def test_inf_edges(self):
# Test using +/-inf bin edges works. See #1788.
with np.errstate(invalid='ignore'):
x = np.arange(6).reshape(3, 2)
expected = np.array([[1, 0], [0, 1], [0, 1]])
h, e = np.histogramdd(x, bins=[3, [-np.inf, 2, 10]])
assert_allclose(h, expected)
h, e = np.histogramdd(x, bins=[3, np.array([-1, 2, np.inf])])
assert_allclose(h, expected)
h, e = np.histogramdd(x, bins=[3, [-np.inf, 3, np.inf]])
assert_allclose(h, expected)
python类histogramdd()的实例源码
def test_finite_range(self):
vals = np.random.random((100, 3))
histogramdd(vals, range=[[0.0, 1.0], [0.25, 0.75], [0.25, 0.5]])
assert_raises(ValueError, histogramdd, vals,
range=[[0.0, 1.0], [0.25, 0.75], [0.25, np.inf]])
assert_raises(ValueError, histogramdd, vals,
range=[[0.0, 1.0], [np.nan, 0.75], [0.25, 0.5]])
def __init__(self, data, names=None):
if names is None:
self.names = range(data.shape[1])
else:
assert (len(names) == self.NVAR), 'Passed-in names length must equal number of data columns'
self.names = names
self.NROW = data.shape[0]
self.NVAR = data.shape[1]
self.bins = [len(np.unique(data[:,n])) for n in range(self.NVAR)]
hist,_ = np.histogramdd(data, bins=self.bins)
self.counts = hist
self.joint = (hist / hist.sum()) + 1e-3
## COMPUTE MARGINAL FOR EACH VARIABLE ##
#_range = range(self.NVAR)
#for i,rv in enumerate(self.names):
# _axis = copy(_range)
# _axis.remove(i)
# self.marginal[rv] = np.sum(self.joint,axis=_axis)
#self.marginal = dict([(rv, np.sum(self.joint,axis=i)) for i,rv in enumerate(self.names)])
self.cache = {}
def image_entropy(img):
w,h = img.shape
a = np.array(img.reshape((w*h,1)))
h,e = np.histogramdd(a, bins=(16,), range=((0,256),))
prob = h/np.sum(h) # normalize
prob = prob[prob>0] # remove zeros
return -np.sum(prob*np.log2(prob))
features.py 文件源码
项目：Building-Machine-Learning-Systems-With-Python-Second-Edition
作者: PacktPublishing
项目源码
文件源码
阅读 36
收藏 0
点赞 0
评论 0
def chist(im):
'''Compute color histogram of input image
Parameters
----------
im : ndarray
should be an RGB image
Returns
-------
c : ndarray
1-D array of histogram values
'''
# Downsample pixel values:
im = im // 64
# We can also implement the following by using np.histogramdd
# im = im.reshape((-1,3))
# bins = [np.arange(5), np.arange(5), np.arange(5)]
# hist = np.histogramdd(im, bins=bins)[0]
# hist = hist.ravel()
# Separate RGB channels:
r,g,b = im.transpose((2,0,1))
pixels = 1 * r + 4 * g + 16 * b
hist = np.bincount(pixels.ravel(), minlength=64)
hist = hist.astype(float)
return np.log1p(hist)
def test_histogramdd_too_many_bins(self):
# Ticket 928.
assert_raises(ValueError, np.histogramdd, np.ones((1, 10)), bins=2**10)
def test_simple(self):
x = np.array([[-.5, .5, 1.5], [-.5, 1.5, 2.5], [-.5, 2.5, .5],
[.5, .5, 1.5], [.5, 1.5, 2.5], [.5, 2.5, 2.5]])
H, edges = histogramdd(x, (2, 3, 3),
range=[[-1, 1], [0, 3], [0, 3]])
answer = np.array([[[0, 1, 0], [0, 0, 1], [1, 0, 0]],
[[0, 1, 0], [0, 0, 1], [0, 0, 1]]])
assert_array_equal(H, answer)
# Check normalization
ed = [[-2, 0, 2], [0, 1, 2, 3], [0, 1, 2, 3]]
H, edges = histogramdd(x, bins=ed, normed=True)
assert_(np.all(H == answer / 12.))
# Check that H has the correct shape.
H, edges = histogramdd(x, (2, 3, 4),
range=[[-1, 1], [0, 3], [0, 4]],
normed=True)
answer = np.array([[[0, 1, 0, 0], [0, 0, 1, 0], [1, 0, 0, 0]],
[[0, 1, 0, 0], [0, 0, 1, 0], [0, 0, 1, 0]]])
assert_array_almost_equal(H, answer / 6., 4)
# Check that a sequence of arrays is accepted and H has the correct
# shape.
z = [np.squeeze(y) for y in split(x, 3, axis=1)]
H, edges = histogramdd(
z, bins=(4, 3, 2), range=[[-2, 2], [0, 3], [0, 2]])
answer = np.array([[[0, 0], [0, 0], [0, 0]],
[[0, 1], [0, 0], [1, 0]],
[[0, 1], [0, 0], [0, 0]],
[[0, 0], [0, 0], [0, 0]]])
assert_array_equal(H, answer)
Z = np.zeros((5, 5, 5))
Z[list(range(5)), list(range(5)), list(range(5))] = 1.
H, edges = histogramdd([np.arange(5), np.arange(5), np.arange(5)], 5)
assert_array_equal(H, Z)
def test_shape_3d(self):
# All possible permutations for bins of different lengths in 3D.
bins = ((5, 4, 6), (6, 4, 5), (5, 6, 4), (4, 6, 5), (6, 5, 4),
(4, 5, 6))
r = rand(10, 3)
for b in bins:
H, edges = histogramdd(r, b)
assert_(H.shape == b)
def test_shape_4d(self):
# All possible permutations for bins of different lengths in 4D.
bins = ((7, 4, 5, 6), (4, 5, 7, 6), (5, 6, 4, 7), (7, 6, 5, 4),
(5, 7, 6, 4), (4, 6, 7, 5), (6, 5, 7, 4), (7, 5, 4, 6),
(7, 4, 6, 5), (6, 4, 7, 5), (6, 7, 5, 4), (4, 6, 5, 7),
(4, 7, 5, 6), (5, 4, 6, 7), (5, 7, 4, 6), (6, 7, 4, 5),
(6, 5, 4, 7), (4, 7, 6, 5), (4, 5, 6, 7), (7, 6, 4, 5),
(5, 4, 7, 6), (5, 6, 7, 4), (6, 4, 5, 7), (7, 5, 6, 4))
r = rand(10, 4)
for b in bins:
H, edges = histogramdd(r, b)
assert_(H.shape == b)
def test_weights(self):
v = rand(100, 2)
hist, edges = histogramdd(v)
n_hist, edges = histogramdd(v, normed=True)
w_hist, edges = histogramdd(v, weights=np.ones(100))
assert_array_equal(w_hist, hist)
w_hist, edges = histogramdd(v, weights=np.ones(100) * 2, normed=True)
assert_array_equal(w_hist, n_hist)
w_hist, edges = histogramdd(v, weights=np.ones(100, int) * 2)
assert_array_equal(w_hist, 2 * hist)
def test_empty(self):
a, b = histogramdd([[], []], bins=([0, 1], [0, 1]))
assert_array_max_ulp(a, np.array([[0.]]))
a, b = np.histogramdd([[], [], []], bins=2)
assert_array_max_ulp(a, np.zeros((2, 2, 2)))
def test_bins_errors(self):
# There are two ways to specify bins. Check for the right errors
# when mixing those.
x = np.arange(8).reshape(2, 4)
assert_raises(ValueError, np.histogramdd, x, bins=[-1, 2, 4, 5])
assert_raises(ValueError, np.histogramdd, x, bins=[1, 0.99, 1, 1])
assert_raises(
ValueError, np.histogramdd, x, bins=[1, 1, 1, [1, 2, 2, 3]])
assert_raises(
ValueError, np.histogramdd, x, bins=[1, 1, 1, [1, 2, 3, -3]])
assert_(np.histogramdd(x, bins=[1, 1, 1, [1, 2, 3, 4]]))
def test_inf_edges(self):
# Test using +/-inf bin edges works. See #1788.
with np.errstate(invalid='ignore'):
x = np.arange(6).reshape(3, 2)
expected = np.array([[1, 0], [0, 1], [0, 1]])
h, e = np.histogramdd(x, bins=[3, [-np.inf, 2, 10]])
assert_allclose(h, expected)
h, e = np.histogramdd(x, bins=[3, np.array([-1, 2, np.inf])])
assert_allclose(h, expected)
h, e = np.histogramdd(x, bins=[3, [-np.inf, 3, np.inf]])
assert_allclose(h, expected)
def test_histogramdd_too_many_bins(self):
# Ticket 928.
assert_raises(ValueError, np.histogramdd, np.ones((1, 10)), bins=2**10)
def test_simple(self):
x = np.array([[-.5, .5, 1.5], [-.5, 1.5, 2.5], [-.5, 2.5, .5],
[.5, .5, 1.5], [.5, 1.5, 2.5], [.5, 2.5, 2.5]])
H, edges = histogramdd(x, (2, 3, 3),
range=[[-1, 1], [0, 3], [0, 3]])
answer = np.array([[[0, 1, 0], [0, 0, 1], [1, 0, 0]],
[[0, 1, 0], [0, 0, 1], [0, 0, 1]]])
assert_array_equal(H, answer)
# Check normalization
ed = [[-2, 0, 2], [0, 1, 2, 3], [0, 1, 2, 3]]
H, edges = histogramdd(x, bins=ed, normed=True)
assert_(np.all(H == answer / 12.))
# Check that H has the correct shape.
H, edges = histogramdd(x, (2, 3, 4),
range=[[-1, 1], [0, 3], [0, 4]],
normed=True)
answer = np.array([[[0, 1, 0, 0], [0, 0, 1, 0], [1, 0, 0, 0]],
[[0, 1, 0, 0], [0, 0, 1, 0], [0, 0, 1, 0]]])
assert_array_almost_equal(H, answer / 6., 4)
# Check that a sequence of arrays is accepted and H has the correct
# shape.
z = [np.squeeze(y) for y in split(x, 3, axis=1)]
H, edges = histogramdd(
z, bins=(4, 3, 2), range=[[-2, 2], [0, 3], [0, 2]])
answer = np.array([[[0, 0], [0, 0], [0, 0]],
[[0, 1], [0, 0], [1, 0]],
[[0, 1], [0, 0], [0, 0]],
[[0, 0], [0, 0], [0, 0]]])
assert_array_equal(H, answer)
Z = np.zeros((5, 5, 5))
Z[list(range(5)), list(range(5)), list(range(5))] = 1.
H, edges = histogramdd([np.arange(5), np.arange(5), np.arange(5)], 5)
assert_array_equal(H, Z)
def test_shape_3d(self):
# All possible permutations for bins of different lengths in 3D.
bins = ((5, 4, 6), (6, 4, 5), (5, 6, 4), (4, 6, 5), (6, 5, 4),
(4, 5, 6))
r = rand(10, 3)
for b in bins:
H, edges = histogramdd(r, b)
assert_(H.shape == b)
def test_shape_4d(self):
# All possible permutations for bins of different lengths in 4D.
bins = ((7, 4, 5, 6), (4, 5, 7, 6), (5, 6, 4, 7), (7, 6, 5, 4),
(5, 7, 6, 4), (4, 6, 7, 5), (6, 5, 7, 4), (7, 5, 4, 6),
(7, 4, 6, 5), (6, 4, 7, 5), (6, 7, 5, 4), (4, 6, 5, 7),
(4, 7, 5, 6), (5, 4, 6, 7), (5, 7, 4, 6), (6, 7, 4, 5),
(6, 5, 4, 7), (4, 7, 6, 5), (4, 5, 6, 7), (7, 6, 4, 5),
(5, 4, 7, 6), (5, 6, 7, 4), (6, 4, 5, 7), (7, 5, 6, 4))
r = rand(10, 4)
for b in bins:
H, edges = histogramdd(r, b)
assert_(H.shape == b)
def test_weights(self):
v = rand(100, 2)
hist, edges = histogramdd(v)
n_hist, edges = histogramdd(v, normed=True)
w_hist, edges = histogramdd(v, weights=np.ones(100))
assert_array_equal(w_hist, hist)
w_hist, edges = histogramdd(v, weights=np.ones(100) * 2, normed=True)
assert_array_equal(w_hist, n_hist)
w_hist, edges = histogramdd(v, weights=np.ones(100, int) * 2)
assert_array_equal(w_hist, 2 * hist)
def test_empty(self):
a, b = histogramdd([[], []], bins=([0, 1], [0, 1]))
assert_array_max_ulp(a, np.array([[0.]]))
a, b = np.histogramdd([[], [], []], bins=2)
assert_array_max_ulp(a, np.zeros((2, 2, 2)))
def test_bins_errors(self):
# There are two ways to specify bins. Check for the right errors
# when mixing those.
x = np.arange(8).reshape(2, 4)
assert_raises(ValueError, np.histogramdd, x, bins=[-1, 2, 4, 5])
assert_raises(ValueError, np.histogramdd, x, bins=[1, 0.99, 1, 1])
assert_raises(
ValueError, np.histogramdd, x, bins=[1, 1, 1, [1, 2, 2, 3]])
assert_raises(
ValueError, np.histogramdd, x, bins=[1, 1, 1, [1, 2, 3, -3]])
assert_(np.histogramdd(x, bins=[1, 1, 1, [1, 2, 3, 4]]))
