0
|
1 <html>
|
|
2 <head>
|
|
3 <title>MayaChemTools:Code:Fingerprints::FingerprintsBitVector.pm</title>
|
|
4 <meta http-equiv="content-type" content="text/html;charset=utf-8">
|
|
5 <link rel="stylesheet" type="text/css" href="../../../css/MayaChemToolsCode.css">
|
|
6 </head>
|
|
7 <body leftmargin="20" rightmargin="20" topmargin="10" bottommargin="10">
|
|
8 <br/>
|
|
9 <center>
|
|
10 <a href="http://www.mayachemtools.org" title="MayaChemTools Home"><img src="../../../images/MayaChemToolsLogo.gif" border="0" alt="MayaChemTools"></a>
|
|
11 </center>
|
|
12 <br/>
|
|
13 <pre>
|
|
14 <a name="package-Fingerprints::FingerprintsBitVector-"></a> 1 <span class="k">package </span><span class="i">Fingerprints::FingerprintsBitVector</span><span class="sc">;</span>
|
|
15 2 <span class="c">#</span>
|
|
16 3 <span class="c"># $RCSfile: FingerprintsBitVector.pm,v $</span>
|
|
17 4 <span class="c"># $Date: 2015/02/28 20:48:54 $</span>
|
|
18 5 <span class="c"># $Revision: 1.27 $</span>
|
|
19 6 <span class="c">#</span>
|
|
20 7 <span class="c"># Author: Manish Sud <msud@san.rr.com></span>
|
|
21 8 <span class="c">#</span>
|
|
22 9 <span class="c"># Copyright (C) 2015 Manish Sud. All rights reserved.</span>
|
|
23 10 <span class="c">#</span>
|
|
24 11 <span class="c"># This file is part of MayaChemTools.</span>
|
|
25 12 <span class="c">#</span>
|
|
26 13 <span class="c"># MayaChemTools is free software; you can redistribute it and/or modify it under</span>
|
|
27 14 <span class="c"># the terms of the GNU Lesser General Public License as published by the Free</span>
|
|
28 15 <span class="c"># Software Foundation; either version 3 of the License, or (at your option) any</span>
|
|
29 16 <span class="c"># later version.</span>
|
|
30 17 <span class="c">#</span>
|
|
31 18 <span class="c"># MayaChemTools is distributed in the hope that it will be useful, but without</span>
|
|
32 19 <span class="c"># any warranty; without even the implied warranty of merchantability of fitness</span>
|
|
33 20 <span class="c"># for a particular purpose. See the GNU Lesser General Public License for more</span>
|
|
34 21 <span class="c"># details.</span>
|
|
35 22 <span class="c">#</span>
|
|
36 23 <span class="c"># You should have received a copy of the GNU Lesser General Public License</span>
|
|
37 24 <span class="c"># along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or</span>
|
|
38 25 <span class="c"># write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,</span>
|
|
39 26 <span class="c"># Boston, MA, 02111-1307, USA.</span>
|
|
40 27 <span class="c">#</span>
|
|
41 28
|
|
42 29 <span class="k">use</span> <span class="w">strict</span><span class="sc">;</span>
|
|
43 30 <span class="k">use</span> <span class="w">Carp</span><span class="sc">;</span>
|
|
44 31 <span class="k">use</span> <span class="w">Exporter</span><span class="sc">;</span>
|
|
45 32 <span class="k">use</span> <span class="w">Scalar::Util</span> <span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
46 33 <span class="k">use</span> <span class="w">BitVector</span><span class="sc">;</span>
|
|
47 34 <span class="k">use</span> <span class="w">MathUtil</span><span class="sc">;</span>
|
|
48 35 <span class="k">use</span> <span class="w">TextUtil</span> <span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
49 36
|
|
50 37 <span class="k">use</span> <span class="w">vars</span> <span class="q">qw(@ISA @EXPORT @EXPORT_OK %EXPORT_TAGS)</span><span class="sc">;</span>
|
|
51 38
|
|
52 39 <span class="i">@ISA</span> = <span class="q">qw(BitVector Exporter)</span><span class="sc">;</span>
|
|
53 40
|
|
54 41 <span class="c"># Similiarity coefficients...</span>
|
|
55 42 <span class="k">my</span><span class="s">(</span><span class="i">@SimilarityCoefficients</span><span class="s">)</span> = <span class="q">qw(BaroniUrbaniSimilarityCoefficient BuserSimilarityCoefficient CosineSimilarityCoefficient DiceSimilarityCoefficient DennisSimilarityCoefficient ForbesSimilarityCoefficient FossumSimilarityCoefficient HamannSimilarityCoefficient JacardSimilarityCoefficient Kulczynski1SimilarityCoefficient Kulczynski2SimilarityCoefficient MatchingSimilarityCoefficient McConnaugheySimilarityCoefficient OchiaiSimilarityCoefficient PearsonSimilarityCoefficient RogersTanimotoSimilarityCoefficient RussellRaoSimilarityCoefficient SimpsonSimilarityCoefficient SkoalSneath1SimilarityCoefficient SkoalSneath2SimilarityCoefficient SkoalSneath3SimilarityCoefficient TanimotoSimilarityCoefficient TverskySimilarityCoefficient YuleSimilarityCoefficient WeightedTanimotoSimilarityCoefficient WeightedTverskySimilarityCoefficient)</span><span class="sc">;</span>
|
|
56 43
|
|
57 44 <span class="c"># New from string...</span>
|
|
58 45 <span class="k">my</span><span class="s">(</span><span class="i">@NewFromString</span><span class="s">)</span> = <span class="q">qw(NewFromBinaryString NewFromHexadecimalString NewFromRawBinaryString)</span><span class="sc">;</span>
|
|
59 46
|
|
60 47 <span class="i">@EXPORT</span> = <span class="q">qw(IsFingerprintsBitVector)</span><span class="sc">;</span>
|
|
61 48 <span class="i">@EXPORT_OK</span> = <span class="q">qw(GetSupportedSimilarityCoefficients @NewFromString @SimilarityCoefficients)</span><span class="sc">;</span>
|
|
62 49
|
|
63 50 <span class="i">%EXPORT_TAGS</span> = <span class="s">(</span>
|
|
64 51 <span class="w">new</span> <span class="cm">=></span> <span class="s">[</span><span class="i">@NewFromString</span><span class="s">]</span><span class="cm">,</span>
|
|
65 52 <span class="w">coefficients</span> <span class="cm">=></span> <span class="s">[</span><span class="i">@SimilarityCoefficients</span><span class="s">]</span><span class="cm">,</span>
|
|
66 53 <span class="w">all</span> <span class="cm">=></span> <span class="s">[</span><span class="i">@EXPORT</span><span class="cm">,</span> <span class="i">@EXPORT_OK</span><span class="s">]</span>
|
|
67 54 <span class="s">)</span><span class="sc">;</span>
|
|
68 55
|
|
69 56 <span class="c"># Setup class variables...</span>
|
|
70 57 <span class="k">my</span><span class="s">(</span><span class="i">$ClassName</span><span class="s">)</span><span class="sc">;</span>
|
|
71 58 <span class="i">_InitializeClass</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
72 59
|
|
73 60 <span class="k">use</span> <span class="w">overload</span> <span class="q">'""'</span> <span class="cm">=></span> <span class="q">'StringifyFingerprintsBitVector'</span><span class="sc">;</span>
|
|
74 61
|
|
75 62 <span class="c"># Class constructor...</span>
|
|
76 <a name="new-"></a> 63 <span class="k">sub </span><span class="m">new</span> <span class="s">{</span>
|
|
77 64 <span class="k">my</span><span class="s">(</span><span class="i">$Class</span><span class="cm">,</span> <span class="i">$Size</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
78 65
|
|
79 66 <span class="c"># Initialize object...</span>
|
|
80 67 <span class="k">my</span> <span class="i">$This</span> = <span class="i">$Class</span><span class="i">->SUPER::new</span><span class="s">(</span><span class="i">$Size</span><span class="s">)</span><span class="sc">;</span>
|
|
81 68 <span class="k">bless</span> <span class="i">$This</span><span class="cm">,</span> <span class="k">ref</span><span class="s">(</span><span class="i">$Class</span><span class="s">)</span> || <span class="i">$Class</span><span class="sc">;</span>
|
|
82 69 <span class="i">$This</span><span class="i">->_InitializeFingerprintsBitVector</span><span class="s">(</span><span class="i">$Size</span><span class="s">)</span><span class="sc">;</span>
|
|
83 70
|
|
84 71 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
85 72 <span class="s">}</span>
|
|
86 73
|
|
87 74 <span class="c"># Initialize object data...</span>
|
|
88 75 <span class="c">#</span>
|
|
89 76 <span class="c"># Note:</span>
|
|
90 77 <span class="c"># . The class, BitVector, used to derive this class provides all the functionality to</span>
|
|
91 78 <span class="c"># manipulate bits.</span>
|
|
92 79 <span class="c"># . Irrespective of specified size, Perl functions used to handle bit data in</span>
|
|
93 80 <span class="c"># BitVector class automatically sets the size to the next nearest power of 2.</span>
|
|
94 81 <span class="c"># SpecifiedSize is used by this class to process any aribitray size during similarity</span>
|
|
95 82 <span class="c"># coefficient calculations.</span>
|
|
96 83 <span class="c">#</span>
|
|
97 <a name="_InitializeFingerprintsBitVector-"></a> 84 <span class="k">sub </span><span class="m">_InitializeFingerprintsBitVector</span> <span class="s">{</span>
|
|
98 85 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Size</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
99 86
|
|
100 87 <span class="k">if</span> <span class="s">(</span>!<span class="k">defined</span> <span class="i">$Size</span><span class="s">)</span> <span class="s">{</span>
|
|
101 88 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->new: FingerprintsBitVector object instantiated without specifying its size ..."</span><span class="sc">;</span>
|
|
102 89 <span class="s">}</span>
|
|
103 90 <span class="k">if</span> <span class="s">(</span><span class="i">$Size</span> <=<span class="n">0</span><span class="s">)</span> <span class="s">{</span>
|
|
104 91 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->new: Fingerprints bit vector size, $Size, must be a positive integer..."</span><span class="sc">;</span>
|
|
105 92 <span class="s">}</span>
|
|
106 93
|
|
107 94 <span class="c"># Specified size of fingerprints...</span>
|
|
108 95 <span class="i">$This</span>->{<span class="w">SpecifiedSize</span>} = <span class="i">$Size</span><span class="sc">;</span>
|
|
109 96
|
|
110 97 <span class="s">}</span>
|
|
111 98
|
|
112 99 <span class="c"># Initialize class ...</span>
|
|
113 <a name="_InitializeClass-"></a> 100 <span class="k">sub </span><span class="m">_InitializeClass</span> <span class="s">{</span>
|
|
114 101 <span class="c">#Class name...</span>
|
|
115 102 <span class="i">$ClassName</span> = <span class="w">__PACKAGE__</span><span class="sc">;</span>
|
|
116 103 <span class="s">}</span>
|
|
117 104
|
|
118 105 <span class="c"># Set specified size...</span>
|
|
119 106 <span class="c">#</span>
|
|
120 107 <span class="c"># Notes:</span>
|
|
121 108 <span class="c"># Irrespective of specified size, Perl functions used to handle bit data in</span>
|
|
122 109 <span class="c"># BitVector class automatically sets the size to the next nearest power of 2.</span>
|
|
123 110 <span class="c"># SpecifiedSize is used by this class to process any aribitray size during similarity</span>
|
|
124 111 <span class="c"># coefficient calculations.</span>
|
|
125 112 <span class="c">#</span>
|
|
126 <a name="SetSpecifiedSize-"></a> 113 <span class="k">sub </span><span class="m">SetSpecifiedSize</span> <span class="s">{</span>
|
|
127 114 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$SpecifiedSize</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
128 115
|
|
129 116 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="i">$SpecifiedSize</span> > <span class="n">0</span> && <span class="i">$SpecifiedSize</span> <= <span class="i">$This</span>->{<span class="w">Size</span>}<span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
130 117 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->SetSpecifiedSize: Specified size, $SpecifiedSize, is not valid: It must be > 0 && <= "</span><span class="cm">,</span> <span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="cm">,</span><span class="q">" ..."</span><span class="sc">;</span>
|
|
131 118 <span class="s">}</span>
|
|
132 119 <span class="i">$This</span>->{<span class="w">SpecifiedSize</span>} = <span class="i">$SpecifiedSize</span><span class="sc">;</span>
|
|
133 120 <span class="s">}</span>
|
|
134 121
|
|
135 122 <span class="c"># Get specified size...</span>
|
|
136 <a name="GetSpecifiedSize-"></a> 123 <span class="k">sub </span><span class="m">GetSpecifiedSize</span> <span class="s">{</span>
|
|
137 124 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
138 125
|
|
139 126 <span class="k">return</span> <span class="i">$This</span>->{<span class="w">SpecifiedSize</span>}<span class="sc">;</span>
|
|
140 127 <span class="s">}</span>
|
|
141 128
|
|
142 129 <span class="c"># Set ID...</span>
|
|
143 <a name="SetID-"></a> 130 <span class="k">sub </span><span class="m">SetID</span> <span class="s">{</span>
|
|
144 131 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Value</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
145 132
|
|
146 133 <span class="i">$This</span>->{<span class="w">ID</span>} = <span class="i">$Value</span><span class="sc">;</span>
|
|
147 134
|
|
148 135 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
149 136 <span class="s">}</span>
|
|
150 137
|
|
151 138 <span class="c"># Get ID...</span>
|
|
152 <a name="GetID-"></a> 139 <span class="k">sub </span><span class="m">GetID</span> <span class="s">{</span>
|
|
153 140 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
154 141
|
|
155 142 <span class="k">return</span> <span class="k">exists</span> <span class="i">$This</span>->{<span class="w">ID</span>} ? <span class="i">$This</span>->{<span class="w">ID</span>} <span class="co">:</span> <span class="q">'None'</span><span class="sc">;</span>
|
|
156 143 <span class="s">}</span>
|
|
157 144
|
|
158 145 <span class="c"># Set description...</span>
|
|
159 <a name="SetDescription-"></a> 146 <span class="k">sub </span><span class="m">SetDescription</span> <span class="s">{</span>
|
|
160 147 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Value</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
161 148
|
|
162 149 <span class="i">$This</span>->{<span class="w">Description</span>} = <span class="i">$Value</span><span class="sc">;</span>
|
|
163 150
|
|
164 151 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
165 152 <span class="s">}</span>
|
|
166 153
|
|
167 154 <span class="c"># Get description...</span>
|
|
168 <a name="GetDescription-"></a> 155 <span class="k">sub </span><span class="m">GetDescription</span> <span class="s">{</span>
|
|
169 156 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
170 157
|
|
171 158 <span class="k">return</span> <span class="k">exists</span> <span class="i">$This</span>->{<span class="w">Description</span>} ? <span class="i">$This</span>->{<span class="w">Description</span>} <span class="co">:</span> <span class="q">'No description available'</span><span class="sc">;</span>
|
|
172 159 <span class="s">}</span>
|
|
173 160
|
|
174 161 <span class="c"># Set vector type...</span>
|
|
175 <a name="SetVectorType-"></a> 162 <span class="k">sub </span><span class="m">SetVectorType</span> <span class="s">{</span>
|
|
176 163 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Value</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
177 164
|
|
178 165 <span class="i">$This</span>->{<span class="w">VectorType</span>} = <span class="i">$Value</span><span class="sc">;</span>
|
|
179 166
|
|
180 167 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
181 168 <span class="s">}</span>
|
|
182 169
|
|
183 170 <span class="c"># Get vector type...</span>
|
|
184 <a name="GetVectorType-"></a> 171 <span class="k">sub </span><span class="m">GetVectorType</span> <span class="s">{</span>
|
|
185 172 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
186 173
|
|
187 174 <span class="k">return</span> <span class="k">exists</span> <span class="i">$This</span>->{<span class="w">VectorType</span>} ? <span class="i">$This</span>->{<span class="w">VectorType</span>} <span class="co">:</span> <span class="q">'FingerprintsBitVector'</span><span class="sc">;</span>
|
|
188 175 <span class="s">}</span>
|
|
189 176
|
|
190 177 <span class="c"># Create a new fingerprints bit vector using binary string. This functionality can be</span>
|
|
191 178 <span class="c"># either invoked as a class function or an object method.</span>
|
|
192 179 <span class="c">#</span>
|
|
193 <a name="NewFromBinaryString-"></a> 180 <span class="k">sub </span><span class="m">NewFromBinaryString ($;$)</span> <span class="s">{</span>
|
|
194 181 <span class="k">my</span><span class="s">(</span><span class="i">$FirstParameter</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="cm">,</span> <span class="i">$ThirdParameter</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
195 182
|
|
196 183 <span class="k">if</span> <span class="s">(</span><span class="i">_IsFingerprintsBitVector</span><span class="s">(</span><span class="i">$FirstParameter</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
197 184 <span class="k">return</span> <span class="i">_NewFingerptinsBitVectorFromString</span><span class="s">(</span><span class="q">'Binary'</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="cm">,</span> <span class="i">$ThirdParameter</span><span class="s">)</span><span class="sc">;</span>
|
|
198 185 <span class="s">}</span>
|
|
199 186 <span class="k">else</span> <span class="s">{</span>
|
|
200 187 <span class="k">return</span> <span class="i">_NewFingerptinsBitVectorFromString</span><span class="s">(</span> <span class="q">'Binary'</span><span class="cm">,</span> <span class="i">$FirstParameter</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="s">)</span><span class="sc">;</span>
|
|
201 188 <span class="s">}</span>
|
|
202 189 <span class="s">}</span>
|
|
203 190
|
|
204 191 <span class="c"># Create a new fingerprints bit vector using hexadecimal string. This functionality can be</span>
|
|
205 192 <span class="c"># either invoked as a class function or an object method.</span>
|
|
206 193 <span class="c">#</span>
|
|
207 <a name="NewFromHexadecimalString-"></a> 194 <span class="k">sub </span><span class="m">NewFromHexadecimalString ($;$)</span> <span class="s">{</span>
|
|
208 195 <span class="k">my</span><span class="s">(</span><span class="i">$FirstParameter</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="cm">,</span> <span class="i">$ThirdParameter</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
209 196
|
|
210 197 <span class="k">if</span> <span class="s">(</span><span class="i">_IsFingerprintsBitVector</span><span class="s">(</span><span class="i">$FirstParameter</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
211 198 <span class="k">return</span> <span class="i">_NewFingerptinsBitVectorFromString</span><span class="s">(</span><span class="q">'Hexadecimal'</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="cm">,</span> <span class="i">$ThirdParameter</span><span class="s">)</span><span class="sc">;</span>
|
|
212 199 <span class="s">}</span>
|
|
213 200 <span class="k">else</span> <span class="s">{</span>
|
|
214 201 <span class="k">return</span> <span class="i">_NewFingerptinsBitVectorFromString</span><span class="s">(</span> <span class="q">'Hexadecimal'</span><span class="cm">,</span> <span class="i">$FirstParameter</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="s">)</span><span class="sc">;</span>
|
|
215 202 <span class="s">}</span>
|
|
216 203 <span class="s">}</span>
|
|
217 204
|
|
218 205 <span class="c"># Create a new fingerprints bit vector using octal string. This functionality can be</span>
|
|
219 206 <span class="c"># either invoked as a class function or an object method.</span>
|
|
220 207 <span class="c">#</span>
|
|
221 208 <span class="c">#</span>
|
|
222 <a name="NewFromOctalString-"></a> 209 <span class="k">sub </span><span class="m">NewFromOctalString ($)</span> <span class="s">{</span>
|
|
223 210 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->NewFromOctalString: Creation of fingerprits bit vector from an octal string is not supported ..."</span><span class="sc">;</span>
|
|
224 211 <span class="s">}</span>
|
|
225 212
|
|
226 213 <span class="c"># Create a new fingerprints bit vector using decimal string. This functionality can be</span>
|
|
227 214 <span class="c"># either invoked as a class function or an object method.</span>
|
|
228 215 <span class="c">#</span>
|
|
229 <a name="NewFromDecimalString-"></a> 216 <span class="k">sub </span><span class="m">NewFromDecimalString ($;$)</span> <span class="s">{</span>
|
|
230 217 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->NewFromDecimalString: Creation of fingerprits bit vector from a decimal string is not supported ..."</span><span class="sc">;</span>
|
|
231 218 <span class="s">}</span>
|
|
232 219
|
|
233 220 <span class="c"># Create a new fingerprints bit vector using raw binary string. This functionality can be</span>
|
|
234 221 <span class="c"># either invoked as a class function or an object method.</span>
|
|
235 222 <span class="c">#</span>
|
|
236 <a name="NewFromRawBinaryString-"></a> 223 <span class="k">sub </span><span class="m">NewFromRawBinaryString ($;$)</span> <span class="s">{</span>
|
|
237 224 <span class="k">my</span><span class="s">(</span><span class="i">$FirstParameter</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="cm">,</span> <span class="i">$ThirdParameter</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
238 225
|
|
239 226 <span class="k">if</span> <span class="s">(</span><span class="i">_IsFingerprintsBitVector</span><span class="s">(</span><span class="i">$FirstParameter</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
240 227 <span class="k">return</span> <span class="i">_NewFingerptinsBitVectorFromString</span><span class="s">(</span><span class="q">'RawBinary'</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="cm">,</span> <span class="i">$ThirdParameter</span><span class="s">)</span><span class="sc">;</span>
|
|
241 228 <span class="s">}</span>
|
|
242 229 <span class="k">else</span> <span class="s">{</span>
|
|
243 230 <span class="k">return</span> <span class="i">_NewFingerptinsBitVectorFromString</span><span class="s">(</span> <span class="q">'RawBinary'</span><span class="cm">,</span> <span class="i">$FirstParameter</span><span class="cm">,</span> <span class="i">$SecondParameter</span><span class="s">)</span><span class="sc">;</span>
|
|
244 231 <span class="s">}</span>
|
|
245 232 <span class="s">}</span>
|
|
246 233
|
|
247 234 <span class="c"># Create a new fingerprints bit vector from a string...</span>
|
|
248 235 <span class="c">#</span>
|
|
249 236 <span class="c">#</span>
|
|
250 <a name="_NewFingerptinsBitVectorFromString-"></a> 237 <span class="k">sub </span><span class="m">_NewFingerptinsBitVectorFromString ($$;$)</span> <span class="s">{</span>
|
|
251 238 <span class="k">my</span><span class="s">(</span><span class="i">$Format</span><span class="cm">,</span> <span class="i">$String</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
252 239 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVector</span><span class="cm">,</span> <span class="i">$Size</span><span class="s">)</span><span class="sc">;</span>
|
|
253 240
|
|
254 241 <span class="i">$Size</span> = <span class="i">BitVector::_CalculateStringSizeInBits</span><span class="s">(</span><span class="i">$Format</span><span class="cm">,</span> <span class="i">$String</span><span class="s">)</span><span class="sc">;</span>
|
|
255 242
|
|
256 243 <span class="i">$FingerprintsBitVector</span> = <span class="i">new</span> <span class="i">Fingerprints::FingerprintsBitVector</span><span class="s">(</span><span class="i">$Size</span><span class="s">)</span><span class="sc">;</span>
|
|
257 244 <span class="i">$FingerprintsBitVector</span><span class="i">->_SetBitsAsString</span><span class="s">(</span><span class="i">$Format</span><span class="cm">,</span> <span class="i">$String</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span><span class="sc">;</span>
|
|
258 245
|
|
259 246 <span class="k">return</span> <span class="i">$FingerprintsBitVector</span><span class="sc">;</span>
|
|
260 247 <span class="s">}</span>
|
|
261 248
|
|
262 249 <span class="c"># Get fingerprint bits as a hexadecimal string...</span>
|
|
263 250 <span class="c">#</span>
|
|
264 <a name="GetBitsAsHexadecimalString-"></a> 251 <span class="k">sub </span><span class="m">GetBitsAsHexadecimalString</span> <span class="s">{</span>
|
|
265 252 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
266 253
|
|
267 254 <span class="k">return</span> <span class="i">$This</span><span class="i">->_GetFingerprintBitsAsString</span><span class="s">(</span><span class="q">'Hexadecimal'</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span><span class="sc">;</span>
|
|
268 255 <span class="s">}</span>
|
|
269 256
|
|
270 257 <span class="c"># Get fingerprint bits as an octal string...</span>
|
|
271 258 <span class="c">#</span>
|
|
272 <a name="GetBitsAsOctalString-"></a> 259 <span class="k">sub </span><span class="m">GetBitsAsOctalString</span> <span class="s">{</span>
|
|
273 260 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
274 261
|
|
275 262 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->GetBitsAsOctalString: Retrieval of fingerprits bits as an octal string is not supported ..."</span><span class="sc">;</span>
|
|
276 263 <span class="s">}</span>
|
|
277 264
|
|
278 265 <span class="c"># Get fingerprint bits as an decimal string...</span>
|
|
279 266 <span class="c">#</span>
|
|
280 <a name="GetBitsAsDecimalString-"></a> 267 <span class="k">sub </span><span class="m">GetBitsAsDecimalString</span> <span class="s">{</span>
|
|
281 268 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
282 269
|
|
283 270 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->GetBitsAsOctalString: Retrieval of fingerprits bits as a decimal string is not supported ..."</span><span class="sc">;</span>
|
|
284 271 <span class="s">}</span>
|
|
285 272
|
|
286 273 <span class="c"># Get fingerprint bits as a binary string conatning 1s and 0s...</span>
|
|
287 274 <span class="c">#</span>
|
|
288 <a name="GetBitsAsBinaryString-"></a> 275 <span class="k">sub </span><span class="m">GetBitsAsBinaryString</span> <span class="s">{</span>
|
|
289 276 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
290 277
|
|
291 278 <span class="k">return</span> <span class="i">$This</span><span class="i">->_GetFingerprintBitsAsString</span><span class="s">(</span><span class="q">'Binary'</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span><span class="sc">;</span>
|
|
292 279 <span class="s">}</span>
|
|
293 280
|
|
294 281 <span class="c"># Get fingerprint bits as a binary string conatning 1s and 0s...</span>
|
|
295 282 <span class="c">#</span>
|
|
296 <a name="GetBitsAsRawBinaryString-"></a> 283 <span class="k">sub </span><span class="m">GetBitsAsRawBinaryString</span> <span class="s">{</span>
|
|
297 284 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
298 285
|
|
299 286 <span class="k">return</span> <span class="i">$This</span><span class="i">->_GetFingerprintBitsAsString</span><span class="s">(</span><span class="q">'RawBinary'</span><span class="s">)</span><span class="sc">;</span>
|
|
300 287 <span class="s">}</span>
|
|
301 288
|
|
302 289 <span class="c"># Return fingerprint bits as a string...</span>
|
|
303 290 <span class="c">#</span>
|
|
304 <a name="_GetFingerprintBitsAsString-"></a> 291 <span class="k">sub </span><span class="m">_GetFingerprintBitsAsString</span> <span class="s">{</span>
|
|
305 292 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Format</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
306 293
|
|
307 294 <span class="i">$BitsOrder</span> = <span class="s">(</span><span class="k">defined</span><span class="s">(</span><span class="i">$BitsOrder</span><span class="s">)</span> && <span class="i">$BitsOrder</span><span class="s">)</span> ? <span class="i">$BitsOrder</span> <span class="co">:</span> <span class="q">'Ascending'</span><span class="sc">;</span>
|
|
308 295
|
|
309 296 <span class="k">return</span> <span class="i">$This</span><span class="i">->_GetBitsAsString</span><span class="s">(</span><span class="i">$Format</span><span class="cm">,</span> <span class="i">$BitsOrder</span><span class="s">)</span><span class="sc">;</span>
|
|
310 297 <span class="s">}</span>
|
|
311 298
|
|
312 299 <span class="c"># Is it a fingerprints bit vector object?</span>
|
|
313 <a name="IsFingerprintsBitVector-"></a> 300 <span class="k">sub </span><span class="m">IsFingerprintsBitVector ($)</span> <span class="s">{</span>
|
|
314 301 <span class="k">my</span><span class="s">(</span><span class="i">$Object</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
315 302
|
|
316 303 <span class="k">return</span> <span class="i">_IsFingerprintsBitVector</span><span class="s">(</span><span class="i">$Object</span><span class="s">)</span><span class="sc">;</span>
|
|
317 304 <span class="s">}</span>
|
|
318 305
|
|
319 306 <span class="c"># Is it a fingerprints bit vector object?</span>
|
|
320 <a name="_IsFingerprintsBitVector-"></a> 307 <span class="k">sub </span><span class="m">_IsFingerprintsBitVector</span> <span class="s">{</span>
|
|
321 308 <span class="k">my</span><span class="s">(</span><span class="i">$Object</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
322 309
|
|
323 310 <span class="k">return</span> <span class="s">(</span><span class="i">Scalar::Util::blessed</span><span class="s">(</span><span class="i">$Object</span><span class="s">)</span> && <span class="i">$Object</span><span class="i">->isa</span><span class="s">(</span><span class="i">$ClassName</span><span class="s">)</span><span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
324 311 <span class="s">}</span>
|
|
325 312
|
|
326 313 <span class="c"># Return a list of supported similarity coefficients...</span>
|
|
327 <a name="GetSupportedSimilarityCoefficients-"></a> 314 <span class="k">sub </span><span class="m">GetSupportedSimilarityCoefficients ()</span> <span class="s">{</span>
|
|
328 315
|
|
329 316 <span class="k">return</span> <span class="i">@SimilarityCoefficients</span><span class="sc">;</span>
|
|
330 317 <span class="s">}</span>
|
|
331 318
|
|
332 319 <span class="c"># Get bit density for fingerprints bit vector corresponding to on bits...</span>
|
|
333 320 <span class="c">#</span>
|
|
334 <a name="GetFingerprintsBitDensity-"></a> 321 <span class="k">sub </span><span class="m">GetFingerprintsBitDensity</span> <span class="s">{</span>
|
|
335 322 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
336 323 <span class="k">my</span><span class="s">(</span><span class="i">$BitDensity</span><span class="s">)</span><span class="sc">;</span>
|
|
337 324
|
|
338 325 <span class="i">$BitDensity</span> = <span class="i">$This</span><span class="i">->GetDensityOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
339 326
|
|
340 327 <span class="k">return</span> <span class="i">round</span><span class="s">(</span><span class="i">$BitDensity</span><span class="cm">,</span> <span class="n">2</span><span class="s">)</span><span class="sc">;</span>
|
|
341 328 <span class="s">}</span>
|
|
342 329
|
|
343 330 <span class="c"># Fold fingerprints bit vector by recursively reducing its size by half untill size is less than or equal to</span>
|
|
344 331 <span class="c"># specified size...</span>
|
|
345 332 <span class="c">#</span>
|
|
346 <a name="FoldFingerprintsBitVectorBySize-"></a> 333 <span class="k">sub </span><span class="m">FoldFingerprintsBitVectorBySize</span> <span class="s">{</span>
|
|
347 334 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Size</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
348 335
|
|
349 336 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="i">$Size</span> > <span class="n">0</span> && <span class="i">$Size</span> <= <span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
350 337 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->FoldFingerprintsBitVectorBySize: Specified size, $Size, is not valid: It must be > 0 && <= "</span><span class="cm">,</span> <span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="cm">,</span><span class="q">" ..."</span><span class="sc">;</span>
|
|
351 338 <span class="s">}</span>
|
|
352 339
|
|
353 340 <span class="k">if</span> <span class="s">(</span><span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span> <= <span class="i">$Size</span><span class="s">)</span> <span class="s">{</span>
|
|
354 341 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
355 342 <span class="s">}</span>
|
|
356 343 <span class="k">return</span> <span class="i">$This</span><span class="i">->_FoldFingerprintsBitVector</span><span class="s">(</span><span class="q">'BySize'</span><span class="cm">,</span> <span class="i">$Size</span><span class="s">)</span><span class="sc">;</span>
|
|
357 344 <span class="s">}</span>
|
|
358 345
|
|
359 346 <span class="c"># Fold fingerprints bit vector by recursively reducing its size by half untill bit density of set bits is greater than</span>
|
|
360 347 <span class="c"># or equal to specified density...</span>
|
|
361 348 <span class="c">#</span>
|
|
362 <a name="FoldFingerprintsBitVectorByDensity-"></a> 349 <span class="k">sub </span><span class="m">FoldFingerprintsBitVectorByDensity</span> <span class="s">{</span>
|
|
363 350 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Density</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
364 351
|
|
365 352 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="i">$Density</span> > <span class="n">0</span> && <span class="i">$Density</span> <= <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
366 353 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->FoldFingerprintsBitVectorByDensity: Specified bit density, $Density, is not valid: It must be > 0 && <= 1 ..."</span><span class="sc">;</span>
|
|
367 354 <span class="s">}</span>
|
|
368 355
|
|
369 356 <span class="k">if</span> <span class="s">(</span><span class="i">$This</span><span class="i">->GetDensityOfSetBits</span><span class="s">(</span><span class="s">)</span> >= <span class="i">$Density</span><span class="s">)</span> <span class="s">{</span>
|
|
370 357 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
371 358 <span class="s">}</span>
|
|
372 359 <span class="k">return</span> <span class="i">$This</span><span class="i">->_FoldFingerprintsBitVector</span><span class="s">(</span><span class="q">'ByDensity'</span><span class="cm">,</span> <span class="i">$Density</span><span class="s">)</span><span class="sc">;</span>
|
|
373 360 <span class="s">}</span>
|
|
374 361
|
|
375 362 <span class="c"># Fold fingerprints bit vector using size or density and return folded fingerprint bit vector...</span>
|
|
376 363 <span class="c">#</span>
|
|
377 <a name="_FoldFingerprintsBitVector-"></a> 364 <span class="k">sub </span><span class="m">_FoldFingerprintsBitVector</span> <span class="s">{</span>
|
|
378 365 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="cm">,</span> <span class="i">$Mode</span><span class="cm">,</span> <span class="i">$Value</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
379 366
|
|
380 367 <span class="c"># Fold upto size of 8 bits...</span>
|
|
381 368 <span class="k">if</span> <span class="s">(</span><span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span> <= <span class="n">8</span><span class="s">)</span> <span class="s">{</span>
|
|
382 369 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
383 370 <span class="s">}</span>
|
|
384 371
|
|
385 372 <span class="c"># Check size or density....</span>
|
|
386 373 <span class="k">if</span> <span class="s">(</span><span class="i">$Mode</span> =~ <span class="q">/^BySize$/i</span><span class="s">)</span> <span class="s">{</span>
|
|
387 374 <span class="k">if</span> <span class="s">(</span><span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span> <= <span class="i">$Value</span><span class="s">)</span> <span class="s">{</span>
|
|
388 375 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
389 376 <span class="s">}</span>
|
|
390 377 <span class="s">}</span>
|
|
391 378 <span class="k">elsif</span> <span class="s">(</span><span class="i">$Mode</span> =~ <span class="q">/^ByDensity$/i</span><span class="s">)</span> <span class="s">{</span>
|
|
392 379 <span class="k">if</span> <span class="s">(</span><span class="i">$This</span><span class="i">->GetDensityOfSetBits</span><span class="s">(</span><span class="s">)</span> >= <span class="i">$Value</span><span class="s">)</span> <span class="s">{</span>
|
|
393 380 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
394 381 <span class="s">}</span>
|
|
395 382 <span class="s">}</span>
|
|
396 383 <span class="k">else</span> <span class="s">{</span>
|
|
397 384 <span class="k">return</span> <span class="i">$This</span><span class="sc">;</span>
|
|
398 385 <span class="s">}</span>
|
|
399 386
|
|
400 387 <span class="c"># Recursively reduce its size by half...</span>
|
|
401 388 <span class="k">my</span><span class="s">(</span><span class="i">$FirstHalfBinaryString</span><span class="cm">,</span> <span class="i">$SecondHalfBinaryString</span><span class="cm">,</span> <span class="i">$FirstHalfFingerprintsBitVector</span><span class="cm">,</span> <span class="i">$SecondHalfFingerprintsBitVector</span><span class="cm">,</span> <span class="i">$FoldedFingerprintsBitVector</span><span class="cm">,</span> <span class="i">$BinaryString</span><span class="cm">,</span> <span class="i">$StringLength</span><span class="s">)</span><span class="sc">;</span>
|
|
402 389
|
|
403 390 <span class="i">$BinaryString</span> = <span class="i">$This</span><span class="i">->GetBitsAsBinaryString</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
404 391 <span class="i">$StringLength</span> = <span class="k">length</span> <span class="i">$BinaryString</span><span class="sc">;</span>
|
|
405 392
|
|
406 393 <span class="i">$FirstHalfBinaryString</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$BinaryString</span><span class="cm">,</span> <span class="n">0</span><span class="cm">,</span> <span class="i">$StringLength</span>/<span class="n">2</span><span class="s">)</span><span class="sc">;</span>
|
|
407 394 <span class="i">$SecondHalfBinaryString</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$BinaryString</span><span class="cm">,</span> <span class="i">$StringLength</span>/<span class="n">2</span><span class="s">)</span><span class="sc">;</span>
|
|
408 395
|
|
409 396 <span class="i">$FirstHalfFingerprintsBitVector</span> = <span class="i">NewFromBinaryString</span><span class="s">(</span><span class="i">$FirstHalfBinaryString</span><span class="s">)</span><span class="sc">;</span>
|
|
410 397 <span class="i">$SecondHalfFingerprintsBitVector</span> = <span class="i">NewFromBinaryString</span><span class="s">(</span><span class="i">$SecondHalfBinaryString</span><span class="s">)</span><span class="sc">;</span>
|
|
411 398
|
|
412 399 <span class="i">$FoldedFingerprintsBitVector</span> = <span class="i">$FirstHalfFingerprintsBitVector</span> | <span class="i">$SecondHalfFingerprintsBitVector</span><span class="sc">;</span>
|
|
413 400
|
|
414 401 <span class="k">return</span> <span class="i">$FoldedFingerprintsBitVector</span><span class="i">->_FoldFingerprintsBitVector</span><span class="s">(</span><span class="i">$Mode</span><span class="cm">,</span> <span class="i">$Value</span><span class="s">)</span><span class="sc">;</span>
|
|
415 402 <span class="s">}</span>
|
|
416 403
|
|
417 404 <span class="c"># Is first bit vector subset of second bit vector?</span>
|
|
418 405 <span class="c">#</span>
|
|
419 406 <span class="c"># For a bit vector to be a subset of another bit vector, both vectors must be of</span>
|
|
420 407 <span class="c"># the same size and the bit positions set in first vector must also be set in the</span>
|
|
421 408 <span class="c"># secons bit vector.</span>
|
|
422 409 <span class="c">#</span>
|
|
423 410 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
424 411 <span class="c">#</span>
|
|
425 <a name="IsSubSet-"></a> 412 <span class="k">sub </span><span class="m">IsSubSet ($$)</span> <span class="s">{</span>
|
|
426 413 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
427 414
|
|
428 415 <span class="k">if</span> <span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span> != <span class="i">$FingerprintsBitVectorB</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
429 416 <span class="k">return</span> <span class="n">0</span><span class="sc">;</span>
|
|
430 417 <span class="s">}</span>
|
|
431 418 <span class="k">my</span><span class="s">(</span><span class="i">$AndFingerprintsBitVector</span><span class="s">)</span><span class="sc">;</span>
|
|
432 419
|
|
433 420 <span class="i">$AndFingerprintsBitVector</span> = <span class="i">$FingerprintsBitVectorA</span> & <span class="i">$FingerprintsBitVectorB</span><span class="sc">;</span>
|
|
434 421
|
|
435 422 <span class="k">return</span> <span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span> == <span class="i">$AndFingerprintsBitVector</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
436 423 <span class="s">}</span>
|
|
437 424
|
|
438 425 <span class="c"># Return a string containing vector values...</span>
|
|
439 <a name="StringifyFingerprintsBitVector-"></a> 426 <span class="k">sub </span><span class="m">StringifyFingerprintsBitVector</span> <span class="s">{</span>
|
|
440 427 <span class="k">my</span><span class="s">(</span><span class="i">$This</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
441 428 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorString</span><span class="s">)</span><span class="sc">;</span>
|
|
442 429
|
|
443 430 <span class="c"># BitVector size information...</span>
|
|
444 431 <span class="c">#</span>
|
|
445 432 <span class="k">if</span> <span class="s">(</span><span class="i">$This</span>->{<span class="w">SpecifiedSize</span>} != <span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
446 433 <span class="i">$FingerprintsBitVectorString</span> = <span class="q">"SpecifiedSize: "</span> . <span class="i">$This</span>->{<span class="w">SpecifiedSize</span>} . <span class="q">"; BitVectorSize: "</span> . <span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
447 434 <span class="s">}</span>
|
|
448 435 <span class="k">else</span> <span class="s">{</span>
|
|
449 436 <span class="i">$FingerprintsBitVectorString</span> = <span class="q">"BitVectorSize: "</span> . <span class="i">$This</span><span class="i">->GetSize</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
450 437 <span class="s">}</span>
|
|
451 438 <span class="k">my</span><span class="s">(</span><span class="i">$NumOfSetBits</span><span class="cm">,</span> <span class="i">$BitDensity</span><span class="s">)</span><span class="sc">;</span>
|
|
452 439 <span class="i">$NumOfSetBits</span> = <span class="i">$This</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
453 440 <span class="i">$BitDensity</span> = <span class="i">$This</span><span class="i">->GetFingerprintsBitDensity</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
454 441
|
|
455 442 <span class="i">$FingerprintsBitVectorString</span> .= <span class="q">"; NumOfOnBits: $NumOfSetBits; BitDensity: $BitDensity"</span><span class="sc">;</span>
|
|
456 443
|
|
457 444 <span class="c"># BitVector values...</span>
|
|
458 445 <span class="i">$FingerprintsBitVectorString</span> .= <span class="q">"; BitVector: "</span> . <span class="i">$This</span><span class="i">->StringifyBitVector</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
459 446
|
|
460 447 <span class="k">return</span> <span class="i">$FingerprintsBitVectorString</span><span class="sc">;</span>
|
|
461 448 <span class="s">}</span>
|
|
462 449
|
|
463 450 <span class="c"># For two fingerprints bit vectors A and B of same size, let:</span>
|
|
464 451 <span class="c">#</span>
|
|
465 452 <span class="c"># Na = Number of bits set to "1" in A</span>
|
|
466 453 <span class="c"># Nb = Number of bits set to "1" in B</span>
|
|
467 454 <span class="c"># Nc = Number of bits set to "1" in both A and B</span>
|
|
468 455 <span class="c"># Nd = Number of bits set to "0" in both A and B</span>
|
|
469 456 <span class="c">#</span>
|
|
470 457 <span class="c"># Nt = Number of bits set to "1" or "0" in A or B = Size of A or B = Na + Nb - Nc + Nd</span>
|
|
471 458 <span class="c">#</span>
|
|
472 459 <span class="c"># Na - Nc = Number of bits set to "1" in A but not in B</span>
|
|
473 460 <span class="c"># Nb - Nc = Number of bits set to "1" in B but not in A</span>
|
|
474 461 <span class="c">#</span>
|
|
475 462 <span class="c"># Various similarity coefficients [ Ref 40 - 42 ] for a pair of bit vectors A and B are</span>
|
|
476 463 <span class="c"># defined as follows:</span>
|
|
477 464 <span class="c">#</span>
|
|
478 465 <span class="c"># . BaroniUrbani: ( SQRT( Nc * Nd ) + Nc ) / ( SQRT ( Nc * Nd ) + Nc + ( Na - Nc ) + ( Nb - Nc ) ) ( same as Buser )</span>
|
|
479 466 <span class="c">#</span>
|
|
480 467 <span class="c"># . Buser: ( SQRT ( Nc * Nd ) + Nc ) / ( SQRT ( Nc * Nd ) + Nc + ( Na - Nc ) + ( Nb - Nc ) ) ( same as BaroniUrbani )</span>
|
|
481 468 <span class="c">#</span>
|
|
482 469 <span class="c"># . Cosine: Nc / SQRT ( Na * Nb ) (same as Ochiai)</span>
|
|
483 470 <span class="c">#</span>
|
|
484 471 <span class="c"># . Dice: (2 * Nc) / ( Na + Nb )</span>
|
|
485 472 <span class="c">#</span>
|
|
486 473 <span class="c"># . Dennis: ( Nc * Nd - ( ( Na - Nc ) * ( Nb - Nc ) ) ) / SQRT ( Nt * Na * Nb)</span>
|
|
487 474 <span class="c">#</span>
|
|
488 475 <span class="c"># . Forbes: ( Nt * Nc ) / ( Na * Nb )</span>
|
|
489 476 <span class="c">#</span>
|
|
490 477 <span class="c"># . Fossum: ( Nt * ( ( Nc - 1/2 ) ** 2 ) / ( Na * Nb )</span>
|
|
491 478 <span class="c">#</span>
|
|
492 479 <span class="c"># . Hamann: ( ( Nc + Nd ) - ( Na - Nc ) - ( Nb - Nc ) ) / Nt</span>
|
|
493 480 <span class="c">#</span>
|
|
494 481 <span class="c"># . Jaccard: Nc / ( ( Na - Nc) + ( Nb - Nc ) + Nc ) = Nc / ( Na + Nb - Nc ) (same as Tanimoto)</span>
|
|
495 482 <span class="c">#</span>
|
|
496 483 <span class="c"># . Kulczynski1: Nc / ( ( Na - Nc ) + ( Nb - Nc) ) = Nc / ( Na + Nb - 2Nc )</span>
|
|
497 484 <span class="c">#</span>
|
|
498 485 <span class="c"># . Kulczynski2: ( ( Nc / 2 ) * ( 2 * Nc + ( Na - Nc ) + ( Nb - Nc) ) ) / ( ( Nc + ( Na - Nc ) ) * ( Nc + ( Nb - Nc ) ) ) = 0.5 * ( Nc / Na + Nc / Nb )</span>
|
|
499 486 <span class="c">#</span>
|
|
500 487 <span class="c"># . Matching: ( Nc + Nd ) / Nt</span>
|
|
501 488 <span class="c">#</span>
|
|
502 489 <span class="c"># . McConnaughey: ( Nc ** 2 - ( Na - Nc ) * ( Nb - Nc) ) / ( Na * Nb )</span>
|
|
503 490 <span class="c">#</span>
|
|
504 491 <span class="c"># . Ochiai: Nc / SQRT ( Na * Nb ) (same as Cosine)</span>
|
|
505 492 <span class="c">#</span>
|
|
506 493 <span class="c"># . Pearson: ( ( Nc * Nd ) - ( ( Na - Nc ) * ( Nb - Nc ) ) / SQRT ( Na * Nb * ( Na - Nc + Nd ) * ( Nb - Nc + Nd ) )</span>
|
|
507 494 <span class="c">#</span>
|
|
508 495 <span class="c"># . RogersTanimoto: ( Nc + Nd ) / ( ( Na - Nc) + ( Nb - Nc) + Nt) = ( Nc + Nd ) / ( Na + Nb - 2Nc + Nt)</span>
|
|
509 496 <span class="c">#</span>
|
|
510 497 <span class="c"># . RussellRao: Nc / Nt</span>
|
|
511 498 <span class="c">#</span>
|
|
512 499 <span class="c"># . Simpson: Nc / MIN ( Na, Nb)</span>
|
|
513 500 <span class="c">#</span>
|
|
514 501 <span class="c"># . SkoalSneath1: Nc / ( Nc + 2 * ( Na - Nc) + 2 * ( Nb - Nc) ) = Nc / ( 2 * Na + 2 * Nb - 3 * Nc )</span>
|
|
515 502 <span class="c">#</span>
|
|
516 503 <span class="c"># . SkoalSneath2: ( 2 * Nc + 2 * Nd ) / ( Nc + Nd + Nt )</span>
|
|
517 504 <span class="c">#</span>
|
|
518 505 <span class="c"># . SkoalSneath3: ( Nc + Nd ) / ( ( Na - Nc ) + ( Nb - Nc ) ) = ( Nc + Nd ) / ( Na + Nb - 2 * Nc )</span>
|
|
519 506 <span class="c">#</span>
|
|
520 507 <span class="c"># . Tanimoto: Nc / ( ( Na - Nc) + ( Nb - Nc ) + Nc ) = Nc / ( Na + Nb - Nc ) (same as Jaccard)</span>
|
|
521 508 <span class="c">#</span>
|
|
522 509 <span class="c"># . Tversky: Nc / ( alpha * ( Na - Nc ) + ( 1 - alpha) * ( Nb - Nc) + Nc ) = Nc / ( alpha * ( Na - Nb ) + Nb)</span>
|
|
523 510 <span class="c">#</span>
|
|
524 511 <span class="c"># . Yule: ( ( Nc * Nd ) - ( ( Na - Nc ) * ( Nb - Nc ) ) ) / ( ( Nc * Nd ) + ( ( Na - Nc ) * ( Nb - Nc ) ) )</span>
|
|
525 512 <span class="c">#</span>
|
|
526 513 <span class="c">#</span>
|
|
527 514 <span class="c"># Values of Tanimoto/Jaccard and Tversky coefficients are dependent on only those bit which</span>
|
|
528 515 <span class="c"># are set to "1" in both A and B. In order to take into account all bit positions, modified versions</span>
|
|
529 516 <span class="c"># of Tanimoto [ Ref. 42 ] and Tversky [ Ref. 43 ] have been developed.</span>
|
|
530 517 <span class="c">#</span>
|
|
531 518 <span class="c"># Let:</span>
|
|
532 519 <span class="c">#</span>
|
|
533 520 <span class="c"># Na' = Number of bits set to "0" in A</span>
|
|
534 521 <span class="c"># Nb' = Number of bits set to "0" in B</span>
|
|
535 522 <span class="c"># Nc' = Number of bits set to "0" in both A and B</span>
|
|
536 523 <span class="c">#</span>
|
|
537 524 <span class="c"># . Tanimoto': Nc' / ( ( Na' - Nc') + ( Nb' - Nc' ) + Nc' ) = Nc' / ( Na' + Nb' - Nc' )</span>
|
|
538 525 <span class="c">#</span>
|
|
539 526 <span class="c"># . Tversky': Nc' / ( alpha * ( Na' - Nc' ) + ( 1 - alpha) * ( Nb' - Nc' ) + Nc' ) = Nc' / ( alpha * ( Na' - Nb' ) + Nb')</span>
|
|
540 527 <span class="c">#</span>
|
|
541 528 <span class="c"># Then:</span>
|
|
542 529 <span class="c">#</span>
|
|
543 530 <span class="c"># . WeightedTanimoto = beta * Tanimoto + (1 - beta) * Tanimoto'</span>
|
|
544 531 <span class="c">#</span>
|
|
545 532 <span class="c"># . WeightedTversky = beta * Tversky + (1 - beta) * Tversky'</span>
|
|
546 533 <span class="c">#</span>
|
|
547 534 <span class="c">#</span>
|
|
548 535
|
|
549 536 <span class="c"># Calculate BaroniUrbani similarity coefficient for two same size bit vectors.</span>
|
|
550 537 <span class="c">#</span>
|
|
551 538 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
552 539 <span class="c">#</span>
|
|
553 <a name="BaroniUrbaniSimilarityCoefficient-"></a> 540 <span class="k">sub </span><span class="m">BaroniUrbaniSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
554 541 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
555 542
|
|
556 543 <span class="k">return</span> <span class="i">BuserSimilarityCoefficient</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
557 544 <span class="s">}</span>
|
|
558 545
|
|
559 546 <span class="c"># Calculate Buser similarity coefficient for two same size bit vectors.</span>
|
|
560 547 <span class="c">#</span>
|
|
561 548 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
562 549 <span class="c">#</span>
|
|
563 <a name="BuserSimilarityCoefficient-"></a> 550 <span class="k">sub </span><span class="m">BuserSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
564 551 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
565 552 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
566 553
|
|
567 554 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
568 555 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
569 556 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
570 557
|
|
571 558 <span class="i">$Numerator</span> = <span class="k">sqrt</span><span class="s">(</span><span class="i">$Nc</span>*<span class="i">$Nd</span><span class="s">)</span> + <span class="i">$Nc</span><span class="sc">;</span>
|
|
572 559 <span class="i">$Denominator</span> = <span class="k">sqrt</span><span class="s">(</span><span class="i">$Nc</span>*<span class="i">$Nd</span><span class="s">)</span> + <span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span> + <span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span> <span class="s">)</span> + <span class="i">$Nc</span><span class="sc">;</span>
|
|
573 560
|
|
574 561 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
575 562 <span class="s">}</span>
|
|
576 563
|
|
577 564 <span class="c"># Calculate Cosine similarity coefficient for two same size bit vectors.</span>
|
|
578 565 <span class="c">#</span>
|
|
579 566 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
580 567 <span class="c">#</span>
|
|
581 <a name="CosineSimilarityCoefficient-"></a> 568 <span class="k">sub </span><span class="m">CosineSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
582 569 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
583 570 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
584 571
|
|
585 572 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
586 573
|
|
587 574 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
588 575 <span class="i">$Denominator</span> = <span class="k">sqrt</span><span class="s">(</span><span class="i">$Na</span>*<span class="i">$Nb</span><span class="s">)</span><span class="sc">;</span>
|
|
589 576
|
|
590 577 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
591 578 <span class="s">}</span>
|
|
592 579
|
|
593 580 <span class="c"># Calculate Dice similarity coefficient for two same size bit vectors.</span>
|
|
594 581 <span class="c">#</span>
|
|
595 582 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
596 583 <span class="c">#</span>
|
|
597 <a name="DiceSimilarityCoefficient-"></a> 584 <span class="k">sub </span><span class="m">DiceSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
598 585 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
599 586 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
600 587
|
|
601 588 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
602 589
|
|
603 590 <span class="i">$Numerator</span> = <span class="n">2</span>*<span class="i">$Nc</span><span class="sc">;</span>
|
|
604 591 <span class="i">$Denominator</span> = <span class="i">$Na</span> + <span class="i">$Nb</span><span class="sc">;</span>
|
|
605 592
|
|
606 593 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
607 594 <span class="s">}</span>
|
|
608 595
|
|
609 596 <span class="c"># Calculate Dennis similarity coefficient for two same size bit vectors.</span>
|
|
610 597 <span class="c">#</span>
|
|
611 598 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
612 599 <span class="c">#</span>
|
|
613 <a name="DennisSimilarityCoefficient-"></a> 600 <span class="k">sub </span><span class="m">DennisSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
614 601 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
615 602 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
616 603
|
|
617 604 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
618 605 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
619 606 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
620 607
|
|
621 608 <span class="i">$Numerator</span> = <span class="i">$Nc</span>*<span class="i">$Nd</span> - <span class="s">(</span><span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span><span class="s">)</span><span class="sc">;</span>
|
|
622 609 <span class="i">$Denominator</span> = <span class="k">sqrt</span><span class="s">(</span><span class="i">$Nt</span>*<span class="i">$Na</span>*<span class="i">$Nb</span><span class="s">)</span><span class="sc">;</span>
|
|
623 610
|
|
624 611 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
625 612 <span class="s">}</span>
|
|
626 613
|
|
627 614 <span class="c"># Calculate Forbes similarity coefficient for two same size bit vectors.</span>
|
|
628 615 <span class="c">#</span>
|
|
629 616 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
630 617 <span class="c">#</span>
|
|
631 <a name="ForbesSimilarityCoefficient-"></a> 618 <span class="k">sub </span><span class="m">ForbesSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
632 619 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
633 620 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
634 621
|
|
635 622 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
636 623 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
637 624 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
638 625
|
|
639 626 <span class="i">$Numerator</span> = <span class="i">$Nt</span>*<span class="i">$Nc</span><span class="sc">;</span>
|
|
640 627 <span class="i">$Denominator</span> = <span class="i">$Na</span>*<span class="i">$Nb</span><span class="sc">;</span>
|
|
641 628
|
|
642 629 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
643 630 <span class="s">}</span>
|
|
644 631
|
|
645 632 <span class="c"># Calculate Fossum similarity coefficient for two same size bit vectors.</span>
|
|
646 633 <span class="c">#</span>
|
|
647 634 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
648 635 <span class="c">#</span>
|
|
649 <a name="FossumSimilarityCoefficient-"></a> 636 <span class="k">sub </span><span class="m">FossumSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
650 637 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
651 638 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
652 639
|
|
653 640 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
654 641 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
655 642 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
656 643
|
|
657 644 <span class="i">$Numerator</span> = <span class="i">$Nt</span>*<span class="s">(</span><span class="s">(</span><span class="i">$Nc</span> - <span class="n">0.5</span><span class="s">)</span>** <span class="n">2</span><span class="s">)</span><span class="sc">;</span>
|
|
658 645 <span class="i">$Denominator</span> = <span class="i">$Na</span>*<span class="i">$Nb</span> <span class="sc">;</span>
|
|
659 646
|
|
660 647 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
661 648 <span class="s">}</span>
|
|
662 649
|
|
663 650 <span class="c"># Calculate Hamann similarity coefficient for two same size bit vectors.</span>
|
|
664 651 <span class="c">#</span>
|
|
665 652 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
666 653 <span class="c">#</span>
|
|
667 <a name="HamannSimilarityCoefficient-"></a> 654 <span class="k">sub </span><span class="m">HamannSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
668 655 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
669 656 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
670 657
|
|
671 658 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
672 659 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
673 660 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
674 661
|
|
675 662 <span class="i">$Numerator</span> = <span class="s">(</span><span class="i">$Nc</span> + <span class="i">$Nd</span> <span class="s">)</span> - <span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span> - <span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span> <span class="sc">;</span>
|
|
676 663 <span class="i">$Denominator</span> = <span class="i">$Nt</span><span class="sc">;</span>
|
|
677 664
|
|
678 665 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
679 666 <span class="s">}</span>
|
|
680 667
|
|
681 668 <span class="c"># Calculate Jacard similarity coefficient for two same size bit vectors.</span>
|
|
682 669 <span class="c">#</span>
|
|
683 670 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
684 671 <span class="c">#</span>
|
|
685 <a name="JacardSimilarityCoefficient-"></a> 672 <span class="k">sub </span><span class="m">JacardSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
686 673 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
687 674
|
|
688 675 <span class="k">return</span> <span class="i">TanimotoSimilarityCoefficient</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
689 676 <span class="s">}</span>
|
|
690 677
|
|
691 678 <span class="c"># Calculate Kulczynski1 similarity coefficient for two same size bit vectors.</span>
|
|
692 679 <span class="c">#</span>
|
|
693 680 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
694 681 <span class="c">#</span>
|
|
695 <a name="Kulczynski1SimilarityCoefficient-"></a> 682 <span class="k">sub </span><span class="m">Kulczynski1SimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
696 683 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
697 684 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
698 685
|
|
699 686 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
700 687
|
|
701 688 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
702 689 <span class="i">$Denominator</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="n">2</span>*<span class="i">$Nc</span><span class="sc">;</span>
|
|
703 690
|
|
704 691 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
705 692 <span class="s">}</span>
|
|
706 693
|
|
707 694 <span class="c"># Calculate Kulczynski2 similarity coefficient for two same size bit vectors.</span>
|
|
708 695 <span class="c">#</span>
|
|
709 696 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
710 697 <span class="c">#</span>
|
|
711 <a name="Kulczynski2SimilarityCoefficient-"></a> 698 <span class="k">sub </span><span class="m">Kulczynski2SimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
712 699 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
713 700 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
714 701
|
|
715 702 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
716 703
|
|
717 704 <span class="i">$Numerator</span> = <span class="n">0.5</span>*<span class="s">(</span><span class="i">$Na</span>*<span class="i">$Nc</span> + <span class="i">$Nb</span>*<span class="i">$Nc</span><span class="s">)</span><span class="sc">;</span>
|
|
718 705 <span class="i">$Denominator</span> = <span class="i">$Na</span>*<span class="i">$Nb</span><span class="sc">;</span>
|
|
719 706
|
|
720 707 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
721 708 <span class="s">}</span>
|
|
722 709
|
|
723 710 <span class="c"># Calculate Matching similarity coefficient for two same size bit vectors.</span>
|
|
724 711 <span class="c">#</span>
|
|
725 712 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
726 713 <span class="c">#</span>
|
|
727 <a name="MatchingSimilarityCoefficient-"></a> 714 <span class="k">sub </span><span class="m">MatchingSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
728 715 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
729 716 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
730 717
|
|
731 718 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
732 719 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
733 720 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
734 721
|
|
735 722 <span class="i">$Numerator</span> = <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
736 723 <span class="i">$Denominator</span> = <span class="i">$Nt</span><span class="sc">;</span>
|
|
737 724
|
|
738 725 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
739 726 <span class="s">}</span>
|
|
740 727
|
|
741 728 <span class="c"># Calculate McConnaughey similarity coefficient for two same size bit vectors.</span>
|
|
742 729 <span class="c">#</span>
|
|
743 730 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
744 731 <span class="c">#</span>
|
|
745 <a name="McConnaugheySimilarityCoefficient-"></a> 732 <span class="k">sub </span><span class="m">McConnaugheySimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
746 733 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
747 734 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
748 735
|
|
749 736 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
750 737
|
|
751 738 <span class="i">$Numerator</span> = <span class="i">$Nc</span>**<span class="n">2</span> - <span class="s">(</span><span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span><span class="s">)</span><span class="sc">;</span>
|
|
752 739 <span class="i">$Denominator</span> = <span class="i">$Na</span>*<span class="i">$Nb</span> <span class="sc">;</span>
|
|
753 740
|
|
754 741 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
755 742 <span class="s">}</span>
|
|
756 743
|
|
757 744 <span class="c"># Calculate Ochiai similarity coefficient for two same size bit vectors.</span>
|
|
758 745 <span class="c">#</span>
|
|
759 746 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
760 747 <span class="c">#</span>
|
|
761 <a name="OchiaiSimilarityCoefficient-"></a> 748 <span class="k">sub </span><span class="m">OchiaiSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
762 749 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
763 750
|
|
764 751 <span class="k">return</span> <span class="i">CosineSimilarityCoefficient</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
765 752 <span class="s">}</span>
|
|
766 753
|
|
767 754 <span class="c"># Calculate Pearson similarity coefficient for two same size bit vectors.</span>
|
|
768 755 <span class="c">#</span>
|
|
769 756 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
770 757 <span class="c">#</span>
|
|
771 <a name="PearsonSimilarityCoefficient-"></a> 758 <span class="k">sub </span><span class="m">PearsonSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
772 759 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
773 760 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
774 761
|
|
775 762 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
776 763 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
777 764 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
778 765
|
|
779 766 <span class="i">$Numerator</span> = <span class="s">(</span><span class="i">$Nc</span>*<span class="i">$Nd</span> <span class="s">)</span> - <span class="s">(</span><span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span><span class="s">)</span><span class="sc">;</span>
|
|
780 767 <span class="i">$Denominator</span> = <span class="k">sqrt</span><span class="s">(</span><span class="i">$Na</span>*<span class="i">$Nb</span>*<span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span> <span class="s">)</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="s">)</span><span class="s">)</span><span class="sc">;</span>
|
|
781 768
|
|
782 769 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
783 770 <span class="s">}</span>
|
|
784 771
|
|
785 772 <span class="c"># Calculate RogersTanimoto similarity coefficient for two same size bit vectors.</span>
|
|
786 773 <span class="c">#</span>
|
|
787 774 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
788 775 <span class="c">#</span>
|
|
789 <a name="RogersTanimotoSimilarityCoefficient-"></a> 776 <span class="k">sub </span><span class="m">RogersTanimotoSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
790 777 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
791 778 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
792 779
|
|
793 780 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
794 781 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
795 782 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
796 783
|
|
797 784 <span class="i">$Numerator</span> = <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
798 785 <span class="i">$Denominator</span> = <span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span> + <span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span> + <span class="i">$Nt</span><span class="sc">;</span>
|
|
799 786
|
|
800 787 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
801 788 <span class="s">}</span>
|
|
802 789
|
|
803 790 <span class="c"># Calculate RussellRao similarity coefficient for two same size bit vectors.</span>
|
|
804 791 <span class="c">#</span>
|
|
805 792 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
806 793 <span class="c">#</span>
|
|
807 <a name="RussellRaoSimilarityCoefficient-"></a> 794 <span class="k">sub </span><span class="m">RussellRaoSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
808 795 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
809 796 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
810 797
|
|
811 798 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
812 799 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
813 800 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
814 801
|
|
815 802 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
816 803 <span class="i">$Denominator</span> = <span class="i">$Nt</span><span class="sc">;</span>
|
|
817 804
|
|
818 805 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
819 806 <span class="s">}</span>
|
|
820 807
|
|
821 808 <span class="c"># Calculate Simpson similarity coefficient for two same size bit vectors.</span>
|
|
822 809 <span class="c">#</span>
|
|
823 810 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
824 811 <span class="c">#</span>
|
|
825 <a name="SimpsonSimilarityCoefficient-"></a> 812 <span class="k">sub </span><span class="m">SimpsonSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
826 813 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
827 814 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
828 815
|
|
829 816 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
830 817
|
|
831 818 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
832 819 <span class="i">$Denominator</span> = <span class="i">min</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="s">)</span><span class="sc">;</span>
|
|
833 820
|
|
834 821 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
835 822 <span class="s">}</span>
|
|
836 823
|
|
837 824 <span class="c"># Calculate SkoalSneath1 similarity coefficient for two same size bit vectors.</span>
|
|
838 825 <span class="c">#</span>
|
|
839 826 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
840 827 <span class="c">#</span>
|
|
841 <a name="SkoalSneath1SimilarityCoefficient-"></a> 828 <span class="k">sub </span><span class="m">SkoalSneath1SimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
842 829 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
843 830 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
844 831
|
|
845 832 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
846 833
|
|
847 834 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
848 835 <span class="i">$Denominator</span> = <span class="i">$Nc</span> + <span class="n">2</span>*<span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span> + <span class="n">2</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span><span class="sc">;</span>
|
|
849 836
|
|
850 837 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
851 838 <span class="s">}</span>
|
|
852 839
|
|
853 840 <span class="c"># Calculate SkoalSneath2 similarity coefficient for two same size bit vectors.</span>
|
|
854 841 <span class="c">#</span>
|
|
855 842 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
856 843 <span class="c">#</span>
|
|
857 <a name="SkoalSneath2SimilarityCoefficient-"></a> 844 <span class="k">sub </span><span class="m">SkoalSneath2SimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
858 845 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
859 846 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
860 847
|
|
861 848 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
862 849 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
863 850 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
864 851
|
|
865 852 <span class="i">$Numerator</span> = <span class="n">2</span>*<span class="i">$Nc</span> + <span class="n">2</span>*<span class="i">$Nd</span> <span class="sc">;</span>
|
|
866 853 <span class="i">$Denominator</span> = <span class="i">$Nc</span> + <span class="i">$Nd</span> + <span class="i">$Nt</span> <span class="sc">;</span>
|
|
867 854
|
|
868 855 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
869 856 <span class="s">}</span>
|
|
870 857
|
|
871 858 <span class="c"># Calculate SkoalSneath3 similarity coefficient for two same size bit vectors.</span>
|
|
872 859 <span class="c">#</span>
|
|
873 860 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
874 861 <span class="c">#</span>
|
|
875 <a name="SkoalSneath3SimilarityCoefficient-"></a> 862 <span class="k">sub </span><span class="m">SkoalSneath3SimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
876 863 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
877 864 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
878 865
|
|
879 866 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
880 867 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
881 868 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
882 869
|
|
883 870 <span class="i">$Numerator</span> = <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
884 871 <span class="i">$Denominator</span> = <span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span> + <span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span> <span class="s">)</span> <span class="sc">;</span>
|
|
885 872
|
|
886 873 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
887 874 <span class="s">}</span>
|
|
888 875
|
|
889 876 <span class="c"># Calculate Tanimoto similarity coefficient for two same size bit vectors.</span>
|
|
890 877 <span class="c">#</span>
|
|
891 878 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
892 879 <span class="c">#</span>
|
|
893 <a name="TanimotoSimilarityCoefficient-"></a> 880 <span class="k">sub </span><span class="m">TanimotoSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
894 881 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
895 882 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
896 883
|
|
897 884 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
898 885
|
|
899 886 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
900 887 <span class="i">$Denominator</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span><span class="sc">;</span>
|
|
901 888
|
|
902 889 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
903 890 <span class="s">}</span>
|
|
904 891
|
|
905 892 <span class="c"># Calculate Tversky similarity coefficient for two same size bit vectors.</span>
|
|
906 893 <span class="c">#</span>
|
|
907 894 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
908 895 <span class="c">#</span>
|
|
909 <a name="TverskySimilarityCoefficient-"></a> 896 <span class="k">sub </span><span class="m">TverskySimilarityCoefficient ($$$)</span> <span class="s">{</span>
|
|
910 897 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="cm">,</span> <span class="i">$Alpha</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
911 898 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
912 899
|
|
913 900 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="k">defined</span><span class="s">(</span><span class="i">$Alpha</span><span class="s">)</span> && <span class="s">(</span><span class="i">$Alpha</span> >= <span class="n">0</span> && <span class="i">$Alpha</span> <= <span class="n">1</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
914 901 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->TverskySimilarityCoefficient: Alpha parameters must be defined and its value must be >=0 and <=1 ..."</span><span class="sc">;</span>
|
|
915 902 <span class="s">}</span>
|
|
916 903
|
|
917 904 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
918 905
|
|
919 906 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
920 907 <span class="i">$Denominator</span> = <span class="i">$Alpha</span>*<span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nb</span> <span class="s">)</span> + <span class="i">$Nb</span><span class="sc">;</span>
|
|
921 908
|
|
922 909 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
923 910 <span class="s">}</span>
|
|
924 911
|
|
925 912 <span class="c"># Calculate Yule similarity coefficient for two same size bit vectors.</span>
|
|
926 913 <span class="c">#</span>
|
|
927 914 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
928 915 <span class="c">#</span>
|
|
929 <a name="YuleSimilarityCoefficient-"></a> 916 <span class="k">sub </span><span class="m">YuleSimilarityCoefficient ($$)</span> <span class="s">{</span>
|
|
930 917 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
931 918 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="cm">,</span> <span class="i">$Nt</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="s">)</span><span class="sc">;</span>
|
|
932 919
|
|
933 920 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
934 921 <span class="i">$Nd</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
935 922 <span class="i">$Nt</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span> + <span class="i">$Nd</span><span class="sc">;</span>
|
|
936 923
|
|
937 924 <span class="i">$Numerator</span> = <span class="s">(</span><span class="i">$Nc</span>*<span class="i">$Nd</span><span class="s">)</span> - <span class="s">(</span><span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span><span class="s">)</span> <span class="sc">;</span>
|
|
938 925 <span class="i">$Denominator</span> = <span class="s">(</span><span class="i">$Nc</span>*<span class="i">$Nd</span><span class="s">)</span> + <span class="s">(</span><span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nc</span><span class="s">)</span>*<span class="s">(</span><span class="i">$Nb</span> - <span class="i">$Nc</span><span class="s">)</span><span class="s">)</span> <span class="sc">;</span>
|
|
939 926
|
|
940 927 <span class="k">return</span> <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
941 928 <span class="s">}</span>
|
|
942 929
|
|
943 930 <span class="c"># Calculate WeightedTanimoto similarity coefficient for two same size bit vectors.</span>
|
|
944 931 <span class="c">#</span>
|
|
945 932 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
946 933 <span class="c">#</span>
|
|
947 <a name="WeightedTanimotoSimilarityCoefficient-"></a> 934 <span class="k">sub </span><span class="m">WeightedTanimotoSimilarityCoefficient ($$$)</span> <span class="s">{</span>
|
|
948 935 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="cm">,</span> <span class="i">$Beta</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
949 936 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$TanimotoForSetBits</span><span class="cm">,</span> <span class="i">$TanimotoForClearBits</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="cm">,</span> <span class="i">$WeightedTanimoto</span><span class="s">)</span><span class="sc">;</span>
|
|
950 937
|
|
951 938 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="k">defined</span><span class="s">(</span><span class="i">$Beta</span><span class="s">)</span> && <span class="s">(</span><span class="i">$Beta</span> >= <span class="n">0</span> && <span class="i">$Beta</span> <= <span class="n">1</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
952 939 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->WeightedTanimotoSimilarityCoefficient: Beta parameters must be defined and its value must be >=0 and <=1 ..."</span><span class="sc">;</span>
|
|
953 940 <span class="s">}</span>
|
|
954 941
|
|
955 942 <span class="c"># Get Tanimoto for set bits...</span>
|
|
956 943 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
957 944
|
|
958 945 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
959 946 <span class="i">$Denominator</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span><span class="sc">;</span>
|
|
960 947 <span class="i">$TanimotoForSetBits</span> = <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
961 948
|
|
962 949 <span class="c"># Get Tanimoto for clear bits...</span>
|
|
963 950 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
964 951
|
|
965 952 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
966 953 <span class="i">$Denominator</span> = <span class="i">$Na</span> + <span class="i">$Nb</span> - <span class="i">$Nc</span><span class="sc">;</span>
|
|
967 954 <span class="i">$TanimotoForClearBits</span> = <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
968 955
|
|
969 956 <span class="i">$WeightedTanimoto</span> = <span class="i">$Beta</span>*<span class="i">$TanimotoForSetBits</span> + <span class="s">(</span><span class="n">1</span> - <span class="i">$Beta</span><span class="s">)</span>*<span class="i">$TanimotoForClearBits</span><span class="sc">;</span>
|
|
970 957
|
|
971 958 <span class="k">return</span> <span class="i">$WeightedTanimoto</span><span class="sc">;</span>
|
|
972 959 <span class="s">}</span>
|
|
973 960
|
|
974 961 <span class="c"># Calculate WeightedTversky similarity coefficient for two same size bit vectors.</span>
|
|
975 962 <span class="c">#</span>
|
|
976 963 <span class="c"># This functionality can be either invoked as a class function or an object method.</span>
|
|
977 964 <span class="c">#</span>
|
|
978 <a name="WeightedTverskySimilarityCoefficient-"></a> 965 <span class="k">sub </span><span class="m">WeightedTverskySimilarityCoefficient ($$$)</span> <span class="s">{</span>
|
|
979 966 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="cm">,</span> <span class="i">$Alpha</span><span class="cm">,</span> <span class="i">$Beta</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
980 967 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$TverskyForSetBits</span><span class="cm">,</span> <span class="i">$TverskyForClearBits</span><span class="cm">,</span> <span class="i">$Numerator</span><span class="cm">,</span> <span class="i">$Denominator</span><span class="cm">,</span> <span class="i">$WeightedTversky</span><span class="s">)</span><span class="sc">;</span>
|
|
981 968
|
|
982 969 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="k">defined</span><span class="s">(</span><span class="i">$Alpha</span><span class="s">)</span> && <span class="s">(</span><span class="i">$Alpha</span> >= <span class="n">0</span> && <span class="i">$Alpha</span> <= <span class="n">1</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
983 970 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->WeightedTverskySimilarityCoefficient: Alpha parameters must be defined and its value must be >=0 and <=1 ..."</span><span class="sc">;</span>
|
|
984 971 <span class="s">}</span>
|
|
985 972 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="k">defined</span><span class="s">(</span><span class="i">$Beta</span><span class="s">)</span> && <span class="s">(</span><span class="i">$Beta</span> >= <span class="n">0</span> && <span class="i">$Beta</span> <= <span class="n">1</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
986 973 <span class="w">croak</span> <span class="q">"Error: ${ClassName}->WeightedTverskySimilarityCoefficient: Beta parameters must be defined and its value must be >=0 and <=1 ..."</span><span class="sc">;</span>
|
|
987 974 <span class="s">}</span>
|
|
988 975
|
|
989 976 <span class="c"># Get Tversky for set bits...</span>
|
|
990 977 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonSetBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
991 978
|
|
992 979 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
993 980 <span class="i">$Denominator</span> = <span class="i">$Alpha</span>*<span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nb</span> <span class="s">)</span> + <span class="i">$Nb</span><span class="sc">;</span>
|
|
994 981 <span class="i">$TverskyForSetBits</span> = <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
995 982
|
|
996 983 <span class="c"># Get Tversky for clear bits...</span>
|
|
997 984 <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span> = <span class="i">_GetNumOfIndividualAndCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
998 985
|
|
999 986 <span class="i">$Numerator</span> = <span class="i">$Nc</span><span class="sc">;</span>
|
|
1000 987 <span class="i">$Denominator</span> = <span class="i">$Alpha</span>*<span class="s">(</span><span class="i">$Na</span> - <span class="i">$Nb</span> <span class="s">)</span> + <span class="i">$Nb</span><span class="sc">;</span>
|
|
1001 988 <span class="i">$TverskyForClearBits</span> = <span class="i">$Denominator</span> ? <span class="s">(</span><span class="i">$Numerator</span>/<span class="i">$Denominator</span><span class="s">)</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
1002 989
|
|
1003 990 <span class="i">$WeightedTversky</span> = <span class="i">$Beta</span>*<span class="i">$TverskyForSetBits</span> + <span class="s">(</span><span class="n">1</span> - <span class="i">$Beta</span><span class="s">)</span>*<span class="i">$TverskyForClearBits</span><span class="sc">;</span>
|
|
1004 991
|
|
1005 992 <span class="k">return</span> <span class="i">$WeightedTversky</span><span class="sc">;</span>
|
|
1006 993 <span class="s">}</span>
|
|
1007 994
|
|
1008 995 <span class="c"># Get number of Na, Nb and Nc bits in bit vector A and B to be used for similarity coefficient calculations...</span>
|
|
1009 996 <span class="c">#</span>
|
|
1010 <a name="_GetNumOfIndividualAndCommonSetBits-"></a> 997 <span class="k">sub </span><span class="m">_GetNumOfIndividualAndCommonSetBits ($$)</span> <span class="s">{</span>
|
|
1011 998 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
1012 999 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="s">)</span><span class="sc">;</span>
|
|
1013 1000
|
|
1014 1001 <span class="c"># Number of bits set to "1" in A</span>
|
|
1015 1002 <span class="i">$Na</span> = <span class="i">$FingerprintsBitVectorA</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
1016 1003
|
|
1017 1004 <span class="c"># Number of bits set to "1" in B</span>
|
|
1018 1005 <span class="i">$Nb</span> = <span class="i">$FingerprintsBitVectorB</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
1019 1006
|
|
1020 1007 <span class="c"># Number of bits set to "1" in both A and B</span>
|
|
1021 1008 <span class="k">my</span><span class="s">(</span><span class="i">$NcBitVector</span><span class="s">)</span><span class="sc">;</span>
|
|
1022 1009 <span class="i">$NcBitVector</span> = <span class="i">$FingerprintsBitVectorA</span> & <span class="i">$FingerprintsBitVectorB</span><span class="sc">;</span>
|
|
1023 1010 <span class="i">$Nc</span> = <span class="i">$NcBitVector</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
1024 1011
|
|
1025 1012 <span class="k">return</span> <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span><span class="sc">;</span>
|
|
1026 1013 <span class="s">}</span>
|
|
1027 1014
|
|
1028 1015 <span class="c"># Get number of Nd bits in bit vector A and B to be used for similarity coefficient calculations...</span>
|
|
1029 1016 <span class="c">#</span>
|
|
1030 <a name="_GetNumOfCommonClearBits-"></a>1017 <span class="k">sub </span><span class="m">_GetNumOfCommonClearBits ($$)</span> <span class="s">{</span>
|
|
1031 1018 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
1032 1019 <span class="k">my</span><span class="s">(</span><span class="i">$Nd</span><span class="cm">,</span> <span class="i">$NdBitVector</span><span class="s">)</span><span class="sc">;</span>
|
|
1033 1020
|
|
1034 1021 <span class="c"># Number of bits set to "0" in both A and B</span>
|
|
1035 1022 <span class="i">$NdBitVector</span> = ~<span class="i">$FingerprintsBitVectorA</span> & ~<span class="i">$FingerprintsBitVectorB</span><span class="sc">;</span>
|
|
1036 1023 <span class="i">$Nd</span> = <span class="i">$NdBitVector</span><span class="i">->GetNumOfSetBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
1037 1024
|
|
1038 1025 <span class="c"># Correct for number of clear bits used for padding...</span>
|
|
1039 1026 <span class="k">if</span> <span class="s">(</span><span class="i">_IsNumOfClearBitsCorrectionRequired</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
1040 1027 <span class="i">$Nd</span> = <span class="i">$Nd</span> - <span class="i">_GetNumOfClearBitsCorrection</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="s">)</span><span class="sc">;</span>
|
|
1041 1028 <span class="s">}</span>
|
|
1042 1029 <span class="k">elsif</span> <span class="s">(</span><span class="i">_IsNumOfClearBitsCorrectionRequired</span><span class="s">(</span><span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
1043 1030 <span class="i">$Nd</span> = <span class="i">$Nd</span> - <span class="i">_GetNumOfClearBitsCorrection</span><span class="s">(</span><span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
1044 1031 <span class="s">}</span>
|
|
1045 1032
|
|
1046 1033 <span class="k">return</span> <span class="i">$Nd</span><span class="sc">;</span>
|
|
1047 1034 <span class="s">}</span>
|
|
1048 1035
|
|
1049 1036 <span class="c"># Get number of Na, Nb and Nc bits in bit vector A and B to be used for similarity coefficient calculations...</span>
|
|
1050 1037 <span class="c">#</span>
|
|
1051 <a name="_GetNumOfIndividualAndCommonClearBits-"></a>1038 <span class="k">sub </span><span class="m">_GetNumOfIndividualAndCommonClearBits ($$)</span> <span class="s">{</span>
|
|
1052 1039 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
1053 1040 <span class="k">my</span><span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="cm">,</span> <span class="i">$Nd</span><span class="s">)</span><span class="sc">;</span>
|
|
1054 1041
|
|
1055 1042 <span class="c"># Number of bits set to "0" in A</span>
|
|
1056 1043 <span class="i">$Na</span> = <span class="i">$FingerprintsBitVectorA</span><span class="i">->GetNumOfClearBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
1057 1044
|
|
1058 1045 <span class="c"># Correct for number of clear bits used for padding...</span>
|
|
1059 1046 <span class="k">if</span> <span class="s">(</span><span class="i">_IsNumOfClearBitsCorrectionRequired</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
1060 1047 <span class="i">$Na</span> = <span class="i">$Na</span> - <span class="i">_GetNumOfClearBitsCorrection</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="s">)</span><span class="sc">;</span>
|
|
1061 1048 <span class="s">}</span>
|
|
1062 1049
|
|
1063 1050 <span class="c"># Number of bits set to "0" in B</span>
|
|
1064 1051 <span class="i">$Nb</span> = <span class="i">$FingerprintsBitVectorB</span><span class="i">->GetNumOfClearBits</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span>
|
|
1065 1052
|
|
1066 1053 <span class="c"># Correct for number of clear bits used for padding...</span>
|
|
1067 1054 <span class="k">if</span> <span class="s">(</span><span class="i">_IsNumOfClearBitsCorrectionRequired</span><span class="s">(</span><span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span>
|
|
1068 1055 <span class="i">$Nb</span> = <span class="i">$Nb</span> - <span class="i">_GetNumOfClearBitsCorrection</span><span class="s">(</span><span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
1069 1056 <span class="s">}</span>
|
|
1070 1057
|
|
1071 1058 <span class="c"># Number of bits set to "0" in both A and B</span>
|
|
1072 1059 <span class="i">$Nc</span> = <span class="i">_GetNumOfCommonClearBits</span><span class="s">(</span><span class="i">$FingerprintsBitVectorA</span><span class="cm">,</span> <span class="i">$FingerprintsBitVectorB</span><span class="s">)</span><span class="sc">;</span>
|
|
1073 1060
|
|
1074 1061 <span class="k">return</span> <span class="s">(</span><span class="i">$Na</span><span class="cm">,</span> <span class="i">$Nb</span><span class="cm">,</span> <span class="i">$Nc</span><span class="s">)</span><span class="sc">;</span>
|
|
1075 1062 <span class="s">}</span>
|
|
1076 1063
|
|
1077 1064 <span class="c"># Irrespective of specified size, Perl functions used to handle bit data data in</span>
|
|
1078 1065 <span class="c"># BitVector class automatically sets the size to the next nearest power of 2</span>
|
|
1079 1066 <span class="c"># and clear the extra bits.</span>
|
|
1080 1067 <span class="c">#</span>
|
|
1081 1068 <span class="c"># SpecifiedSize is used by this class to process any aribitray size during similarity</span>
|
|
1082 1069 <span class="c"># coefficient calculations.</span>
|
|
1083 1070 <span class="c">#</span>
|
|
1084 1071 <span class="c"># Assuming the FingerprintsBitBector class only manipulates bits upto specified</span>
|
|
1085 1072 <span class="c"># size, a correction for the extra bits added by BitVector class needs to be applied</span>
|
|
1086 1073 <span class="c"># to number of clear bits.</span>
|
|
1087 1074 <span class="c">#</span>
|
|
1088 <a name="_GetNumOfClearBitsCorrection-"></a>1075 <span class="k">sub </span><span class="m">_GetNumOfClearBitsCorrection</span> <span class="s">{</span>
|
|
1089 1076 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVector</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
1090 1077
|
|
1091 1078 <span class="k">return</span> <span class="s">(</span><span class="i">$FingerprintsBitVector</span>->{<span class="w">Size</span>} - <span class="i">$FingerprintsBitVector</span>->{<span class="w">SpecifiedSize</span>}<span class="s">)</span><span class="sc">;</span>
|
|
1092 1079 <span class="s">}</span>
|
|
1093 1080
|
|
1094 1081 <span class="c"># Is number of clear bits correction required?</span>
|
|
1095 1082 <span class="c">#</span>
|
|
1096 <a name="_IsNumOfClearBitsCorrectionRequired-"></a>1083 <span class="k">sub </span><span class="m">_IsNumOfClearBitsCorrectionRequired</span> <span class="s">{</span>
|
|
1097 1084 <span class="k">my</span><span class="s">(</span><span class="i">$FingerprintsBitVector</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span>
|
|
1098 1085
|
|
1099 1086 <span class="k">return</span> <span class="s">(</span><span class="i">$FingerprintsBitVector</span>->{<span class="w">Size</span>} > <span class="i">$FingerprintsBitVector</span>->{<span class="w">SpecifiedSize</span>}<span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span>
|
|
1100 1087 <span class="s">}</span>
|
|
1101 1088
|
|
1102 1089
|
|
1103 <a name="EOF-"></a></pre>
|
|
1104 <p> </p>
|
|
1105 <br />
|
|
1106 <center>
|
|
1107 <img src="../../../images/h2o2.png">
|
|
1108 </center>
|
|
1109 </body>
|
|
1110 </html>
|