def test_groupby1(self):
df = load_iris()
train_out = glm_train(
df,
feature_cols=['sepal_length', 'sepal_width', 'petal_length'],
label_col='petal_width',
group_by=['species'])
predict_out = glm_predict(df, train_out['model'])
def test_groupby1(self):
df = get_iris()
train_out = glm_train(
df,
feature_cols=['sepal_length', 'sepal_width', 'petal_length'],
label_col='petal_width',
group_by=['species'])
predict_out = glm_predict(df, train_out['model'])
print(predict_out['out_table'][['petal_width', 'prediction']])
def test(self):
glm_model = glm_train(
self.testdata,
feature_cols=['sepal_length', 'sepal_width', 'petal_length'],
label_col='petal_width',
family="Poisson",
link='log',
group_by=['species'])['model']
np.testing.assert_array_almost_equal(
glm_model['_grouped_data']['data']['setosa']['coefficients'],
[-3.6342016377, 0.1245708937, 0.1885508496, 0.6428621488], 10)
predict = glm_predict(self.testdata,
glm_model)['out_table']['prediction']
np.testing.assert_array_almost_equal(predict[:5], [
0.2371754544, 0.2105262982, 0.1999606014, 0.2203860121,
0.2386977666
], 10)