def test_categorical_with_nan_consistency(self):
c = pd.Categorical.from_codes(
[-1, 0, 1, 2, 3, 4],
categories=pd.date_range('2012-01-01', periods=5, name='B'))
expected = hash_array(c, categorize=False)
c = pd.Categorical.from_codes(
[-1, 0],
categories=[pd.Timestamp('2012-01-01')])
result = hash_array(c, categorize=False)
assert result[0] in expected
assert result[1] in expected
def test_categorical_with_nan_consistency(self):
c = pd.Categorical.from_codes([-1, 0, 1, 2, 3, 4],
categories=pd.date_range('2012-01-01',
periods=5,
name='B'))
expected = hash_array(c, categorize=False)
c = pd.Categorical.from_codes([-1, 0],
categories=[pd.Timestamp('2012-01-01')])
result = hash_array(c, categorize=False)
assert result[0] in expected
assert result[1] in expected
def test_same_len_hash_collisions(self):
for l in range(8):
length = 2**(l + 8) + 1
s = tm.rands_array(length, 2)
result = hash_array(s, 'utf8')
self.assertFalse(result[0] == result[1])
for l in range(8):
length = 2**(l + 8)
s = tm.rands_array(length, 2)
result = hash_array(s, 'utf8')
self.assertFalse(result[0] == result[1])
def test_same_len_hash_collisions(self):
for l in range(8):
length = 2**(l + 8) + 1
s = tm.rands_array(length, 2)
result = hash_array(s, 'utf8')
self.assertFalse(result[0] == result[1])
for l in range(8):
length = 2**(l + 8)
s = tm.rands_array(length, 2)
result = hash_array(s, 'utf8')
self.assertFalse(result[0] == result[1])
def test_hash_collisions(self):
# hash collisions are bad
# https://github.com/pandas-dev/pandas/issues/14711#issuecomment-264885726
L = ['Ingrid-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', # noqa
'Tim-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'] # noqa
# these should be different!
result1 = hash_array(np.asarray(L[0:1], dtype=object), 'utf8')
expected1 = np.array([14963968704024874985], dtype=np.uint64)
tm.assert_numpy_array_equal(result1, expected1)
result2 = hash_array(np.asarray(L[1:2], dtype=object), 'utf8')
expected2 = np.array([16428432627716348016], dtype=np.uint64)
tm.assert_numpy_array_equal(result2, expected2)
result = hash_array(np.asarray(L, dtype=object), 'utf8')
tm.assert_numpy_array_equal(
result, np.concatenate([expected1, expected2], axis=0))
def test_hash_collisions(self):
# hash collisions are bad
# https://github.com/pandas-dev/pandas/issues/14711#issuecomment-264885726
L = ['Ingrid-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', # noqa
'Tim-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'] # noqa
# these should be different!
result1 = hash_array(np.asarray(L[0:1], dtype=object), 'utf8')
expected1 = np.array([14963968704024874985], dtype=np.uint64)
self.assert_numpy_array_equal(result1, expected1)
result2 = hash_array(np.asarray(L[1:2], dtype=object), 'utf8')
expected2 = np.array([16428432627716348016], dtype=np.uint64)
self.assert_numpy_array_equal(result2, expected2)
result = hash_array(np.asarray(L, dtype=object), 'utf8')
self.assert_numpy_array_equal(
result, np.concatenate([expected1, expected2], axis=0))
def test_hash_array(self):
for name, s in self.df.iteritems():
a = s.values
tm.assert_numpy_array_equal(hash_array(a), hash_array(a))
def test_hash_array_mixed(self):
result1 = hash_array(np.array([3, 4, 'All']))
result2 = hash_array(np.array(['3', '4', 'All']))
result3 = hash_array(np.array([3, 4, 'All'], dtype=object))
tm.assert_numpy_array_equal(result1, result2)
tm.assert_numpy_array_equal(result1, result3)
def test_hash_array(self):
for name, s in self.df.iteritems():
a = s.values
tm.assert_numpy_array_equal(hash_array(a), hash_array(a))
def test_hash_array_mixed(self):
result1 = hash_array(np.array([3, 4, 'All']))
result2 = hash_array(np.array(['3', '4', 'All']))
result3 = hash_array(np.array([3, 4, 'All'], dtype=object))
tm.assert_numpy_array_equal(result1, result2)
tm.assert_numpy_array_equal(result1, result3)