Spaces:
Runtime error
Runtime error
File size: 9,270 Bytes
4610f7a |
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 |
#!/usr/local/bin/python3
# avenir-python: Machine Learning
# Author: Pranab Ghosh
#
# Licensed under the Apache License, Version 2.0 (the "License"); you
# may not use this file except in compliance with the License. You may
# obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied. See the License for the specific language governing
# permissions and limitations under the License.
import sys
import random
import time
import math
import numpy as np
import statistics
from .util import *
"""
histogram class
"""
class Histogram:
def __init__(self, min, binWidth):
"""
initializer
Parameters
min : min x
binWidth : bin width
"""
self.xmin = min
self.binWidth = binWidth
self.normalized = False
@classmethod
def createInitialized(cls, xmin, binWidth, values):
"""
create histogram instance with min domain, bin width and values
Parameters
min : min x
binWidth : bin width
values : y values
"""
instance = cls(xmin, binWidth)
instance.xmax = xmin + binWidth * (len(values) - 1)
instance.ymin = 0
instance.bins = np.array(values)
instance.fmax = 0
for v in values:
if (v > instance.fmax):
instance.fmax = v
instance.ymin = 0.0
instance.ymax = instance.fmax
return instance
@classmethod
def createWithNumBins(cls, values, numBins=20):
"""
create histogram instance values and no of bins
Parameters
values : y values
numBins : no of bins
"""
xmin = min(values)
xmax = max(values)
binWidth = (xmax + .01 - (xmin - .01)) / numBins
instance = cls(xmin, binWidth)
instance.xmax = xmax
instance.numBin = numBins
instance.bins = np.zeros(instance.numBin)
for v in values:
instance.add(v)
return instance
@classmethod
def createUninitialized(cls, xmin, xmax, binWidth):
"""
create histogram instance with no y values using domain min , max and bin width
Parameters
min : min x
max : max x
binWidth : bin width
"""
instance = cls(xmin, binWidth)
instance.xmax = xmax
instance.numBin = (xmax - xmin) / binWidth + 1
instance.bins = np.zeros(instance.numBin)
return instance
def initialize(self):
"""
set y values to 0
"""
self.bins = np.zeros(self.numBin)
def add(self, value):
"""
adds a value to a bin
Parameters
value : value
"""
bin = int((value - self.xmin) / self.binWidth)
if (bin < 0 or bin > self.numBin - 1):
print (bin)
raise ValueError("outside histogram range")
self.bins[bin] += 1.0
def normalize(self):
"""
normalize bin counts
"""
if not self.normalized:
total = self.bins.sum()
self.bins = np.divide(self.bins, total)
self.normalized = True
def cumDistr(self):
"""
cumulative dists
"""
self.normalize()
self.cbins = np.cumsum(self.bins)
return self.cbins
def distr(self):
"""
distr
"""
self.normalize()
return self.bins
def percentile(self, percent):
"""
return value corresponding to a percentile
Parameters
percent : percentile value
"""
if self.cbins is None:
raise ValueError("cumulative distribution is not available")
for i,cuml in enumerate(self.cbins):
if percent > cuml:
value = (i * self.binWidth) - (self.binWidth / 2) + \
(percent - self.cbins[i-1]) * self.binWidth / (self.cbins[i] - self.cbins[i-1])
break
return value
def max(self):
"""
return max bin value
"""
return self.bins.max()
def value(self, x):
"""
return a bin value
Parameters
x : x value
"""
bin = int((x - self.xmin) / self.binWidth)
f = self.bins[bin]
return f
def bin(self, x):
"""
return a bin index
Parameters
x : x value
"""
return int((x - self.xmin) / self.binWidth)
def cumValue(self, x):
"""
return a cumulative bin value
Parameters
x : x value
"""
bin = int((x - self.xmin) / self.binWidth)
c = self.cbins[bin]
return c
def getMinMax(self):
"""
returns x min and x max
"""
return (self.xmin, self.xmax)
def boundedValue(self, x):
"""
return x bounde by min and max
Parameters
x : x value
"""
if x < self.xmin:
x = self.xmin
elif x > self.xmax:
x = self.xmax
return x
"""
categorical histogram class
"""
class CatHistogram:
def __init__(self):
"""
initializer
"""
self.binCounts = dict()
self.counts = 0
self.normalized = False
def add(self, value):
"""
adds a value to a bin
Parameters
x : x value
"""
addToKeyedCounter(self.binCounts, value)
self.counts += 1
def normalize(self):
"""
normalize
"""
if not self.normalized:
self.binCounts = dict(map(lambda r : (r[0],r[1] / self.counts), self.binCounts.items()))
self.normalized = True
def getMode(self):
"""
get mode
"""
maxk = None
maxv = 0
#print(self.binCounts)
for k,v in self.binCounts.items():
if v > maxv:
maxk = k
maxv = v
return (maxk, maxv)
def getEntropy(self):
"""
get entropy
"""
self.normalize()
entr = 0
#print(self.binCounts)
for k,v in self.binCounts.items():
entr -= v * math.log(v)
return entr
def getUniqueValues(self):
"""
get unique values
"""
return list(self.binCounts.keys())
def getDistr(self):
"""
get distribution
"""
self.normalize()
return self.binCounts.copy()
class RunningStat:
"""
running stat class
"""
def __init__(self):
"""
initializer
"""
self.sum = 0.0
self.sumSq = 0.0
self.count = 0
@staticmethod
def create(count, sum, sumSq):
"""
creates iinstance
Parameters
sum : sum of values
sumSq : sum of valure squared
"""
rs = RunningStat()
rs.sum = sum
rs.sumSq = sumSq
rs.count = count
return rs
def add(self, value):
"""
adds new value
Parameters
value : value to add
"""
self.sum += value
self.sumSq += (value * value)
self.count += 1
def getStat(self):
"""
return mean and std deviation
"""
mean = self.sum /self. count
t = self.sumSq / (self.count - 1) - mean * mean * self.count / (self.count - 1)
sd = math.sqrt(t)
re = (mean, sd)
return re
def addGetStat(self,value):
"""
calculate mean and std deviation with new value added
Parameters
value : value to add
"""
self.add(value)
re = self.getStat()
return re
def getCount(self):
"""
return count
"""
return self.count
def getState(self):
"""
return state
"""
s = (self.count, self.sum, self.sumSq)
return s
class SlidingWindowStat:
"""
sliding window stats
"""
def __init__(self):
"""
initializer
"""
self.sum = 0.0
self.sumSq = 0.0
self.count = 0
self.values = None
@staticmethod
def create(values, sum, sumSq):
"""
creates iinstance
Parameters
sum : sum of values
sumSq : sum of valure squared
"""
sws = SlidingWindowStat()
sws.sum = sum
sws.sumSq = sumSq
self.values = values.copy()
sws.count = len(self.values)
return sws
@staticmethod
def initialize(values):
"""
creates iinstance
Parameters
values : list of values
"""
sws = SlidingWindowStat()
sws.values = values.copy()
for v in sws.values:
sws.sum += v
sws.sumSq += v * v
sws.count = len(sws.values)
return sws
@staticmethod
def createEmpty(count):
"""
creates iinstance
Parameters
count : count of values
"""
sws = SlidingWindowStat()
sws.count = count
sws.values = list()
return sws
def add(self, value):
"""
adds new value
Parameters
value : value to add
"""
self.values.append(value)
if len(self.values) > self.count:
self.sum += value - self.values[0]
self.sumSq += (value * value) - (self.values[0] * self.values[0])
self.values.pop(0)
else:
self.sum += value
self.sumSq += (value * value)
def getStat(self):
"""
calculate mean and std deviation
"""
mean = self.sum /self. count
t = self.sumSq / (self.count - 1) - mean * mean * self.count / (self.count - 1)
sd = math.sqrt(t)
re = (mean, sd)
return re
def addGetStat(self,value):
"""
calculate mean and std deviation with new value added
"""
self.add(value)
re = self.getStat()
return re
def getCount(self):
"""
return count
"""
return self.count
def getCurSize(self):
"""
return count
"""
return len(self.values)
def getState(self):
"""
return state
"""
s = (self.count, self.sum, self.sumSq)
return s
def basicStat(ldata):
"""
mean and std dev
Parameters
ldata : list of values
"""
m = statistics.mean(ldata)
s = statistics.stdev(ldata, xbar=m)
r = (m, s)
return r
def getFileColumnStat(filePath, col, delem=","):
"""
gets stats for a file column
Parameters
filePath : file path
col : col index
delem : field delemter
"""
rs = RunningStat()
for rec in fileRecGen(filePath, delem):
va = float(rec[col])
rs.add(va)
return rs.getStat()
|