/usr/lib/python3/dist-packages/astroML/density_estimation/histtools.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 | """
Tools for working with distributions
"""
import numpy as np
from astroML.density_estimation import bayesian_blocks
from scipy.special import gammaln
from scipy import optimize
def scotts_bin_width(data, return_bins=False):
r"""Return the optimal histogram bin width using Scott's rule:
Parameters
----------
data : array-like, ndim=1
observed (one-dimensional) data
return_bins : bool (optional)
if True, then return the bin edges
Returns
-------
width : float
optimal bin width using Scott's rule
bins : ndarray
bin edges: returned if `return_bins` is True
Notes
-----
The optimal bin width is
.. math::
\Delta_b = \frac{3.5\sigma}{n^{1/3}}
where :math:`\sigma` is the standard deviation of the data, and
:math:`n` is the number of data points.
See Also
--------
knuth_bin_width
freedman_bin_width
astroML.plotting.hist
"""
data = np.asarray(data)
if data.ndim != 1:
raise ValueError("data should be one-dimensional")
n = data.size
sigma = np.std(data)
dx = 3.5 * sigma * 1. / (n ** (1. / 3))
if return_bins:
Nbins = np.ceil((data.max() - data.min()) * 1. / dx)
Nbins = max(1, Nbins)
bins = data.min() + dx * np.arange(Nbins + 1)
return dx, bins
else:
return dx
def freedman_bin_width(data, return_bins=False):
r"""Return the optimal histogram bin width using the Freedman-Diaconis rule
Parameters
----------
data : array-like, ndim=1
observed (one-dimensional) data
return_bins : bool (optional)
if True, then return the bin edges
Returns
-------
width : float
optimal bin width using Scott's rule
bins : ndarray
bin edges: returned if `return_bins` is True
Notes
-----
The optimal bin width is
.. math::
\Delta_b = \frac{2(q_{75} - q_{25})}{n^{1/3}}
where :math:`q_{N}` is the :math:`N` percent quartile of the data, and
:math:`n` is the number of data points.
See Also
--------
knuth_bin_width
scotts_bin_width
astroML.plotting.hist
"""
data = np.asarray(data)
if data.ndim != 1:
raise ValueError("data should be one-dimensional")
n = data.size
if n < 4:
raise ValueError("data should have more than three entries")
dsorted = np.sort(data)
v25 = dsorted[n // 4 - 1]
v75 = dsorted[(3 * n) // 4 - 1]
dx = 2 * (v75 - v25) * 1. / (n ** (1. / 3))
if return_bins:
Nbins = np.ceil((dsorted[-1] - dsorted[0]) * 1. / dx)
Nbins = max(1, Nbins)
bins = dsorted[0] + dx * np.arange(Nbins + 1)
return dx, bins
else:
return dx
class KnuthF(object):
r"""Class which implements the function minimized by knuth_bin_width
Parameters
----------
data : array-like, one dimension
data to be histogrammed
Notes
-----
the function F is given by
.. math::
F(M|x,I) = n\log(M) + \log\Gamma(\frac{M}{2})
- M\log\Gamma(\frac{1}{2})
- \log\Gamma(\frac{2n+M}{2})
+ \sum_{k=1}^M \log\Gamma(n_k + \frac{1}{2})
where :math:`\Gamma` is the Gamma function, :math:`n` is the number of
data points, :math:`n_k` is the number of measurements in bin :math:`k`.
See Also
--------
knuth_bin_width
astroML.plotting.hist
"""
def __init__(self, data):
self.data = np.array(data, copy=True)
if self.data.ndim != 1:
raise ValueError("data should be 1-dimensional")
self.data.sort()
self.n = self.data.size
def bins(self, M):
"""Return the bin edges given a width dx"""
return np.linspace(self.data[0], self.data[-1], int(M) + 1)
def __call__(self, M):
return self.eval(M)
def eval(self, M):
"""Evaluate the Knuth function
Parameters
----------
dx : float
Width of bins
Returns
-------
F : float
evaluation of the negative Knuth likelihood function:
smaller values indicate a better fit.
"""
M = int(M)
if M <= 0:
return np.inf
bins = self.bins(M)
nk, bins = np.histogram(self.data, bins)
return -(self.n * np.log(M)
+ gammaln(0.5 * M)
- M * gammaln(0.5)
- gammaln(self.n + 0.5 * M)
+ np.sum(gammaln(nk + 0.5)))
def knuth_bin_width(data, return_bins=False, disp=True):
r"""Return the optimal histogram bin width using Knuth's rule [1]_
Parameters
----------
data : array-like, ndim=1
observed (one-dimensional) data
return_bins : bool (optional)
if True, then return the bin edges
Returns
-------
dx : float
optimal bin width. Bins are measured starting at the first data point.
bins : ndarray
bin edges: returned if `return_bins` is True
Notes
-----
The optimal number of bins is the value M which maximizes the function
.. math::
F(M|x,I) = n\log(M) + \log\Gamma(\frac{M}{2})
- M\log\Gamma(\frac{1}{2})
- \log\Gamma(\frac{2n+M}{2})
+ \sum_{k=1}^M \log\Gamma(n_k + \frac{1}{2})
where :math:`\Gamma` is the Gamma function, :math:`n` is the number of
data points, :math:`n_k` is the number of measurements in bin :math:`k`.
References
----------
.. [1] Knuth, K.H. "Optimal Data-Based Binning for Histograms".
arXiv:0605197, 2006
See Also
--------
KnuthF
freedman_bin_width
scotts_bin_width
"""
knuthF = KnuthF(data)
dx0, bins0 = freedman_bin_width(data, True)
M0 = len(bins0) - 1
M = optimize.fmin(knuthF, len(bins0), disp=disp)[0]
bins = knuthF.bins(M)
dx = bins[1] - bins[0]
if return_bins:
return dx, bins
else:
return dx
def histogram(a, bins=10, range=None, **kwargs):
"""Enhanced histogram
This is a histogram function that enables the use of more sophisticated
algorithms for determining bins. Aside from the `bins` argument allowing
a string specified how bins are computed, the parameters are the same
as numpy.histogram().
Parameters
----------
a : array_like
array of data to be histogrammed
bins : int or list or str (optional)
If bins is a string, then it must be one of:
'blocks' : use bayesian blocks for dynamic bin widths
'knuth' : use Knuth's rule to determine bins
'scotts' : use Scott's rule to determine bins
'freedman' : use the Freedman-diaconis rule to determine bins
range : tuple or None (optional)
the minimum and maximum range for the histogram. If not specified,
it will be (x.min(), x.max())
other keyword arguments are described in numpy.hist().
Returns
-------
hist : array
The values of the histogram. See `normed` and `weights` for a
description of the possible semantics.
bin_edges : array of dtype float
Return the bin edges ``(length(hist)+1)``.
See Also
--------
numpy.histogram
astroML.plotting.hist
"""
a = np.asarray(a)
# if range is specified, we need to truncate the data for
# the bin-finding routines
if (range is not None and (bins in ['blocks', 'knuth',
'scotts', 'freedman'])):
a = a[(a >= range[0]) & (a <= range[1])]
if bins == 'blocks':
bins = bayesian_blocks(a)
elif bins == 'knuth':
da, bins = knuth_bin_width(a, True)
elif bins == 'scotts':
da, bins = scotts_bin_width(a, True)
elif bins == 'freedman':
da, bins = freedman_bin_width(a, True)
elif isinstance(bins, str):
raise ValueError("unrecognized bin code: '%s'" % bins)
return np.histogram(a, bins, range, **kwargs)
|