def has_normal_distribution(dataset, var_data, alpha):
assert (len(var_data) == 1)
assert (isinstance(var_data[0], VarData))
# Must be continuous to be normally distributed
assert (is_continuous_var(dataset, var_data, alpha))
# Get data from datasest using var_data's query
data = get_data(dataset, var_data[0])
norm_test_results = compute_normal_distribution(data)
return (norm_test_results[1] > alpha), norm_test_results
def test_compute_normal_distribution(self):
np.random.seed(0)
data = [
3.03319599, -1.9392511, 5.19637956, 4.93035686, 6.67777232,
3.33221652, 4.48231727, 5.7451167, 1.74927197, -1.13835557,
4.71136013, 0.94368067, 3.45836918, 4.80279979, 6.41550484,
5.19735433, 3.68366857, 5.19261866, 6.08280386, 1.21590325,
4.67839939, 2.15511797, 8.16360168, 4.04091618, 6.77094548
]
returned_value = compute_normal_distribution(data)
self.assertAlmostEqual(0.2147399485, returned_value.p_value, 10)
self.assertAlmostEqual(0.9470322132, returned_value.W, 10)
def has_groups_normal_distribution(dataset, var_data, alpha):
xs = []
ys = []
cat_xs = []
cont_ys = []
grouped_data = []
result = None
if isinstance(var_data, CombinedData):
xs = var_data.get_explanatory_variables()
ys = var_data.get_explained_variables()
else:
for var in var_data:
if var.role == iv_identifier or var.role == contributor_identifier:
xs.append(var)
if var.role == dv_identifier or var.role == outcome_identifier:
ys.append(var)
for x in xs:
if x.is_categorical():
cat_xs.append(x)
for y in ys:
if y.is_continuous():
cont_ys.append(y)
if cat_xs and cont_ys:
for y in ys:
for x in xs:
cat = [k for k, v in x.metadata[categories].items()]
for c in cat:
data = dataset.select(
y.metadata[name],
where=[f"{x.metadata[name]} == '{c}'"])
grouped_data.append(data)
for group in grouped_data:
result = compute_normal_distribution(group)
if result[1] <= alpha:
return False, result
return True, result