def test_select_neighbours_5(self):
# wrong distance function given
with self.assertRaises(ValueError) as c:
select_neighbours(self.x,
np.array([4, 3, 2]),
n=1,
dist_fun='euclidean')
def test_select_neighbours_8(self):
sample_x = select_neighbours(pd.DataFrame(self.x,
columns=['a', 'b', 'c']),
[4, 1, 5],
n=10,
selected_variables=['a', 'd'])
sample_x2 = select_neighbours(pd.DataFrame(self.x), [4, 1, 5], n=10)
np.testing.assert_array_equal(sample_x, sample_x2)
def test_select_neighbours(self):
neighbours = select_neighbours(self.x,
self.x[0],
dist_fun=euclidean_distances,
n=1)
neighbours2 = select_neighbours(self.x,
self.x[0],
dist_fun='gower',
n=1)
self.assertSequenceEqual(list(neighbours.iloc[0]), list(self.x[0]))
self.assertSequenceEqual(list(neighbours2.iloc[0]), list(self.x[0]))
def test_select_neighbours_2(self):
(_, m) = self.x.shape
size = 3
neighbours = select_neighbours(self.x,
np.array([4, 3, 2]),
dist_fun=euclidean_distances,
n=size)
self.assertEqual(neighbours.shape, (size, m))
neighbours2 = select_neighbours(self.x,
np.array([4, 3, 2]),
dist_fun='gower',
n=size)
self.assertEqual(neighbours2.shape, (size, m))
def test_select_neighbours_3(self):
sample_x, sample_y = select_neighbours(self.x,
np.array([4, 3, 2]),
y=self.y,
n=3)
pos = list(self.y).index(sample_y[1])
self.assertSequenceEqual(list(sample_x.iloc[1]), list(self.x[pos]))
def test_select_neighbours_7(self):
sample_x = select_neighbours(pd.DataFrame(self.x,
columns=['a', 'b', 'c']),
[4, 1, 5],
n=2,
selected_variables=['a', 'b'])
self.assertEqual(sample_x.shape, (2, 3))
def test_select_neighbours_10(self):
df = pd.DataFrame({
'a': list(range(100)),
'b': 11,
'c': np.arange(0, 200, 2) / 7
})
y = pd.Series(range(100))
sample_x, sample_y = select_neighbours(df, [3, 11, 7.4], y, n=5)
self.assertEqual(sample_x.shape, (5, 3))
self.assertEqual(len(sample_y), 5)
np.testing.assert_array_equal(sample_x['a'], sample_y)
def test_regression_3(self):
variable_names = self.variable_names
neighbours = select_neighbours(self.X_train,
self.X_train[0],
variable_names=variable_names,
selected_variables=variable_names,
n=15)
cp3 = individual_variable_profile(self.explainer_rf,
neighbours,
variables=['LSTAT', 'RM'],
variable_splits={
'LSTAT': [10, 20, 30],
'RM': [4, 5, 6, 7]
})
self.assertEqual(cp3.selected_variables, ['LSTAT', 'RM'])
# num of different values in splits
self.assertEqual(len(cp3.profile), 15 * 7)
(gb_model, _, _, _) = gradient_boosting_model()
(svm_model, _, _, _) = supported_vector_machines_model()
explainer_linear = explain(linear_model, variable_names, data, y)
explainer_gb = explain(gb_model, variable_names, data, y)
explainer_svm = explain(svm_model, variable_names, data, y)
# single profile
cp_1 = individual_variable_profile(explainer_gb, x[0], y[0])
plot(cp_1,
destination="notebook",
selected_variables=["bmi"],
print_observations=False)
# local fit
neighbours_x, neighbours_y = select_neighbours(x, x[10], y=y, n=10)
cp_2 = individual_variable_profile(explainer_gb, neighbours_x,
neighbours_y)
plot(cp_2,
show_residuals=True,
selected_variables=["age"],
print_observations=False,
color_residuals='red',
plot_title='')
# aggregate profiles
plot(cp_2,
aggregate_profiles="mean",
selected_variables=["age"],
color_pdps='black',
size_pdps=6,
def test_select_neighbours_6(self):
sample_x = select_neighbours(pd.DataFrame(self.x),
np.array([4, 3, 2]),
n=300)
self.assertEqual(len(sample_x), len(self.x))
def test_select_neighbours_4(self):
# it logs warning
sample_x = select_neighbours(self.x, np.array([4, 3, 2]), n=300)
self.assertEqual(len(sample_x), len(self.x))
if __name__ == "__main__":
(model, data, labels, variable_names) = random_forest_regression()
explainer_rf = explain(model, variable_names, data, labels)
cp_profile = individual_variable_profile(explainer_rf,
X_train[0],
y=y_train[0],
variables=['TAX', 'CRIM'])
plot(cp_profile)
sample = select_sample(X_train, n=3)
cp2 = individual_variable_profile(explainer_rf,
sample,
variables=['TAX', 'CRIM'])
plot(cp2)
neighbours = select_neighbours(X_train,
X_train[0],
variable_names=variable_names,
selected_variables=variable_names,
n=15)
cp3 = individual_variable_profile(explainer_rf,
neighbours,
variables=['LSTAT', 'RM'],
variable_splits={
'LSTAT': [10, 20, 30],
'RM': [4, 5, 6, 7]
})
plot(cp3)