2021-04-15 19:53:30 -04:00
|
|
|
#
|
|
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
|
|
# this work for additional information regarding copyright ownership.
|
|
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
|
|
# (the "License"); you may not use this file except in compliance with
|
|
|
|
# the License. You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
|
|
|
#
|
|
|
|
|
|
|
|
import datetime
|
|
|
|
|
|
|
|
from distutils.version import LooseVersion
|
|
|
|
|
|
|
|
import pandas as pd
|
|
|
|
|
|
|
|
import pyspark.pandas as ps
|
2021-04-22 16:07:35 -04:00
|
|
|
from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
|
2021-04-22 16:07:35 -04:00
|
|
|
class DatetimeIndexTest(PandasOnSparkTestCase, TestUtils):
|
2021-04-15 19:53:30 -04:00
|
|
|
@property
|
|
|
|
def fixed_freqs(self):
|
|
|
|
return [
|
|
|
|
"D",
|
|
|
|
"H",
|
|
|
|
"T", # min
|
|
|
|
"S",
|
|
|
|
"L", # ms
|
|
|
|
"U", # us
|
|
|
|
# 'N' not supported
|
|
|
|
]
|
|
|
|
|
|
|
|
@property
|
|
|
|
def non_fixed_freqs(self):
|
|
|
|
return ["W", "Q"]
|
|
|
|
|
|
|
|
@property
|
|
|
|
def pidxs(self):
|
|
|
|
return [
|
|
|
|
pd.DatetimeIndex([0]),
|
|
|
|
pd.DatetimeIndex(["2004-01-01", "2002-12-31", "2000-04-01"]),
|
|
|
|
] + [
|
|
|
|
pd.date_range("2000-01-01", periods=3, freq=freq)
|
|
|
|
for freq in (self.fixed_freqs + self.non_fixed_freqs)
|
|
|
|
]
|
|
|
|
|
|
|
|
@property
|
2021-05-20 18:08:30 -04:00
|
|
|
def psidxs(self):
|
2021-04-15 19:53:30 -04:00
|
|
|
return [ps.from_pandas(pidx) for pidx in self.pidxs]
|
|
|
|
|
|
|
|
@property
|
|
|
|
def idx_pairs(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
return list(zip(self.psidxs, self.pidxs))
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def _disallow_nanoseconds(self, f):
|
|
|
|
self.assertRaises(ValueError, lambda: f(freq="ns"))
|
|
|
|
self.assertRaises(ValueError, lambda: f(freq="N"))
|
|
|
|
|
|
|
|
def test_properties(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
|
|
|
self.assert_eq(psidx.year, pidx.year)
|
|
|
|
self.assert_eq(psidx.month, pidx.month)
|
|
|
|
self.assert_eq(psidx.day, pidx.day)
|
|
|
|
self.assert_eq(psidx.hour, pidx.hour)
|
|
|
|
self.assert_eq(psidx.minute, pidx.minute)
|
|
|
|
self.assert_eq(psidx.second, pidx.second)
|
|
|
|
self.assert_eq(psidx.microsecond, pidx.microsecond)
|
|
|
|
self.assert_eq(psidx.week, pidx.week)
|
|
|
|
self.assert_eq(psidx.weekofyear, pidx.weekofyear)
|
|
|
|
self.assert_eq(psidx.dayofweek, pidx.dayofweek)
|
|
|
|
self.assert_eq(psidx.weekday, pidx.weekday)
|
|
|
|
self.assert_eq(psidx.dayofyear, pidx.dayofyear)
|
|
|
|
self.assert_eq(psidx.quarter, pidx.quarter)
|
|
|
|
self.assert_eq(psidx.daysinmonth, pidx.daysinmonth)
|
|
|
|
self.assert_eq(psidx.days_in_month, pidx.days_in_month)
|
|
|
|
self.assert_eq(psidx.is_month_start, pd.Index(pidx.is_month_start))
|
|
|
|
self.assert_eq(psidx.is_month_end, pd.Index(pidx.is_month_end))
|
|
|
|
self.assert_eq(psidx.is_quarter_start, pd.Index(pidx.is_quarter_start))
|
|
|
|
self.assert_eq(psidx.is_quarter_end, pd.Index(pidx.is_quarter_end))
|
|
|
|
self.assert_eq(psidx.is_year_start, pd.Index(pidx.is_year_start))
|
|
|
|
self.assert_eq(psidx.is_year_end, pd.Index(pidx.is_year_end))
|
|
|
|
self.assert_eq(psidx.is_leap_year, pd.Index(pidx.is_leap_year))
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
if LooseVersion(pd.__version__) >= LooseVersion("1.2.0"):
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assert_eq(psidx.day_of_year, pidx.day_of_year)
|
|
|
|
self.assert_eq(psidx.day_of_week, pidx.day_of_week)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_ceil(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
for freq in self.fixed_freqs:
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assert_eq(psidx.ceil(freq), pidx.ceil(freq))
|
2021-04-15 19:53:30 -04:00
|
|
|
|
2021-05-20 18:08:30 -04:00
|
|
|
self._disallow_nanoseconds(self.psidxs[0].ceil)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_floor(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
for freq in self.fixed_freqs:
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assert_eq(psidx.floor(freq), pidx.floor(freq))
|
2021-04-15 19:53:30 -04:00
|
|
|
|
2021-05-20 18:08:30 -04:00
|
|
|
self._disallow_nanoseconds(self.psidxs[0].floor)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_round(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
for freq in self.fixed_freqs:
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assert_eq(psidx.round(freq), pidx.round(freq))
|
2021-04-15 19:53:30 -04:00
|
|
|
|
2021-05-20 18:08:30 -04:00
|
|
|
self._disallow_nanoseconds(self.psidxs[0].round)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_day_name(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
|
|
|
self.assert_eq(psidx.day_name(), pidx.day_name())
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_month_name(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
|
|
|
self.assert_eq(psidx.day_name(), pidx.day_name())
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_normalize(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
|
|
|
self.assert_eq(psidx.normalize(), pidx.normalize())
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
def test_strftime(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.strftime(date_format="%B %d, %Y"), pidx.strftime(date_format="%B %d, %Y")
|
2021-04-15 19:53:30 -04:00
|
|
|
)
|
|
|
|
|
|
|
|
def test_indexer_between_time(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_between_time("00:00:00", "00:01:00").sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_between_time("00:00:00", "00:01:00")),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_between_time(
|
2021-04-15 19:53:30 -04:00
|
|
|
datetime.time(0, 0, 0), datetime.time(0, 1, 0)
|
|
|
|
).sort_values(),
|
|
|
|
pd.Index(pidx.indexer_between_time(datetime.time(0, 0, 0), datetime.time(0, 1, 0))),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_between_time("00:00:00", "00:01:00", True, False).sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_between_time("00:00:00", "00:01:00", True, False)),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_between_time("00:00:00", "00:01:00", False, True).sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_between_time("00:00:00", "00:01:00", False, True)),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_between_time("00:00:00", "00:01:00", False, False).sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_between_time("00:00:00", "00:01:00", False, False)),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_between_time("00:00:00", "00:01:00", True, True).sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_between_time("00:00:00", "00:01:00", True, True)),
|
|
|
|
)
|
|
|
|
|
|
|
|
def test_indexer_at_time(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_at_time("00:00:00").sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_at_time("00:00:00")),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_at_time(datetime.time(0, 1, 0)).sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_at_time(datetime.time(0, 1, 0))),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assert_eq(
|
2021-05-20 18:08:30 -04:00
|
|
|
psidx.indexer_at_time("00:00:01").sort_values(),
|
2021-04-15 19:53:30 -04:00
|
|
|
pd.Index(pidx.indexer_at_time("00:00:01")),
|
|
|
|
)
|
|
|
|
|
|
|
|
self.assertRaises(
|
|
|
|
NotImplementedError,
|
|
|
|
lambda: ps.DatetimeIndex([0]).indexer_at_time("00:00:00", asof=True),
|
|
|
|
)
|
|
|
|
|
|
|
|
def test_arithmetic_op_exceptions(self):
|
2021-05-20 18:08:30 -04:00
|
|
|
for psidx, pidx in self.idx_pairs:
|
2021-04-15 19:53:30 -04:00
|
|
|
py_datetime = pidx.to_pydatetime()
|
2021-05-20 18:08:30 -04:00
|
|
|
for other in [1, 0.1, psidx, psidx.to_series().reset_index(drop=True), py_datetime]:
|
[SPARK-35338][PYTHON] Separate arithmetic operations into data type based structures
### What changes were proposed in this pull request?
The PR is proposed for **pandas APIs on Spark**, in order to separate arithmetic operations shown as below into data-type-based structures.
`__add__, __sub__, __mul__, __truediv__, __floordiv__, __pow__, __mod__,
__radd__, __rsub__, __rmul__, __rtruediv__, __rfloordiv__, __rpow__,__rmod__`
DataTypeOps and subclasses are introduced.
The existing behaviors of each arithmetic operation should be preserved.
### Why are the changes needed?
Currently, the same arithmetic operation of all data types is defined in one function, so it’s difficult to extend the behavior change based on the data types.
Introducing DataTypeOps would be the foundation for [pandas APIs on Spark: Separate basic operations into data type based structures.](https://docs.google.com/document/d/12MS6xK0hETYmrcl5b9pX5lgV4FmGVfpmcSKq--_oQlc/edit?usp=sharing).
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tests are introduced under pyspark.pandas.tests.data_type_ops. One test file per DataTypeOps class.
Closes #32596 from xinrong-databricks/datatypeop_arith_fix.
Authored-by: Xinrong Meng <xinrong.meng@databricks.com>
Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
2021-05-19 22:47:00 -04:00
|
|
|
expected_err_msg = "Addition can not be applied to datetimes."
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx + other)
|
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: other + psidx)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
[SPARK-35338][PYTHON] Separate arithmetic operations into data type based structures
### What changes were proposed in this pull request?
The PR is proposed for **pandas APIs on Spark**, in order to separate arithmetic operations shown as below into data-type-based structures.
`__add__, __sub__, __mul__, __truediv__, __floordiv__, __pow__, __mod__,
__radd__, __rsub__, __rmul__, __rtruediv__, __rfloordiv__, __rpow__,__rmod__`
DataTypeOps and subclasses are introduced.
The existing behaviors of each arithmetic operation should be preserved.
### Why are the changes needed?
Currently, the same arithmetic operation of all data types is defined in one function, so it’s difficult to extend the behavior change based on the data types.
Introducing DataTypeOps would be the foundation for [pandas APIs on Spark: Separate basic operations into data type based structures.](https://docs.google.com/document/d/12MS6xK0hETYmrcl5b9pX5lgV4FmGVfpmcSKq--_oQlc/edit?usp=sharing).
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tests are introduced under pyspark.pandas.tests.data_type_ops. One test file per DataTypeOps class.
Closes #32596 from xinrong-databricks/datatypeop_arith_fix.
Authored-by: Xinrong Meng <xinrong.meng@databricks.com>
Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
2021-05-19 22:47:00 -04:00
|
|
|
expected_err_msg = "Multiplication can not be applied to datetimes."
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx * other)
|
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: other * psidx)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
[SPARK-35338][PYTHON] Separate arithmetic operations into data type based structures
### What changes were proposed in this pull request?
The PR is proposed for **pandas APIs on Spark**, in order to separate arithmetic operations shown as below into data-type-based structures.
`__add__, __sub__, __mul__, __truediv__, __floordiv__, __pow__, __mod__,
__radd__, __rsub__, __rmul__, __rtruediv__, __rfloordiv__, __rpow__,__rmod__`
DataTypeOps and subclasses are introduced.
The existing behaviors of each arithmetic operation should be preserved.
### Why are the changes needed?
Currently, the same arithmetic operation of all data types is defined in one function, so it’s difficult to extend the behavior change based on the data types.
Introducing DataTypeOps would be the foundation for [pandas APIs on Spark: Separate basic operations into data type based structures.](https://docs.google.com/document/d/12MS6xK0hETYmrcl5b9pX5lgV4FmGVfpmcSKq--_oQlc/edit?usp=sharing).
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tests are introduced under pyspark.pandas.tests.data_type_ops. One test file per DataTypeOps class.
Closes #32596 from xinrong-databricks/datatypeop_arith_fix.
Authored-by: Xinrong Meng <xinrong.meng@databricks.com>
Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
2021-05-19 22:47:00 -04:00
|
|
|
expected_err_msg = "True division can not be applied to datetimes."
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx / other)
|
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: other / psidx)
|
[SPARK-35338][PYTHON] Separate arithmetic operations into data type based structures
### What changes were proposed in this pull request?
The PR is proposed for **pandas APIs on Spark**, in order to separate arithmetic operations shown as below into data-type-based structures.
`__add__, __sub__, __mul__, __truediv__, __floordiv__, __pow__, __mod__,
__radd__, __rsub__, __rmul__, __rtruediv__, __rfloordiv__, __rpow__,__rmod__`
DataTypeOps and subclasses are introduced.
The existing behaviors of each arithmetic operation should be preserved.
### Why are the changes needed?
Currently, the same arithmetic operation of all data types is defined in one function, so it’s difficult to extend the behavior change based on the data types.
Introducing DataTypeOps would be the foundation for [pandas APIs on Spark: Separate basic operations into data type based structures.](https://docs.google.com/document/d/12MS6xK0hETYmrcl5b9pX5lgV4FmGVfpmcSKq--_oQlc/edit?usp=sharing).
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tests are introduced under pyspark.pandas.tests.data_type_ops. One test file per DataTypeOps class.
Closes #32596 from xinrong-databricks/datatypeop_arith_fix.
Authored-by: Xinrong Meng <xinrong.meng@databricks.com>
Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
2021-05-19 22:47:00 -04:00
|
|
|
|
|
|
|
expected_err_msg = "Floor division can not be applied to datetimes."
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx // other)
|
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: other // psidx)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
[SPARK-35338][PYTHON] Separate arithmetic operations into data type based structures
### What changes were proposed in this pull request?
The PR is proposed for **pandas APIs on Spark**, in order to separate arithmetic operations shown as below into data-type-based structures.
`__add__, __sub__, __mul__, __truediv__, __floordiv__, __pow__, __mod__,
__radd__, __rsub__, __rmul__, __rtruediv__, __rfloordiv__, __rpow__,__rmod__`
DataTypeOps and subclasses are introduced.
The existing behaviors of each arithmetic operation should be preserved.
### Why are the changes needed?
Currently, the same arithmetic operation of all data types is defined in one function, so it’s difficult to extend the behavior change based on the data types.
Introducing DataTypeOps would be the foundation for [pandas APIs on Spark: Separate basic operations into data type based structures.](https://docs.google.com/document/d/12MS6xK0hETYmrcl5b9pX5lgV4FmGVfpmcSKq--_oQlc/edit?usp=sharing).
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tests are introduced under pyspark.pandas.tests.data_type_ops. One test file per DataTypeOps class.
Closes #32596 from xinrong-databricks/datatypeop_arith_fix.
Authored-by: Xinrong Meng <xinrong.meng@databricks.com>
Signed-off-by: Takuya UESHIN <ueshin@databricks.com>
2021-05-19 22:47:00 -04:00
|
|
|
expected_err_msg = "Modulo can not be applied to datetimes."
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx % other)
|
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: other % psidx)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
expected_err_msg = "datetime subtraction can only be applied to datetime series."
|
|
|
|
|
|
|
|
for other in [1, 0.1]:
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx - other)
|
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: other - psidx)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
2021-05-20 18:08:30 -04:00
|
|
|
self.assertRaisesRegex(TypeError, expected_err_msg, lambda: psidx - other)
|
|
|
|
self.assertRaises(NotImplementedError, lambda: py_datetime - psidx)
|
2021-04-15 19:53:30 -04:00
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
import unittest
|
|
|
|
from pyspark.pandas.tests.indexes.test_datetime import * # noqa: F401
|
|
|
|
|
|
|
|
try:
|
|
|
|
import xmlrunner # type: ignore[import]
|
2021-05-20 18:08:30 -04:00
|
|
|
|
|
|
|
testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
|
2021-04-15 19:53:30 -04:00
|
|
|
except ImportError:
|
|
|
|
testRunner = None
|
|
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|