Implemented dateframe.between_time (#2111)

ref #1929

Implement `DataFrame.between_time`

```py
>>> i = pd.date_range('2018-04-09', periods=4, freq='1D20min')
>>> ts = pd.DataFrame({'A': [1, 2, 3, 4]}, index=i)
>>> kts = ks.from_pandas(ts)
>>> kts
                     A
2018-04-09 00:00:00  1
2018-04-10 00:20:00  2
2018-04-11 00:40:00  3
2018-04-12 01:00:00  4

>>> kts.between_time('0:15', '0:45')
                     A
2018-04-10 00:20:00  2
2018-04-11 00:40:00  3

You get the times that are *not* between two times by setting
``start_time`` later than ``end_time``:

>>> kts.between_time('0:45', '0:15')
                     A
2018-04-09 00:00:00  1
2018-04-12 01:00:00  4
```

Author: LSturtew

databricks/koalas/frame.py

@@ -43,6 +43,7 @@
     cast,
     TYPE_CHECKING,
 )
+import datetime
 
 import numpy as np
 import pandas as pd
@@ -2982,6 +2983,90 @@ class  locomotion
             ).resolved_copy
             return DataFrame(internal)
 
+    def between_time(
+        self,
+        start_time: Union[datetime.time, str],
+        end_time: Union[datetime.time, str],
+        include_start: bool = True,
+        include_end: bool = True,
+        axis: Union[int, str] = 0,
+    ) -> Union["Series", "DataFrame"]:
+        """
+        Select values between particular times of the day (e.g., 9:00-9:30 AM).
+
+        By setting ``start_time`` to be later than ``end_time``,
+        you can get the times that are *not* between the two times.
+
+        Parameters
+        ----------
+        start_time : datetime.time or str
+            Initial time as a time filter limit.
+        end_time : datetime.time or str
+            End time as a time filter limit.
+        include_start : bool, default True
+            Whether the start time needs to be included in the result.
+        include_end : bool, default True
+            Whether the end time needs to be included in the result.
+        axis : {0 or 'index', 1 or 'columns'}, default 0
+            Determine range time on index or columns value.
+
+        Returns
+        -------
+        Series or DataFrame
+            Data from the original object filtered to the specified dates range.
+
+        Raises
+        ------
+        TypeError
+            If the index is not  a :class:`DatetimeIndex`
+
+        See Also
+        --------
+        at_time : Select values at a particular time of the day.
+        first : Select initial periods of time series based on a date offset.
+        last : Select final periods of time series based on a date offset.
+        DatetimeIndex.indexer_between_time : Get just the index locations for
+            values between particular times of the day.
+
+        Examples
+        --------
+        >>> idx = pd.date_range('2018-04-09', periods=4, freq='1D20min')
+        >>> kdf = ks.DataFrame({'A': [1, 2, 3, 4]}, index=idx)
+        >>> kdf
+                             A
+        2018-04-09 00:00:00  1
+        2018-04-10 00:20:00  2
+        2018-04-11 00:40:00  3
+        2018-04-12 01:00:00  4
+
+        >>> kdf.between_time('0:15', '0:45')
+                             A
+        2018-04-10 00:20:00  2
+        2018-04-11 00:40:00  3
+
+        You get the times that are *not* between two times by setting
+        ``start_time`` later than ``end_time``:
+
+        >>> kdf.between_time('0:45', '0:15')
+                             A
+        2018-04-09 00:00:00  1
+        2018-04-12 01:00:00  4
+        """
+        from databricks.koalas.indexes import DatetimeIndex
+
+        axis = validate_axis(axis)
+
+        if axis != 0:
+            raise NotImplementedError("between_time currently only works for axis=0")
+
+        if not isinstance(self.index, DatetimeIndex):
+            raise TypeError("Index must be DatetimeIndex")
+
+        def pandas_between_time(pdf):
+            return pdf.between_time(start_time, end_time, include_start, include_end)
+
+        return self.koalas.apply_batch(pandas_between_time)
+
     def where(self, cond, other=np.nan) -> "DataFrame":
         """
         Replace values where the condition is False.

databricks/koalas/missing/frame.py

@@ -38,7 +38,6 @@ class _MissingPandasLikeDataFrame(object):
     asfreq = _unsupported_function("asfreq")
     asof = _unsupported_function("asof")
     at_time = _unsupported_function("at_time")
-    between_time = _unsupported_function("between_time")
     boxplot = _unsupported_function("boxplot")
     combine = _unsupported_function("combine")
     combine_first = _unsupported_function("combine_first")

databricks/koalas/tests/test_dataframe.py

@@ -5422,3 +5422,26 @@ def test_align(self):
             pdf_l, pdf_r = pdf1.align(pdf2, join=join, axis=1)
             self.assert_eq(kdf_l.sort_index(), pdf_l.sort_index())
             self.assert_eq(kdf_r.sort_index(), pdf_r.sort_index())
+
+    def test_between_time(self):
+        idx = pd.date_range("2018-04-09", periods=4, freq="1D20min")
+        pdf = pd.DataFrame({"A": [1, 2, 3, 4]}, index=idx)
+        kdf = ks.from_pandas(pdf)
+        self.assert_eq(
+            pdf.between_time("0:15", "0:45"),
+            kdf.between_time("0:15", "0:45").sort_index(),
+            almost=True,
+        )
+
+        with self.assertRaisesRegex(
+            NotImplementedError, "between_time currently only works for axis=0"
+        ):
+            kdf.between_time("0:15", "0:45", axis=1)
+
+        kdf = ks.DataFrame({"A": [1, 2, 3, 4]})
+        with self.assertRaisesRegex(TypeError, "Index must be DatetimeIndex"):
+            kdf.between_time("0:15", "0:45")
+
+    def test_between_time_no_shortcut(self):
+        with ks.option_context("compute.shortcut_limit", 0):
+            self.test_between_time()

docs/source/reference/frame.rst

@@ -164,6 +164,7 @@ Reindexing / Selection / Label manipulation
    DataFrame.add_prefix
    DataFrame.add_suffix
    DataFrame.align
+   DataFrame.between_time
    DataFrame.drop
    DataFrame.droplevel
    DataFrame.drop_duplicates