def test_decision_tree_classification3(self):
train_out = decision_tree_classification_train(table=self.iris,
feature_cols=[
'sepal_length',
'sepal_width',
'petal_length',
'petal_width'
],
label_col='species',
random_state=12345,
criterion='entropy',
max_leaf_nodes=2,
group_by=['species'])
predict_out = decision_tree_classification_predict(
table=self.iris, model=train_out['model'])
table = predict_out['out_table'].values.tolist()
self.assertListEqual(table[0],
[5.1, 3.5, 1.4, 0.2, 'setosa', 'setosa'])
self.assertListEqual(table[1],
[4.9, 3.0, 1.4, 0.2, 'setosa', 'setosa'])
self.assertListEqual(table[2],
[4.7, 3.2, 1.3, 0.2, 'setosa', 'setosa'])
self.assertListEqual(table[3],
[4.6, 3.1, 1.5, 0.2, 'setosa', 'setosa'])
self.assertListEqual(table[4],
[5.0, 3.6, 1.4, 0.2, 'setosa', 'setosa'])
def test_groupby1(self):
df = load_iris()
random_group = []
for _ in range(len(df)):
random_group.append(random.randint(1, 2))
df['random_group'] = random_group
train_out = decision_tree_classification_train(table=df, feature_cols=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'], label_col='species', group_by=['random_group'])
predict_out = decision_tree_classification_predict(table=df, model=train_out['model'])
def groupby1(self):
df = get_iris()
random_group = []
for i in range(len(df)):
random_group.append(random.randint(1, 2))
df['random_group'] = random_group
train_out = decision_tree_classification_train(
df,
feature_cols=[
'sepal_length', 'sepal_width', 'petal_length', 'petal_width'
],
label_col='species',
group_by=['random_group'])
predict_out = decision_tree_classification_predict(
df, train_out['model'])
print(predict_out['out_table'][['species', 'prediction']])