二、MLlib统计指标之关联/抽样/汇总

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<Vector> 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

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<Vector> 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");

import java.util.Map;

import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;

JavaSparkContext jsc = ...

JavaPairRDD<K, V> data = ... // an RDD of any key value pairs
Map<K, Object> fractions = ... // specify the exact fraction desired from each key

// Get an exact sample from each stratum
JavaPairRDD<K, V> approxSample = data.sampleByKey(false, fractions);
JavaPairRDD<K, V> exactSample = data.sampleByKeyExact(false, fractions);

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<LabeledPoint> 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++;
}

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);

import org.apache.spark.SparkContext;
import org.apache.spark.api.JavaDoubleRDD;
import static org.apache.spark.mllib.random.RandomRDDs.*;

JavaSparkContext jsc = ...

// Generate a random double RDD that contains 1 million i.i.d. values drawn from the
// standard normal distribution `N(0, 1)`, evenly distributed in 10 partitions.
JavaDoubleRDD u = normalJavaRDD(jsc, 1000000L, 10);
// Apply a transform to get a random double RDD following `N(1, 4)`.
JavaDoubleRDD v = u.map(
  new Function<Double, Double>() {
    public Double call(Double x) {
      return 1.0 + 2.0 * x;
    }
  });