def test_check_array_pandas_dtype_object_conversion():
# test that data-frame like objects with dtype object
# get converted
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]], dtype=np.object)
X_df = MockDataFrame(X)
assert check_array(X_df).dtype.kind == "f"
assert check_array(X_df, ensure_2d=False).dtype.kind == "f"
# smoke-test against dataframes with column named "dtype"
X_df.dtype = "Hans"
assert check_array(X_df, ensure_2d=False).dtype.kind == "f"
def test_check_array_on_mock_dataframe():
arr = np.array([[0.2, 0.7], [0.6, 0.5], [0.4, 0.1], [0.7, 0.2]])
mock_df = MockDataFrame(arr)
checked_arr = check_array(mock_df)
assert checked_arr.dtype == arr.dtype
checked_arr = check_array(mock_df, dtype=np.float32)
assert checked_arr.dtype == np.dtype(np.float32)
def test_clone_pandas_dataframe():
class DummyEstimator(TransformerMixin, BaseEstimator):
"""This is a dummy class for generating numerical features
This feature extractor extracts numerical features from pandas data
frame.
Parameters
----------
df: pandas data frame
The pandas data frame parameter.
Notes
-----
"""
def __init__(self, df=None, scalar_param=1):
self.df = df
self.scalar_param = scalar_param
def fit(self, X, y=None):
pass
def transform(self, X):
pass
# build and clone estimator
d = np.arange(10)
df = MockDataFrame(d)
e = DummyEstimator(df, scalar_param=1)
cloned_e = clone(e)
# the test
assert (e.df == cloned_e.df).values.all()
assert e.scalar_param == cloned_e.scalar_param
def test_shuffle_dont_convert_to_array():
# Check that shuffle does not try to convert to numpy arrays with float
# dtypes can let any indexable datastructure pass-through.
a = ['a', 'b', 'c']
b = np.array(['a', 'b', 'c'], dtype=object)
c = [1, 2, 3]
d = MockDataFrame(np.array([['a', 0],
['b', 1],
['c', 2]],
dtype=object))
e = sp.csc_matrix(np.arange(6).reshape(3, 2))
a_s, b_s, c_s, d_s, e_s = shuffle(a, b, c, d, e, random_state=0)
assert a_s == ['c', 'b', 'a']
assert type(a_s) == list
assert_array_equal(b_s, ['c', 'b', 'a'])
assert b_s.dtype == object
assert c_s == [3, 2, 1]
assert type(c_s) == list
assert_array_equal(d_s, np.array([['c', 2],
['b', 1],
['a', 0]],
dtype=object))
assert type(d_s) == MockDataFrame
assert_array_equal(e_s.toarray(), np.array([[4, 5],
[2, 3],
[0, 1]]))
def test_check_array_complex_data_error():
X = np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]])
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# list of lists
X = [[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# tuple of tuples
X = ((1 + 2j, 3 + 4j, 5 + 7j), (2 + 3j, 4 + 5j, 6 + 7j))
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# list of np arrays
X = [np.array([1 + 2j, 3 + 4j, 5 + 7j]), np.array([2 + 3j, 4 + 5j, 6 + 7j])]
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# tuple of np arrays
X = (np.array([1 + 2j, 3 + 4j, 5 + 7j]), np.array([2 + 3j, 4 + 5j, 6 + 7j]))
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# dataframe
X = MockDataFrame(np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]))
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# sparse matrix
X = sp.coo_matrix([[0, 1 + 2j], [0, 0]])
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# target variable does not always go through check_array but should
# never accept complex data either.
y = np.array([1 + 2j, 3 + 4j, 5 + 7j, 2 + 3j, 4 + 5j, 6 + 7j])
with pytest.raises(ValueError, match="Complex data not supported"):
_check_y(y)
def test_check_array_complex_data_error():
X = np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]])
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
# list of lists
X = [[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
# tuple of tuples
X = ((1 + 2j, 3 + 4j, 5 + 7j), (2 + 3j, 4 + 5j, 6 + 7j))
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
# list of np arrays
X = [
np.array([1 + 2j, 3 + 4j, 5 + 7j]),
np.array([2 + 3j, 4 + 5j, 6 + 7j])
]
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
# tuple of np arrays
X = (np.array([1 + 2j, 3 + 4j, 5 + 7j]), np.array([2 + 3j, 4 + 5j,
6 + 7j]))
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
# dataframe
X = MockDataFrame(
np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]))
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
# sparse matrix
X = sp.coo_matrix([[0, 1 + 2j], [0, 0]])
assert_raises_regex(ValueError, "Complex data not supported", check_array,
X)
def test_check_array_complex_data_error():
X = np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]])
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
# list of lists
X = [[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
# tuple of tuples
X = ((1 + 2j, 3 + 4j, 5 + 7j), (2 + 3j, 4 + 5j, 6 + 7j))
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
# list of np arrays
X = [
np.array([1 + 2j, 3 + 4j, 5 + 7j]),
np.array([2 + 3j, 4 + 5j, 6 + 7j])
]
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
# tuple of np arrays
X = (np.array([1 + 2j, 3 + 4j, 5 + 7j]), np.array([2 + 3j, 4 + 5j,
6 + 7j]))
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
# dataframe
X = MockDataFrame(
np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]))
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
# sparse matrix
X = sp.coo_matrix([[0, 1 + 2j], [0, 0]])
with pytest.raises(ValueError, match="Complex area_data not supported"):
check_array(X)
