def test_empty_hinds(self):
for h_model in ['linear', 'forest']:
for classification in [True, False]:
X1 = np.random.normal(0, 1, size=(500, 5))
X2 = np.random.choice([0, 1], size=(500, 1))
X3 = np.random.choice([0, 1, 2], size=(500, 1))
X = np.hstack((X1, X2, X3))
X_df = pd.DataFrame(X, columns=[f"x{i} " for i in range(7)])
y = np.random.choice([0, 1], size=(500, ))
y_df = pd.Series(y)
# model
hetero_inds = [[], [], []]
feat_inds = [1, 3, 5]
categorical = [5, 6]
ca = CausalAnalysis(feat_inds,
categorical,
heterogeneity_inds=hetero_inds,
classification=classification,
nuisance_models='linear',
heterogeneity_model=h_model,
n_jobs=-1)
ca.fit(X_df, y)
eff = ca.global_causal_effect(alpha=0.05)
eff = ca.local_causal_effect(X_df, alpha=0.05)
for ind in feat_inds:
pto = ca._policy_tree_output(X_df, ind)
ca._individualized_policy_dict(X_df, ind)
def test_individualized_policy(self):
y_arr = np.random.choice([0, 1], size=(500, ))
X = pd.DataFrame({
'a': np.random.normal(size=500),
'b': np.random.normal(size=500),
'c': np.random.choice([0, 1], size=500),
'd': np.random.choice(['a', 'b', 'c'], size=500)
})
inds = ['a', 'b', 'c', 'd']
cats = ['c', 'd']
hinds = ['a', 'd']
for y in [pd.Series(y_arr), y_arr.reshape(-1, 1)]:
for classification in [True, False]:
ca = CausalAnalysis(inds,
cats,
hinds,
heterogeneity_model='linear',
classification=classification)
ca.fit(X, y)
df = ca.individualized_policy(X, 'a')
self.assertEqual(df.shape[0],
500) # all rows included by default
self.assertEqual(
df.shape[1], 4 + X.shape[1]
) # new cols for policy, effect, upper and lower bounds
df = ca.individualized_policy(X, 'b', n_rows=5)
self.assertEqual(df.shape[0], 5)
self.assertEqual(
df.shape[1], 4 + X.shape[1]
) # new cols for policy, effect, upper and lower bounds
# verify that we can use a scalar treatment cost
df = ca.individualized_policy(X, 'c', treatment_costs=100)
self.assertEqual(df.shape[0], 500)
self.assertEqual(
df.shape[1], 4 + X.shape[1]
) # new cols for policy, effect, upper and lower bounds
# verify that we can specify per-treatment costs for each sample
df = ca.individualized_policy(
X,
'd',
alpha=0.05,
treatment_costs=np.random.normal(size=(500, 2)))
self.assertEqual(df.shape[0], 500)
self.assertEqual(
df.shape[1], 4 + X.shape[1]
) # new cols for policy, effect, upper and lower bounds
dictionary = ca._individualized_policy_dict(X, 'a')
