Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||||
EmpiricalDistribution |
|
| 1.0;1 |
1 | /* |
|
2 | * Copyright 2003-2004 The Apache Software Foundation. |
|
3 | * |
|
4 | * Licensed under the Apache License, Version 2.0 (the "License"); |
|
5 | * you may not use this file except in compliance with the License. |
|
6 | * You may obtain a copy of the License at |
|
7 | * |
|
8 | * http://www.apache.org/licenses/LICENSE-2.0 |
|
9 | * |
|
10 | * Unless required by applicable law or agreed to in writing, software |
|
11 | * distributed under the License is distributed on an "AS IS" BASIS, |
|
12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|
13 | * See the License for the specific language governing permissions and |
|
14 | * limitations under the License. |
|
15 | */ |
|
16 | ||
17 | package org.apache.commons.math.random; |
|
18 | ||
19 | import java.io.IOException; |
|
20 | import java.io.File; |
|
21 | import java.net.URL; |
|
22 | import java.util.List; |
|
23 | ||
24 | import org.apache.commons.math.stat.descriptive.StatisticalSummary; |
|
25 | ||
26 | /** |
|
27 | * Represents an <a href="http://random.mat.sbg.ac.at/~ste/dipl/node11.html"> |
|
28 | * empirical probability distribution</a> -- a probability distribution derived |
|
29 | * from observed data without making any assumptions about the functional form |
|
30 | * of the population distribution that the data come from.<p> |
|
31 | * Implementations of this interface maintain data structures, called |
|
32 | * <i>distribution digests</i>, that describe empirical distributions and |
|
33 | * support the following operations: <ul> |
|
34 | * <li>loading the distribution from a file of observed data values</li> |
|
35 | * <li>dividing the input data into "bin ranges" and reporting bin frequency |
|
36 | * counts (data for histogram)</li> |
|
37 | * <li>reporting univariate statistics describing the full set of data values |
|
38 | * as well as the observations within each bin</li> |
|
39 | * <li>generating random values from the distribution</li> |
|
40 | * </ul> |
|
41 | * Applications can use <code>EmpiricalDistribution</code> implementations to |
|
42 | * build grouped frequnecy histograms representing the input data or to |
|
43 | * generate random values "like" those in the input file -- i.e., the values |
|
44 | * generated will follow the distribution of the values in the file. |
|
45 | * |
|
46 | * @version $Revision$ $Date: 2005-02-26 05:11:52 -0800 (Sat, 26 Feb 2005) $ |
|
47 | */ |
|
48 | public interface EmpiricalDistribution { |
|
49 | ||
50 | /** |
|
51 | * Computes the empirical distribution from the provided |
|
52 | * array of numbers. |
|
53 | * |
|
54 | * @param dataArray the data array |
|
55 | */ |
|
56 | void load(double[] dataArray); |
|
57 | ||
58 | /** |
|
59 | * Computes the empirical distribution from the input file. |
|
60 | * |
|
61 | * @param file the input file |
|
62 | * @throws IOException if an IO error occurs |
|
63 | */ |
|
64 | void load(File file) throws IOException; |
|
65 | ||
66 | /** |
|
67 | * Computes the empirical distribution using data read from a URL. |
|
68 | * |
|
69 | * @param url url of the input file |
|
70 | * @throws IOException if an IO error occurs |
|
71 | */ |
|
72 | void load(URL url) throws IOException; |
|
73 | ||
74 | /** |
|
75 | * Generates a random value from this distribution. |
|
76 | * <strong>Preconditions:</strong><ul> |
|
77 | * <li>the distribution must be loaded before invoking this method</li></ul> |
|
78 | * @return the random value. |
|
79 | * |
|
80 | * @throws IllegalStateException if the distribution has not been loaded |
|
81 | */ |
|
82 | double getNextValue() throws IllegalStateException; |
|
83 | ||
84 | ||
85 | /** |
|
86 | * Returns a |
|
87 | * {@link org.apache.commons.math.stat.descriptive.StatisticalSummary} |
|
88 | * describing this distribution. |
|
89 | * <strong>Preconditions:</strong><ul> |
|
90 | * <li>the distribution must be loaded before invoking this method</li> |
|
91 | * </ul> |
|
92 | * |
|
93 | * @return the sample statistics |
|
94 | * @throws IllegalStateException if the distribution has not been loaded |
|
95 | */ |
|
96 | StatisticalSummary getSampleStats() throws IllegalStateException; |
|
97 | ||
98 | /** |
|
99 | * Property indicating whether or not the distribution has been loaded. |
|
100 | * |
|
101 | * @return true if the distribution has been loaded |
|
102 | */ |
|
103 | boolean isLoaded(); |
|
104 | ||
105 | /** |
|
106 | * Returns the number of bins. |
|
107 | * |
|
108 | * @return the number of bins |
|
109 | */ |
|
110 | int getBinCount(); |
|
111 | ||
112 | /** |
|
113 | * Returns a list of |
|
114 | * {@link org.apache.commons.math.stat.descriptive.SummaryStatistics} |
|
115 | * containing statistics describing the values in each of the bins. The |
|
116 | * List is indexed on the bin number. |
|
117 | * |
|
118 | * @return List of bin statistics |
|
119 | */ |
|
120 | List getBinStats(); |
|
121 | ||
122 | /** |
|
123 | * Returns the array of upper bounds for the bins. Bins are: <br/> |
|
124 | * [min,upperBounds[0]],(upperBounds[0],upperBounds[1]],..., |
|
125 | * (upperBounds[binCount-1],max]. |
|
126 | * |
|
127 | * @return array of bin upper bounds |
|
128 | */ |
|
129 | double[] getUpperBounds(); |
|
130 | ||
131 | } |