From 159239e6225b5beaa4c101509a38d211975ebc87 Mon Sep 17 00:00:00 2001 From: Xin Ren Date: Mon, 21 Mar 2016 16:09:34 -0700 Subject: [PATCH] [SPARK-13019][DOCS] Replace example code in mllib-statistics.md using include_example https://issues.apache.org/jira/browse/SPARK-13019 The example code in the user guide is embedded in the markdown and hence it is not easy to test. It would be nice to automatically test them. This JIRA is to discuss options to automate example code testing and see what we can do in Spark 1.6. Goal is to move actual example code to spark/examples and test compilation in Jenkins builds. Then in the markdown, we can reference part of the code to show in the user guide. This requires adding a Jekyll tag that is similar to https://github.com/jekyll/jekyll/blob/master/lib/jekyll/tags/include.rb, e.g., called include_example. `{% include_example scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala %}` Jekyll will find `examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala` and pick code blocks marked "example" and replace code block in `{% highlight %}` in the markdown. See more sub-tasks in parent ticket: https://issues.apache.org/jira/browse/SPARK-11337 Author: Xin Ren Closes #11108 from keypointt/SPARK-13019. --- docs/mllib-statistics.md | 438 +++--------------- .../mllib/JavaCorrelationsExample.java | 70 +++ .../mllib/JavaHypothesisTestingExample.java | 84 ++++ ...isTestingKolmogorovSmirnovTestExample.java | 49 ++ .../JavaKernelDensityEstimationExample.java | 53 +++ .../mllib/JavaStratifiedSamplingExample.java | 75 +++ .../mllib/JavaSummaryStatisticsExample.java | 56 +++ .../main/python/mllib/correlations_example.py | 48 ++ .../mllib/hypothesis_testing_example.py | 65 +++ ...testing_kolmogorov_smirnov_test_example.py | 40 ++ .../kernel_density_estimation_example.py | 44 ++ .../mllib/stratified_sampling_example.py | 38 ++ .../mllib/summary_statistics_example.py | 42 ++ .../examples/mllib/CorrelationsExample.scala | 62 +++ .../mllib/HypothesisTestingExample.scala | 80 ++++ ...sTestingKolmogorovSmirnovTestExample.scala | 54 +++ .../KernelDensityEstimationExample.scala | 54 +++ .../mllib/StratifiedSamplingExample.scala | 53 +++ .../mllib/SummaryStatisticsExample.scala | 53 +++ 19 files changed, 1076 insertions(+), 382 deletions(-) create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java create mode 100644 examples/src/main/python/mllib/correlations_example.py create mode 100644 examples/src/main/python/mllib/hypothesis_testing_example.py create mode 100644 examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py create mode 100644 examples/src/main/python/mllib/kernel_density_estimation_example.py create mode 100644 examples/src/main/python/mllib/stratified_sampling_example.py create mode 100644 examples/src/main/python/mllib/summary_statistics_example.py create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/CorrelationsExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingKolmogorovSmirnovTestExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/KernelDensityEstimationExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala diff --git a/docs/mllib-statistics.md b/docs/mllib-statistics.md index b773031bc72ee..02b81f153bf7f 100644 --- a/docs/mllib-statistics.md +++ b/docs/mllib-statistics.md @@ -10,24 +10,24 @@ displayTitle: Basic Statistics - spark.mllib `\[ \newcommand{\R}{\mathbb{R}} -\newcommand{\E}{\mathbb{E}} +\newcommand{\E}{\mathbb{E}} \newcommand{\x}{\mathbf{x}} \newcommand{\y}{\mathbf{y}} \newcommand{\wv}{\mathbf{w}} \newcommand{\av}{\mathbf{\alpha}} \newcommand{\bv}{\mathbf{b}} \newcommand{\N}{\mathbb{N}} -\newcommand{\id}{\mathbf{I}} -\newcommand{\ind}{\mathbf{1}} -\newcommand{\0}{\mathbf{0}} -\newcommand{\unit}{\mathbf{e}} -\newcommand{\one}{\mathbf{1}} +\newcommand{\id}{\mathbf{I}} +\newcommand{\ind}{\mathbf{1}} +\newcommand{\0}{\mathbf{0}} +\newcommand{\unit}{\mathbf{e}} +\newcommand{\one}{\mathbf{1}} \newcommand{\zero}{\mathbf{0}} \]` -## Summary statistics +## Summary statistics -We provide column summary statistics for `RDD[Vector]` through the function `colStats` +We provide column summary statistics for `RDD[Vector]` through the function `colStats` available in `Statistics`.
@@ -40,19 +40,7 @@ total count. Refer to the [`MultivariateStatisticalSummary` Scala docs](api/scala/index.html#org.apache.spark.mllib.stat.MultivariateStatisticalSummary) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.linalg.Vector -import org.apache.spark.mllib.stat.{MultivariateStatisticalSummary, Statistics} - -val observations: RDD[Vector] = ... // an RDD of Vectors - -// Compute column summary statistics. -val summary: MultivariateStatisticalSummary = Statistics.colStats(observations) -println(summary.mean) // a dense vector containing the mean value for each column -println(summary.variance) // column-wise variance -println(summary.numNonzeros) // number of nonzeros in each column - -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala %}
@@ -64,24 +52,7 @@ total count. Refer to the [`MultivariateStatisticalSummary` Java docs](api/java/org/apache/spark/mllib/stat/MultivariateStatisticalSummary.html) for details on the API. -{% highlight java %} -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.mllib.linalg.Vector; -import org.apache.spark.mllib.stat.MultivariateStatisticalSummary; -import org.apache.spark.mllib.stat.Statistics; - -JavaSparkContext jsc = ... - -JavaRDD mat = ... // an RDD of Vectors - -// Compute column summary statistics. -MultivariateStatisticalSummary summary = Statistics.colStats(mat.rdd()); -System.out.println(summary.mean()); // a dense vector containing the mean value for each column -System.out.println(summary.variance()); // column-wise variance -System.out.println(summary.numNonzeros()); // number of nonzeros in each column - -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java %}
@@ -92,20 +63,7 @@ total count. Refer to the [`MultivariateStatisticalSummary` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.stat.MultivariateStatisticalSummary) for more details on the API. -{% highlight python %} -from pyspark.mllib.stat import Statistics - -sc = ... # SparkContext - -mat = ... # an RDD of Vectors - -# Compute column summary statistics. -summary = Statistics.colStats(mat) -print(summary.mean()) -print(summary.variance()) -print(summary.numNonzeros()) - -{% endhighlight %} +{% include_example python/mllib/summary_statistics_example.py %}
@@ -113,96 +71,38 @@ print(summary.numNonzeros()) ## Correlations Calculating the correlation between two series of data is a common operation in Statistics. In `spark.mllib` -we provide the flexibility to calculate pairwise correlations among many series. The supported +we provide the flexibility to calculate pairwise correlations among many series. The supported correlation methods are currently Pearson's and Spearman's correlation. - +
-[`Statistics`](api/scala/index.html#org.apache.spark.mllib.stat.Statistics$) provides methods to -calculate correlations between series. Depending on the type of input, two `RDD[Double]`s or +[`Statistics`](api/scala/index.html#org.apache.spark.mllib.stat.Statistics$) provides methods to +calculate correlations between series. Depending on the type of input, two `RDD[Double]`s or an `RDD[Vector]`, the output will be a `Double` or the correlation `Matrix` respectively. Refer to the [`Statistics` Scala docs](api/scala/index.html#org.apache.spark.mllib.stat.Statistics) for details on the API. -{% highlight scala %} -import org.apache.spark.SparkContext -import org.apache.spark.mllib.linalg._ -import org.apache.spark.mllib.stat.Statistics - -val sc: SparkContext = ... - -val seriesX: RDD[Double] = ... // a series -val seriesY: RDD[Double] = ... // must have the same number of partitions and cardinality as seriesX - -// compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. If a -// method is not specified, Pearson's method will be used by default. -val correlation: Double = Statistics.corr(seriesX, seriesY, "pearson") - -val data: RDD[Vector] = ... // note that each Vector is a row and not a column - -// calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method. -// If a method is not specified, Pearson's method will be used by default. -val correlMatrix: Matrix = Statistics.corr(data, "pearson") - -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/CorrelationsExample.scala %}
-[`Statistics`](api/java/org/apache/spark/mllib/stat/Statistics.html) provides methods to -calculate correlations between series. Depending on the type of input, two `JavaDoubleRDD`s or +[`Statistics`](api/java/org/apache/spark/mllib/stat/Statistics.html) provides methods to +calculate correlations between series. Depending on the type of input, two `JavaDoubleRDD`s or a `JavaRDD`, the output will be a `Double` or the correlation `Matrix` respectively. Refer to the [`Statistics` Java docs](api/java/org/apache/spark/mllib/stat/Statistics.html) for details on the API. -{% highlight java %} -import org.apache.spark.api.java.JavaDoubleRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.mllib.linalg.*; -import org.apache.spark.mllib.stat.Statistics; - -JavaSparkContext jsc = ... - -JavaDoubleRDD seriesX = ... // a series -JavaDoubleRDD seriesY = ... // must have the same number of partitions and cardinality as seriesX - -// compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. If a -// method is not specified, Pearson's method will be used by default. -Double correlation = Statistics.corr(seriesX.srdd(), seriesY.srdd(), "pearson"); - -JavaRDD data = ... // note that each Vector is a row and not a column - -// calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method. -// If a method is not specified, Pearson's method will be used by default. -Matrix correlMatrix = Statistics.corr(data.rdd(), "pearson"); - -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java %}
-[`Statistics`](api/python/pyspark.mllib.html#pyspark.mllib.stat.Statistics) provides methods to -calculate correlations between series. Depending on the type of input, two `RDD[Double]`s or +[`Statistics`](api/python/pyspark.mllib.html#pyspark.mllib.stat.Statistics) provides methods to +calculate correlations between series. Depending on the type of input, two `RDD[Double]`s or an `RDD[Vector]`, the output will be a `Double` or the correlation `Matrix` respectively. Refer to the [`Statistics` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.stat.Statistics) for more details on the API. -{% highlight python %} -from pyspark.mllib.stat import Statistics - -sc = ... # SparkContext - -seriesX = ... # a series -seriesY = ... # must have the same number of partitions and cardinality as seriesX - -# Compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. If a -# method is not specified, Pearson's method will be used by default. -print(Statistics.corr(seriesX, seriesY, method="pearson")) - -data = ... # an RDD of Vectors -# calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method. -# If a method is not specified, Pearson's method will be used by default. -print(Statistics.corr(data, method="pearson")) - -{% endhighlight %} +{% include_example python/mllib/correlations_example.py %}
@@ -211,187 +111,76 @@ print(Statistics.corr(data, method="pearson")) Unlike the other statistics functions, which reside in `spark.mllib`, stratified sampling methods, `sampleByKey` and `sampleByKeyExact`, can be performed on RDD's of key-value pairs. For stratified -sampling, the keys can be thought of as a label and the value as a specific attribute. For example -the key can be man or woman, or document ids, and the respective values can be the list of ages -of the people in the population or the list of words in the documents. The `sampleByKey` method -will flip a coin to decide whether an observation will be sampled or not, therefore requires one -pass over the data, and provides an *expected* sample size. `sampleByKeyExact` requires significant +sampling, the keys can be thought of as a label and the value as a specific attribute. For example +the key can be man or woman, or document ids, and the respective values can be the list of ages +of the people in the population or the list of words in the documents. The `sampleByKey` method +will flip a coin to decide whether an observation will be sampled or not, therefore requires one +pass over the data, and provides an *expected* sample size. `sampleByKeyExact` requires significant more resources than the per-stratum simple random sampling used in `sampleByKey`, but will provide -the exact sampling size with 99.99% confidence. `sampleByKeyExact` is currently not supported in +the exact sampling size with 99.99% confidence. `sampleByKeyExact` is currently not supported in python.
[`sampleByKeyExact()`](api/scala/index.html#org.apache.spark.rdd.PairRDDFunctions) allows users to -sample exactly $\lceil f_k \cdot n_k \rceil \, \forall k \in K$ items, where $f_k$ is the desired +sample exactly $\lceil f_k \cdot n_k \rceil \, \forall k \in K$ items, where $f_k$ is the desired fraction for key $k$, $n_k$ is the number of key-value pairs for key $k$, and $K$ is the set of -keys. Sampling without replacement requires one additional pass over the RDD to guarantee sample +keys. Sampling without replacement requires one additional pass over the RDD to guarantee sample size, whereas sampling with replacement requires two additional passes. -{% highlight scala %} -import org.apache.spark.SparkContext -import org.apache.spark.SparkContext._ -import org.apache.spark.rdd.PairRDDFunctions - -val sc: SparkContext = ... - -val data = ... // an RDD[(K, V)] of any key value pairs -val fractions: Map[K, Double] = ... // specify the exact fraction desired from each key - -// Get an exact sample from each stratum -val approxSample = data.sampleByKey(withReplacement = false, fractions) -val exactSample = data.sampleByKeyExact(withReplacement = false, fractions) - -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala %}
[`sampleByKeyExact()`](api/java/org/apache/spark/api/java/JavaPairRDD.html) allows users to -sample exactly $\lceil f_k \cdot n_k \rceil \, \forall k \in K$ items, where $f_k$ is the desired +sample exactly $\lceil f_k \cdot n_k \rceil \, \forall k \in K$ items, where $f_k$ is the desired fraction for key $k$, $n_k$ is the number of key-value pairs for key $k$, and $K$ is the set of -keys. Sampling without replacement requires one additional pass over the RDD to guarantee sample +keys. Sampling without replacement requires one additional pass over the RDD to guarantee sample size, whereas sampling with replacement requires two additional passes. -{% highlight java %} -import java.util.Map; - -import org.apache.spark.api.java.JavaPairRDD; -import org.apache.spark.api.java.JavaSparkContext; - -JavaSparkContext jsc = ... - -JavaPairRDD data = ... // an RDD of any key value pairs -Map fractions = ... // specify the exact fraction desired from each key - -// Get an exact sample from each stratum -JavaPairRDD approxSample = data.sampleByKey(false, fractions); -JavaPairRDD exactSample = data.sampleByKeyExact(false, fractions); - -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java %}
[`sampleByKey()`](api/python/pyspark.html#pyspark.RDD.sampleByKey) allows users to -sample approximately $\lceil f_k \cdot n_k \rceil \, \forall k \in K$ items, where $f_k$ is the -desired fraction for key $k$, $n_k$ is the number of key-value pairs for key $k$, and $K$ is the +sample approximately $\lceil f_k \cdot n_k \rceil \, \forall k \in K$ items, where $f_k$ is the +desired fraction for key $k$, $n_k$ is the number of key-value pairs for key $k$, and $K$ is the set of keys. *Note:* `sampleByKeyExact()` is currently not supported in Python. -{% highlight python %} - -sc = ... # SparkContext - -data = ... # an RDD of any key value pairs -fractions = ... # specify the exact fraction desired from each key as a dictionary - -approxSample = data.sampleByKey(False, fractions); - -{% endhighlight %} +{% include_example python/mllib/stratified_sampling_example.py %}
## Hypothesis testing -Hypothesis testing is a powerful tool in statistics to determine whether a result is statistically -significant, whether this result occurred by chance or not. `spark.mllib` currently supports Pearson's +Hypothesis testing is a powerful tool in statistics to determine whether a result is statistically +significant, whether this result occurred by chance or not. `spark.mllib` currently supports Pearson's chi-squared ( $\chi^2$) tests for goodness of fit and independence. The input data types determine -whether the goodness of fit or the independence test is conducted. The goodness of fit test requires +whether the goodness of fit or the independence test is conducted. The goodness of fit test requires an input type of `Vector`, whereas the independence test requires a `Matrix` as input. -`spark.mllib` also supports the input type `RDD[LabeledPoint]` to enable feature selection via chi-squared +`spark.mllib` also supports the input type `RDD[LabeledPoint]` to enable feature selection via chi-squared independence tests.
-[`Statistics`](api/scala/index.html#org.apache.spark.mllib.stat.Statistics$) provides methods to -run Pearson's chi-squared tests. The following example demonstrates how to run and interpret +[`Statistics`](api/scala/index.html#org.apache.spark.mllib.stat.Statistics$) provides methods to +run Pearson's chi-squared tests. The following example demonstrates how to run and interpret hypothesis tests. -{% highlight scala %} -import org.apache.spark.SparkContext -import org.apache.spark.mllib.linalg._ -import org.apache.spark.mllib.regression.LabeledPoint -import org.apache.spark.mllib.stat.Statistics._ - -val sc: SparkContext = ... - -val vec: Vector = ... // 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. -val goodnessOfFitTestResult = Statistics.chiSqTest(vec) -println(goodnessOfFitTestResult) // summary of the test including the p-value, degrees of freedom, - // test statistic, the method used, and the null hypothesis. - -val mat: Matrix = ... // a contingency matrix - -// conduct Pearson's independence test on the input contingency matrix -val independenceTestResult = Statistics.chiSqTest(mat) -println(independenceTestResult) // summary of the test including the p-value, degrees of freedom... - -val obs: RDD[LabeledPoint] = ... // (feature, label) pairs. - -// The contingency table is constructed from the raw (feature, label) pairs and used to conduct -// the independence test. Returns an array containing the ChiSquaredTestResult for every feature -// against the label. -val featureTestResults: Array[ChiSqTestResult] = Statistics.chiSqTest(obs) -var i = 1 -featureTestResults.foreach { result => - println(s"Column $i:\n$result") - i += 1 -} // summary of the test - -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala %}
-[`Statistics`](api/java/org/apache/spark/mllib/stat/Statistics.html) provides methods to -run Pearson's chi-squared tests. The following example demonstrates how to run and interpret +[`Statistics`](api/java/org/apache/spark/mllib/stat/Statistics.html) provides methods to +run Pearson's chi-squared tests. The following example demonstrates how to run and interpret hypothesis tests. Refer to the [`ChiSqTestResult` Java docs](api/java/org/apache/spark/mllib/stat/test/ChiSqTestResult.html) for details on the API. -{% highlight java %} -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; -import org.apache.spark.mllib.linalg.*; -import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.mllib.stat.Statistics; -import org.apache.spark.mllib.stat.test.ChiSqTestResult; - -JavaSparkContext jsc = ... - -Vector vec = ... // 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. -ChiSqTestResult goodnessOfFitTestResult = Statistics.chiSqTest(vec); -// summary of the test including the p-value, degrees of freedom, test statistic, the method used, -// and the null hypothesis. -System.out.println(goodnessOfFitTestResult); - -Matrix mat = ... // a contingency matrix - -// conduct Pearson's independence test on the input contingency matrix -ChiSqTestResult independenceTestResult = Statistics.chiSqTest(mat); -// summary of the test including the p-value, degrees of freedom... -System.out.println(independenceTestResult); - -JavaRDD obs = ... // an RDD of labeled points - -// The contingency table is constructed from the raw (feature, label) pairs and used to conduct -// the independence test. Returns an array containing the ChiSquaredTestResult for every feature -// against the label. -ChiSqTestResult[] featureTestResults = Statistics.chiSqTest(obs.rdd()); -int i = 1; -for (ChiSqTestResult result : featureTestResults) { - System.out.println("Column " + i + ":"); - System.out.println(result); // summary of the test - i++; -} - -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java %}
@@ -401,50 +190,18 @@ hypothesis tests. Refer to the [`Statistics` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.stat.Statistics) for more details on the API. -{% 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 %} +{% include_example python/mllib/hypothesis_testing_example.py %}
Additionally, `spark.mllib` provides a 1-sample, 2-sided implementation of the Kolmogorov-Smirnov (KS) test for equality of probability distributions. By providing the name of a theoretical distribution -(currently solely supported for the normal distribution) and its parameters, or a function to +(currently solely supported for the normal distribution) and its parameters, or a function to calculate the cumulative distribution according to a given theoretical distribution, the user can test the null hypothesis that their sample is drawn from that distribution. In the case that the user tests against the normal distribution (`distName="norm"`), but does not provide distribution -parameters, the test initializes to the standard normal distribution and logs an appropriate +parameters, the test initializes to the standard normal distribution and logs an appropriate message.
@@ -455,21 +212,7 @@ and interpret the hypothesis tests. Refer to the [`Statistics` Scala docs](api/scala/index.html#org.apache.spark.mllib.stat.Statistics) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.stat.Statistics - -val data: RDD[Double] = ... // an RDD of sample data - -// run a KS test for the sample versus a standard normal distribution -val testResult = Statistics.kolmogorovSmirnovTest(data, "norm", 0, 1) -println(testResult) // summary of the test including the p-value, test statistic, - // and null hypothesis - // if our p-value indicates significance, we can reject the null hypothesis - -// perform a KS test using a cumulative distribution function of our making -val myCDF: Double => Double = ... -val testResult2 = Statistics.kolmogorovSmirnovTest(data, myCDF) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/HypothesisTestingKolmogorovSmirnovTestExample.scala %}
@@ -479,23 +222,7 @@ and interpret the hypothesis tests. Refer to the [`Statistics` Java docs](api/java/org/apache/spark/mllib/stat/Statistics.html) for details on the API. -{% highlight java %} -import java.util.Arrays; - -import org.apache.spark.api.java.JavaDoubleRDD; -import org.apache.spark.api.java.JavaSparkContext; - -import org.apache.spark.mllib.stat.Statistics; -import org.apache.spark.mllib.stat.test.KolmogorovSmirnovTestResult; - -JavaSparkContext jsc = ... -JavaDoubleRDD data = jsc.parallelizeDoubles(Arrays.asList(0.2, 1.0, ...)); -KolmogorovSmirnovTestResult testResult = Statistics.kolmogorovSmirnovTest(data, "norm", 0.0, 1.0); -// summary of the test including the p-value, test statistic, -// and null hypothesis -// if our p-value indicates significance, we can reject the null hypothesis -System.out.println(testResult); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java %}
@@ -505,19 +232,7 @@ and interpret the hypothesis tests. Refer to the [`Statistics` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.stat.Statistics) for more details on the API. -{% highlight python %} -from pyspark.mllib.stat import Statistics - -parallelData = sc.parallelize([1.0, 2.0, ... ]) - -# run a KS test for the sample versus a standard normal distribution -testResult = Statistics.kolmogorovSmirnovTest(parallelData, "norm", 0, 1) -print(testResult) # summary of the test including the p-value, test statistic, - # and null hypothesis - # if our p-value indicates significance, we can reject the null hypothesis -# Note that the Scala functionality of calling Statistics.kolmogorovSmirnovTest with -# a lambda to calculate the CDF is not made available in the Python API -{% endhighlight %} +{% include_example python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py %}
@@ -651,21 +366,7 @@ to do so. Refer to the [`KernelDensity` Scala docs](api/scala/index.html#org.apache.spark.mllib.stat.KernelDensity) for details on the API. -{% highlight scala %} -import org.apache.spark.mllib.stat.KernelDensity -import org.apache.spark.rdd.RDD - -val data: RDD[Double] = ... // an RDD of sample data - -// Construct the density estimator with the sample data and a standard deviation for the Gaussian -// kernels -val kd = new KernelDensity() - .setSample(data) - .setBandwidth(3.0) - -// Find density estimates for the given values -val densities = kd.estimate(Array(-1.0, 2.0, 5.0)) -{% endhighlight %} +{% include_example scala/org/apache/spark/examples/mllib/KernelDensityEstimationExample.scala %}
@@ -675,21 +376,7 @@ to do so. Refer to the [`KernelDensity` Java docs](api/java/org/apache/spark/mllib/stat/KernelDensity.html) for details on the API. -{% highlight java %} -import org.apache.spark.mllib.stat.KernelDensity; -import org.apache.spark.rdd.RDD; - -RDD data = ... // an RDD of sample data - -// Construct the density estimator with the sample data and a standard deviation for the Gaussian -// kernels -KernelDensity kd = new KernelDensity() - .setSample(data) - .setBandwidth(3.0); - -// Find density estimates for the given values -double[] densities = kd.estimate(new double[] {-1.0, 2.0, 5.0}); -{% endhighlight %} +{% include_example java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java %}
@@ -699,20 +386,7 @@ to do so. Refer to the [`KernelDensity` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.stat.KernelDensity) for more details on the API. -{% highlight python %} -from pyspark.mllib.stat import KernelDensity - -data = ... # an RDD of sample data - -# Construct the density estimator with the sample data and a standard deviation for the Gaussian -# kernels -kd = KernelDensity() -kd.setSample(data) -kd.setBandwidth(3.0) - -# Find density estimates for the given values -densities = kd.estimate([-1.0, 2.0, 5.0]) -{% endhighlight %} +{% include_example python/mllib/kernel_density_estimation_example.py %}
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java new file mode 100644 index 0000000000000..fd19b43504ac1 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaCorrelationsExample.java @@ -0,0 +1,70 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaDoubleRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.mllib.linalg.Matrix; +import org.apache.spark.mllib.linalg.Vector; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.mllib.stat.Statistics; +// $example off$ + +public class JavaCorrelationsExample { + public static void main(String[] args) { + + SparkConf conf = new SparkConf().setAppName("JavaCorrelationsExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + + // $example on$ + JavaDoubleRDD seriesX = jsc.parallelizeDoubles( + Arrays.asList(1.0, 2.0, 3.0, 3.0, 5.0)); // a series + + // must have the same number of partitions and cardinality as seriesX + JavaDoubleRDD seriesY = jsc.parallelizeDoubles( + Arrays.asList(11.0, 22.0, 33.0, 33.0, 555.0)); + + // compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. + // If a method is not specified, Pearson's method will be used by default. + Double correlation = Statistics.corr(seriesX.srdd(), seriesY.srdd(), "pearson"); + System.out.println("Correlation is: " + correlation); + + // note that each Vector is a row and not a column + JavaRDD data = jsc.parallelize( + Arrays.asList( + Vectors.dense(1.0, 10.0, 100.0), + Vectors.dense(2.0, 20.0, 200.0), + Vectors.dense(5.0, 33.0, 366.0) + ) + ); + + // calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method. + // If a method is not specified, Pearson's method will be used by default. + Matrix correlMatrix = Statistics.corr(data.rdd(), "pearson"); + System.out.println(correlMatrix.toString()); + // $example off$ + + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java new file mode 100644 index 0000000000000..b48b95ff1d2a3 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingExample.java @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; + +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.mllib.linalg.Matrices; +import org.apache.spark.mllib.linalg.Matrix; +import org.apache.spark.mllib.linalg.Vector; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.stat.Statistics; +import org.apache.spark.mllib.stat.test.ChiSqTestResult; +// $example off$ + +public class JavaHypothesisTestingExample { + public static void main(String[] args) { + + SparkConf conf = new SparkConf().setAppName("JavaHypothesisTestingExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + + // $example on$ + // a vector composed of the frequencies of events + Vector vec = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25); + + // 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. + ChiSqTestResult goodnessOfFitTestResult = Statistics.chiSqTest(vec); + // summary of the test including the p-value, degrees of freedom, test statistic, + // the method used, and the null hypothesis. + System.out.println(goodnessOfFitTestResult + "\n"); + + // Create a contingency matrix ((1.0, 2.0), (3.0, 4.0), (5.0, 6.0)) + Matrix mat = Matrices.dense(3, 2, new double[]{1.0, 3.0, 5.0, 2.0, 4.0, 6.0}); + + // conduct Pearson's independence test on the input contingency matrix + ChiSqTestResult independenceTestResult = Statistics.chiSqTest(mat); + // summary of the test including the p-value, degrees of freedom... + System.out.println(independenceTestResult + "\n"); + + // an RDD of labeled points + JavaRDD obs = jsc.parallelize( + Arrays.asList( + new LabeledPoint(1.0, Vectors.dense(1.0, 0.0, 3.0)), + new LabeledPoint(1.0, Vectors.dense(1.0, 2.0, 0.0)), + new LabeledPoint(-1.0, Vectors.dense(-1.0, 0.0, -0.5)) + ) + ); + + // The contingency table is constructed from the raw (feature, label) pairs and used to conduct + // the independence test. Returns an array containing the ChiSquaredTestResult for every feature + // against the label. + ChiSqTestResult[] featureTestResults = Statistics.chiSqTest(obs.rdd()); + int i = 1; + for (ChiSqTestResult result : featureTestResults) { + System.out.println("Column " + i + ":"); + System.out.println(result + "\n"); // summary of the test + i++; + } + // $example off$ + + jsc.stop(); + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java new file mode 100644 index 0000000000000..fe611c9ae67c9 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaHypothesisTestingKolmogorovSmirnovTestExample.java @@ -0,0 +1,49 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaDoubleRDD; +import org.apache.spark.mllib.stat.Statistics; +import org.apache.spark.mllib.stat.test.KolmogorovSmirnovTestResult; +// $example off$ + +public class JavaHypothesisTestingKolmogorovSmirnovTestExample { + public static void main(String[] args) { + + SparkConf conf = + new SparkConf().setAppName("JavaHypothesisTestingKolmogorovSmirnovTestExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + + // $example on$ + JavaDoubleRDD data = jsc.parallelizeDoubles(Arrays.asList(0.1, 0.15, 0.2, 0.3, 0.25)); + KolmogorovSmirnovTestResult testResult = + Statistics.kolmogorovSmirnovTest(data, "norm", 0.0, 1.0); + // summary of the test including the p-value, test statistic, and null hypothesis + // if our p-value indicates significance, we can reject the null hypothesis + System.out.println(testResult); + // $example off$ + + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java new file mode 100644 index 0000000000000..41de0d90eccd7 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaKernelDensityEstimationExample.java @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.mllib.stat.KernelDensity; +// $example off$ + +public class JavaKernelDensityEstimationExample { + public static void main(String[] args) { + + SparkConf conf = new SparkConf().setAppName("JavaKernelDensityEstimationExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + + // $example on$ + // an RDD of sample data + JavaRDD data = jsc.parallelize( + Arrays.asList(1.0, 1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 5.0, 6.0, 7.0, 8.0, 9.0, 9.0)); + + // Construct the density estimator with the sample data + // and a standard deviation for the Gaussian kernels + KernelDensity kd = new KernelDensity().setSample(data).setBandwidth(3.0); + + // Find density estimates for the given values + double[] densities = kd.estimate(new double[]{-1.0, 2.0, 5.0}); + + System.out.println(Arrays.toString(densities)); + // $example off$ + + jsc.stop(); + } +} + diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java new file mode 100644 index 0000000000000..f5a451019bd21 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaStratifiedSamplingExample.java @@ -0,0 +1,75 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import com.google.common.collect.ImmutableMap; +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; + +// $example on$ +import java.util.*; + +import scala.Tuple2; + +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.VoidFunction; +// $example off$ + +public class JavaStratifiedSamplingExample { + public static void main(String[] args) { + + SparkConf conf = new SparkConf().setAppName("JavaStratifiedSamplingExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + + // $example on$ + List> list = new ArrayList>( + Arrays.>asList( + new Tuple2(1, 'a'), + new Tuple2(1, 'b'), + new Tuple2(2, 'c'), + new Tuple2(2, 'd'), + new Tuple2(2, 'e'), + new Tuple2(3, 'f') + ) + ); + + JavaPairRDD data = jsc.parallelizePairs(list); + + // specify the exact fraction desired from each key Map + ImmutableMap fractions = + ImmutableMap.of(1, (Object)0.1, 2, (Object) 0.6, 3, (Object) 0.3); + + // Get an approximate sample from each stratum + JavaPairRDD approxSample = data.sampleByKey(false, fractions); + // Get an exact sample from each stratum + JavaPairRDD exactSample = data.sampleByKeyExact(false, fractions); + // $example off$ + + System.out.println("approxSample size is " + approxSample.collect().size()); + for (Tuple2 t : approxSample.collect()) { + System.out.println(t._1() + " " + t._2()); + } + + System.out.println("exactSample size is " + exactSample.collect().size()); + for (Tuple2 t : exactSample.collect()) { + System.out.println(t._1() + " " + t._2()); + } + + jsc.stop(); + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java new file mode 100644 index 0000000000000..278706bc8f6ed --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaSummaryStatisticsExample.java @@ -0,0 +1,56 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaSparkContext; +// $example on$ +import java.util.Arrays; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.mllib.linalg.Vector; +import org.apache.spark.mllib.linalg.Vectors; +import org.apache.spark.mllib.stat.MultivariateStatisticalSummary; +import org.apache.spark.mllib.stat.Statistics; +// $example off$ + +public class JavaSummaryStatisticsExample { + public static void main(String[] args) { + + SparkConf conf = new SparkConf().setAppName("JavaSummaryStatisticsExample"); + JavaSparkContext jsc = new JavaSparkContext(conf); + + // $example on$ + JavaRDD mat = jsc.parallelize( + Arrays.asList( + Vectors.dense(1.0, 10.0, 100.0), + Vectors.dense(2.0, 20.0, 200.0), + Vectors.dense(3.0, 30.0, 300.0) + ) + ); // an RDD of Vectors + + // Compute column summary statistics. + MultivariateStatisticalSummary summary = Statistics.colStats(mat.rdd()); + System.out.println(summary.mean()); // a dense vector containing the mean value for each column + System.out.println(summary.variance()); // column-wise variance + System.out.println(summary.numNonzeros()); // number of nonzeros in each column + // $example off$ + + jsc.stop(); + } +} diff --git a/examples/src/main/python/mllib/correlations_example.py b/examples/src/main/python/mllib/correlations_example.py new file mode 100644 index 0000000000000..66d18f6e5df17 --- /dev/null +++ b/examples/src/main/python/mllib/correlations_example.py @@ -0,0 +1,48 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +import numpy as np + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.stat import Statistics +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="CorrelationsExample") # SparkContext + + # $example on$ + seriesX = sc.parallelize([1.0, 2.0, 3.0, 3.0, 5.0]) # a series + # seriesY must have the same number of partitions and cardinality as seriesX + seriesY = sc.parallelize([11.0, 22.0, 33.0, 33.0, 555.0]) + + # Compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. + # If a method is not specified, Pearson's method will be used by default. + print("Correlation is: " + str(Statistics.corr(seriesX, seriesY, method="pearson"))) + + data = sc.parallelize( + [np.array([1.0, 10.0, 100.0]), np.array([2.0, 20.0, 200.0]), np.array([5.0, 33.0, 366.0])] + ) # an RDD of Vectors + + # calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method. + # If a method is not specified, Pearson's method will be used by default. + print(Statistics.corr(data, method="pearson")) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/mllib/hypothesis_testing_example.py b/examples/src/main/python/mllib/hypothesis_testing_example.py new file mode 100644 index 0000000000000..e566ead0d318d --- /dev/null +++ b/examples/src/main/python/mllib/hypothesis_testing_example.py @@ -0,0 +1,65 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.linalg import Matrices, Vectors +from pyspark.mllib.regression import LabeledPoint +from pyspark.mllib.stat import Statistics +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="HypothesisTestingExample") + + # $example on$ + vec = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25) # 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) + + # summary of the test including the p-value, degrees of freedom, + # test statistic, the method used, and the null hypothesis. + print("%s\n" % goodnessOfFitTestResult) + + mat = Matrices.dense(3, 2, [1.0, 3.0, 5.0, 2.0, 4.0, 6.0]) # a contingency matrix + + # conduct Pearson's independence test on the input contingency matrix + independenceTestResult = Statistics.chiSqTest(mat) + + # summary of the test including the p-value, degrees of freedom, + # test statistic, the method used, and the null hypothesis. + print("%s\n" % independenceTestResult) + + obs = sc.parallelize( + [LabeledPoint(1.0, [1.0, 0.0, 3.0]), + LabeledPoint(1.0, [1.0, 2.0, 0.0]), + LabeledPoint(1.0, [-1.0, 0.0, -0.5])] + ) # 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:\n%s" % (i + 1, result)) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py b/examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py new file mode 100644 index 0000000000000..ef380dee79d3d --- /dev/null +++ b/examples/src/main/python/mllib/hypothesis_testing_kolmogorov_smirnov_test_example.py @@ -0,0 +1,40 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.stat import Statistics +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="HypothesisTestingKolmogorovSmirnovTestExample") + + # $example on$ + parallelData = sc.parallelize([0.1, 0.15, 0.2, 0.3, 0.25]) + + # run a KS test for the sample versus a standard normal distribution + testResult = Statistics.kolmogorovSmirnovTest(parallelData, "norm", 0, 1) + # summary of the test including the p-value, test statistic, and null hypothesis + # if our p-value indicates significance, we can reject the null hypothesis + # Note that the Scala functionality of calling Statistics.kolmogorovSmirnovTest with + # a lambda to calculate the CDF is not made available in the Python API + print(testResult) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/mllib/kernel_density_estimation_example.py b/examples/src/main/python/mllib/kernel_density_estimation_example.py new file mode 100644 index 0000000000000..3e8f7241a4a1e --- /dev/null +++ b/examples/src/main/python/mllib/kernel_density_estimation_example.py @@ -0,0 +1,44 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.stat import KernelDensity +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="KernelDensityEstimationExample") # SparkContext + + # $example on$ + # an RDD of sample data + data = sc.parallelize([1.0, 1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 5.0, 6.0, 7.0, 8.0, 9.0, 9.0]) + + # Construct the density estimator with the sample data and a standard deviation for the Gaussian + # kernels + kd = KernelDensity() + kd.setSample(data) + kd.setBandwidth(3.0) + + # Find density estimates for the given values + densities = kd.estimate([-1.0, 2.0, 5.0]) + # $example off$ + + print(densities) + + sc.stop() diff --git a/examples/src/main/python/mllib/stratified_sampling_example.py b/examples/src/main/python/mllib/stratified_sampling_example.py new file mode 100644 index 0000000000000..a13f8f08dd68b --- /dev/null +++ b/examples/src/main/python/mllib/stratified_sampling_example.py @@ -0,0 +1,38 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext + +if __name__ == "__main__": + sc = SparkContext(appName="StratifiedSamplingExample") # SparkContext + + # $example on$ + # an RDD of any key value pairs + data = sc.parallelize([(1, 'a'), (1, 'b'), (2, 'c'), (2, 'd'), (2, 'e'), (3, 'f')]) + + # specify the exact fraction desired from each key as a dictionary + fractions = {1: 0.1, 2: 0.6, 3: 0.3} + + approxSample = data.sampleByKey(False, fractions) + # $example off$ + + for each in approxSample.collect(): + print(each) + + sc.stop() diff --git a/examples/src/main/python/mllib/summary_statistics_example.py b/examples/src/main/python/mllib/summary_statistics_example.py new file mode 100644 index 0000000000000..d55d1a2c2d0e1 --- /dev/null +++ b/examples/src/main/python/mllib/summary_statistics_example.py @@ -0,0 +1,42 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from __future__ import print_function + +from pyspark import SparkContext +# $example on$ +import numpy as np + +from pyspark.mllib.stat import Statistics +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="SummaryStatisticsExample") # SparkContext + + # $example on$ + mat = sc.parallelize( + [np.array([1.0, 10.0, 100.0]), np.array([2.0, 20.0, 200.0]), np.array([3.0, 30.0, 300.0])] + ) # an RDD of Vectors + + # Compute column summary statistics. + summary = Statistics.colStats(mat) + print(summary.mean()) # a dense vector containing the mean value for each column + print(summary.variance()) # column-wise variance + print(summary.numNonzeros()) # number of nonzeros in each column + # $example off$ + + sc.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/CorrelationsExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/CorrelationsExample.scala new file mode 100644 index 0000000000000..1202caf534e95 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/CorrelationsExample.scala @@ -0,0 +1,62 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkConf, SparkContext} +// $example on$ +import org.apache.spark.mllib.linalg._ +import org.apache.spark.mllib.stat.Statistics +import org.apache.spark.rdd.RDD +// $example off$ + +object CorrelationsExample { + + def main(args: Array[String]): Unit = { + + val conf = new SparkConf().setAppName("CorrelationsExample") + val sc = new SparkContext(conf) + + // $example on$ + val seriesX: RDD[Double] = sc.parallelize(Array(1, 2, 3, 3, 5)) // a series + // must have the same number of partitions and cardinality as seriesX + val seriesY: RDD[Double] = sc.parallelize(Array(11, 22, 33, 33, 555)) + + // compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. If a + // method is not specified, Pearson's method will be used by default. + val correlation: Double = Statistics.corr(seriesX, seriesY, "pearson") + println(s"Correlation is: $correlation") + + val data: RDD[Vector] = sc.parallelize( + Seq( + Vectors.dense(1.0, 10.0, 100.0), + Vectors.dense(2.0, 20.0, 200.0), + Vectors.dense(5.0, 33.0, 366.0)) + ) // note that each Vector is a row and not a column + + // calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method + // If a method is not specified, Pearson's method will be used by default. + val correlMatrix: Matrix = Statistics.corr(data, "pearson") + println(correlMatrix.toString) + // $example off$ + + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala new file mode 100644 index 0000000000000..0d391a3637c07 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala @@ -0,0 +1,80 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkConf, SparkContext} +// $example on$ +import org.apache.spark.mllib.linalg._ +import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.mllib.stat.Statistics +import org.apache.spark.mllib.stat.test.ChiSqTestResult +import org.apache.spark.rdd.RDD +// $example off$ + +object HypothesisTestingExample { + + def main(args: Array[String]) { + + val conf = new SparkConf().setAppName("HypothesisTestingExample") + val sc = new SparkContext(conf) + + // $example on$ + // a vector composed of the frequencies of events + val vec: Vector = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25) + + // 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. + val goodnessOfFitTestResult = Statistics.chiSqTest(vec) + // summary of the test including the p-value, degrees of freedom, test statistic, the method + // used, and the null hypothesis. + println(s"$goodnessOfFitTestResult\n") + + // a contingency matrix. Create a dense matrix ((1.0, 2.0), (3.0, 4.0), (5.0, 6.0)) + val mat: Matrix = Matrices.dense(3, 2, Array(1.0, 3.0, 5.0, 2.0, 4.0, 6.0)) + + // conduct Pearson's independence test on the input contingency matrix + val independenceTestResult = Statistics.chiSqTest(mat) + // summary of the test including the p-value, degrees of freedom + println(s"$independenceTestResult\n") + + val obs: RDD[LabeledPoint] = + sc.parallelize( + Seq( + LabeledPoint(1.0, Vectors.dense(1.0, 0.0, 3.0)), + LabeledPoint(1.0, Vectors.dense(1.0, 2.0, 0.0)), + LabeledPoint(-1.0, Vectors.dense(-1.0, 0.0, -0.5) + ) + ) + ) // (feature, label) pairs. + + // The contingency table is constructed from the raw (feature, label) pairs and used to conduct + // the independence test. Returns an array containing the ChiSquaredTestResult for every feature + // against the label. + val featureTestResults: Array[ChiSqTestResult] = Statistics.chiSqTest(obs) + featureTestResults.zipWithIndex.foreach { case (k, v) => + println("Column " + (v + 1).toString + ":") + println(k) + } // summary of the test + // $example off$ + + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingKolmogorovSmirnovTestExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingKolmogorovSmirnovTestExample.scala new file mode 100644 index 0000000000000..840874cf3c2fe --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingKolmogorovSmirnovTestExample.scala @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkConf, SparkContext} +// $example on$ +import org.apache.spark.mllib.stat.Statistics +import org.apache.spark.rdd.RDD +// $example off$ + +object HypothesisTestingKolmogorovSmirnovTestExample { + + def main(args: Array[String]): Unit = { + + val conf = new SparkConf().setAppName("HypothesisTestingKolmogorovSmirnovTestExample") + val sc = new SparkContext(conf) + + // $example on$ + val data: RDD[Double] = sc.parallelize(Seq(0.1, 0.15, 0.2, 0.3, 0.25)) // an RDD of sample data + + // run a KS test for the sample versus a standard normal distribution + val testResult = Statistics.kolmogorovSmirnovTest(data, "norm", 0, 1) + // summary of the test including the p-value, test statistic, and null hypothesis if our p-value + // indicates significance, we can reject the null hypothesis. + println(testResult) + println() + + // perform a KS test using a cumulative distribution function of our making + val myCDF = Map(0.1 -> 0.2, 0.15 -> 0.6, 0.2 -> 0.05, 0.3 -> 0.05, 0.25 -> 0.1) + val testResult2 = Statistics.kolmogorovSmirnovTest(data, myCDF) + println(testResult2) + // $example off$ + + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/KernelDensityEstimationExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/KernelDensityEstimationExample.scala new file mode 100644 index 0000000000000..cc5d159b36cc9 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/KernelDensityEstimationExample.scala @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkConf, SparkContext} +// $example on$ +import org.apache.spark.mllib.stat.KernelDensity +import org.apache.spark.rdd.RDD +// $example off$ + +object KernelDensityEstimationExample { + + def main(args: Array[String]): Unit = { + + val conf = new SparkConf().setAppName("KernelDensityEstimationExample") + val sc = new SparkContext(conf) + + // $example on$ + // an RDD of sample data + val data: RDD[Double] = sc.parallelize(Seq(1, 1, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 9)) + + // Construct the density estimator with the sample data and a standard deviation + // for the Gaussian kernels + val kd = new KernelDensity() + .setSample(data) + .setBandwidth(3.0) + + // Find density estimates for the given values + val densities = kd.estimate(Array(-1.0, 2.0, 5.0)) + // $example off$ + + densities.foreach(println) + + sc.stop() + } +} +// scalastyle:on println + diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala new file mode 100644 index 0000000000000..169467926ce46 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkConf, SparkContext} + +object StratifiedSamplingExample { + + def main(args: Array[String]): Unit = { + + val conf = new SparkConf().setAppName("StratifiedSamplingExample") + val sc = new SparkContext(conf) + + // $example on$ + // an RDD[(K, V)] of any key value pairs + val data = sc.parallelize( + Seq((1, 'a'), (1, 'b'), (2, 'c'), (2, 'd'), (2, 'e'), (3, 'f'))) + + // specify the exact fraction desired from each key + val fractions = Map(1 -> 0.1, 2 -> 0.6, 3 -> 0.3) + + // Get an approximate sample from each stratum + val approxSample = data.sampleByKey(withReplacement = false, fractions) + // Get an exact sample from each stratum + val exactSample = data.sampleByKeyExact(withReplacement = false, fractions) + // $example off$ + + println("approxSample size is " + approxSample.collect().size.toString) + approxSample.collect().foreach(println) + + println("exactSample its size is " + exactSample.collect().size.toString) + exactSample.collect().foreach(println) + + sc.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala new file mode 100644 index 0000000000000..948b443c0a754 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.mllib + +import org.apache.spark.{SparkConf, SparkContext} +// $example on$ +import org.apache.spark.mllib.linalg.Vectors +import org.apache.spark.mllib.stat.{MultivariateStatisticalSummary, Statistics} +// $example off$ + +object SummaryStatisticsExample { + + def main(args: Array[String]): Unit = { + + val conf = new SparkConf().setAppName("SummaryStatisticsExample") + val sc = new SparkContext(conf) + + // $example on$ + val observations = sc.parallelize( + Seq( + Vectors.dense(1.0, 10.0, 100.0), + Vectors.dense(2.0, 20.0, 200.0), + Vectors.dense(3.0, 30.0, 300.0) + ) + ) + + // Compute column summary statistics. + val summary: MultivariateStatisticalSummary = Statistics.colStats(observations) + println(summary.mean) // a dense vector containing the mean value for each column + println(summary.variance) // column-wise variance + println(summary.numNonzeros) // number of nonzeros in each column + // $example off$ + + sc.stop() + } +} +// scalastyle:on println