001 /*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements. See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License. You may obtain a copy of the License at
008 *
009 * http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017 package org.apache.commons.math.stat.descriptive;
018
019 import java.io.Serializable;
020 import java.util.Arrays;
021
022 import org.apache.commons.math.DimensionMismatchException;
023 import org.apache.commons.math.MathRuntimeException;
024 import org.apache.commons.math.linear.RealMatrix;
025 import org.apache.commons.math.stat.descriptive.moment.GeometricMean;
026 import org.apache.commons.math.stat.descriptive.moment.Mean;
027 import org.apache.commons.math.stat.descriptive.moment.VectorialCovariance;
028 import org.apache.commons.math.stat.descriptive.rank.Max;
029 import org.apache.commons.math.stat.descriptive.rank.Min;
030 import org.apache.commons.math.stat.descriptive.summary.Sum;
031 import org.apache.commons.math.stat.descriptive.summary.SumOfLogs;
032 import org.apache.commons.math.stat.descriptive.summary.SumOfSquares;
033 import org.apache.commons.math.util.MathUtils;
034
035 /**
036 * <p>Computes summary statistics for a stream of n-tuples added using the
037 * {@link #addValue(double[]) addValue} method. The data values are not stored
038 * in memory, so this class can be used to compute statistics for very large
039 * n-tuple streams.</p>
040 *
041 * <p>The {@link StorelessUnivariateStatistic} instances used to maintain
042 * summary state and compute statistics are configurable via setters.
043 * For example, the default implementation for the mean can be overridden by
044 * calling {@link #setMeanImpl(StorelessUnivariateStatistic[])}. Actual
045 * parameters to these methods must implement the
046 * {@link StorelessUnivariateStatistic} interface and configuration must be
047 * completed before <code>addValue</code> is called. No configuration is
048 * necessary to use the default, commons-math provided implementations.</p>
049 *
050 * <p>To compute statistics for a stream of n-tuples, construct a
051 * MultivariateStatistics instance with dimension n and then use
052 * {@link #addValue(double[])} to add n-tuples. The <code>getXxx</code>
053 * methods where Xxx is a statistic return an array of <code>double</code>
054 * values, where for <code>i = 0,...,n-1</code> the i<sup>th</sup> array element is the
055 * value of the given statistic for data range consisting of the i<sup>th</sup> element of
056 * each of the input n-tuples. For example, if <code>addValue</code> is called
057 * with actual parameters {0, 1, 2}, then {3, 4, 5} and finally {6, 7, 8},
058 * <code>getSum</code> will return a three-element array with values
059 * {0+3+6, 1+4+7, 2+5+8}</p>
060 *
061 * <p>Note: This class is not thread-safe. Use
062 * {@link SynchronizedMultivariateSummaryStatistics} if concurrent access from multiple
063 * threads is required.</p>
064 *
065 * @since 1.2
066 * @version $Revision: 811833 $ $Date: 2009-09-06 12:27:50 -0400 (Sun, 06 Sep 2009) $
067 */
068 public class MultivariateSummaryStatistics
069 implements StatisticalMultivariateSummary, Serializable {
070
071 /** Serialization UID */
072 private static final long serialVersionUID = 2271900808994826718L;
073
074 /** Dimension of the data. */
075 private int k;
076
077 /** Count of values that have been added */
078 private long n = 0;
079
080 /** Sum statistic implementation - can be reset by setter. */
081 private StorelessUnivariateStatistic[] sumImpl;
082
083 /** Sum of squares statistic implementation - can be reset by setter. */
084 private StorelessUnivariateStatistic[] sumSqImpl;
085
086 /** Minimum statistic implementation - can be reset by setter. */
087 private StorelessUnivariateStatistic[] minImpl;
088
089 /** Maximum statistic implementation - can be reset by setter. */
090 private StorelessUnivariateStatistic[] maxImpl;
091
092 /** Sum of log statistic implementation - can be reset by setter. */
093 private StorelessUnivariateStatistic[] sumLogImpl;
094
095 /** Geometric mean statistic implementation - can be reset by setter. */
096 private StorelessUnivariateStatistic[] geoMeanImpl;
097
098 /** Mean statistic implementation - can be reset by setter. */
099 private StorelessUnivariateStatistic[] meanImpl;
100
101 /** Covariance statistic implementation - cannot be reset. */
102 private VectorialCovariance covarianceImpl;
103
104 /**
105 * Construct a MultivariateSummaryStatistics instance
106 * @param k dimension of the data
107 * @param isCovarianceBiasCorrected if true, the unbiased sample
108 * covariance is computed, otherwise the biased population covariance
109 * is computed
110 */
111 public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
112 this.k = k;
113
114 sumImpl = new StorelessUnivariateStatistic[k];
115 sumSqImpl = new StorelessUnivariateStatistic[k];
116 minImpl = new StorelessUnivariateStatistic[k];
117 maxImpl = new StorelessUnivariateStatistic[k];
118 sumLogImpl = new StorelessUnivariateStatistic[k];
119 geoMeanImpl = new StorelessUnivariateStatistic[k];
120 meanImpl = new StorelessUnivariateStatistic[k];
121
122 for (int i = 0; i < k; ++i) {
123 sumImpl[i] = new Sum();
124 sumSqImpl[i] = new SumOfSquares();
125 minImpl[i] = new Min();
126 maxImpl[i] = new Max();
127 sumLogImpl[i] = new SumOfLogs();
128 geoMeanImpl[i] = new GeometricMean();
129 meanImpl[i] = new Mean();
130 }
131
132 covarianceImpl =
133 new VectorialCovariance(k, isCovarianceBiasCorrected);
134
135 }
136
137 /**
138 * Add an n-tuple to the data
139 *
140 * @param value the n-tuple to add
141 * @throws DimensionMismatchException if the length of the array
142 * does not match the one used at construction
143 */
144 public void addValue(double[] value)
145 throws DimensionMismatchException {
146 checkDimension(value.length);
147 for (int i = 0; i < k; ++i) {
148 double v = value[i];
149 sumImpl[i].increment(v);
150 sumSqImpl[i].increment(v);
151 minImpl[i].increment(v);
152 maxImpl[i].increment(v);
153 sumLogImpl[i].increment(v);
154 geoMeanImpl[i].increment(v);
155 meanImpl[i].increment(v);
156 }
157 covarianceImpl.increment(value);
158 n++;
159 }
160
161 /**
162 * Returns the dimension of the data
163 * @return The dimension of the data
164 */
165 public int getDimension() {
166 return k;
167 }
168
169 /**
170 * Returns the number of available values
171 * @return The number of available values
172 */
173 public long getN() {
174 return n;
175 }
176
177 /**
178 * Returns an array of the results of a statistic.
179 * @param stats univariate statistic array
180 * @return results array
181 */
182 private double[] getResults(StorelessUnivariateStatistic[] stats) {
183 double[] results = new double[stats.length];
184 for (int i = 0; i < results.length; ++i) {
185 results[i] = stats[i].getResult();
186 }
187 return results;
188 }
189
190 /**
191 * Returns an array whose i<sup>th</sup> entry is the sum of the
192 * i<sup>th</sup> entries of the arrays that have been added using
193 * {@link #addValue(double[])}
194 *
195 * @return the array of component sums
196 */
197 public double[] getSum() {
198 return getResults(sumImpl);
199 }
200
201 /**
202 * Returns an array whose i<sup>th</sup> entry is the sum of squares of the
203 * i<sup>th</sup> entries of the arrays that have been added using
204 * {@link #addValue(double[])}
205 *
206 * @return the array of component sums of squares
207 */
208 public double[] getSumSq() {
209 return getResults(sumSqImpl);
210 }
211
212 /**
213 * Returns an array whose i<sup>th</sup> entry is the sum of logs of the
214 * i<sup>th</sup> entries of the arrays that have been added using
215 * {@link #addValue(double[])}
216 *
217 * @return the array of component log sums
218 */
219 public double[] getSumLog() {
220 return getResults(sumLogImpl);
221 }
222
223 /**
224 * Returns an array whose i<sup>th</sup> entry is the mean of the
225 * i<sup>th</sup> entries of the arrays that have been added using
226 * {@link #addValue(double[])}
227 *
228 * @return the array of component means
229 */
230 public double[] getMean() {
231 return getResults(meanImpl);
232 }
233
234 /**
235 * Returns an array whose i<sup>th</sup> entry is the standard deviation of the
236 * i<sup>th</sup> entries of the arrays that have been added using
237 * {@link #addValue(double[])}
238 *
239 * @return the array of component standard deviations
240 */
241 public double[] getStandardDeviation() {
242 double[] stdDev = new double[k];
243 if (getN() < 1) {
244 Arrays.fill(stdDev, Double.NaN);
245 } else if (getN() < 2) {
246 Arrays.fill(stdDev, 0.0);
247 } else {
248 RealMatrix matrix = covarianceImpl.getResult();
249 for (int i = 0; i < k; ++i) {
250 stdDev[i] = Math.sqrt(matrix.getEntry(i, i));
251 }
252 }
253 return stdDev;
254 }
255
256 /**
257 * Returns the covariance matrix of the values that have been added.
258 *
259 * @return the covariance matrix
260 */
261 public RealMatrix getCovariance() {
262 return covarianceImpl.getResult();
263 }
264
265 /**
266 * Returns an array whose i<sup>th</sup> entry is the maximum of the
267 * i<sup>th</sup> entries of the arrays that have been added using
268 * {@link #addValue(double[])}
269 *
270 * @return the array of component maxima
271 */
272 public double[] getMax() {
273 return getResults(maxImpl);
274 }
275
276 /**
277 * Returns an array whose i<sup>th</sup> entry is the minimum of the
278 * i<sup>th</sup> entries of the arrays that have been added using
279 * {@link #addValue(double[])}
280 *
281 * @return the array of component minima
282 */
283 public double[] getMin() {
284 return getResults(minImpl);
285 }
286
287 /**
288 * Returns an array whose i<sup>th</sup> entry is the geometric mean of the
289 * i<sup>th</sup> entries of the arrays that have been added using
290 * {@link #addValue(double[])}
291 *
292 * @return the array of component geometric means
293 */
294 public double[] getGeometricMean() {
295 return getResults(geoMeanImpl);
296 }
297
298 /**
299 * Generates a text report displaying
300 * summary statistics from values that
301 * have been added.
302 * @return String with line feeds displaying statistics
303 */
304 @Override
305 public String toString() {
306 StringBuffer outBuffer = new StringBuffer();
307 outBuffer.append("MultivariateSummaryStatistics:\n");
308 outBuffer.append("n: " + getN() + "\n");
309 append(outBuffer, getMin(), "min: ", ", ", "\n");
310 append(outBuffer, getMax(), "max: ", ", ", "\n");
311 append(outBuffer, getMean(), "mean: ", ", ", "\n");
312 append(outBuffer, getGeometricMean(), "geometric mean: ", ", ", "\n");
313 append(outBuffer, getSumSq(), "sum of squares: ", ", ", "\n");
314 append(outBuffer, getSumLog(), "sum of logarithms: ", ", ", "\n");
315 append(outBuffer, getStandardDeviation(), "standard deviation: ", ", ", "\n");
316 outBuffer.append("covariance: " + getCovariance().toString() + "\n");
317 return outBuffer.toString();
318 }
319
320 /**
321 * Append a text representation of an array to a buffer.
322 * @param buffer buffer to fill
323 * @param data data array
324 * @param prefix text prefix
325 * @param separator elements separator
326 * @param suffix text suffix
327 */
328 private void append(StringBuffer buffer, double[] data,
329 String prefix, String separator, String suffix) {
330 buffer.append(prefix);
331 for (int i = 0; i < data.length; ++i) {
332 if (i > 0) {
333 buffer.append(separator);
334 }
335 buffer.append(data[i]);
336 }
337 buffer.append(suffix);
338 }
339
340 /**
341 * Resets all statistics and storage
342 */
343 public void clear() {
344 this.n = 0;
345 for (int i = 0; i < k; ++i) {
346 minImpl[i].clear();
347 maxImpl[i].clear();
348 sumImpl[i].clear();
349 sumLogImpl[i].clear();
350 sumSqImpl[i].clear();
351 geoMeanImpl[i].clear();
352 meanImpl[i].clear();
353 }
354 covarianceImpl.clear();
355 }
356
357 /**
358 * Returns true iff <code>object</code> is a <code>SummaryStatistics</code>
359 * instance and all statistics have the same values as this.
360 * @param object the object to test equality against.
361 * @return true if object equals this
362 */
363 @Override
364 public boolean equals(Object object) {
365 if (object == this ) {
366 return true;
367 }
368 if (object instanceof MultivariateSummaryStatistics == false) {
369 return false;
370 }
371 MultivariateSummaryStatistics stat = (MultivariateSummaryStatistics) object;
372 return MathUtils.equals(stat.getGeometricMean(), getGeometricMean()) &&
373 MathUtils.equals(stat.getMax(), getMax()) &&
374 MathUtils.equals(stat.getMean(), getMean()) &&
375 MathUtils.equals(stat.getMin(), getMin()) &&
376 MathUtils.equals(stat.getN(), getN()) &&
377 MathUtils.equals(stat.getSum(), getSum()) &&
378 MathUtils.equals(stat.getSumSq(), getSumSq()) &&
379 MathUtils.equals(stat.getSumLog(), getSumLog()) &&
380 stat.getCovariance().equals( getCovariance());
381 }
382
383 /**
384 * Returns hash code based on values of statistics
385 *
386 * @return hash code
387 */
388 @Override
389 public int hashCode() {
390 int result = 31 + MathUtils.hash(getGeometricMean());
391 result = result * 31 + MathUtils.hash(getGeometricMean());
392 result = result * 31 + MathUtils.hash(getMax());
393 result = result * 31 + MathUtils.hash(getMean());
394 result = result * 31 + MathUtils.hash(getMin());
395 result = result * 31 + MathUtils.hash(getN());
396 result = result * 31 + MathUtils.hash(getSum());
397 result = result * 31 + MathUtils.hash(getSumSq());
398 result = result * 31 + MathUtils.hash(getSumLog());
399 result = result * 31 + getCovariance().hashCode();
400 return result;
401 }
402
403 // Getters and setters for statistics implementations
404 /**
405 * Sets statistics implementations.
406 * @param newImpl new implementations for statistics
407 * @param oldImpl old implementations for statistics
408 * @throws DimensionMismatchException if the array dimension
409 * does not match the one used at construction
410 * @throws IllegalStateException if data has already been added
411 * (i.e if n > 0)
412 */
413 private void setImpl(StorelessUnivariateStatistic[] newImpl,
414 StorelessUnivariateStatistic[] oldImpl)
415 throws DimensionMismatchException, IllegalStateException {
416 checkEmpty();
417 checkDimension(newImpl.length);
418 System.arraycopy(newImpl, 0, oldImpl, 0, newImpl.length);
419 }
420
421 /**
422 * Returns the currently configured Sum implementation
423 *
424 * @return the StorelessUnivariateStatistic implementing the sum
425 */
426 public StorelessUnivariateStatistic[] getSumImpl() {
427 return sumImpl.clone();
428 }
429
430 /**
431 * <p>Sets the implementation for the Sum.</p>
432 * <p>This method must be activated before any data has been added - i.e.,
433 * before {@link #addValue(double[]) addValue} has been used to add data;
434 * otherwise an IllegalStateException will be thrown.</p>
435 *
436 * @param sumImpl the StorelessUnivariateStatistic instance to use
437 * for computing the Sum
438 * @throws DimensionMismatchException if the array dimension
439 * does not match the one used at construction
440 * @throws IllegalStateException if data has already been added
441 * (i.e if n > 0)
442 */
443 public void setSumImpl(StorelessUnivariateStatistic[] sumImpl)
444 throws DimensionMismatchException {
445 setImpl(sumImpl, this.sumImpl);
446 }
447
448 /**
449 * Returns the currently configured sum of squares implementation
450 *
451 * @return the StorelessUnivariateStatistic implementing the sum of squares
452 */
453 public StorelessUnivariateStatistic[] getSumsqImpl() {
454 return sumSqImpl.clone();
455 }
456
457 /**
458 * <p>Sets the implementation for the sum of squares.</p>
459 * <p>This method must be activated before any data has been added - i.e.,
460 * before {@link #addValue(double[]) addValue} has been used to add data;
461 * otherwise an IllegalStateException will be thrown.</p>
462 *
463 * @param sumsqImpl the StorelessUnivariateStatistic instance to use
464 * for computing the sum of squares
465 * @throws DimensionMismatchException if the array dimension
466 * does not match the one used at construction
467 * @throws IllegalStateException if data has already been added
468 * (i.e if n > 0)
469 */
470 public void setSumsqImpl(StorelessUnivariateStatistic[] sumsqImpl)
471 throws DimensionMismatchException {
472 setImpl(sumsqImpl, this.sumSqImpl);
473 }
474
475 /**
476 * Returns the currently configured minimum implementation
477 *
478 * @return the StorelessUnivariateStatistic implementing the minimum
479 */
480 public StorelessUnivariateStatistic[] getMinImpl() {
481 return minImpl.clone();
482 }
483
484 /**
485 * <p>Sets the implementation for the minimum.</p>
486 * <p>This method must be activated before any data has been added - i.e.,
487 * before {@link #addValue(double[]) addValue} has been used to add data;
488 * otherwise an IllegalStateException will be thrown.</p>
489 *
490 * @param minImpl the StorelessUnivariateStatistic instance to use
491 * for computing the minimum
492 * @throws DimensionMismatchException if the array dimension
493 * does not match the one used at construction
494 * @throws IllegalStateException if data has already been added
495 * (i.e if n > 0)
496 */
497 public void setMinImpl(StorelessUnivariateStatistic[] minImpl)
498 throws DimensionMismatchException {
499 setImpl(minImpl, this.minImpl);
500 }
501
502 /**
503 * Returns the currently configured maximum implementation
504 *
505 * @return the StorelessUnivariateStatistic implementing the maximum
506 */
507 public StorelessUnivariateStatistic[] getMaxImpl() {
508 return maxImpl.clone();
509 }
510
511 /**
512 * <p>Sets the implementation for the maximum.</p>
513 * <p>This method must be activated before any data has been added - i.e.,
514 * before {@link #addValue(double[]) addValue} has been used to add data;
515 * otherwise an IllegalStateException will be thrown.</p>
516 *
517 * @param maxImpl the StorelessUnivariateStatistic instance to use
518 * for computing the maximum
519 * @throws DimensionMismatchException if the array dimension
520 * does not match the one used at construction
521 * @throws IllegalStateException if data has already been added
522 * (i.e if n > 0)
523 */
524 public void setMaxImpl(StorelessUnivariateStatistic[] maxImpl)
525 throws DimensionMismatchException {
526 setImpl(maxImpl, this.maxImpl);
527 }
528
529 /**
530 * Returns the currently configured sum of logs implementation
531 *
532 * @return the StorelessUnivariateStatistic implementing the log sum
533 */
534 public StorelessUnivariateStatistic[] getSumLogImpl() {
535 return sumLogImpl.clone();
536 }
537
538 /**
539 * <p>Sets the implementation for the sum of logs.</p>
540 * <p>This method must be activated before any data has been added - i.e.,
541 * before {@link #addValue(double[]) addValue} has been used to add data;
542 * otherwise an IllegalStateException will be thrown.</p>
543 *
544 * @param sumLogImpl the StorelessUnivariateStatistic instance to use
545 * for computing the log sum
546 * @throws DimensionMismatchException if the array dimension
547 * does not match the one used at construction
548 * @throws IllegalStateException if data has already been added
549 * (i.e if n > 0)
550 */
551 public void setSumLogImpl(StorelessUnivariateStatistic[] sumLogImpl)
552 throws DimensionMismatchException {
553 setImpl(sumLogImpl, this.sumLogImpl);
554 }
555
556 /**
557 * Returns the currently configured geometric mean implementation
558 *
559 * @return the StorelessUnivariateStatistic implementing the geometric mean
560 */
561 public StorelessUnivariateStatistic[] getGeoMeanImpl() {
562 return geoMeanImpl.clone();
563 }
564
565 /**
566 * <p>Sets the implementation for the geometric mean.</p>
567 * <p>This method must be activated before any data has been added - i.e.,
568 * before {@link #addValue(double[]) addValue} has been used to add data;
569 * otherwise an IllegalStateException will be thrown.</p>
570 *
571 * @param geoMeanImpl the StorelessUnivariateStatistic instance to use
572 * for computing the geometric mean
573 * @throws DimensionMismatchException if the array dimension
574 * does not match the one used at construction
575 * @throws IllegalStateException if data has already been added
576 * (i.e if n > 0)
577 */
578 public void setGeoMeanImpl(StorelessUnivariateStatistic[] geoMeanImpl)
579 throws DimensionMismatchException {
580 setImpl(geoMeanImpl, this.geoMeanImpl);
581 }
582
583 /**
584 * Returns the currently configured mean implementation
585 *
586 * @return the StorelessUnivariateStatistic implementing the mean
587 */
588 public StorelessUnivariateStatistic[] getMeanImpl() {
589 return meanImpl.clone();
590 }
591
592 /**
593 * <p>Sets the implementation for the mean.</p>
594 * <p>This method must be activated before any data has been added - i.e.,
595 * before {@link #addValue(double[]) addValue} has been used to add data;
596 * otherwise an IllegalStateException will be thrown.</p>
597 *
598 * @param meanImpl the StorelessUnivariateStatistic instance to use
599 * for computing the mean
600 * @throws DimensionMismatchException if the array dimension
601 * does not match the one used at construction
602 * @throws IllegalStateException if data has already been added
603 * (i.e if n > 0)
604 */
605 public void setMeanImpl(StorelessUnivariateStatistic[] meanImpl)
606 throws DimensionMismatchException {
607 setImpl(meanImpl, this.meanImpl);
608 }
609
610 /**
611 * Throws IllegalStateException if n > 0.
612 */
613 private void checkEmpty() {
614 if (n > 0) {
615 throw MathRuntimeException.createIllegalStateException(
616 "{0} values have been added before statistic is configured",
617 n);
618 }
619 }
620
621 /**
622 * Throws DimensionMismatchException if dimension != k.
623 * @param dimension dimension to check
624 * @throws DimensionMismatchException if dimension != k
625 */
626 private void checkDimension(int dimension)
627 throws DimensionMismatchException {
628 if (dimension != k) {
629 throw new DimensionMismatchException(dimension, k);
630 }
631 }
632
633 }