def plothist(x, bin=None, nbins=None, xrange=None, yrange=None, min=None,
max=None, overplot=False, color='black', xlog=False, ylog=False,
nan=False, weights=None, norm=False, kernel=None, retpoints=False,
adaptive=False, adaptive_thresh=30, adaptive_depth=[2,10],
weight_norm=False, apply_func=None, **kw):
"""
Plot the 1D histogram
Example:
>> plothist(dat, bin=0.1, min=0, max=3)
Keyword parameters:
------------------
bin
the binsize(float)
nbins
number of bins(integer)
It cannot be specified together with the bin= parameter
xlog, ylog
log the appropriate axis
weights
the 1-D array of weights used in the histogram creation
nan
boolean flag to ignore nan's
norm
boolean flag to normalize the histogram by the peak value
min,max
range of data for which the histogram is constructed
retpoints
boolean parameter controlling whether to return or not the
computed histogram.
If yes the tuple with two arrays (bin centers, Number of points in bins)
is returned
overplot
boolean parameter for overplotting
adaptive
boolean for turning on/off the adaptive regime of
histogramming (adaptive bin size).
If True weights, nbins, bin,kernel parameters are ignored
adaptive_thresh
the limiting number of points in the bin for the adaptive
histogramming (default 30)
adaptive_depth
the list of two integers for the detalisation levels of
adaptive histogramming (default [2,10])
weight_norm
if True the value in each bin is mean weight of points within
the bin
"""
if nan:
ind = numpy.isfinite(x)
if weights is not None:
ind = numpy.isfinite(weights)&ind
dat = x[ind]
if weights is not None:
weights =weights[ind]
else:
dat = x
maxNone = False
if min is None:
min = numpy.min(dat)
if max is None:
maxNone = True
max = numpy.max(dat)
if bin is None and nbins is None:
nbins = 100
bin = (max - min) * 1. / nbins
elif nbins is None:
nbins = int(math.ceil((max - min) * 1. / bin))
if maxNone:
max = min + nbins * bin
elif bin is None:
bin = (max - min) * 1. / nbins
else:
warnings.warn("both bin= and nbins= keywords were specified in the plothist call",RuntimeWarning)
pass
# if both nbins and bin are defined I don't do anything
# it may be non-intuitive if kernel option is used, because
# it uses both nbins and bin options
if kernel is None:
if not adaptive:
if not np.isscalar(weights):
hh, loc = numpy.histogram(dat, range=(min, max), bins=nbins, weights=weights)
else:
hh, loc = numpy.histogram(dat, range=(min, max), bins=nbins)
hh = hh * weights
if weight_norm:
hh1, loc = numpy.histogram(dat, range=(min, max), bins=nbins, weights=None)
hh = hh*1./hh1
else:
import adabinner
hh, loc = adabinner.hist(dat, xmin=min, xmax=max, hi=adaptive_depth,
thresh=adaptive_thresh)
hh1 = np.repeat(hh,2)
loc1 = np.concatenate(([loc[0]],np.repeat(loc[1:-1],2),[loc[-1]]))
else:
loc1=numpy.linspace(min,max,nbins*5)
import statistics
if weights is not None:
hh1 = statistics.pdf( dat, loc1, h=bin/2.,kernel=kernel,weight=weights)*bin*len(dat)
else:
hh1 = statistics.pdf( dat, loc1, h=bin/2.,kernel=kernel)*bin*len(dat)
if overplot:
func = oplot
else:
func = plot
if norm:
hh1=hh1*1./hh1.max()
kw['ps'] = kw.get('ps') or 0
if 'yr' not in kw:
kw['yr']=[hh1.min(),hh1.max()]
if 'xr' not in kw:
kw['xr']=[min,max]
if apply_func is not None:
hh1 = apply_func (loc1,hh1)
func(loc1, hh1, color=color,
xlog=xlog, ylog=ylog, **kw)
if retpoints:
return 0.5*(loc[1:]+loc[:-1]),hh
def plothist(x,
bin=None,
nbins=None,
xrange=None,
yrange=None,
min=None,
max=None,
overplot=False,
color='black',
xlog=False,
ylog=False,
nan=False,
weights=None,
norm=False,
kernel=None,
retpoints=False,
adaptive=False,
adaptive_thresh=30,
adaptive_depth=[2, 10],
weight_norm=False,
apply_func=None,
statistic=None,
knuth=False,
cumulative=False,
**kw):
"""
Plot the 1D histogram
Example:
>> plothist(dat, bin=0.1, min=0, max=3)
Keyword parameters:
------------------
bin
the binsize(float)
nbins
number of bins(integer)
It cannot be specified together with the bin= parameter
xlog, ylog
log the appropriate axis
weights
the 1-D array of weights used in the histogram creation
nan
boolean flag to ignore nan's
norm
boolean flag to normalize the histogram by the peak value
min,max
range of data for which the histogram is constructed
retpoints
boolean parameter controlling whether to return or not the
computed histogram. If yes the tuple with two arrays
(bin centers, Number of points in bins) is returned
overplot
boolean parameter for overplotting
adaptive
boolean for turning on/off the adaptive regime of
histogramming (adaptive bin size).
If True weights, nbins, bin,kernel parameters are ignored
adaptive_thresh
the limiting number of points in the bin for the adaptive
histogramming (default 30)
adaptive_depth
the list of two integers for the detalisation levels of
adaptive histogramming (default [2,10])
weight_norm
if True the value in each bin is mean weight of points within
the bin
"""
if nan:
ind = np.isfinite(x)
if weights is not None:
ind = np.isfinite(weights) & ind
dat = x[ind]
if weights is not None:
weights = weights[ind]
else:
dat = x
maxNone = False
if min is None:
min = np.nanmin(dat)
if max is None:
maxNone = True
max = np.nanmax(dat)
if bin is None and nbins is None:
if not knuth:
nbins = 100
else:
nbins = __findKnuth(dat, min, max)
bin = (max - min) * 1. / nbins
elif nbins is None:
nbins = int(math.ceil((max - min) * 1. / bin))
if maxNone:
max = min + nbins * bin
elif bin is None:
bin = (max - min) * 1. / nbins
else:
warnings.warn(
'both bin= and nbins= keywords were specified in ' +
'the plothist call', RuntimeWarning)
pass
# if both nbins and bin are defined I don't do anything
# it may be non-intuitive if kernel option is used, because
# it uses both nbins and bin options
if cumulative:
if (kernel is not None or adaptive or weights is not None):
raise RuntimeError(
'cumulative is incompatible with weights, kernel ' +
'or adaptive options')
if kernel is None:
if not adaptive:
if np.isscalar(weights) and weights is not None:
weights = np.zeros_like(dat) + weights
if statistic is None:
hh, loc = np.histogram(dat,
range=(min, max),
bins=nbins,
weights=weights)
if weight_norm:
hh1, loc = np.histogram(dat,
range=(min, max),
bins=nbins,
weights=None)
hh = hh * 1. / hh1
else:
S = scipy.stats.binned_statistic(dat,
weights,
statistic,
range=[min, max],
bins=nbins)
hh = S.statistic
loc = S.bin_edges
else:
import adabinner
hh, loc = adabinner.hist(dat,
xmin=min,
xmax=max,
hi=adaptive_depth,
thresh=adaptive_thresh)
if cumulative:
hh = np.cumsum(hh)
hh1 = np.repeat(hh, 2)
loc1 = np.concatenate(([loc[0]], np.repeat(loc[1:-1], 2), [loc[-1]]))
else:
loc1 = np.linspace(min, max, nbins * 10)
import sklearn.neighbors
xind = np.isfinite(dat)
kde = sklearn.neighbors.KernelDensity(bandwidth=bin, kernel=kernel)
kde.fit(np.asarray(dat[xind]).flatten().reshape(-1, 1))
hh1 = np.exp(kde.score_samples(loc1.reshape(-1, 1)))
if weights is not None:
print('WARNING weights ignored for KDE !')
if overplot:
func = oplot
else:
func = plot
if norm:
hh1 = hh1 * 1. / hh1.max()
kw['ps'] = kw.get('ps') or 0
if 'yr' not in kw:
kw['yr'] = [np.nanmin(hh1), np.nanmax(hh1)]
if 'xr' not in kw:
kw['xr'] = [min, max]
if apply_func is not None:
hh1 = apply_func(loc1, hh1)
func(loc1, hh1, color=color, xlog=xlog, ylog=ylog, **kw)
if retpoints:
return 0.5 * (loc[1:] + loc[:-1]), hh