def test_standard_moment1():
ns = range(3, 10)
ps = np.linspace(0.1, 0.9, 9)
for n, p in product(ns, ps):
d = binomial(n, p)
for i, m in {1: 0, 2: 1, 3: (1-2*p)/np.sqrt(n*p*(1-p))}.items():
assert_almost_equal(standard_moment(d, i), m, places=5)
def test_standard_deviation1():
""" Test standard_deviation on binomial distribution """
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
yield assert_almost_equal, standard_deviation(d), np.sqrt(n*p*(1-p))
def test_mode1():
""" Test mode on binomial distribution """
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
yield assert_true, mode(d)[0][0] in [floor((n+1)*p), floor((n+1)*p)-1]
def test_median1():
""" Test median on binomial distribution """
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
yield assert_true, median(d) in [floor(n*p), n*p, ceil(n*p)]
def test_mean1():
""" Test mean on binomial distribution """
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
yield assert_almost_equal, mean(d), n*p
def test_standard_moment1():
""" Test standard_moment on binomial distribution """
ns = range(3, 10)
ps = np.linspace(0.1, 0.9, 9)
for n, p in product(ns, ps):
d = binomial(n, p)
for i, m in {1: 0, 2: 1, 3: (1-2*p)/np.sqrt(n*p*(1-p))}.items():
yield assert_almost_equal, standard_moment(d, i), m, 5
def test_standard_moment1(n, p):
""" Test standard_moment on binomial distribution """
d = binomial(n, p)
for i, m in {
1: 0,
2: 1,
3: (1 - 2 * p) / np.sqrt(n * p * (1 - p))
}.items():
assert standard_moment(d, i) == pytest.approx(m, abs=1e-5)
def test_mean1(n, p):
""" Test mean on binomial distribution """
d = binomial(n, p)
assert mean(d) == pytest.approx(n * p)
def test_binomial1(n):
""" Test binomial distribution """
d = binomial(n, 1/2)
assert d.outcomes == tuple(range(n+1))
assert sum(d.pmf) == pytest.approx(1)
def test_binomial2(n):
""" Test binomial distribution failures """
with pytest.raises(ValueError):
binomial(n, 1/2)
def test_binomial1(n):
""" Test binomial distribution """
d = binomial(n, 1 / 2)
assert d.outcomes == tuple(range(n + 1))
assert sum(d.pmf) == pytest.approx(1)
def test_binomial2(n):
""" Test binomial distribution failures """
with pytest.raises(ValueError):
binomial(n, 1 / 2)
def test_standard_deviation1(n, p):
""" Test standard_deviation on binomial distribution """
d = binomial(n, p)
assert standard_deviation(d) == pytest.approx(np.sqrt(n * p * (1 - p)))
def test_mean1(n, p):
""" Test mean on binomial distribution """
d = binomial(n, p)
assert mean(d) == pytest.approx(n*p)
def test_median1():
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
assert(median(d) in [floor(n*p), n*p, ceil(n*p)])
def test_mode1():
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
assert(mode(d)[0][0] in [floor((n+1)*p), floor((n+1)*p)-1])
def test_standard_moment1(n, p):
""" Test standard_moment on binomial distribution """
d = binomial(n, p)
for i, m in {1: 0, 2: 1, 3: (1-2*p)/np.sqrt(n*p*(1-p))}.items():
assert standard_moment(d, i) == pytest.approx(m, abs=1e-5)
def test_binomial1():
""" Test binomial distribution """
for n in range(1, 10):
d = binomial(n, 1 / 2)
assert_equal(d.outcomes, tuple(range(n + 1)))
assert_almost_equal(sum(d.pmf), 1)
def test_standard_deviation1(n, p):
""" Test standard_deviation on binomial distribution """
d = binomial(n, p)
assert standard_deviation(d) == pytest.approx(np.sqrt(n*p*(1-p)))
def test_mode1(n, p):
""" Test mode on binomial distribution """
d = binomial(n, p)
assert mode(d)[0][0] in [floor((n+1)*p), floor((n+1)*p)-1]
def test_median1(n, p):
""" Test median on binomial distribution """
d = binomial(n, p)
assert median(d) in [floor(n*p), n*p, ceil(n*p)]
def test_median1(n, p):
""" Test median on binomial distribution """
d = binomial(n, p)
assert median(d) in [floor(n * p), n * p, ceil(n * p)]
def test_standard_deviation1():
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
assert_almost_equal(standard_deviation(d), np.sqrt(n*p*(1-p)))
def test_mode1(n, p):
""" Test mode on binomial distribution """
d = binomial(n, p)
assert mode(d)[0][0] in [floor((n + 1) * p), floor((n + 1) * p) - 1]
def test_binomial1():
""" Test binomial distribution """
for n in range(1, 10):
d = binomial(n, 1/2)
assert_equal(d.outcomes, tuple(range(n+1)))
assert_almost_equal(sum(d.pmf), 1)
def test_mean1():
ns = range(2, 10)
ps = np.linspace(0, 1, 11)
for n, p in product(ns, ps):
d = binomial(n, p)
assert_almost_equal(mean(d), n*p)
def test_binomial1():
for n in range(1, 10):
d = binomial(n, 1/2)
assert_equal(d.outcomes, tuple(range(n+1)))
assert_almost_equal(sum(d.pmf), 1)