xinrong-databricks commented on a change in pull request #33752:
URL: https://github.com/apache/spark/pull/33752#discussion_r692360720
##########
File path: python/pyspark/pandas/series.py
##########
@@ -944,6 +944,50 @@ def between(self, left: Any, right: Any, inclusive: bool =
True) -> "Series":
return lmask & rmask
+ def cov(self, other: "Series", min_periods: Optional[int] = None) -> float:
+ """
+ Compute covariance with Series, excluding missing values.
+
+ Parameters
+ ----------
+ other : Series
+ Series with which to compute the covariance.
+ min_periods : int, optional
+ Minimum number of observations needed to have a valid result.
+
+ Returns
+ -------
+ float
+ Covariance between Series and other
+
+ Examples
+ --------
+ >>> from pyspark.pandas.config import set_option, reset_option
+ >>> set_option("compute.ops_on_diff_frames", True)
+ >>> s1 = ps.Series([0.90010907, 0.13484424, 0.62036035])
+ >>> s2 = ps.Series([0.12528585, 0.26962463, 0.51111198])
+ >>> s1.cov(s2)
+ -0.016857626527158744
+ >>> reset_option("compute.ops_on_diff_frames")
+ """
+ if not isinstance(other, Series):
+ raise TypeError("unsupported type: %s" % type(other))
Review comment:
nit: `type(other).__name__`? I'm also fine if you want to follow pandas.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
