You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2022/09/21 05:50:05 UTC
[GitHub] [spark] itholic commented on a diff in pull request #37948: [SPARK-40327][PS][DOCS] Add resampling to API references
itholic commented on code in PR #37948:
URL: https://github.com/apache/spark/pull/37948#discussion_r976058915
##########
python/pyspark/pandas/resample.py:
##########
@@ -412,21 +412,267 @@ def _handle_output(self, psdf: DataFrame) -> FrameLike:
pass
def min(self) -> FrameLike:
+ """
+ Compute max of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").min().sort_index()
+ A B
+ 2022-05-01 0.171162 0.338864
+ 2022-05-04 0.010527 0.561204
+ 2022-05-07 NaN NaN
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("min"))
def max(self) -> FrameLike:
+ """
+ Compute max of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").max().sort_index()
+ A B
+ 2022-05-01 0.420538 0.859182
+ 2022-05-04 0.270533 0.691041
+ 2022-05-07 NaN NaN
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("max"))
def sum(self) -> FrameLike:
+ """
+ Compute sum of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").sum().sort_index()
+ A B
+ 2022-05-01 0.800160 1.679727
+ 2022-05-04 0.281060 1.252245
+ 2022-05-07 0.000000 0.000000
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("sum").fillna(0.0))
def mean(self) -> FrameLike:
+ """
+ Compute mean of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").mean().sort_index()
+ A B
+ 2022-05-01 0.266720 0.559909
+ 2022-05-04 0.140530 0.626123
+ 2022-05-07 NaN NaN
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("mean"))
def std(self) -> FrameLike:
+ """
+ Compute mean of resampled values.
Review Comment:
mean -> std ?
##########
python/pyspark/pandas/resample.py:
##########
@@ -412,21 +412,267 @@ def _handle_output(self, psdf: DataFrame) -> FrameLike:
pass
def min(self) -> FrameLike:
+ """
+ Compute max of resampled values.
Review Comment:
max -> min ?
##########
python/pyspark/pandas/resample.py:
##########
@@ -412,21 +412,267 @@ def _handle_output(self, psdf: DataFrame) -> FrameLike:
pass
def min(self) -> FrameLike:
+ """
+ Compute max of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").min().sort_index()
+ A B
+ 2022-05-01 0.171162 0.338864
+ 2022-05-04 0.010527 0.561204
+ 2022-05-07 NaN NaN
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("min"))
def max(self) -> FrameLike:
+ """
+ Compute max of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").max().sort_index()
+ A B
+ 2022-05-01 0.420538 0.859182
+ 2022-05-04 0.270533 0.691041
+ 2022-05-07 NaN NaN
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("max"))
def sum(self) -> FrameLike:
+ """
+ Compute sum of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").sum().sort_index()
+ A B
+ 2022-05-01 0.800160 1.679727
+ 2022-05-04 0.281060 1.252245
+ 2022-05-07 0.000000 0.000000
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("sum").fillna(0.0))
def mean(self) -> FrameLike:
+ """
+ Compute mean of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").mean().sort_index()
+ A B
+ 2022-05-01 0.266720 0.559909
+ 2022-05-04 0.140530 0.626123
+ 2022-05-07 NaN NaN
+ 2022-05-10 0.813726 0.745100
+ """
return self._handle_output(self._downsample("mean"))
def std(self) -> FrameLike:
+ """
+ Compute mean of resampled values.
+
+ .. versionadded:: 3.4.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> np.random.seed(22)
+ >>> dates = [
+ ... datetime(2022, 5, 1, 4, 5, 6),
+ ... datetime(2022, 5, 3),
+ ... datetime(2022, 5, 3, 23, 59, 59),
+ ... datetime(2022, 5, 4),
+ ... pd.NaT,
+ ... datetime(2022, 5, 4, 0, 0, 1),
+ ... datetime(2022, 5, 11),
+ ... ]
+ >>> df = ps.DataFrame(
+ ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]
+ ... )
+ >>> df
+ A B
+ 2022-05-01 04:05:06 0.208461 0.481681
+ 2022-05-03 00:00:00 0.420538 0.859182
+ 2022-05-03 23:59:59 0.171162 0.338864
+ 2022-05-04 00:00:00 0.270533 0.691041
+ NaT 0.220405 0.811951
+ 2022-05-04 00:00:01 0.010527 0.561204
+ 2022-05-11 00:00:00 0.813726 0.745100
+ >>> df.resample("3D").std().sort_index()
+ A B
+ 2022-05-01 0.134509 0.268835
+ 2022-05-04 0.183852 0.091809
+ 2022-05-07 NaN NaN
+ 2022-05-10 NaN NaN
+ """
return self._handle_output(self._downsample("std"))
def var(self) -> FrameLike:
+ """
+ Compute mean of resampled values.
Review Comment:
mean -> var ?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org