1 | #ifndef _theplu_yat_statistics_histogram_ |
---|
2 | #define _theplu_yat_statistics_histogram_ |
---|
3 | |
---|
4 | // $Id: Histogram.h 718 2006-12-26 09:56:26Z jari $ |
---|
5 | |
---|
6 | /* |
---|
7 | Copyright (C) The authors contributing to this file. |
---|
8 | |
---|
9 | This file is part of the yat library, http://lev.thep.lu.se/trac/yat |
---|
10 | |
---|
11 | The yat library is free software; you can redistribute it and/or |
---|
12 | modify it under the terms of the GNU General Public License as |
---|
13 | published by the Free Software Foundation; either version 2 of the |
---|
14 | License, or (at your option) any later version. |
---|
15 | |
---|
16 | The yat library is distributed in the hope that it will be useful, |
---|
17 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
18 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
---|
19 | General Public License for more details. |
---|
20 | |
---|
21 | You should have received a copy of the GNU General Public License |
---|
22 | along with this program; if not, write to the Free Software |
---|
23 | Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA |
---|
24 | 02111-1307, USA. |
---|
25 | */ |
---|
26 | |
---|
27 | #include "AveragerWeighted.h" |
---|
28 | |
---|
29 | #include <string> |
---|
30 | #include <vector> |
---|
31 | |
---|
32 | namespace theplu { |
---|
33 | namespace yat { |
---|
34 | namespace statistics { |
---|
35 | |
---|
36 | /// |
---|
37 | /// Histograms provide a convenient way of presenting the |
---|
38 | /// distribution of a set of data. A histogram consists of a set of |
---|
39 | /// bins which count the number of events falling into these |
---|
40 | /// bins. Currently only one dimensional histograms with uniformly |
---|
41 | /// spaced bins are supported. |
---|
42 | /// |
---|
43 | class Histogram |
---|
44 | { |
---|
45 | public: |
---|
46 | |
---|
47 | /// |
---|
48 | /// The default constructor. |
---|
49 | /// |
---|
50 | Histogram(void); |
---|
51 | |
---|
52 | /// |
---|
53 | /// The copy constructor. |
---|
54 | /// |
---|
55 | Histogram(const Histogram&); |
---|
56 | |
---|
57 | /// |
---|
58 | /// Construct a histogram object that covers \f$(xmin,xmax]\f$ |
---|
59 | /// with the bin spacing \f$(xmax-xmin)/n\f$. |
---|
60 | /// |
---|
61 | Histogram(const double xmin, const double xmax, const size_t n); |
---|
62 | |
---|
63 | virtual ~Histogram(void); |
---|
64 | |
---|
65 | /// |
---|
66 | /// Update the histogram by adding \a weight to the bin whose |
---|
67 | /// range contains the observation \a x. No bins are updated when |
---|
68 | /// \a x lies outside the range of the histogram but the value is |
---|
69 | /// added to the overall integral of the histogram. |
---|
70 | /// |
---|
71 | /// @short Add an data point to the histogram. |
---|
72 | /// |
---|
73 | /// @return 0 if \a x lies within the range of the histogram, -1 |
---|
74 | /// if \a x is smaller than the lower limit of the histogram, and |
---|
75 | /// similarly, 1 is returned if \a x is greater than or equal to |
---|
76 | /// the upper limit. |
---|
77 | /// |
---|
78 | int add(const double x,const double weight=1.0); |
---|
79 | |
---|
80 | /// |
---|
81 | /// Gives access to the AveragerWeighted object that keeps track of |
---|
82 | /// average of all events presented to the histogram. |
---|
83 | /// |
---|
84 | /// @short Average of all events presented to the histogram. |
---|
85 | /// |
---|
86 | /// @return A const reference to an AveragerWeighted object. |
---|
87 | /// |
---|
88 | const statistics::AveragerWeighted& averager_all(void) const; |
---|
89 | |
---|
90 | /// |
---|
91 | /// Gives access to the AveragerWeighted object that keeps track of |
---|
92 | /// average of events that fits within the histogram lower and |
---|
93 | /// upper limits. This function is equivalent to averager(). |
---|
94 | /// |
---|
95 | /// @short Average of events fitting within histogram. |
---|
96 | /// |
---|
97 | /// @return A const reference to an AveragerWeighted object. |
---|
98 | /// |
---|
99 | const statistics::AveragerWeighted& averager_histogram(void) const; |
---|
100 | |
---|
101 | /// |
---|
102 | /// @return The number of bins in the histogram |
---|
103 | /// |
---|
104 | size_t nof_bins(void) const; |
---|
105 | |
---|
106 | /// |
---|
107 | /// There are two ways to normalize the counts. |
---|
108 | /// |
---|
109 | /// If choice is true: The normalized count is the count in a |
---|
110 | /// bin divided by the total number of observations. In this |
---|
111 | /// case the relative counts are normalized to sum to unity ( |
---|
112 | /// minus values outside histogram). This is the intuitive case |
---|
113 | /// where the height of the histogram bar represents the |
---|
114 | /// proportion of the data in each class. |
---|
115 | /// |
---|
116 | /// If choice is false: The normalized count is the count in the |
---|
117 | /// class divided by the number of observations times the bin |
---|
118 | /// width. For this normalization, the area (or integral) under |
---|
119 | /// the histogram is equal to unity (minus the missing area |
---|
120 | /// corresponding to counts outside histogram). From a |
---|
121 | /// probabilistic point of view, this normalization results in a |
---|
122 | /// relative histogram that is most akin to the probability |
---|
123 | /// density function If you want to overlay a probability density |
---|
124 | /// on top of the histogram, use this normalization. Although this |
---|
125 | /// normalization is less intuitive (relative frequencies greater |
---|
126 | /// than 1 are quite permissible), it is the appropriate |
---|
127 | /// normalization if you are using the histogram to model a |
---|
128 | /// probability density function. |
---|
129 | /// |
---|
130 | /// @short Normalizing the histogram |
---|
131 | /// |
---|
132 | void normalize(bool choice = true); |
---|
133 | |
---|
134 | /// |
---|
135 | /// @return The value in the middle of bin \a k. |
---|
136 | /// |
---|
137 | /// @note No check is done that \a k is within the size of the |
---|
138 | /// histogram. |
---|
139 | /// |
---|
140 | double observation_value(const size_t k) const; |
---|
141 | |
---|
142 | /// |
---|
143 | /// Set everyting to default values, here it means that everything |
---|
144 | /// is set to zero except the boundary values that are kept. |
---|
145 | /// |
---|
146 | void reset(void); |
---|
147 | |
---|
148 | /// |
---|
149 | /// @return The width of the bins in the histogram. |
---|
150 | /// |
---|
151 | double spacing(void) const; |
---|
152 | |
---|
153 | /// |
---|
154 | /// @return The histogram upper boundary. |
---|
155 | /// |
---|
156 | /// @note The upper boundary value is outside the histogram. |
---|
157 | /// |
---|
158 | double xmax(void) const; |
---|
159 | |
---|
160 | /// |
---|
161 | /// @return The histogram lower boundary. |
---|
162 | /// |
---|
163 | /// @note The lower boundary value is inside the histogram. |
---|
164 | /// |
---|
165 | double xmin(void) const; |
---|
166 | |
---|
167 | /// |
---|
168 | /// @return The count of bin \a k in the histogram. |
---|
169 | /// |
---|
170 | double operator[](size_t k) const; |
---|
171 | |
---|
172 | /// |
---|
173 | /// The assignment operator |
---|
174 | /// |
---|
175 | const Histogram& operator=(const Histogram&); |
---|
176 | |
---|
177 | private: |
---|
178 | // Returns zero if outside boundaries |
---|
179 | size_t bin(double d); |
---|
180 | |
---|
181 | std::vector<double> histogram_; |
---|
182 | double xmax_; |
---|
183 | double xmin_; |
---|
184 | statistics::AveragerWeighted sum_all_; // average of all data |
---|
185 | statistics::AveragerWeighted sum_histogram_;// average of data in histogram |
---|
186 | }; |
---|
187 | |
---|
188 | /// |
---|
189 | /// The Histogram output operator |
---|
190 | /// |
---|
191 | std::ostream& operator<<(std::ostream& s,const Histogram&); |
---|
192 | |
---|
193 | }}} // of namespace statistics, yat, and theplu |
---|
194 | |
---|
195 | #endif |
---|