chrislit /
abydos
| @@ 50-87 (lines=38) @@ | ||
| 47 | alignment and disallows negative scores. |
|
| 48 | """ |
|
| 49 | ||
| 50 | def dist_abs(self, src, tar, gap_cost=1, sim_func=sim_ident): |
|
| 51 | """Return the Smith-Waterman score of two strings. |
|
| 52 | ||
| 53 | Parameters |
|
| 54 | ---------- |
|
| 55 | src : str |
|
| 56 | Source string for comparison |
|
| 57 | tar : str |
|
| 58 | Target string for comparison |
|
| 59 | gap_cost : float |
|
| 60 | The cost of an alignment gap (1 by default) |
|
| 61 | sim_func : function |
|
| 62 | A function that returns the similarity of two characters (identity |
|
| 63 | similarity by default) |
|
| 64 | ||
| 65 | Returns |
|
| 66 | ------- |
|
| 67 | float |
|
| 68 | Smith-Waterman score |
|
| 69 | ||
| 70 | Examples |
|
| 71 | -------- |
|
| 72 | >>> cmp = SmithWaterman() |
|
| 73 | >>> cmp.dist_abs('cat', 'hat') |
|
| 74 | 2.0 |
|
| 75 | >>> cmp.dist_abs('Niall', 'Neil') |
|
| 76 | 1.0 |
|
| 77 | >>> cmp.dist_abs('aluminum', 'Catalan') |
|
| 78 | 0.0 |
|
| 79 | >>> cmp.dist_abs('ATCG', 'TAGC') |
|
| 80 | 1.0 |
|
| 81 | ||
| 82 | """ |
|
| 83 | d_mat = np_zeros((len(src) + 1, len(tar) + 1), dtype=np_float32) |
|
| 84 | ||
| 85 | for i in range(len(src) + 1): |
|
| 86 | d_mat[i, 0] = 0 |
|
| 87 | for j in range(len(tar) + 1): |
|
| 88 | d_mat[0, j] = 0 |
|
| 89 | for i in range(1, len(src) + 1): |
|
| 90 | for j in range(1, len(tar) + 1): |
|
| @@ 129-166 (lines=38) @@ | ||
| 126 | return mat[(tar, src)] |
|
| 127 | return mismatch_cost |
|
| 128 | ||
| 129 | def dist_abs(self, src, tar, gap_cost=1, sim_func=sim_ident): |
|
| 130 | """Return the Needleman-Wunsch score of two strings. |
|
| 131 | ||
| 132 | Parameters |
|
| 133 | ---------- |
|
| 134 | src : str |
|
| 135 | Source string for comparison |
|
| 136 | tar : str |
|
| 137 | Target string for comparison |
|
| 138 | gap_cost : float |
|
| 139 | The cost of an alignment gap (1 by default) |
|
| 140 | sim_func : function |
|
| 141 | A function that returns the similarity of two characters (identity |
|
| 142 | similarity by default) |
|
| 143 | ||
| 144 | Returns |
|
| 145 | ------- |
|
| 146 | float |
|
| 147 | Needleman-Wunsch score |
|
| 148 | ||
| 149 | Examples |
|
| 150 | -------- |
|
| 151 | >>> cmp = NeedlemanWunsch() |
|
| 152 | >>> cmp.dist_abs('cat', 'hat') |
|
| 153 | 2.0 |
|
| 154 | >>> cmp.dist_abs('Niall', 'Neil') |
|
| 155 | 1.0 |
|
| 156 | >>> cmp.dist_abs('aluminum', 'Catalan') |
|
| 157 | -1.0 |
|
| 158 | >>> cmp.dist_abs('ATCG', 'TAGC') |
|
| 159 | 0.0 |
|
| 160 | ||
| 161 | """ |
|
| 162 | d_mat = np_zeros((len(src) + 1, len(tar) + 1), dtype=np_float32) |
|
| 163 | ||
| 164 | for i in range(len(src) + 1): |
|
| 165 | d_mat[i, 0] = -(i * gap_cost) |
|
| 166 | for j in range(len(tar) + 1): |
|
| 167 | d_mat[0, j] = -(j * gap_cost) |
|
| 168 | for i in range(1, len(src) + 1): |
|
| 169 | for j in range(1, len(tar) + 1): |
|
