def test_titanic_feature_names():
path = os.path.dirname(__file__)
titanic = pd.read_csv(os.path.join(path, '../datasets/titanic.csv'))
ep = EasyPreprocessor()
ep.fit(clean(titanic.drop('survived', axis=1)))
expected_names = [
'sibsp', 'parch', 'age_dabl_continuous', 'fare_dabl_continuous',
'body_dabl_continuous', 'pclass_1', 'pclass_2', 'pclass_3',
'sex_female', 'sex_male', 'sibsp_0', 'sibsp_1', 'sibsp_2', 'sibsp_3',
'sibsp_4', 'sibsp_5', 'sibsp_8', 'parch_0', 'parch_1', 'parch_2',
'parch_3', 'parch_4', 'parch_5', 'parch_6', 'parch_9', 'embarked_?',
'embarked_C', 'embarked_Q', 'embarked_S', 'boat_1', 'boat_10',
'boat_11', 'boat_12', 'boat_13', 'boat_13 15', 'boat_13 15 B',
'boat_14', 'boat_15', 'boat_15 16', 'boat_16', 'boat_2', 'boat_3',
'boat_4', 'boat_5', 'boat_5 7', 'boat_5 9', 'boat_6', 'boat_7',
'boat_8', 'boat_8 10', 'boat_9', 'boat_?', 'boat_A', 'boat_B',
'boat_C', 'boat_C D', 'boat_D', 'age_?_0.0', 'age_?_1.0', 'body_?_0.0',
'body_?_1.0'
]
assert ep.get_feature_names() == expected_names
# without clean
X = ep.fit_transform(titanic.drop('survived', axis=1))
# FIXME can't do that yet
# assert ep.get_feature_names() == expected_names_no_clean
assert not np.isnan(X).any()
def test_simple_preprocessor():
sp = EasyPreprocessor()
trans = sp.fit_transform(X_cat)
assert trans.shape == (3, 6)
iris = load_iris()
sp = EasyPreprocessor()
sp.fit(iris.data)
def test_simple_preprocessor():
sp = EasyPreprocessor()
sp.fit(X_cat)
trans = sp.transform(X_cat)
assert trans.shape == (3, 7) # FIXME should be 6?
iris = load_iris()
sp = EasyPreprocessor()
sp.fit(iris.data)
def test_simple_preprocessor_imputed_features():
# Issue: 211
data = pd.DataFrame({'A': [0, 1, 2, 1, np.NaN]}, dtype=int)
types = detect_types(data, type_hints={'A': 'categorical'})
ep = EasyPreprocessor(types=types)
ep.fit(data)
expected_names = ['A_0', 'A_1', 'A_2', 'A_imputed_False', 'A_imputed_True']
assert ep.get_feature_names() == expected_names
def test_simple_preprocessor_dirty_float():
dirty = pd.DataFrame(make_dirty_float())
fp = EasyPreprocessor()
fp.fit(dirty)
res = fp.transform(dirty)
assert res.shape == (100, 3)
rowsum = res.sum(axis=0)
# count of "garbage"
assert rowsum[1] == 1
# count of "missing"
assert rowsum[2] == 9
# make sure we can transform a clean column
fp.transform(pd.DataFrame(['0', '1', '2'], columns=['a_column']))
def test_titanic_feature_names():
path = os.path.dirname(__file__)
titanic = pd.read_csv(os.path.join(path, '../datasets/titanic.csv'))
ep = EasyPreprocessor()
ep.fit(clean(titanic.drop('survived', axis=1)))
expected_names = [
'age_dabl_continuous', 'body_dabl_continuous', 'fare_dabl_continuous',
'age_?_0.0', 'age_?_1.0', 'body_?_0.0', 'body_?_1.0', 'pclass_1',
'pclass_2', 'pclass_3', 'sex_female', 'sex_male', 'embarked_?',
'embarked_C', 'embarked_Q', 'embarked_S', 'boat_1', 'boat_10',
'boat_11', 'boat_12', 'boat_13', 'boat_13 15', 'boat_13 15 B',
'boat_14', 'boat_15', 'boat_15 16', 'boat_16', 'boat_2', 'boat_3',
'boat_4', 'boat_5', 'boat_5 7', 'boat_5 9', 'boat_6', 'boat_7',
'boat_8', 'boat_8 10', 'boat_9', 'boat_?', 'boat_A', 'boat_B',
'boat_C', 'boat_C D', 'boat_D'
]
assert ep.get_feature_names() == expected_names