>
# Jacob Schreiber <jmschreiber91@gmail.com>
# Nelson Liu <nelson@nelsonliu.me>
#
#
# License: BSD 3 clause
from libc.stdlib cimport free
from libc.stdlib cimport realloc
from libc.math cimport log as ln
cimport numpy as cnp
cnp.import_array()
from ..utils._random cimport our_rand_r
# =============================================================================
# Helper functions
# =============================================================================
cdef realloc_ptr safe_realloc(realloc_ptr* p, size_t nelems) nogil except *:
# sizeof(realloc_ptr[0]) would be more like idiomatic C, but causes Cython
# 0.20.1 to crash.
cdef size_t nbytes = nelems * sizeof(p[0][0])
if nbytes / sizeof(p[0][0]) != nelems:
# Overflow in the multiplication
with gil:
raise MemoryError("could not allocate (%d * %d) bytes"
% (nelems, sizeof(p[0][0])))
cdef realloc_ptr tmp = <realloc_ptr>realloc(p[0], nbytes)
if tmp == NULL:
with gil:
raise MemoryError("could not allocate %d bytes" % nbytes)
p[0] = tmp
return tmp # for convenience
def _realloc_test():
# Helper for tests. Tries to allocate <size_t>(-1) / 2 * sizeof(size_t)
# bytes, which will always overflow.
cdef SIZE_t* p = NULL
safe_realloc(&p, <size_t>(-1) / 2)
if p != NULL:
free(p)
assert False
cdef inline cnp.ndarray sizet_ptr_to_ndarray(SIZE_t* data, SIZE_t size):
"""Return copied data as 1D numpy array of intp's."""
cdef cnp.npy_intp shape[1]
shape[0] = <cnp.npy_intp> size
return cnp.PyArray_SimpleNewFromData(1, shape, cnp.NPY_INTP, data).copy()
cdef inline SIZE_t rand_int(SIZE_t low, SIZE_t high,
UINT32_t* random_state) nogil:
"""Generate a random integer in [low; end)."""
return low + our_rand_r(random_state) % (high - low)
cdef inline double rand_uniform(double low, double high,
UINT32_t* random_state) nogil:
"""Generate a random double in [low; high)."""
return ((high - low) * <double> our_rand_r(random_state) /
<double> RAND_R_MAX) + low
cdef inline double log(double x) nogil:
return ln(x) / ln(2.0)
# =============================================================================
# WeightedPQueue data structure
# =============================================================================
cdef class WeightedPQueue:
"""A priority queue class, always sorted in increasing order.
Attributes
----------
capacity : SIZE_t
The capacity of the priority queue.
array_ptr : SIZE_t
The water mark of the priority queue; the priority queue grows from
left to right in the array ``array_``. ``array_ptr`` is always
less than ``capacity``.
array_ : WeightedPQueueRecord*
The array of priority queue records. The minimum element is on the
left at index 0, and the maximum element is on the right at index
``array_ptr-1``.
"""
def __cinit__(self, SIZE_t capacity):
self.capacity = capacity
self.array_ptr = 0
safe_realloc(&self.array_, capacity)
def __dealloc__(self):
free(self.array_)
cdef int reset(self) nogil except -1:
"""Reset the WeightedPQueue to its state at construction
Return -1 in case of failure to allocate memory (and raise MemoryError)
or 0 otherwise.
"""
self.array_ptr = 0
# Since safe_realloc can raise MemoryError, use `except *`
safe_realloc(&self.array_, self.capacity)
return 0
cdef bint is_empty(self) nogil:
return self.array_ptr <= 0
cdef SIZE_t size(self) nogil:
return self.array_ptr
cdef int push(self, DOUBLE_t data, DOUBLE_t weight) nogil except -1:
"""Push record on the array.
Return -1 in case of failure to allocate memory (and raise MemoryError)
or 0 otherwise.
"""
cdef SIZE_t array_ptr = self.array_ptr
cdef WeightedPQueueRecord* array = NULL
cdef SIZE_t i
# Resize if capacity not sufficient
if array_ptr >= self.capacity:
self.capacity *= 2
# Since safe_realloc can raise MemoryError, use `except -1`
safe_realloc(&self.array_, self.capacity)
# Put element as last element of array
array = self.array_
array[array_ptr].data = data
array[array_ptr].weight = weight
# bubble last element up according until it is sorted
# in ascending order
i = array_ptr
while(i != 0 and array[i].data < array[i-1].data):
array[i], array[i-1] = array[i-1], array[i]
i -= 1
# Increase element count
self.array_ptr = array_ptr + 1
return 0
cdef int remove(self, DOUBLE_t data, DOUBLE_t weight) nogil:
"""Remove a specific value/weight record from the array.
Returns 0 if successful, -1 if record not found."""
cdef SIZE_t array_ptr = self.array_ptr
cdef WeightedPQueueRecord* array = self.array_
cdef SIZE_t idx_to_remove = -1
cdef SIZE_t i
if array_ptr <= 0:
return -1
# find element to remove
for i in range(array_ptr):
if array[i].data == data and array[i].weight == weight:
idx_to_remove = i
break
if idx_to_remove == -1:
return -1
# shift the elements after the removed element
# to the left.
for i in range(idx_to_remove, array_ptr-1):
array[i] = array[i+1]
self.array_ptr = array_ptr - 1
return 0
cdef int pop(self, DOUBLE_t* data, DOUBLE_t* weight) nogil:
"""Remove the top (minimum) element from array.
Returns 0 if successful, -1 if nothing to remove."""
cdef SIZE_t array_ptr = self.array_ptr
cdef WeightedPQueueRecord* array = self.array_
cdef SIZE_t i
if array_ptr <= 0:
return -1
data[0] = array[0].data
weight[0] = array[0].weight
# shift the elements after the removed element
# to the left.
for i in range(0, array_ptr-1):
array[i] = array[i+1]
self.array_ptr = array_ptr - 1
return 0
cdef int peek(self, DOUBLE_t* data, DOUBLE_t* weight) nogil:
"""Write the top element from array to a pointer.
Returns 0 if successful, -1 if nothing to write."""
cdef WeightedPQueueRecord* array = self.array_
if self.array_ptr <= 0:
return -1
# Take first value
data[0] = array[0].data
weight[0] = array[0].weight
return 0
cdef DOUBLE_t get_weight_from_index(self, SIZE_t index) nogil:
"""Given an index between [0,self.current_capacity], access
the appropriate heap and return the requested weight"""
cdef WeightedPQueueRecord* array = self.array_
# get weight at index
return array[index].weight
cdef DOUBLE_t get_value_from_index(self, SIZE_t index) nogil:
"""Given an index between [0,self.current_capacity], access
the appropriate heap and return the requested value"""
cdef WeightedPQueueRecord* array = self.array_
# get value at index
return array[index].data
# =============================================================================
# WeightedMedianCalculator data structure
# =============================================================================
cdef class WeightedMedianCalculator:
"""A class to handle calculation of the weighted median from streams of
data. To do so, it maintains a parameter ``k`` such that the sum of the
weights in the range [0,k) is greater than or equal to half of the total
weight. By minimizing the value of ``k`` that fulfills this constraint,
calculating the median is done by either taking the value of the sample
at index ``k-1`` of ``samples`` (samples[k-1].data) or the average of
the samples at index ``k-1`` and ``k`` of ``samples``
((samples[k-1] + samples[k]) / 2).
Attributes
----------
initial_capacity : SIZE_t
The initial capacity of the WeightedMedianCalculator.
samples : WeightedPQueue
Holds the samples (consisting of values and their weights) used in the
weighted median calculation.
total_weight : DOUBLE_t
The sum of the weights of items in ``samples``. Represents the total
weight of all samples used in the median calculation.
k : SIZE_t
Index used to calculate the median.
sum_w_0_k : DOUBLE_t
The sum of the weights from samples[0:k]. Used in the weighted
median calculation; minimizing the value of ``k`` such that
``sum_w_0_k`` >= ``total_weight / 2`` provides a mechanism for
calculating the median in constant time.
"""
def __cinit__(self, SIZE_t initial_capacity):
self.initial_capacity = initial_capacity
self.samples = WeightedPQueue(initial_capacity)
self.total_weight = 0
self.k = 0
self.sum_w_0_k = 0
cdef SIZE_t size(self) nogil:
"""Return the number of samples in the
WeightedMedianCalculator"""
return self.samples.size()
cdef int reset(self) nogil except -1:
"""Reset the WeightedMedianCalculator to its state at construction
Return -1 in case of failure to allocate memory (and raise MemoryError)
or 0 otherwise.
"""
# samples.reset (WeightedPQueue.reset) uses safe_realloc, hence
# except -1
self.samples.reset()
self.total_weight = 0
self.k = 0
self.sum_w_0_k = 0
return 0
cdef int push(self, DOUBLE_t data, DOUBLE_t weight) nogil except -1:
"""Push a value and its associated weight to the WeightedMedianCalculator
Return -1 in case of failure to allocate memory (and raise MemoryError)
or 0 otherwise.
"""
cdef int return_value
cdef DOUBLE_t original_median = 0.0
if self.size() != 0:
original_median = self.get_median()
# samples.push (WeightedPQueue.push) uses safe_realloc, hence except -1
return_value = self.samples.push(data, weight)
self.update_median_parameters_post_push(data, weight,
original_median)
return return_value
cdef int update_median_parameters_post_push(
self, DOUBLE_t data, DOUBLE_t weight,
DOUBLE_t original_median) nogil:
"""Update the parameters used in the median calculation,
namely `k` and `sum_w_0_k` after an insertion"""
# trivial case of one element.
if self.size() == 1:
self.k = 1
self.total_weight = weight
self.sum_w_0_k = self.total_weight
return 0
# get the original weighted median
self.total_weight += weight
if data < original_median:
# inserting below the median, so increment k and
# then update self.sum_w_0_k accordingly by adding
# the weight that was added.
self.k += 1
# update sum_w_0_k by adding the weight added
self.sum_w_0_k += weight
# minimize k such that sum(W[0:k]) >= total_weight / 2
# minimum value of k is 1
while(self.k > 1 and ((self.sum_w_0_k -
self.samples.get_weight_from_index(self.k-1))
>= self.total_weight / 2.0)):
self.k -= 1
self.sum_w_0_k -= self.samples.get_weight_from_index(self.k)
return 0
if data >= original_median:
# inserting above or at the median
# minimize k such that sum(W[0:k]) >= total_weight / 2
while(self.k < self.samples.size() and
(self.sum_w_0_k < self.total_weight / 2.0)):
self.k += 1
self.sum_w_0_k += self.samples.get_weight_from_index(self.k-1)
return 0
cdef int remove(self, DOUBLE_t data, DOUBLE_t weight) nogil:
"""Remove a value from the MedianHeap, removing it
from consideration in the median calculation
"""
cdef int return_value
cdef DOUBLE_t original_median = 0.0
if self.size() != 0:
original_median = self.get_median()
return_value = self.samples.remove(data, weight)
self.update_median_parameters_post_remove(data, weight,
original_median)
return return_value
cdef int pop(self, DOUBLE_t* data, DOUBLE_t* weight) nogil:
"""Pop a value from the MedianHeap, starting from the
left and moving to the right.
"""
cdef int return_value
cdef double original_median = 0.0
if self.size() != 0:
original_median = self.get_median()
# no elements to pop
if self.samples.size() == 0:
return -1
return_value = self.samples.pop(data, weight)
self.update_median_parameters_post_remove(data[0],
weight[0],
original_median)
return return_value
cdef int update_median_parameters_post_remove(
self, DOUBLE_t data, DOUBLE_t weight,
double original_median) nogil:
"""Update the parameters used in the median calculation,
namely `k` and `sum_w_0_k` after a removal"""
# reset parameters because it there are no elements
if self.samples.size() == 0:
self.k = 0
self.total_weight = 0
self.sum_w_0_k = 0
return 0
# trivial case of one element.
if self.samples.size() == 1:
self.k = 1
self.total_weight -= weight
self.sum_w_0_k = self.total_weight
return 0
# get the current weighted median
self.total_weight -= weight
if data < original_median:
# removing below the median, so decrement k and
# then update self.sum_w_0_k accordingly by subtracting
# the removed weight
self.k -= 1
# update sum_w_0_k by removing the weight at index k
self.sum_w_0_k -= weight
# minimize k such that sum(W[0:k]) >= total_weight / 2
# by incrementing k and updating sum_w_0_k accordingly
# until the condition is met.
while(self.k < self.samples.size() and
(self.sum_w_0_k < self.total_weight / 2.0)):
self.k += 1
self.sum_w_0_k += self.samples.get_weight_from_index(self.k-1)
return 0
if data >= original_median:
# removing above the median
# minimize k such that sum(W[0:k]) >= total_weight / 2
while(self.k > 1 and ((self.sum_w_0_k -
self.samples.get_weight_from_index(self.k-1))
>= self.total_weight / 2.0)):
self.k -= 1
self.sum_w_0_k -= self.samples.get_weight_from_index(self.k)
return 0
cdef DOUBLE_t get_median(self) nogil:
"""Write the median to a pointer, taking into account
sample weights."""
if self.sum_w_0_k == (self.total_weight / 2.0):
# split median
return (self.samples.get_value_from_index(self.k) +
self.samples.get_value_from_index(self.k-1)) / 2.0
if self.sum_w_0_k > (self.total_weight / 2.0):
# whole median
return self.samples.get_value_from_index(self.k-1)