source: cpp/frams/_demos/simil_test.cpp @ 1026

Last change on this file since 1026 was 1005, checked in by Maciej Komosinski, 4 years ago

Higher conformance with C++17, but gave up after missing M_PI, M_PI_2, strdup() and more; other cosmetic improvements

File size: 6.2 KB
Line 
1// This file is a part of Framsticks SDK.  http://www.framsticks.com/
2// Copyright (C) 1999-2020  Maciej Komosinski and Szymon Ulatowski.
3// See LICENSE.txt for details.
4
5
6#include <vector>
7#include "common/loggers/loggertostdout.h"
8#include "frams/_demos/genotypeloader.h"
9#include "frams/genetics/preconfigured.h"
10#include "common/virtfile/stdiofile.h"
11#include "frams/model/similarity/simil_model.h"
12
13
14
15/** Computes a matrix of distances between all genotypes in the specified
16        .gen file, using the matching and measure weights as specified in the
17        command line. */
18int main(int argc, char *argv[])
19{
20        LoggerToStdout messages_to_stdout(LoggerBase::Enable);
21        int iCurrParam = 0; // index of the currently processed parameter
22        char *szCurrParam = NULL;
23        ModelSimil M; // similarity computing object
24        bool bPrintNames = false; // specifies if names of genotypes are to be printed
25        int nResult = 0; // a temporary result
26
27        if (argc < 8)
28        {
29                printf("Too few parameters!\n");
30                printf("Command line: [-names] <genotypesFile> <measure> <w_dP> <w_dDEG> <w_dNEU> <w_dGEO> <fixZaxis?>\n\n");
31
32                printf("Parameters:\n");
33                printf("  <genotypesFile> name of a file with genotypes\n");
34                printf("  <measure> similarity measure\n");
35                printf("  <w_dP> weight of the difference in the number of parts\n");
36                printf("  <w_dDEG> weight of the difference in degrees of matched parts\n");
37                printf("  <w_dNEU> weight of the difference in neurons of matched parts\n");
38                printf("  <w_dGEO> weight of the distance of matched parts\n");
39                printf("  <fixZaxis?> should the 'z' (vertical) coordinate be fixed during the alignment? (0 or 1)\n\n");
40
41                printf("Switches:\n");
42                printf("  -names specifies that the number and names of genotypes are to be printed to output\n");
43                printf("  before the distance matrix; by default the number and names are not printed\n\n");
44
45                printf("Outputs a symmetric distance matrix in the format:\n");
46                printf("  <row_1> (columns in a row are separated by TABs)\n");
47                printf("  ...\n");
48                printf("  <row_n>\n");
49
50                return -1;
51        }
52
53        // prepare output parameters from .gen file
54        vector<Geno *> pvGenos;
55        vector<char *> pvNames;
56
57        // check if there is a switch
58        iCurrParam = 1;
59        szCurrParam = argv[iCurrParam];
60        if (strcmp(szCurrParam, "-names") == 0)
61        {
62                // switch "-names" was given; print names also
63                bPrintNames = true;
64                // pass to the next parameter
65                iCurrParam++;
66        }
67
68        // check the parameters
69        // get <genotypesFile> name from command line
70        char *szFileName = argv[iCurrParam];
71
72        // initially set measure components' weights to invalid values (negative)
73        for (int i = 0; i < M.GetNOFactors(); i++)
74        {
75                M.m_adFactors[i] = -1.0;
76        }
77
78        iCurrParam++;
79        szCurrParam = argv[iCurrParam];
80        int measure_type = -1;
81        nResult = sscanf(szCurrParam, "%d", &measure_type);
82        if (nResult != 1)
83        {
84                printf("Measure type should be a number!\n");
85                return -1;
86        }
87
88        if (measure_type != 0 && measure_type != 1)
89        {
90                printf("Measure type should be 0 (flexible criteria order and optimal matching) or 1 (vertex degree order and greedy matching)!\n");
91                return -1;
92        }
93
94        M.matching_method = measure_type;
95
96        const char *params[] = { "<w_dP>", "<w_dDEG>", "<w_dNEU>", "<w_dGEO>" };
97        for (int i = 0; i < M.GetNOFactors(); i++)
98        {
99                iCurrParam++;
100                szCurrParam = argv[iCurrParam];
101                nResult = sscanf(szCurrParam, "%lf", &M.m_adFactors[i]);
102                if (nResult != 1)
103                {
104                        // <w_dX> is not a number -- error
105                        printf("%s", params[i]);
106                        printf(" should be a number\n");
107                        return -1;
108                }
109                else
110                {
111                        // <w_dX> is a number; check if nonnegative
112                        if (M.m_adFactors[i] < 0.0)
113                        {
114                                printf("%s", params[i]);
115                                printf(" should be a nonnegative number\n");
116                                return -1;
117                        }
118                }
119        }
120
121        iCurrParam++;
122        szCurrParam = argv[iCurrParam];
123        nResult = sscanf(szCurrParam, "%d", &M.fixedZaxis);
124        if (nResult != 1)
125        {
126                // <isZFixed> is not a number -- error
127                printf("<isZFixed> should be a number\n");
128                return -1;
129        }
130        else if (M.fixedZaxis != 0 && M.fixedZaxis != 1)
131        {
132                printf("<isZFixed>=%d. <isZFixed> should be equal to 0 or 1\n", M.fixedZaxis);
133                return -1;
134        }
135
136        // read the input file
137        // prepare loading of genotypes from a .gen file
138        // create some basic genotype converters
139        PreconfiguredGenetics genetics;
140        StdioFileSystem_autoselect stdiofilesys;
141
142        long count = 0, totalsize = 0;
143        GenotypeMiniLoader loader(szFileName);
144        GenotypeMini *loaded;
145        while (loaded = loader.loadNextGenotype())
146        {
147                // while a valid genotype was loaded
148                count++;
149                totalsize += loaded->genotype.length();
150                // create a Geno object based on the MiniGenotype
151                Geno *pNextGenotype = new Geno(loaded->genotype);
152                if ((pNextGenotype != NULL) && (pNextGenotype->isValid()))
153                {
154                        pvGenos.push_back(pNextGenotype);
155                        char *szNewName = new char[loaded->name.length() + 1];
156                        strcpy(szNewName, loaded->name.c_str());
157                        pvNames.push_back(szNewName);
158                }
159                else
160                {
161                        printf("Genotype %2li is not valid\n", count);
162                        if (pNextGenotype != NULL) delete pNextGenotype;
163                }
164        }
165        if (loader.getStatus() == GenotypeMiniLoader::OnError)
166        {
167                printf("Error: %s", loader.getError().c_str());
168        }
169
170        double dSimilarity = 0.0;
171        double **aaSimil = NULL; // array of similarities
172
173        // create an empty array of similarities
174        aaSimil = new double*[pvGenos.size()];
175        for (unsigned int k = 0; k < pvGenos.size(); k++)
176        {
177                aaSimil[k] = new double[pvGenos.size()];
178                for (unsigned int l = 0; l < pvGenos.size(); l++)
179                        aaSimil[k][l] = 0.0;
180        }
181
182        // compute and store similarities
183        for (unsigned int i = 0; i < pvGenos.size(); i++)
184        {
185                for (unsigned int j = 0; j < pvGenos.size(); j++)
186                {
187                        dSimilarity = M.EvaluateDistance(pvGenos.operator[](i), pvGenos.operator[](j));
188                        aaSimil[i][j] = dSimilarity;
189                }
190        }
191
192        if (bPrintNames)
193        {
194                // if the "-names" switch was given, print the number of genotypes and their names
195                printf("%li\n", pvGenos.size());
196                for (unsigned int iGen = 0; iGen < pvNames.size(); iGen++)
197                {
198                        printf("%s\n", pvNames.at(iGen));
199                }
200        }
201
202        // print out the matrix of similarities
203        for (unsigned int i = 0; i < pvGenos.size(); i++)
204        {
205                for (unsigned int j = 0; j < pvGenos.size(); j++)
206                {
207                        printf("%.2lf\t", aaSimil[i][j]);
208                }
209                printf("\n");
210        }
211
212        // delete vectors and arrays
213        for (unsigned int i = 0; i < pvGenos.size(); i++)
214        {
215                delete pvGenos.operator[](i);
216                delete[] pvNames.operator[](i);
217                delete[] aaSimil[i];
218        }
219
220        delete[] aaSimil;
221
222        return 0;
223}
Note: See TracBrowser for help on using the repository browser.