/usr/lib/python3/dist-packages/astroML/correlation.py is in python3-astroml 0.3-6.
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 | """
Tools for computing two-point correlation functions.
"""
import warnings
import numpy as np
from sklearn.neighbors import BallTree
from .utils import check_random_state
# Check if scikit-learn's two-point functionality is available.
# This was added in scikit-learn version 0.14
try:
from sklearn.neighbors import KDTree
sklearn_has_two_point = True
except ImportError:
import warnings
sklearn_has_two_point = False
def uniform_sphere(RAlim, DEClim, size=1):
"""Draw a uniform sample on a sphere
Parameters
----------
RAlim : tuple
select Right Ascension between RAlim[0] and RAlim[1]
units are degrees
DEClim : tuple
select Declination between DEClim[0] and DEClim[1]
size : int (optional)
the size of the random arrays to return (default = 1)
Returns
-------
RA, DEC : ndarray
the random sample on the sphere within the given limits.
arrays have shape equal to size.
"""
zlim = np.sin(np.pi * np.asarray(DEClim) / 180.)
z = zlim[0] + (zlim[1] - zlim[0]) * np.random.random(size)
DEC = (180. / np.pi) * np.arcsin(z)
RA = RAlim[0] + (RAlim[1] - RAlim[0]) * np.random.random(size)
return RA, DEC
def ra_dec_to_xyz(ra, dec):
"""Convert ra & dec to Euclidean points
Parameters
----------
ra, dec : ndarrays
Returns
x, y, z : ndarrays
"""
sin_ra = np.sin(ra * np.pi / 180.)
cos_ra = np.cos(ra * np.pi / 180.)
sin_dec = np.sin(np.pi / 2 - dec * np.pi / 180.)
cos_dec = np.cos(np.pi / 2 - dec * np.pi / 180.)
return (cos_ra * sin_dec,
sin_ra * sin_dec,
cos_dec)
def angular_dist_to_euclidean_dist(D, r=1):
"""convert angular distances to euclidean distances"""
return 2 * r * np.sin(0.5 * D * np.pi / 180.)
def two_point(data, bins, method='standard',
data_R=None, random_state=None):
"""Two-point correlation function
Parameters
----------
data : array_like
input data, shape = [n_samples, n_features]
bins : array_like
bins within which to compute the 2-point correlation.
shape = Nbins + 1
method : string
"standard" or "landy-szalay".
data_R : array_like (optional)
if specified, use this as the random comparison sample
random_state : integer, np.random.RandomState, or None
specify the random state to use for generating background
Returns
-------
corr : ndarray
the estimate of the correlation function within each bin
shape = Nbins
"""
data = np.asarray(data)
bins = np.asarray(bins)
rng = check_random_state(random_state)
if method not in ['standard', 'landy-szalay']:
raise ValueError("method must be 'standard' or 'landy-szalay'")
if bins.ndim != 1:
raise ValueError("bins must be a 1D array")
if data.ndim == 1:
data = data[:, np.newaxis]
elif data.ndim != 2:
raise ValueError("data should be 1D or 2D")
n_samples, n_features = data.shape
Nbins = len(bins) - 1
# shuffle all but one axis to get background distribution
if data_R is None:
data_R = data.copy()
for i in range(n_features - 1):
rng.shuffle(data_R[:, i])
else:
data_R = np.asarray(data_R)
if (data_R.ndim != 2) or (data_R.shape[-1] != n_features):
raise ValueError('data_R must have same n_features as data')
factor = len(data_R) * 1. / len(data)
if sklearn_has_two_point:
# Fast two-point correlation functions added in scikit-learn v. 0.14
KDT_D = KDTree(data)
KDT_R = KDTree(data_R)
counts_DD = KDT_D.two_point_correlation(data, bins)
counts_RR = KDT_R.two_point_correlation(data_R, bins)
else:
warnings.warn("Version 0.3 of astroML will require scikit-learn "
"version 0.14 or higher for correlation function "
"calculations. Upgrade to sklearn 0.14+ now for much "
"faster correlation function calculations.")
BT_D = BallTree(data)
BT_R = BallTree(data_R)
counts_DD = np.zeros(Nbins + 1)
counts_RR = np.zeros(Nbins + 1)
for i in range(Nbins + 1):
counts_DD[i] = np.sum(BT_D.query_radius(data, bins[i],
count_only=True))
counts_RR[i] = np.sum(BT_R.query_radius(data_R, bins[i],
count_only=True))
DD = np.diff(counts_DD)
RR = np.diff(counts_RR)
# check for zero in the denominator
RR_zero = (RR == 0)
RR[RR_zero] = 1
if method == 'standard':
corr = factor ** 2 * DD / RR - 1
elif method == 'landy-szalay':
if sklearn_has_two_point:
counts_DR = KDT_R.two_point_correlation(data, bins)
else:
counts_DR = np.zeros(Nbins + 1)
for i in range(Nbins + 1):
counts_DR[i] = np.sum(BT_R.query_radius(data, bins[i],
count_only=True))
DR = np.diff(counts_DR)
corr = (factor ** 2 * DD - 2 * factor * DR + RR) / RR
corr[RR_zero] = np.nan
return corr
def bootstrap_two_point(data, bins, Nbootstrap=10,
method='standard', return_bootstraps=False,
random_state=None):
"""Bootstrapped two-point correlation function
Parameters
----------
data : array_like
input data, shape = [n_samples, n_features]
bins : array_like
bins within which to compute the 2-point correlation.
shape = Nbins + 1
Nbootstrap : integer
number of bootstrap resamples to perform (default = 10)
method : string
"standard" or "landy-szalay".
return_bootstraps: bool
if True, return full bootstrapped samples
random_state : integer, np.random.RandomState, or None
specify the random state to use for generating background
Returns
-------
corr, corr_err : ndarrays
the estimate of the correlation function and the bootstrap
error within each bin. shape = Nbins
"""
data = np.asarray(data)
bins = np.asarray(bins)
rng = check_random_state(random_state)
if method not in ['standard', 'landy-szalay']:
raise ValueError("method must be 'standard' or 'landy-szalay'")
if bins.ndim != 1:
raise ValueError("bins must be a 1D array")
if data.ndim == 1:
data = data[:, np.newaxis]
elif data.ndim != 2:
raise ValueError("data should be 1D or 2D")
if Nbootstrap < 2:
raise ValueError("Nbootstrap must be greater than 1")
n_samples, n_features = data.shape
# get the baseline estimate
corr = two_point(data, bins, method=method, random_state=rng)
bootstraps = np.zeros((Nbootstrap, len(corr)))
for i in range(Nbootstrap):
indices = rng.randint(0, n_samples, n_samples)
bootstraps[i] = two_point(data[indices, :], bins, method=method,
random_state=rng)
# use masked std dev in case of NaNs
corr_err = np.asarray(np.ma.masked_invalid(bootstraps).std(0, ddof=1))
if return_bootstraps:
return corr, corr_err, bootstraps
else:
return corr, corr_err
def two_point_angular(ra, dec, bins, method='standard', random_state=None):
"""Angular two-point correlation function
A separate function is needed because angular distances are not
euclidean, and random sampling needs to take into account the
spherical volume element.
Parameters
----------
ra : array_like
input right ascention, shape = (n_samples,)
dec : array_like
input declination
bins : array_like
bins within which to compute the 2-point correlation.
shape = Nbins + 1
method : string
"standard" or "landy-szalay".
random_state : integer, np.random.RandomState, or None
specify the random state to use for generating background
Returns
-------
corr : ndarray
the estimate of the correlation function within each bin
shape = Nbins
"""
ra = np.asarray(ra)
dec = np.asarray(dec)
rng = check_random_state(random_state)
if method not in ['standard', 'landy-szalay']:
raise ValueError("method must be 'standard' or 'landy-szalay'")
if bins.ndim != 1:
raise ValueError("bins must be a 1D array")
if (ra.ndim != 1) or (dec.ndim != 1) or (ra.shape != dec.shape):
raise ValueError('ra and dec must be 1-dimensional '
'arrays of the same length')
n_features = len(ra)
Nbins = len(bins) - 1
# draw a random sample with N points
ra_R, dec_R = uniform_sphere((min(ra), max(ra)),
(min(dec), max(dec)),
2 * len(ra))
data = np.asarray(ra_dec_to_xyz(ra, dec), order='F').T
data_R = np.asarray(ra_dec_to_xyz(ra_R, dec_R), order='F').T
# convert spherical bins to cartesian bins
bins_transform = angular_dist_to_euclidean_dist(bins)
return two_point(data, bins_transform, method=method,
data_R=data_R, random_state=rng)
def bootstrap_two_point_angular(ra, dec, bins, method='standard',
Nbootstraps=10, random_state=None):
"""Angular two-point correlation function
A separate function is needed because angular distances are not
euclidean, and random sampling needs to take into account the
spherical volume element.
Parameters
----------
ra : array_like
input right ascention, shape = (n_samples,)
dec : array_like
input declination
bins : array_like
bins within which to compute the 2-point correlation.
shape = Nbins + 1
method : string
"standard" or "landy-szalay".
Nbootstraps : int
number of bootstrap resamples
random_state : integer, np.random.RandomState, or None
specify the random state to use for generating background
Returns
-------
corr : ndarray
the estimate of the correlation function within each bin
shape = Nbins
dcorr : ndarray
error estimate on dcorr (sample standard deviation of
bootstrap resamples)
bootstraps : ndarray
The full sample of bootstraps used to compute corr and dcorr
"""
ra = np.asarray(ra)
dec = np.asarray(dec)
rng = check_random_state(random_state)
if method not in ['standard', 'landy-szalay']:
raise ValueError("method must be 'standard' or 'landy-szalay'")
if bins.ndim != 1:
raise ValueError("bins must be a 1D array")
if (ra.ndim != 1) or (dec.ndim != 1) or (ra.shape != dec.shape):
raise ValueError('ra and dec must be 1-dimensional '
'arrays of the same length')
n_features = len(ra)
Nbins = len(bins) - 1
data = np.asarray(ra_dec_to_xyz(ra, dec), order='F').T
# convert spherical bins to cartesian bins
bins_transform = angular_dist_to_euclidean_dist(bins)
bootstraps = []
for i in range(Nbootstraps):
# draw a random sample with N points
ra_R, dec_R = uniform_sphere((min(ra), max(ra)),
(min(dec), max(dec)),
2 * len(ra))
data_R = np.asarray(ra_dec_to_xyz(ra_R, dec_R), order='F').T
if i > 0:
# random sample of the data
ind = np.random.randint(0, data.shape[0], data.shape[0])
data_b = data[ind]
else:
data_b = data
bootstraps.append(two_point(data_b, bins_transform, method=method,
data_R=data_R, random_state=rng))
bootstraps = np.asarray(bootstraps)
corr = np.mean(bootstraps, 0)
corr_err = np.std(bootstraps, 0, ddof=1)
return corr, corr_err, bootstraps
|