def test_transform_unseen(self, X, handle_unseen, expected):
enc = LabelEncoder(cols=['cat'], handle_unseen=handle_unseen)
X = pd.DataFrame(X, columns=['cat'])
enc.fit(X)
X.iloc[0, 0] = 'foo'
result = enc.transform(X)
assert_array_equal(result, pd.DataFrame(expected))
def test_encode_nans(self, X, expected, columns):
enc = LabelEncoder(cols=['cat'])
result = enc.fit_transform(pd.DataFrame(X, columns=['cat']))
assert_array_equal(result, pd.DataFrame(expected))
ok_('cat' in enc._mapping)
ok_(isinstance(enc._mapping['cat'], pd.DataFrame))
eq_(enc._mapping['cat'].index[1], -99999)
assert_array_equal(enc._mapping['cat'].index, pd.Series(columns))
assert_array_equal(enc._mapping['cat'].columns, ['value'])
def test_encode_multiple_cols(self, X, expected):
enc = LabelEncoder(cols=['cat1', 'cat2'])
result = enc.fit_transform(pd.DataFrame(X, columns=['cat1', 'cat2']))
assert_array_equal(result, pd.DataFrame(expected))
ok_('cat1' in enc._mapping)
ok_('cat2' in enc._mapping)
ok_(isinstance(enc._mapping['cat1'], pd.DataFrame))
ok_(isinstance(enc._mapping['cat2'], pd.DataFrame))
assert_array_equal(enc._mapping['cat1'].index, ['a', 'b'])
assert_array_equal(enc._mapping['cat2'].index, ['foo', 'bar'])
assert_array_equal(enc._mapping['cat1'].columns, ['value'])
assert_array_equal(enc._mapping['cat2'].columns, ['value'])
def test_encode_all(self, X, expected):
# all columns are encoded if no cols arg passed
enc = LabelEncoder()
result = enc.fit_transform(pd.DataFrame(X, columns=['cat1', 'cat2']))
assert_array_equal(result, pd.DataFrame(expected))
assert_array_equal(enc.cols, ['cat1', 'cat2'])
ok_('cat1' in enc._mapping)
ok_('cat2' in enc._mapping)
ok_(isinstance(enc._mapping['cat1'], pd.DataFrame))
ok_(isinstance(enc._mapping['cat2'], pd.DataFrame))
assert_array_equal(enc._mapping['cat1'].index, ['a', 'b'])
assert_array_equal(enc._mapping['cat2'].index, ['foo', 'bar'])
assert_array_equal(enc._mapping['cat1'].columns, ['value'])
assert_array_equal(enc._mapping['cat2'].columns, ['value'])
def test_transform_error(self, X, expected):
enc = LabelEncoder(cols=['cat'], handle_unseen='error')
X = pd.DataFrame(X, columns=['cat'])
enc.fit(X)
X.iloc[0, 0] = 'foo'
assert_raises(ValueError, enc.transform, X)
def test_transform_before_fit(self):
enc = LabelEncoder()
assert_raises(ValueError, enc.transform, 1)
def test_init(self, kwargs, cols, handle_unseen):
enc = LabelEncoder(**kwargs)
eq_(enc.cols, cols)
eq_(enc.handle_unseen, handle_unseen)
eq_(enc._imputed, -99999)
eq_(enc._mapping, {})