def test_variance_no_side_effect(transition: Transition):
df, w = data(60)
transition.fit(df, w)
# very intrusive test. touches internals of m. not very nice.
X_orig_id = id(transition.X)
transition.mean_cv() # this has to be called here
assert id(transition.X) == X_orig_id
def test_mean_coefficient_of_variation_sample_not_full_rank(
transition: Transition):
"""
This is a test created after I encountered this kind of bug
"""
n = 13
df = pd.DataFrame({"a": np.ones(n) * 2, "b": np.ones(n)})
w = np.ones(len(df)) / len(df)
transition.fit(df, w)
transition.mean_cv()
def test_variance_estimate(transition: Transition):
var_list = []
for n in [20, 250]:
df, w = data(n)
transition.fit(df, w)
var = transition.mean_cv()
var_list.append(var)
assert var_list[0] >= var_list[1]
def test_variance_estimate_higher_n_than_sample(transition: Transition):
n = 100
df, w = data(n)
transition.fit(df, w)
var_list = []
for n_test in [n, n*4, n*10]:
var = transition.mean_cv(n_test)
var_list.append(var)
for lower, upper in zip(var_list[:-1], var_list[1:]):
assert lower >= upper
def test_variance_estimate_higher_n_than_sample(transition: Transition):
n = 100
df, w = data(n)
transition.fit(df, w)
var_list = []
for n_test in [n, n * 4, n * 10]:
var = transition.mean_cv(n_test)
var_list.append(var)
for lower, upper in zip(var_list[:-1], var_list[1:]):
# add a little buffer to overcome slight random fluctuations
assert lower + 1e-2 >= upper
