def test_density(self):
# Check that the integral of the density equals 1.
n = 100
v = np.random.rand(n)
a, b = histogram(v, density=True)
area = np.sum(a * np.diff(b))
assert_almost_equal(area, 1)
# Check with non-constant bin widths
v = np.arange(10)
bins = [0, 1, 3, 6, 10]
a, b = histogram(v, bins, density=True)
assert_array_equal(a, .1)
assert_equal(np.sum(a * np.diff(b)), 1)
# Test that passing False works too
a, b = histogram(v, bins, density=False)
assert_array_equal(a, [1, 2, 3, 4])
# Variale bin widths are especially useful to deal with
# infinities.
v = np.arange(10)
bins = [0, 1, 3, 6, np.inf]
a, b = histogram(v, bins, density=True)
assert_array_equal(a, [.1, .1, .1, 0.])
# Taken from a bug report from N. Becker on the numpy-discussion
# mailing list Aug. 6, 2010.
counts, dmy = np.histogram([1, 2, 3, 4], [0.5, 1.5, np.inf],
density=True)
assert_equal(counts, [.25, 0])
def _unique1d(ar,
return_index=False,
return_inverse=False,
return_counts=False):
"""
Find the unique elements of an array, ignoring shape.
"""
ar = np.asanyarray(ar).flatten()
optional_indices = return_index or return_inverse
if optional_indices:
perm = ar.argsort(kind='mergesort' if return_index else 'quicksort')
aux = ar[perm]
else:
ar.sort()
aux = ar
mask = np.empty(aux.shape, dtype=np.bool_)
mask[:1] = True
mask[1:] = aux[1:] != aux[:-1]
ret = (aux[mask], )
if return_index:
ret += (perm[mask], )
if return_inverse:
imask = np.cumsum(mask) - 1
inv_idx = np.empty(mask.shape, dtype=np.intp)
inv_idx[perm] = imask
ret += (inv_idx, )
if return_counts:
idx = np.concatenate(np.nonzero(mask) + ([mask.size], ))
ret += (np.diff(idx), )
return ret
def test_normed(self):
sup = suppress_warnings()
with sup:
rec = sup.record(np.VisibleDeprecationWarning, '.*normed.*')
# Check that the integral of the density equals 1.
n = 100
v = np.random.rand(n)
a, b = histogram(v, normed=True)
area = np.sum(a * np.diff(b))
assert_almost_equal(area, 1)
assert_equal(len(rec), 1)
sup = suppress_warnings()
with sup:
rec = sup.record(np.VisibleDeprecationWarning, '.*normed.*')
# Check with non-constant bin widths (buggy but backwards
# compatible)
v = np.arange(10)
bins = [0, 1, 5, 9, 10]
a, b = histogram(v, bins, normed=True)
area = np.sum(a * np.diff(b))
assert_almost_equal(area, 1)
assert_equal(len(rec), 1)
def test_outliers(self):
# Check that outliers are not tallied
a = np.arange(10) + .5
# Lower outliers
h, b = histogram(a, range=[0, 9])
assert_equal(h.sum(), 9)
# Upper outliers
h, b = histogram(a, range=[1, 10])
assert_equal(h.sum(), 9)
# Normalization
h, b = histogram(a, range=[1, 9], density=True)
assert_almost_equal((h * np.diff(b)).sum(), 1, decimal=15)
# Weights
w = np.arange(10) + .5
h, b = histogram(a, range=[1, 9], weights=w, density=True)
assert_equal((h * np.diff(b)).sum(), 1)
h, b = histogram(a, bins=8, range=[1, 9], weights=w)
assert_equal(h, w[1:-1])
def histogramdd(sample,
bins=10,
range=None,
normed=None,
weights=None,
density=None):
"""
Compute the multidimensional histogram of some data.
Parameters
----------
sample : (N, D) array, or (D, N) array_like
The data to be histogrammed.
Note the unusual interpretation of sample when an array_like:
* When an array, each row is a coordinate in a D-dimensional space -
such as ``histogramgramdd(np.array([p1, p2, p3]))``.
* When an array_like, each element is the list of values for single
coordinate - such as ``histogramgramdd((X, Y, Z))``.
The first form should be preferred.
bins : sequence or int, optional
The bin specification:
* A sequence of arrays describing the bin edges along each dimension.
* The number of bins for each dimension (nx, ny, ... =bins)
* The number of bins for all dimensions (nx=ny=...=bins).
range : sequence, optional
A sequence of length D, each an optional (lower, upper) tuple giving
the outer bin edges to be used if the edges are not given explicitly in
`bins`.
An entry of None in the sequence results in the minimum and maximum
values being used for the corresponding dimension.
The default, None, is equivalent to passing a tuple of D None values.
density : bool, optional
If False, the default, returns the number of samples in each bin.
If True, returns the probability *density* function at the bin,
``bin_count / sample_count / bin_volume``.
normed : bool, optional
An alias for the density argument that behaves identically. To avoid
confusion with the broken normed argument to `histogram`, `density`
should be preferred.
weights : (N,) array_like, optional
An array of values `w_i` weighing each sample `(x_i, y_i, z_i, ...)`.
Weights are normalized to 1 if normed is True. If normed is False,
the values of the returned histogram are equal to the sum of the
weights belonging to the samples falling into each bin.
Returns
-------
H : ndarray
The multidimensional histogram of sample x. See normed and weights
for the different possible semantics.
edges : list
A list of D arrays describing the bin edges for each dimension.
See Also
--------
histogram: 1-D histogram
histogram2d: 2-D histogram
Examples
--------
>>> r = np.random.randn(100,3)
>>> H, edges = np.histogramdd(r, bins = (5, 8, 4))
>>> H.shape, edges[0].size, edges[1].size, edges[2].size
((5, 8, 4), 6, 9, 5)
"""
try:
# Sample is an ND-array.
N, D = sample.shape
except (AttributeError, ValueError):
# Sample is a sequence of 1D arrays.
sample = np.atleast_2d(sample).T
N, D = sample.shape
nbin = np.empty(D, int)
edges = D * [None]
dedges = D * [None]
if weights is not None:
weights = np.asarray(weights)
try:
M = len(bins)
if M != D:
raise ValueError(
'The dimension of bins must be equal to the dimension of the '
' sample x.')
except TypeError:
# bins is an integer
bins = D * [bins]
# normalize the range argument
if range is None:
range = (None, ) * D
elif len(range) != D:
raise ValueError('range argument must have one entry per dimension')
# Create edge arrays
for i in _range(D):
if np.ndim(bins[i]) == 0:
if bins[i] < 1:
raise ValueError(
'`bins[{}]` must be positive, when an integer'.format(i))
smin, smax = _get_outer_edges(sample[:, i], range[i])
edges[i] = np.linspace(smin, smax, bins[i] + 1)
elif np.ndim(bins[i]) == 1:
edges[i] = np.asarray(bins[i])
if np.any(edges[i][:-1] > edges[i][1:]):
raise ValueError(
'`bins[{}]` must be monotonically increasing, when an array'
.format(i))
else:
raise ValueError(
'`bins[{}]` must be a scalar or 1d array'.format(i))
nbin[i] = len(edges[i]) + 1 # includes an outlier on each end
dedges[i] = np.diff(edges[i])
# Compute the bin number each sample falls into.
Ncount = tuple(
# avoid np.digitize to work around gh-11022
np.searchsorted(edges[i], sample[:, i], side='right')
for i in _range(D))
# Using digitize, values that fall on an edge are put in the right bin.
# For the rightmost bin, we want values equal to the right edge to be
# counted in the last bin, and not as an outlier.
for i in _range(D):
# Find which points are on the rightmost edge.
on_edge = (sample[:, i] == edges[i][-1])
# Shift these points one bin to the left.
Ncount[i][on_edge] -= 1
# Compute the sample indices in the flattened histogram matrix.
# This raises an error if the array is too large.
xy = np.ravel_multi_index(Ncount, nbin)
# Compute the number of repetitions in xy and assign it to the
# flattened histmat.
hist = np.bincount(xy, weights, minlength=nbin.prod())
# Shape into a proper matrix
hist = hist.reshape(nbin)
# This preserves the (bad) behavior observed in gh-7845, for now.
hist = hist.astype(float, casting='safe')
# Remove outliers (indices 0 and -1 for each dimension).
core = D * (slice(1, -1), )
hist = hist[core]
# handle the aliasing normed argument
if normed is None:
if density is None:
density = False
elif density is None:
# an explicit normed argument was passed, alias it to the new name
density = normed
else:
raise TypeError("Cannot specify both 'normed' and 'density'")
if density:
# calculate the probability density function
s = hist.sum()
for i in _range(D):
shape = np.ones(D, int)
shape[i] = nbin[i] - 2
hist = hist / dedges[i].reshape(shape)
hist /= s
if (hist.shape != nbin - 2).any():
raise RuntimeError("Internal Shape Error")
return hist, edges
def histogram(a, bins=10, range=None, normed=None, weights=None, density=None):
r"""
Compute the histogram of a set of data.
Parameters
----------
a : array_like
Input data. The histogram is computed over the flattened array.
bins : int or sequence of scalars or str, optional
If `bins` is an int, it defines the number of equal-width
bins in the given range (10, by default). If `bins` is a
sequence, it defines the bin edges, including the rightmost
edge, allowing for non-uniform bin widths.
.. versionadded:: 1.11.0
If `bins` is a string, it defines the method used to calculate the
optimal bin width, as defined by `histogram_bin_edges`.
range : (float, float), optional
The lower and upper range of the bins. If not provided, range
is simply ``(a.min(), a.max())``. Values outside the range are
ignored. The first element of the range must be less than or
equal to the second. `range` affects the automatic bin
computation as well. While bin width is computed to be optimal
based on the actual data within `range`, the bin count will fill
the entire range including portions containing no data.
normed : bool, optional
.. deprecated:: 1.6.0
This is equivalent to the `density` argument, but produces incorrect
results for unequal bin widths. It should not be used.
.. versionchanged:: 1.15.0
DeprecationWarnings are actually emitted.
weights : array_like, optional
An array of weights, of the same shape as `a`. Each value in
`a` only contributes its associated weight towards the bin count
(instead of 1). If `density` is True, the weights are
normalized, so that the integral of the density over the range
remains 1.
density : bool, optional
If ``False``, the result will contain the number of samples in
each bin. If ``True``, the result is the value of the
probability *density* function at the bin, normalized such that
the *integral* over the range is 1. Note that the sum of the
histogram values will not be equal to 1 unless bins of unity
width are chosen; it is not a probability *mass* function.
Overrides the ``normed`` keyword if given.
Returns
-------
hist : array
The values of the histogram. See `density` and `weights` for a
description of the possible semantics.
bin_edges : array of dtype float
Return the bin edges ``(length(hist)+1)``.
See Also
--------
histogramdd, bincount, searchsorted, digitize, histogram_bin_edges
Notes
-----
All but the last (righthand-most) bin is half-open. In other words,
if `bins` is::
[1, 2, 3, 4]
then the first bin is ``[1, 2)`` (including 1, but excluding 2) and
the second ``[2, 3)``. The last bin, however, is ``[3, 4]``, which
*includes* 4.
Examples
--------
>>> np.histogram([1, 2, 1], bins=[0, 1, 2, 3])
(array([0, 2, 1]), array([0, 1, 2, 3]))
>>> np.histogram(np.arange(4), bins=np.arange(5), density=True)
(array([ 0.25, 0.25, 0.25, 0.25]), array([0, 1, 2, 3, 4]))
>>> np.histogram([[1, 2, 1], [1, 0, 1]], bins=[0,1,2,3])
(array([1, 4, 1]), array([0, 1, 2, 3]))
>>> a = np.arange(5)
>>> hist, bin_edges = np.histogram(a, density=True)
>>> hist
array([ 0.5, 0. , 0.5, 0. , 0. , 0.5, 0. , 0.5, 0. , 0.5])
>>> hist.sum()
2.4999999999999996
>>> np.sum(hist * np.diff(bin_edges))
1.0
.. versionadded:: 1.11.0
Automated Bin Selection Methods example, using 2 peak random data
with 2000 points:
>>> import matplotlib.pyplot as plt
>>> rng = np.random.RandomState(10) # deterministic random data
>>> a = np.hstack((rng.normal(size=1000),
... rng.normal(loc=5, scale=2, size=1000)))
>>> plt.hist(a, bins='auto') # arguments are passed to np.histogram
>>> plt.title("Histogram with 'auto' bins")
>>> plt.show()
"""
a, weights = _ravel_and_check_weights(a, weights)
bin_edges, uniform_bins = _get_bin_edges(a, bins, range, weights)
# Histogram is an integer or a float array depending on the weights.
if weights is None:
ntype = np.dtype(np.intp)
else:
ntype = weights.dtype
# We set a block size, as this allows us to iterate over chunks when
# computing histograms, to minimize memory usage.
BLOCK = 65536
# The fast path uses bincount, but that only works for certain types
# of weight
simple_weights = (weights is None or np.can_cast(weights.dtype, np.double)
or np.can_cast(weights.dtype, complex))
if uniform_bins is not None and simple_weights:
# Fast algorithm for equal bins
# We now convert values of a to bin indices, under the assumption of
# equal bin widths (which is valid here).
first_edge, last_edge, n_equal_bins = uniform_bins
# Initialize empty histogram
n = np.zeros(n_equal_bins, ntype)
# Pre-compute histogram scaling factor
norm = n_equal_bins / _unsigned_subtract(last_edge, first_edge)
# We iterate over blocks here for two reasons: the first is that for
# large arrays, it is actually faster (for example for a 10^8 array it
# is 2x as fast) and it results in a memory footprint 3x lower in the
# limit of large arrays.
for i in _range(0, len(a), BLOCK):
tmp_a = a[i:i + BLOCK]
if weights is None:
tmp_w = None
else:
tmp_w = weights[i:i + BLOCK]
# Only include values in the right range
keep = (tmp_a >= first_edge)
keep &= (tmp_a <= last_edge)
if not np.logical_and.reduce(keep):
tmp_a = tmp_a[keep]
if tmp_w is not None:
tmp_w = tmp_w[keep]
# This cast ensures no type promotions occur below, which gh-10322
# make unpredictable. Getting it wrong leads to precision errors
# like gh-8123.
tmp_a = tmp_a.astype(bin_edges.dtype, copy=False)
# Compute the bin indices, and for values that lie exactly on
# last_edge we need to subtract one
f_indices = _unsigned_subtract(tmp_a, first_edge) * norm
indices = f_indices.astype(np.intp)
indices[indices == n_equal_bins] -= 1
# The index computation is not guaranteed to give exactly
# consistent results within ~1 ULP of the bin edges.
decrement = tmp_a < bin_edges[indices]
indices[decrement] -= 1
# The last bin includes the right edge. The other bins do not.
increment = ((tmp_a >= bin_edges[indices + 1])
& (indices != n_equal_bins - 1))
indices[increment] += 1
# We now compute the histogram using bincount
if ntype.kind == 'c':
n.real += np.bincount(indices,
weights=tmp_w.real,
minlength=n_equal_bins)
n.imag += np.bincount(indices,
weights=tmp_w.imag,
minlength=n_equal_bins)
else:
n += np.bincount(indices,
weights=tmp_w,
minlength=n_equal_bins).astype(ntype)
else:
# Compute via cumulative histogram
cum_n = np.zeros(bin_edges.shape, ntype)
if weights is None:
for i in _range(0, len(a), BLOCK):
sa = np.sort(a[i:i + BLOCK])
cum_n += _search_sorted_inclusive(sa, bin_edges)
else:
zero = np.zeros(1, dtype=ntype)
for i in _range(0, len(a), BLOCK):
tmp_a = a[i:i + BLOCK]
tmp_w = weights[i:i + BLOCK]
sorting_index = np.argsort(tmp_a)
sa = tmp_a[sorting_index]
sw = tmp_w[sorting_index]
cw = np.concatenate((zero, sw.cumsum()))
bin_index = _search_sorted_inclusive(sa, bin_edges)
cum_n += cw[bin_index]
n = np.diff(cum_n)
# density overrides the normed keyword
if density is not None:
if normed is not None:
# 2018-06-13, numpy 1.15.0 (this was not noisily deprecated in 1.6)
warnings.warn(
"The normed argument is ignored when density is provided. "
"In future passing both will result in an error.",
DeprecationWarning,
stacklevel=2)
normed = None
if density:
db = np.array(np.diff(bin_edges), float)
return n / db / n.sum(), bin_edges
elif normed:
# 2018-06-13, numpy 1.15.0 (this was not noisily deprecated in 1.6)
warnings.warn(
"Passing `normed=True` on non-uniform bins has always been "
"broken, and computes neither the probability density "
"function nor the probability mass function. "
"The result is only correct if the bins are uniform, when "
"density=True will produce the same result anyway. "
"The argument will be removed in a future version of "
"numpy.",
np.VisibleDeprecationWarning,
stacklevel=2)
# this normalization is incorrect, but
db = np.array(np.diff(bin_edges), float)
return n / (n * db).sum(), bin_edges
else:
if normed is not None:
# 2018-06-13, numpy 1.15.0 (this was not noisily deprecated in 1.6)
warnings.warn(
"Passing normed=False is deprecated, and has no effect. "
"Consider passing the density argument instead.",
DeprecationWarning,
stacklevel=2)
return n, bin_edges