def test_attributes_arff_from_df_mixed_dtype_categories(self):
# liac-arff imposed categorical attributes to be of sting dtype. We
# raise an error if this is not the case.
df = pd.DataFrame([[1], ['2'], [3.]])
df[0] = df[0].astype('category')
err_msg = "The column '0' of the dataframe is of 'category' dtype."
with pytest.raises(ValueError, match=err_msg):
attributes_arff_from_df(df)
def test_attributes_arff_from_df_unknown_dtype(self):
# check that an error is raised when the dtype is not supptagorted by
# liac-arff
data = [
[[1], ['2'], [3.]],
[pd.Timestamp('2012-05-01'),
pd.Timestamp('2012-05-02')],
]
dtype = ['mixed-integer', 'datetime64']
for arr, dt in zip(data, dtype):
df = pd.DataFrame(arr)
err_msg = ("The dtype '{}' of the column '0' is not currently "
"supported by liac-arff".format(dt))
with pytest.raises(ValueError, match=err_msg):
attributes_arff_from_df(df)
def test_attributes_arff_from_df_unknown_dtype(self):
# check that an error is raised when the dtype is not supported by
# liac-arff
data = [
[[1], ['2'], [3.]],
[pd.Timestamp('2012-05-01'), pd.Timestamp('2012-05-02')],
]
dtype = [
'mixed-integer',
'datetime64'
]
for arr, dt in zip(data, dtype):
df = pd.DataFrame(arr)
err_msg = ("The dtype '{}' of the column '0' is not currently "
"supported by liac-arff".format(dt))
with pytest.raises(ValueError, match=err_msg):
attributes_arff_from_df(df)
def test_attributes_arff_from_df(self):
# DataFrame case
df = pd.DataFrame(
[[1, 1.0, 'xxx', 'A', True], [2, 2.0, 'yyy', 'B', False]],
columns=['integer', 'floating', 'string', 'category', 'boolean'])
df['category'] = df['category'].astype('category')
attributes = attributes_arff_from_df(df)
self.assertEqual(attributes, [('integer', 'INTEGER'),
('floating', 'REAL'),
('string', 'STRING'),
('category', ['A', 'B']),
('boolean', ['True', 'False'])])
# SparseDataFrame case
df = pd.SparseDataFrame([[1, 1.0], [2, 2.0], [0, 0]],
columns=['integer', 'floating'],
default_fill_value=0)
df['integer'] = df['integer'].astype(np.int64)
attributes = attributes_arff_from_df(df)
self.assertEqual(attributes, [('integer', 'INTEGER'),
('floating', 'REAL')])
def test_attributes_arff_from_df(self):
# DataFrame case
df = pd.DataFrame(
[[1, 1.0, 'xxx', 'A', True], [2, 2.0, 'yyy', 'B', False]],
columns=['integer', 'floating', 'string', 'category', 'boolean']
)
df['category'] = df['category'].astype('category')
attributes = attributes_arff_from_df(df)
self.assertEqual(attributes, [('integer', 'INTEGER'),
('floating', 'REAL'),
('string', 'STRING'),
('category', ['A', 'B']),
('boolean', ['True', 'False'])])
# SparseDataFrame case
df = pd.SparseDataFrame([[1, 1.0],
[2, 2.0],
[0, 0]],
columns=['integer', 'floating'],
default_fill_value=0)
df['integer'] = df['integer'].astype(np.int64)
attributes = attributes_arff_from_df(df)
self.assertEqual(attributes, [('integer', 'INTEGER'),
('floating', 'REAL')])