def test_categorical_dtype(self):
# GH 10153
data = """a,b,c
1,a,3.4
1,a,3.4
2,b,4.5"""
expected = pd.DataFrame({'a': Categorical(['1', '1', '2']),
'b': Categorical(['a', 'a', 'b']),
'c': Categorical(['3.4', '3.4', '4.5'])})
actual = self.read_csv(StringIO(data), dtype='category')
tm.assert_frame_equal(actual, expected)
actual = self.read_csv(StringIO(data), dtype=CategoricalDtype())
tm.assert_frame_equal(actual, expected)
actual = self.read_csv(StringIO(data), dtype={'a': 'category',
'b': 'category',
'c': CategoricalDtype()})
tm.assert_frame_equal(actual, expected)
actual = self.read_csv(StringIO(data), dtype={'b': 'category'})
expected = pd.DataFrame({'a': [1, 1, 2],
'b': Categorical(['a', 'a', 'b']),
'c': [3.4, 3.4, 4.5]})
tm.assert_frame_equal(actual, expected)
actual = self.read_csv(StringIO(data), dtype={1: 'category'})
tm.assert_frame_equal(actual, expected)
# unsorted
data = """a,b,c
1,b,3.4
1,b,3.4
2,a,4.5"""
expected = pd.DataFrame({'a': Categorical(['1', '1', '2']),
'b': Categorical(['b', 'b', 'a']),
'c': Categorical(['3.4', '3.4', '4.5'])})
actual = self.read_csv(StringIO(data), dtype='category')
tm.assert_frame_equal(actual, expected)
# missing
data = """a,b,c
1,b,3.4
1,nan,3.4
2,a,4.5"""
expected = pd.DataFrame({'a': Categorical(['1', '1', '2']),
'b': Categorical(['b', np.nan, 'a']),
'c': Categorical(['3.4', '3.4', '4.5'])})
actual = self.read_csv(StringIO(data), dtype='category')
tm.assert_frame_equal(actual, expected)
def test_pandas_dtype():
assert pandas_dtype('datetime64[ns, US/Eastern]') == DatetimeTZDtype(
'datetime64[ns, US/Eastern]')
assert pandas_dtype('category') == CategoricalDtype()
for dtype in ['M8[ns]', 'm8[ns]', 'object', 'float64', 'int64']:
assert pandas_dtype(dtype) == np.dtype(dtype)
def test_hash_vs_equality(self):
# make sure that we satisfy is semantics
dtype = self.dtype
dtype2 = CategoricalDtype()
self.assertTrue(dtype == dtype2)
self.assertTrue(dtype2 == dtype)
self.assertTrue(dtype is dtype2)
self.assertTrue(dtype2 is dtype)
self.assertTrue(hash(dtype) == hash(dtype2))
def test_is_dtype(self):
self.assertTrue(CategoricalDtype.is_dtype(self.dtype))
self.assertTrue(CategoricalDtype.is_dtype('category'))
self.assertTrue(CategoricalDtype.is_dtype(CategoricalDtype()))
self.assertFalse(CategoricalDtype.is_dtype('foo'))
self.assertFalse(CategoricalDtype.is_dtype(np.float64))
def test_construction_from_string(self):
result = CategoricalDtype.construct_from_string('category')
self.assertTrue(is_dtype_equal(self.dtype, result))
self.assertRaises(
TypeError, lambda: CategoricalDtype.construct_from_string('foo'))
def test_equality(self):
self.assertTrue(is_dtype_equal(self.dtype, 'category'))
self.assertTrue(is_dtype_equal(self.dtype, CategoricalDtype()))
self.assertFalse(is_dtype_equal(self.dtype, 'foo'))
def setUp(self):
self.dtype = CategoricalDtype()
def test_categorical_dtype(self):
dtype = CategoricalDtype()
self.assertEqual(find_common_type([dtype]), 'category')
self.assertEqual(find_common_type([dtype, dtype]), 'category')
self.assertEqual(find_common_type([np.object, dtype]), np.object)
def test_is_dtype(self):
self.assertTrue(CategoricalDtype.is_dtype(self.dtype))
self.assertTrue(CategoricalDtype.is_dtype('category'))
self.assertTrue(CategoricalDtype.is_dtype(CategoricalDtype()))
self.assertFalse(CategoricalDtype.is_dtype('foo'))
self.assertFalse(CategoricalDtype.is_dtype(np.float64))
def test_construction_from_string(self):
result = CategoricalDtype.construct_from_string('category')
self.assertTrue(is_dtype_equal(self.dtype, result))
self.assertRaises(
TypeError, lambda: CategoricalDtype.construct_from_string('foo'))
def test_categorical_dtype(self):
self.assertEqual(pandas_dtype('category'), CategoricalDtype())
def test_as_json_table_type_categorical_dtypes(self):
self.assertEqual(as_json_table_type(pd.Categorical), 'any')
self.assertEqual(as_json_table_type(CategoricalDtype()), 'any')
