def test_sum_first_half_of_first_bin():
# test sum at point between min and first bin value
# https://github.com/carsonfarmer/streamhist/issues/13
h = StreamHist(maxbins=5)
h.update((1, 2, 3, 4, 5, .5))
assert h.min() == 0.5
bin0 = h.bins[0]
assert bin0.value == 0.75
assert bin0.count == 2
assert h.sum(h.min()) == 0
assert h.sum((h.min() + bin0.value) / 2) == (.5**2) * bin0.count / 2
def test_negative_densities():
points = 10000
h = StreamHist()
data = make_normal(points)
h.update(data)
from numpy import linspace
x = linspace(h.min(), h.max(), 100)
assert all([h.pdf(t) >= 0. for t in x])
def test_negative_densities():
points = 10000
h = StreamHist()
data = make_normal(points)
h.update(data)
from numpy import linspace
x = linspace(h.min(), h.max(), 100)
assert all([h.pdf(t) >= 0. for t in x])
def test_min_max():
h = StreamHist()
assert h.min() is None
assert h.max() is None
for _ in range(1000):
h.update(rand_int(10))
assert h.min() == 0
assert h.max() == 10
h1 = StreamHist()
h2 = StreamHist()
for p in range(4):
h1.update(p)
h2.update(p + 2)
merged = h1.merge(h2)
assert merged.min() == 0
assert merged.max() == 5
def test_min_max():
h = StreamHist()
assert h.min() is None
assert h.max() is None
for _ in range(1000):
h.update(rand_int(10))
assert h.min() == 0
assert h.max() == 10
h1 = StreamHist()
h2 = StreamHist()
for p in range(4):
h1.update(p)
h2.update(p+2)
merged = h1.merge(h2)
assert merged.min() == 0
assert merged.max() == 5
def test_histogram_exact():
"""A StreamHist which is not at capacity matches numpy statistics"""
max_bins = 50
points = [random.expovariate(1 / 5) for _ in range(max_bins)]
h = StreamHist(max_bins)
h.update(points)
q = [i / 100 for i in range(101)]
import numpy as np
assert h.quantiles(*q) == approx(np.quantile(points, q))
assert h.mean() == approx(np.mean(points))
assert h.var() == approx(np.var(points))
assert h.min() == min(points)
assert h.max() == max(points)
assert h.count() == max_bins
def test_histogram_approx(max_bins, num_points, expected_error):
"""Test accuracy of StreamHist over capacity, especially quantiles."""
points = [random.expovariate(1 / 5) for _ in range(num_points)]
h = StreamHist(max_bins)
h.update(points)
import numpy as np
q = [i / 100 for i in range(101)]
err_sum = 0 # avg percent error across samples
for p, b, b_np, b_np_min, b_np_max in zip(
q, h.quantiles(*q), np.quantile(points, q),
np.quantile(points, [0] * 7 + q),
np.quantile(points, q[7:] + [1] * 7)):
err_denom = b_np_max - b_np_min
err_sum += abs(b - b_np) / err_denom
assert err_sum <= expected_error
assert h.mean() == approx(np.mean(points))
assert h.var() == approx(np.var(points), rel=.05)
assert h.min() == min(points)
assert h.max() == max(points)
assert h.count() == num_points
