Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/20904#discussion_r179831482
--- Diff: python/pyspark/ml/stat.py ---
@@ -134,6 +134,65 @@ def corr(dataset, column, method="pearson"):
return _java2py(sc, javaCorrObj.corr(*args))
+class KolmogorovSmirnovTest(object):
+ """
+ .. note:: Experimental
+
+ Conduct the two-sided Kolmogorov Smirnov (KS) test for data sampled
from a continuous
+ distribution.
+
+ By comparing the largest difference between the empirical cumulative
+ distribution of the sample data and the theoretical distribution we
can provide a test for the
+ the null hypothesis that the sample data comes from that theoretical
distribution.
+
+ :param dataset:
+ a dataset or a dataframe containing the sample of data to test.
+ :param sampleCol:
+ Name of sample column in dataset, of any numerical type.
+ :param distName:
+ a `string` name for a theoretical distribution, currently only
support "norm".
+ :param params:
+ a list of `Double` values specifying the parameters to be used for
the theoretical
+ distribution
+ :return:
+ A dataframe that contains the Kolmogorov-Smirnov test result for the
input sampled data.
+ This DataFrame will contain a single Row with the following fields:
+ - `pValue: Double`
+ - `statistic: Double`
+
+ >>> from pyspark.ml.stat import KolmogorovSmirnovTest
+ >>> dataset = [[-1.0], [0.0], [1.0]]
+ >>> dataset = spark.createDataFrame(dataset, ['sample'])
+ >>> ksResult = KolmogorovSmirnovTest.test(dataset, 'sample', 'norm',
0.0, 1.0).collect()[0]
--- End diff --
nit: use first() instead of collect()[0]
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
