def test_to_datetime():
wrong_args = [pd.DataFrame({'a': [1, 2]}), {'a': [1, 2]}]
for arg in wrong_args:
with pytest.raises(ValueError) as cm:
md.to_datetime(arg)
assert '[year, month, day]' in str(cm.value)
with pytest.raises(TypeError):
md.to_datetime([[1, 2], [3, 4]])
def testToDatetime(self):
wrong_args = [pd.DataFrame({'a': [1, 2]}), {'a': [1, 2]}]
for arg in wrong_args:
with self.assertRaises(ValueError) as cm:
md.to_datetime(arg)
self.assertIn('[year, month, day]', str(cm.exception))
with self.assertRaises(TypeError):
md.to_datetime([[1, 2], [3, 4]])
def test_date_time_bin(setup):
rs = np.random.RandomState(0)
df_raw = pd.DataFrame({'a': rs.randint(1000, size=10),
'b': rs.rand(10),
'c': [pd.Timestamp(rs.randint(1604000000, 1604481373))
for _ in range(10)]},
index=pd.RangeIndex(9, -1, -1))
df = from_pandas(df_raw, chunk_size=5)
r = (df['c'] > to_datetime('2000-01-01')) & (df['c'] < to_datetime('2021-01-01'))
result = r.execute().fetch()
expected = (df_raw['c'] > pd.to_datetime('2000-01-01')) & \
(df_raw['c'] < pd.to_datetime('2021-01-01'))
pd.testing.assert_series_equal(result, expected)
def testToDatetimeExecution(self):
# scalar
r = to_datetime(1490195805, unit='s')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(1490195805, unit='s')
self.assertEqual(pd.to_datetime(result.item()), expected)
# test list like
raw = ['3/11/2000', '3/12/2000', '3/13/2000']
t = tensor(raw, chunk_size=2)
r = to_datetime(t, infer_datetime_format=True)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw, infer_datetime_format=True)
pd.testing.assert_index_equal(result, expected)
# test series
raw_series = pd.Series(raw)
s = Series(raw_series, chunk_size=2)
r = to_datetime(s)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw_series)
pd.testing.assert_series_equal(result, expected)
# test DataFrame
raw_df = pd.DataFrame({
'year': [2015, 2016],
'month': [2, 3],
'day': [4, 5]
})
df = DataFrame(raw_df, chunk_size=(1, 2))
r = to_datetime(df)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw_df)
pd.testing.assert_series_equal(result, expected)
# test Index
raw_index = pd.Index([1, 2, 3])
s = Index(raw_index, chunk_size=2)
r = to_datetime(s)
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw_index)
pd.testing.assert_index_equal(result, expected)
# test raises == 'ignore'
raw = ['13000101']
r = to_datetime(raw, format='%Y%m%d', errors='ignore')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime(raw, format='%Y%m%d', errors='ignore')
pd.testing.assert_index_equal(result, expected)
# test unit
r = to_datetime([1490195805], unit='s')
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime([1490195805], unit='s')
pd.testing.assert_index_equal(result, expected)
# test origin
r = to_datetime([1, 2, 3], unit='D', origin=pd.Timestamp('1960-01-01'))
result = self.executor.execute_dataframe(r, concat=True)[0]
expected = pd.to_datetime([1, 2, 3],
unit='D',
origin=pd.Timestamp('1960-01-01'))
pd.testing.assert_index_equal(result, expected)
def test_to_datetime_execution(setup):
# scalar
r = to_datetime(1490195805, unit='s')
result = r.execute().fetch(extra_config={
'check_dtypes': False,
'check_shape': False
})
expected = pd.to_datetime(1490195805, unit='s')
assert pd.to_datetime(result) == expected
# test list like
raw = ['3/11/2000', '3/12/2000', '3/13/2000']
t = tensor(raw, chunk_size=2)
r = to_datetime(t, infer_datetime_format=True)
result = r.execute().fetch()
expected = pd.to_datetime(raw, infer_datetime_format=True)
pd.testing.assert_index_equal(result, expected)
# test series
raw_series = pd.Series(raw)
s = Series(raw_series, chunk_size=2)
r = to_datetime(s)
result = r.execute().fetch()
expected = pd.to_datetime(raw_series)
pd.testing.assert_series_equal(result, expected)
# test DataFrame
raw_df = pd.DataFrame({
'year': [2015, 2016],
'month': [2, 3],
'day': [4, 5]
})
df = DataFrame(raw_df, chunk_size=(1, 2))
r = to_datetime(df)
result = r.execute().fetch()
expected = pd.to_datetime(raw_df)
pd.testing.assert_series_equal(result, expected)
# test Index
raw_index = pd.Index([1, 2, 3])
s = Index(raw_index, chunk_size=2)
r = to_datetime(s)
result = r.execute().fetch()
expected = pd.to_datetime(raw_index)
pd.testing.assert_index_equal(result, expected)
# test raises == 'ignore'
raw = ['13000101']
r = to_datetime(raw, format='%Y%m%d', errors='ignore')
result = r.execute().fetch()
expected = pd.to_datetime(raw, format='%Y%m%d', errors='ignore')
pd.testing.assert_index_equal(result, expected)
# test unit
r = to_datetime([1490195805], unit='s')
result = r.execute().fetch()
expected = pd.to_datetime([1490195805], unit='s')
pd.testing.assert_index_equal(result, expected)
# test origin
r = to_datetime([1, 2, 3], unit='D', origin=pd.Timestamp('1960-01-01'))
result = r.execute().fetch()
expected = pd.to_datetime([1, 2, 3],
unit='D',
origin=pd.Timestamp('1960-01-01'))
pd.testing.assert_index_equal(result, expected)