diff options
Diffstat (limited to 'docs/mllib-statistics.md')
-rw-r--r-- | docs/mllib-statistics.md | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/docs/mllib-statistics.md b/docs/mllib-statistics.md index 10a5131c07..ca8c29218f 100644 --- a/docs/mllib-statistics.md +++ b/docs/mllib-statistics.md @@ -380,6 +380,46 @@ for (ChiSqTestResult result : featureTestResults) { {% endhighlight %} </div> +<div data-lang="python" markdown="1"> +[`Statistics`](api/python/index.html#pyspark.mllib.stat.Statistics$) provides methods to +run Pearson's chi-squared tests. The following example demonstrates how to run and interpret +hypothesis tests. + +{% highlight python %} +from pyspark import SparkContext +from pyspark.mllib.linalg import Vectors, Matrices +from pyspark.mllib.regresssion import LabeledPoint +from pyspark.mllib.stat import Statistics + +sc = SparkContext() + +vec = Vectors.dense(...) # a vector composed of the frequencies of events + +# compute the goodness of fit. If a second vector to test against is not supplied as a parameter, +# the test runs against a uniform distribution. +goodnessOfFitTestResult = Statistics.chiSqTest(vec) +print goodnessOfFitTestResult # summary of the test including the p-value, degrees of freedom, + # test statistic, the method used, and the null hypothesis. + +mat = Matrices.dense(...) # a contingency matrix + +# conduct Pearson's independence test on the input contingency matrix +independenceTestResult = Statistics.chiSqTest(mat) +print independenceTestResult # summary of the test including the p-value, degrees of freedom... + +obs = sc.parallelize(...) # LabeledPoint(feature, label) . + +# The contingency table is constructed from an RDD of LabeledPoint and used to conduct +# the independence test. Returns an array containing the ChiSquaredTestResult for every feature +# against the label. +featureTestResults = Statistics.chiSqTest(obs) + +for i, result in enumerate(featureTestResults): + print "Column $d:" % (i + 1) + print result +{% endhighlight %} +</div> + </div> ## Random data generation |