3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2010 Christian M. Zmasek
7 // Copyright (C) 2008-2010 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.surfacing;
29 import java.util.ArrayList;
30 import java.util.List;
31 import java.util.SortedMap;
32 import java.util.TreeMap;
34 import org.forester.species.Species;
35 import org.forester.util.BasicDescriptiveStatistics;
36 import org.forester.util.DescriptiveStatistics;
38 public class DomainLengths {
40 final String _domain_id;
41 final SortedMap<Species, DescriptiveStatistics> _length_statistics;
43 public DomainLengths( final String domain_id ) {
44 _domain_id = domain_id;
45 _length_statistics = new TreeMap<Species, DescriptiveStatistics>();
48 public void addLength( final Species species, final int domain_length ) {
49 if ( !getLengthStatistics().containsKey( species ) ) {
50 addLengthStatistics( species, new BasicDescriptiveStatistics() );
52 getLengthStatistic( species ).addValue( domain_length );
56 * Returns descriptive statistics based on the arithmetic means
62 public DescriptiveStatistics calculateMeanBasedStatistics() {
63 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
64 for( final DescriptiveStatistics s : getLengthStatisticsList() ) {
65 stats.addValue( s.arithmeticMean() );
72 * Note. This is not technically a Z-score since the distribution
73 * of means is unknown (and not normal).
78 public double calculateZScoreForSpecies( final Species species ) {
79 final double species_mean = getLengthStatistic( species ).arithmeticMean();
80 final DescriptiveStatistics domain_stats = calculateMeanBasedStatistics();
81 final double population_sd = domain_stats.sampleStandardDeviation();
82 final double population_mean = domain_stats.arithmeticMean();
83 return ( species_mean - population_mean ) / population_sd;
86 public String getDomainId() {
90 public DescriptiveStatistics getLengthStatistic( final Species species ) {
91 return getLengthStatistics().get( species );
94 public List<DescriptiveStatistics> getLengthStatisticsList() {
95 final List<DescriptiveStatistics> list = new ArrayList<DescriptiveStatistics>();
96 for( final DescriptiveStatistics stats : _length_statistics.values() ) {
102 public List<Species> getMeanBasedOutlierSpecies( final double z_score_limit ) {
103 final List<Species> species = new ArrayList<Species>();
104 if ( getSpeciesList().size() > 1 ) {
105 for( final Species s : getSpeciesList() ) {
106 final double z = calculateZScoreForSpecies( s );
107 if ( z_score_limit < 0 ) {
108 if ( z <= z_score_limit ) {
112 else if ( z_score_limit > 0 ) {
113 if ( z >= z_score_limit ) {
122 public List<Species> getSpeciesList() {
123 final List<Species> list = new ArrayList<Species>();
124 for( final Species s : _length_statistics.keySet() ) {
130 public boolean isHasLengthStatistic( final Species species ) {
131 return getLengthStatistics().containsKey( species );
134 private void addLengthStatistics( final Species species, final DescriptiveStatistics length_statistic ) {
135 if ( getLengthStatistics().containsKey( species ) ) {
136 throw new IllegalArgumentException( "length statistics for [" + species.getSpeciesId() + "] already added" );
138 getLengthStatistics().put( species, length_statistic );
141 private SortedMap<Species, DescriptiveStatistics> getLengthStatistics() {
142 return _length_statistics;