double FrVectorSimilarity(FrClusteringMeasure sim,
const double *vec1, const double *vec2,
size_t veclen, bool normalize)
{
if (veclen == 0)
return 1.0 ; // empty vectors are always identical
if (!vec1 || !vec2)
return -1.0 ; // maximum diff if vector missing
switch (sim)
{
case FrCM_COSINE:
return cosine_similarity(vec1,vec2,veclen,normalize) ;
case FrCM_EUCLIDEAN:
return 1.0 - euclidean_distance(vec1,vec2,veclen,normalize) ;
case FrCM_MANHATTAN:
return 1.0 - manhattan_distance(vec1,vec2,veclen,normalize) ;
case FrCM_JACCARD:
return jaccard_coefficient(vec1,vec2,veclen) ;
case FrCM_SIMPSON:
return simpson_coefficient(vec1,vec2,veclen) ;
case FrCM_EXTSIMPSON:
return extended_simpson_coefficient(vec1,vec2,veclen,normalize) ;
case FrCM_DICE:
return dice_coefficient(vec1,vec2,veclen,normalize) ;
case FrCM_ANTIDICE:
return antidice_coefficient(vec1,vec2,veclen,normalize) ;
case FrCM_TANIMOTO:
return tanimoto_coefficient(vec1,vec2,veclen,normalize) ;
case FrCM_BRAUN_BLANQUET:
return braun_blanquet_coefficient(vec1,vec2,veclen,normalize) ;
case FrCM_KULCZYNSKI1:
return kulczynski_measure1(vec1,vec2,veclen,normalize) ;
case FrCM_KULCZYNSKI2:
return kulczynski_measure2(vec1,vec2,veclen,normalize) ;
case FrCM_OCHIAI:
return ochiai_measure(vec1,vec2,veclen,normalize) ;
case FrCM_SOKALSNEATH:
return sokal_sneath_measure(vec1,vec2,veclen,normalize) ;
case FrCM_MCCONNAUGHEY:
// mcConnaughey_measure() return is in range -1.0...+1.0
return (mcConnaughey_measure(vec1,vec2,veclen,normalize)+1.0) / 2.0 ;
case FrCM_LANCEWILLIAMS:
return 1.0 - lance_williams_distance(vec1,vec2,veclen,normalize) ;
case FrCM_BRAYCURTIS:
return bray_curtis_measure(vec1,vec2,veclen,normalize) ;
case FrCM_CANBERRA:
return 1.0 - canberra_measure(vec1,vec2,veclen,normalize) ;
case FrCM_CIRCLEPROD:
return circle_product(vec1,vec2,veclen,normalize) / veclen ;
case FrCM_CZEKANOWSKI:
return czekanowski_measure(vec1,vec2,veclen,normalize) ;
case FrCM_ROBINSON:
return robinson_coefficient(vec1,vec2,veclen,normalize) / 2.0 ;
case FrCM_DRENNAN:
return 1.0 - drennan_dissimilarity(vec1,vec2,veclen,normalize) ;
case FrCM_SIMILARITYRATIO:
return similarity_ratio(vec1,vec2,veclen,normalize) ;
case FrCM_JENSENSHANNON:
return 1.0 - jensen_shannon_divergence(vec1,vec2,veclen,normalize) ;
case FrCM_MOUNTFORD:
return mountford_coefficient(vec1,vec2,veclen) ;
case FrCM_FAGER_MCGOWAN:
return fager_mcgowan_coefficient(vec1,vec2,veclen) ;
case FrCM_TRIPARTITE:
return tripartite_similarity_index(vec1,vec2,veclen) ;
case FrCM_BIN_DICE:
return binary_dice_coefficient(vec1,vec2,veclen) ;
case FrCM_BIN_ANTIDICE:
return binary_antidice_coefficient(vec1,vec2,veclen) ;
case FrCM_BIN_GAMMA:
return binary_gamma_coefficient(vec1,vec2,veclen) ;
case FrCM_NONE:
return 0.0 ;
default:
FrMissedCase("FrVectorSimilarity()") ;
return 0.0 ;
}
}
int main(int argc, char *argv[]) {
if (argc != 4) {
printf("usage: \n\t$ %s <SimMetric> <string1> <string2>\n", basename(argv[0]));
printf("\nWhere SimMetric is one of:\n");
int i;
for (i=0; i < SIMMETC; i++) {
if (i > 0)
printf(",");
printf(" %s", SIMMETS[i]);
}
printf("\n");
return (1);
}
else if (strcmp(argv[1], "all") == 0) {
argv[1] = "block_distance"; main(argc, argv);
argv[1] = "cosine"; main(argc, argv);
argv[1] = "dice"; main(argc, argv);
argv[1] = "euclidean_distance"; main(argc, argv);
argv[1] = "jaccard"; main(argc, argv);
argv[1] = "jaro"; main(argc, argv);
argv[1] = "jaro_winkler"; main(argc, argv);
argv[1] = "levenshtein"; main(argc, argv);
argv[1] = "matching_coefficient"; main(argc, argv);
argv[1] = "monge_elkan"; main(argc, argv);
argv[1] = "needleman_wunch"; main(argc, argv);
argv[1] = "overlap_coefficient"; main(argc, argv);
argv[1] = "qgrams_distance"; main(argc, argv);
argv[1] = "smith_waterman"; main(argc, argv);
argv[1] = "smith_waterman_gotoh"; main(argc, argv);
argv[1] = "soundex"; main(argc, argv);
argv[1] = "metaphone"; main(argc, argv);
argv[1] = "double_metaphone"; main(argc, argv);
}
else {
float similarity = 0;
char *sm_name, metrics[50], compare[50];
sprintf(compare, "%10s & %-10s", argv[2], argv[3]);
switch (which_type(argv[1])) {
case 0:
case 1:
sm_name = "Block Distance";
sprintf(metrics, "%d", block_distance(argv[2], argv[3]));
similarity = block_distance_similarity(argv[2], argv[3]);
break;
case 2:
case 3:
sm_name = "Cosine Similarity";
similarity = cosine_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 4:
sm_name = "Dice Similarity";
similarity = dice_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 5:
case 6:
sm_name = "Euclidean Distance";
sprintf(metrics, "%3.2f", euclidean_distance(argv[2], argv[3]));
similarity = euclidean_distance_similarity(argv[2], argv[3]);
break;
case 7:
case 8:
sm_name = "Jaccard Similarity";
similarity = jaccard_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 9:
case 10:
sm_name = "Jaro Similarity";
similarity = jaro_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 11:
case 12:
sm_name = "Jaro Winkler Similarity";
similarity = jaro_winkler_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 13:
case 14:
sm_name = "Levenshtein Distance";
sprintf(metrics, "%d", levenshtein(argv[2], argv[3]));
similarity = levenshtein_similarity(argv[2], argv[3]);
break;
case 15:
case 16:
sm_name = "Matching Coefficient SimMetrics";
sprintf(metrics, "%3.2f", matching_coefficient(argv[2], argv[3]));
similarity = matching_coefficient_similarity(argv[2], argv[3]);
break;
case 17:
case 18:
sm_name = "Monge Elkan Similarity";
similarity = monge_elkan_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 19:
case 20:
sm_name = "Needleman Wunch SimMetrics";
sprintf(metrics, "%3.2f", needleman_wunch(argv[2], argv[3]));
similarity = needleman_wunch_similarity(argv[2], argv[3]);
break;
case 21:
case 22:
sm_name = "Overlap Coefficient Similarity";
similarity = overlap_coefficient_similarity(argv[2], argv[3]);
sprintf(metrics, "%f", similarity);
break;
case 23:
case 24:
sm_name = "QGrams Distance";
sprintf(metrics, "%d", qgrams_distance(argv[2], argv[3]));
similarity = qgrams_distance_similarity(argv[2], argv[3]);
break;
case 25:
case 26:
sm_name = "Smith Waterman SimMetrics";
sprintf(metrics, "%3.2f", smith_waterman(argv[2], argv[3]));
similarity = smith_waterman_similarity(argv[2], argv[3]);
break;
case 27:
case 28:
sm_name = "Smith Waterman Gotoh SimMetrics";
sprintf(metrics, "%3.2f", smith_waterman_gotoh(argv[2], argv[3]));
similarity = smith_waterman_gotoh_similarity(argv[2], argv[3]);
break;
case 29:
case 30:
sm_name = "Soundex Phonetics";
char *s1 = soundex(argv[2]);
char *s2 = soundex(argv[3]);
sprintf(metrics, "%s & %s", s1, s2);
free(s1);
free(s2);
similarity = soundex_similarity(argv[2], argv[3]);
break;
case 31:
case 32:
sm_name = "Metaphone Phonetics";
char *m1 = metaphone(argv[2]);
char *m2 = metaphone(argv[3]);
sprintf(metrics, "%s & %s", m1, m2);
free(m1);
free(m2);
similarity = metaphone_similarity(argv[2], argv[3]);
break;
case 33:
case 34:
sm_name = "Double Metaphone Phonetics";
char *dm1 = double_metaphone(argv[2]);
char *dm2 = double_metaphone(argv[3]);
sprintf(metrics, "%s & %s", dm1, dm2);
free(dm1);
free(dm2);
similarity = double_metaphone_similarity(argv[2], argv[3]);
break;
default:
printf("Unknown SimMetric %s, not found.\n", argv[1]);
return (1);
}
printf("%-31s between %-25s is %12s ", sm_name, compare, metrics);
printf("and yields a %3.0f%% similarity\n", similarity * 100);
return (EXIT_SUCCESS);
}
}
