},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 6,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import random\n",
+ "import string"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 139,
"metadata": {
"collapsed": true
},
{
"cell_type": "code",
"execution_count": 8,
- "metadata": {
- "collapsed": false
- },
+ "metadata": {},
"outputs": [
{
"data": {
"cell_type": "markdown",
"metadata": {},
"source": [
- "`dp_table[i, j]` is True if `s3[:i+j]` can be formed from interleaving `s1[:i]` and `s2[:j]`."
+ "`dp_table[i, j]` is True if first `i` + `j` characters of `s3` can be formed from interleaving of first `i` characters of `s1` and first `j` characters of `s2`."
]
},
{
"cell_type": "code",
- "execution_count": 11,
- "metadata": {
- "collapsed": false
- },
+ "execution_count": 9,
+ "metadata": {},
"outputs": [
{
"data": {
" [False, False, False, False, False, False]]"
]
},
- "execution_count": 11,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 10,
"metadata": {
- "collapsed": false,
"scrolled": true
},
"outputs": [
" (5, 5): False}"
]
},
- "execution_count": 24,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 135,
"metadata": {
"collapsed": true
},
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 136,
"metadata": {
- "collapsed": false
+ "collapsed": true
},
+ "outputs": [],
+ "source": [
+ "def show_table(table):\n",
+ " return '\\n'.join(\n",
+ " ' '.join('T' if table[i, j] else '.' for j in sorted(set([k[1] for k in table])))\n",
+ " for i in sorted(set([k[0] for k in table]))) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 137,
+ "metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "F F F F F F\n",
- "F F F F F F\n",
- "F F F F F F\n",
- "F F F F F F\n",
- "F F F F F F\n",
- "F F F F F F\n"
+ "T . . . . .\n",
+ "T . . . . .\n",
+ "T T T T . .\n",
+ ". T T T . .\n",
+ ". . . . . .\n",
+ ". . . . . .\n"
]
}
],
},
{
"cell_type": "code",
- "execution_count": 39,
- "metadata": {
- "collapsed": false
- },
+ "execution_count": 140,
+ "metadata": {},
"outputs": [
{
"name": "stdout",
"xx 5 3 c b c False\n",
"xx 5 4 c c c False\n",
"xx 5 5 c a c False\n",
- "T F F F F F\n",
- "T F F F F F\n",
- "T T T T F F\n",
- "F T T T F F\n",
- "F F F F F F\n",
- "F F F F F F\n"
+ "T . . . . .\n",
+ "T . . . . .\n",
+ "T T T T . .\n",
+ ". T T T . .\n",
+ ". . . . . .\n",
+ ". . . . . .\n"
]
},
{
" (3, 3): (2, 3, 'b', 's1')}"
]
},
- "execution_count": 39,
+ "execution_count": 140,
"metadata": {},
"output_type": "execute_result"
}
},
{
"cell_type": "code",
- "execution_count": 49,
- "metadata": {
- "collapsed": false
- },
+ "execution_count": 83,
+ "metadata": {},
"outputs": [],
"source": [
- "def is_interleave(seq1, seq2, seq3, return_backpointers=False, debug=False):\n",
+ "def is_interleave(seq1, seq2, seq3, return_backpointers=False, return_table=False, debug=False):\n",
" \"\"\"Return true if seq3 is some interleaved merge of seq1 and seq2.\n",
" If return_backpointers, also return the set of backpointers to\n",
" reconstruct the interleaving\"\"\"\n",
" \n",
- " # dp_table[i, j] is True if seq3[:i+j-1] is made up of an interleaving\n",
- " # of the first i characters of seq1 and the first j characters of seq2\n",
+ " # dp_table[i, j] is True if first i+j characters of seq is made up of \n",
+ " # an interleaving of the first i characters of seq1 and the \n",
+ " # first j characters of seq2\n",
" \n",
" if len(seq1) + len(seq2) != len(seq3):\n",
- " if return_backpointers:\n",
- " return False, {}\n",
+ " if return_backpointers or return_table:\n",
+ " retval = [False]\n",
+ " if return_backpointers:\n",
+ " retval += [{}]\n",
+ " if return_table:\n",
+ " retval += [{}]\n",
+ " return tuple(retval)\n",
" else:\n",
" return False\n",
" \n",
" for j in range(len(seq2)+1):\n",
" if i == 0 and j == 0:\n",
" dp_table[i, j] = True\n",
- " if debug: print('aa', i, j, '!', '!', '!', dp_table[i, j])\n",
+ " if debug: print('xxxx', i, j, '!', '!', '!', dp_table[i, j])\n",
" elif i == 0:\n",
" # extend by character from seq2\n",
" if dp_table[i, j-1] and seq2[j-1] == seq3[i+j-1]:\n",
" backpointers[i, j] = (i-1, j, seq1[i-1], 'seq1') \n",
" if debug: print('seq1', i, j, seq1[i-1], seq2[j-1], seq3[i+j-1], dp_table[i, j])\n",
" if not dp_table[i, j]:\n",
- " if debug: print('xx', i, j, seq1[i-1], seq2[j-1], seq3[i+j-1], dp_table[i, j])\n",
+ " if debug: print('xxxx', i, j, seq1[i-1], seq2[j-1], seq3[i+j-1], dp_table[i, j])\n",
"\n",
- " if return_backpointers:\n",
- " return dp_table[len(seq1), len(seq2)], backpointers\n",
+ " if return_backpointers or return_table:\n",
+ " retval = [dp_table[len(seq1), len(seq2)]]\n",
+ " if return_backpointers:\n",
+ " retval += [backpointers]\n",
+ " if return_table:\n",
+ " retval += [dp_table]\n",
+ " return tuple(retval)\n",
" else:\n",
" return dp_table[len(seq1), len(seq2)]"
]
},
{
"cell_type": "code",
- "execution_count": 50,
- "metadata": {
- "collapsed": false
- },
+ "execution_count": 67,
+ "metadata": {},
"outputs": [
{
"data": {
"True"
]
},
- "execution_count": 50,
+ "execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
},
{
"cell_type": "code",
- "execution_count": 51,
- "metadata": {
- "collapsed": false
- },
+ "execution_count": 71,
+ "metadata": {},
"outputs": [
{
"data": {
" (5, 5): (4, 5, 'c', 'seq1')})"
]
},
- "execution_count": 51,
+ "execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
},
{
"cell_type": "code",
- "execution_count": 52,
+ "execution_count": 72,
"metadata": {
- "collapsed": false
+ "scrolled": true
},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(True,\n",
+ " {(1, 0): (0, 0, 'a', 'seq1'),\n",
+ " (2, 0): (1, 0, 'a', 'seq1'),\n",
+ " (2, 1): (2, 0, 'd', 'seq2'),\n",
+ " (2, 2): (2, 1, 'b', 'seq2'),\n",
+ " (2, 3): (2, 2, 'b', 'seq2'),\n",
+ " (2, 4): (2, 3, 'c', 'seq2'),\n",
+ " (3, 1): (2, 1, 'b', 'seq1'),\n",
+ " (3, 2): (2, 2, 'b', 'seq1'),\n",
+ " (3, 4): (2, 4, 'b', 'seq1'),\n",
+ " (4, 2): (3, 2, 'c', 'seq1'),\n",
+ " (4, 3): (4, 2, 'b', 'seq2'),\n",
+ " (4, 4): (3, 4, 'c', 'seq1'),\n",
+ " (4, 5): (4, 4, 'a', 'seq2'),\n",
+ " (5, 3): (4, 3, 'c', 'seq1'),\n",
+ " (5, 5): (4, 5, 'c', 'seq1')},\n",
+ " {(0, 0): True,\n",
+ " (0, 1): False,\n",
+ " (0, 2): False,\n",
+ " (0, 3): False,\n",
+ " (0, 4): False,\n",
+ " (0, 5): False,\n",
+ " (1, 0): True,\n",
+ " (1, 1): False,\n",
+ " (1, 2): False,\n",
+ " (1, 3): False,\n",
+ " (1, 4): False,\n",
+ " (1, 5): False,\n",
+ " (2, 0): True,\n",
+ " (2, 1): True,\n",
+ " (2, 2): True,\n",
+ " (2, 3): True,\n",
+ " (2, 4): True,\n",
+ " (2, 5): False,\n",
+ " (3, 0): False,\n",
+ " (3, 1): True,\n",
+ " (3, 2): True,\n",
+ " (3, 3): False,\n",
+ " (3, 4): True,\n",
+ " (3, 5): False,\n",
+ " (4, 0): False,\n",
+ " (4, 1): False,\n",
+ " (4, 2): True,\n",
+ " (4, 3): True,\n",
+ " (4, 4): True,\n",
+ " (4, 5): True,\n",
+ " (5, 0): False,\n",
+ " (5, 1): False,\n",
+ " (5, 2): False,\n",
+ " (5, 3): True,\n",
+ " (5, 4): False,\n",
+ " (5, 5): True})"
+ ]
+ },
+ "execution_count": 72,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "is_interleave(s1, s2, s3t, return_backpointers=True, return_table=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
"outputs": [
{
"data": {
"False"
]
},
- "execution_count": 52,
+ "execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
},
{
"cell_type": "code",
- "execution_count": 54,
- "metadata": {
- "collapsed": false
- },
+ "execution_count": 18,
+ "metadata": {},
"outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "xxxx 0 0 ! ! ! True\n",
+ "seq2 0 1 ! b a False\n",
+ "seq2 0 2 ! b a False\n",
+ "seq2 0 3 ! b a False\n",
+ "seq1 1 0 a ! a True\n",
+ "xxxx 1 1 a b a False\n",
+ "xxxx 1 2 a b a False\n",
+ "xxxx 1 3 a b b False\n",
+ "seq1 2 0 a ! a True\n",
+ "xxxx 2 1 a b a False\n",
+ "xxxx 2 2 a b b False\n",
+ "xxxx 2 3 a b a False\n",
+ "seq1 3 0 a ! a True\n",
+ "seq2 3 1 a b b True\n",
+ "xxxx 3 2 a b a False\n",
+ "xxxx 3 3 a b b False\n",
+ "seq1 4 0 a ! b False\n",
+ "seq1 4 1 a b a True\n",
+ "seq2 4 2 a b b True\n",
+ "seq2 4 3 a b b True\n"
+ ]
+ },
{
"data": {
"text/plain": [
" (4, 3): (4, 2, 'b', 'seq2')})"
]
},
- "execution_count": 54,
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "is_interleave('aaaa', 'bbb', 'aaababb', return_backpointers=True, debug=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 109,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def show_backtrace(bps):\n",
+ " i = max([0] + [k[0] for k in bps])\n",
+ " j = max([0] + [k[1] for k in bps])\n",
+ " chars = ''\n",
+ " if (i, j) in bps:\n",
+ " while i != 0 or j != 0:\n",
+ " if bps[i, j][3] == 'seq1':\n",
+ " chars += bps[i, j][2].upper()\n",
+ " else:\n",
+ " chars += bps[i, j][2]\n",
+ " i, j = bps[i, j][0], bps[i, j][1] \n",
+ " return ''.join(list(reversed(chars)))\n",
+ " else:\n",
+ " return ''"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def make_string(length, alphabet=None):\n",
+ " if not alphabet:\n",
+ " alphabet = 'abcdefgh'\n",
+ " return ''.join(random.choice(alphabet) for _ in range(length)) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'abgdfggfabffcagcagdhaedeeecedcdbaeaahdfgegacbhbdba'"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "make_string(50)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 94,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def interleave(s1, s2, wander_limit=10, debug=False):\n",
+ " i1 = i2 = wander = 0\n",
+ " interleaved = []\n",
+ " while i1 <= len(s1) and i2 <= len(s2):\n",
+ " if i1 == len(s1):\n",
+ " if debug: print(i1, i2, wander, 'remaining s2', s2[i2:])\n",
+ " interleaved += s2[i2:]\n",
+ " i2 = len(s2) + 1\n",
+ " elif i2 == len(s2):\n",
+ " if debug: print(i1, i2, wander, 'remaining s1', s1[i1:])\n",
+ " interleaved += s1[i1:]\n",
+ " i1 = len(s1) + 1\n",
+ " else:\n",
+ " if wander == wander_limit:\n",
+ " step = -1\n",
+ " elif wander == -wander_limit:\n",
+ " step = +1\n",
+ " else:\n",
+ " step = random.choice([+1, -1])\n",
+ " if step == +1:\n",
+ " if debug: print(i1, i2, wander, 'adding', s1[i1])\n",
+ " interleaved += s1[i1]\n",
+ " i1 += 1\n",
+ " wander += 1\n",
+ " else:\n",
+ " if debug: print(i1, i2, wander, 'adding', s2[i2])\n",
+ " interleaved += s2[i2]\n",
+ " i2 += 1\n",
+ " wander -= 1\n",
+ " return ''.join(interleaved)\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 142,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0 0 0 adding d\n",
+ "1 0 1 adding v\n",
+ "1 1 0 adding v\n",
+ "1 2 -1 adding f\n",
+ "2 2 0 adding v\n",
+ "2 3 -1 adding w\n",
+ "2 4 -2 adding g\n",
+ "3 4 -1 adding y\n",
+ "3 5 -2 adding a\n",
+ "4 5 -1 adding w\n",
+ "4 6 -2 adding w\n",
+ "4 7 -3 adding w\n",
+ "4 8 -4 adding g\n",
+ "5 8 -3 adding h\n",
+ "6 8 -2 adding u\n",
+ "6 9 -3 adding v\n",
+ "6 10 -4 adding w\n",
+ "6 11 -5 adding f\n",
+ "7 11 -4 adding z\n",
+ "7 12 -5 adding f\n",
+ "8 12 -4 adding d\n",
+ "9 12 -3 adding x\n",
+ "9 13 -4 adding y\n",
+ "9 14 -5 adding g\n",
+ "10 14 -4 adding h\n",
+ "11 14 -3 adding u\n",
+ "11 15 -4 adding g\n",
+ "12 15 -3 adding b\n",
+ "13 15 -2 adding u\n",
+ "13 16 -3 adding z\n",
+ "13 17 -4 adding a\n",
+ "14 17 -3 adding u\n",
+ "14 18 -4 adding x\n",
+ "14 19 -5 adding a\n",
+ "15 19 -4 adding d\n",
+ "16 19 -3 adding g\n",
+ "17 19 -2 adding c\n",
+ "18 19 -1 adding x\n",
+ "18 20 -2 remaining s1 cg\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "('dfgaghffdghgbaadgccg',\n",
+ " 'vvvwywwwuvwzxyuuzuxx',\n",
+ " 'dvvfvwgyawwwghuvwfzfdxyghugbuzauxadgcxcg',\n",
+ " 40)"
+ ]
+ },
+ "execution_count": 142,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s1 = make_string(20)\n",
+ "s2 = make_string(20, alphabet='uvwxyz')\n",
+ "il = interleave(s1, s2, wander_limit=5, debug=True)\n",
+ "s1, s2, il, len(il)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 143,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "xxxx 0 0 ! ! ! True\n",
+ "seq2 0 1 ! d d True\n",
+ "seq2 0 2 ! f v False\n",
+ "seq2 0 3 ! g v False\n",
+ "seq2 0 4 ! a f False\n",
+ "seq2 0 5 ! g v False\n",
+ "seq2 0 6 ! h w False\n",
+ "seq2 0 7 ! f g False\n",
+ "seq2 0 8 ! f y False\n",
+ "seq2 0 9 ! d a False\n",
+ "seq2 0 10 ! g w False\n",
+ "seq2 0 11 ! h w False\n",
+ "seq2 0 12 ! g w False\n",
+ "seq2 0 13 ! b g False\n",
+ "seq2 0 14 ! a h False\n",
+ "seq2 0 15 ! a u False\n",
+ "seq2 0 16 ! d v False\n",
+ "seq2 0 17 ! g w False\n",
+ "seq2 0 18 ! c f False\n",
+ "seq2 0 19 ! c z False\n",
+ "seq2 0 20 ! g f False\n",
+ "seq1 1 0 v ! d False\n",
+ "seq1 1 1 v d v True\n",
+ "xxxx 1 2 v f v False\n",
+ "xxxx 1 3 v g f False\n",
+ "xxxx 1 4 v a v False\n",
+ "xxxx 1 5 v g w False\n",
+ "xxxx 1 6 v h g False\n",
+ "xxxx 1 7 v f y False\n",
+ "xxxx 1 8 v f a False\n",
+ "xxxx 1 9 v d w False\n",
+ "xxxx 1 10 v g w False\n",
+ "xxxx 1 11 v h w False\n",
+ "xxxx 1 12 v g g False\n",
+ "xxxx 1 13 v b h False\n",
+ "xxxx 1 14 v a u False\n",
+ "xxxx 1 15 v a v False\n",
+ "xxxx 1 16 v d w False\n",
+ "xxxx 1 17 v g f False\n",
+ "xxxx 1 18 v c z False\n",
+ "xxxx 1 19 v c f False\n",
+ "xxxx 1 20 v g d False\n",
+ "seq1 2 0 v ! v False\n",
+ "seq1 2 1 v d v True\n",
+ "seq2 2 2 v f f True\n",
+ "xxxx 2 3 v g v False\n",
+ "xxxx 2 4 v a w False\n",
+ "xxxx 2 5 v g g False\n",
+ "xxxx 2 6 v h y False\n",
+ "xxxx 2 7 v f a False\n",
+ "xxxx 2 8 v f w False\n",
+ "xxxx 2 9 v d w False\n",
+ "xxxx 2 10 v g w False\n",
+ "xxxx 2 11 v h g False\n",
+ "xxxx 2 12 v g h False\n",
+ "xxxx 2 13 v b u False\n",
+ "xxxx 2 14 v a v False\n",
+ "xxxx 2 15 v a w False\n",
+ "xxxx 2 16 v d f False\n",
+ "xxxx 2 17 v g z False\n",
+ "xxxx 2 18 v c f False\n",
+ "xxxx 2 19 v c d False\n",
+ "xxxx 2 20 v g x False\n",
+ "seq1 3 0 v ! v False\n",
+ "xxxx 3 1 v d f False\n",
+ "seq1 3 2 v f v True\n",
+ "xxxx 3 3 v g w False\n",
+ "xxxx 3 4 v a g False\n",
+ "xxxx 3 5 v g y False\n",
+ "xxxx 3 6 v h a False\n",
+ "xxxx 3 7 v f w False\n",
+ "xxxx 3 8 v f w False\n",
+ "xxxx 3 9 v d w False\n",
+ "xxxx 3 10 v g g False\n",
+ "xxxx 3 11 v h h False\n",
+ "xxxx 3 12 v g u False\n",
+ "xxxx 3 13 v b v False\n",
+ "xxxx 3 14 v a w False\n",
+ "xxxx 3 15 v a f False\n",
+ "xxxx 3 16 v d z False\n",
+ "xxxx 3 17 v g f False\n",
+ "xxxx 3 18 v c d False\n",
+ "xxxx 3 19 v c x False\n",
+ "xxxx 3 20 v g y False\n",
+ "seq1 4 0 w ! f False\n",
+ "xxxx 4 1 w d v False\n",
+ "seq1 4 2 w f w True\n",
+ "seq2 4 3 w g g True\n",
+ "xxxx 4 4 w a y False\n",
+ "xxxx 4 5 w g a False\n",
+ "xxxx 4 6 w h w False\n",
+ "xxxx 4 7 w f w False\n",
+ "xxxx 4 8 w f w False\n",
+ "xxxx 4 9 w d g False\n",
+ "xxxx 4 10 w g h False\n",
+ "xxxx 4 11 w h u False\n",
+ "xxxx 4 12 w g v False\n",
+ "xxxx 4 13 w b w False\n",
+ "xxxx 4 14 w a f False\n",
+ "xxxx 4 15 w a z False\n",
+ "xxxx 4 16 w d f False\n",
+ "xxxx 4 17 w g d False\n",
+ "xxxx 4 18 w c x False\n",
+ "xxxx 4 19 w c y False\n",
+ "xxxx 4 20 w g g False\n",
+ "seq1 5 0 y ! v False\n",
+ "xxxx 5 1 y d w False\n",
+ "xxxx 5 2 y f g False\n",
+ "seq1 5 3 y g y True\n",
+ "seq2 5 4 y a a True\n",
+ "xxxx 5 5 y g w False\n",
+ "xxxx 5 6 y h w False\n",
+ "xxxx 5 7 y f w False\n",
+ "xxxx 5 8 y f g False\n",
+ "xxxx 5 9 y d h False\n",
+ "xxxx 5 10 y g u False\n",
+ "xxxx 5 11 y h v False\n",
+ "xxxx 5 12 y g w False\n",
+ "xxxx 5 13 y b f False\n",
+ "xxxx 5 14 y a z False\n",
+ "xxxx 5 15 y a f False\n",
+ "xxxx 5 16 y d d False\n",
+ "xxxx 5 17 y g x False\n",
+ "xxxx 5 18 y c y False\n",
+ "xxxx 5 19 y c g False\n",
+ "xxxx 5 20 y g h False\n",
+ "seq1 6 0 w ! w False\n",
+ "xxxx 6 1 w d g False\n",
+ "xxxx 6 2 w f y False\n",
+ "xxxx 6 3 w g a False\n",
+ "seq1 6 4 w a w True\n",
+ "xxxx 6 5 w g w False\n",
+ "xxxx 6 6 w h w False\n",
+ "xxxx 6 7 w f g False\n",
+ "xxxx 6 8 w f h False\n",
+ "xxxx 6 9 w d u False\n",
+ "xxxx 6 10 w g v False\n",
+ "xxxx 6 11 w h w False\n",
+ "xxxx 6 12 w g f False\n",
+ "xxxx 6 13 w b z False\n",
+ "xxxx 6 14 w a f False\n",
+ "xxxx 6 15 w a d False\n",
+ "xxxx 6 16 w d x False\n",
+ "xxxx 6 17 w g y False\n",
+ "xxxx 6 18 w c g False\n",
+ "xxxx 6 19 w c h False\n",
+ "xxxx 6 20 w g u False\n",
+ "seq1 7 0 w ! g False\n",
+ "xxxx 7 1 w d y False\n",
+ "xxxx 7 2 w f a False\n",
+ "xxxx 7 3 w g w False\n",
+ "seq1 7 4 w a w True\n",
+ "xxxx 7 5 w g w False\n",
+ "xxxx 7 6 w h g False\n",
+ "xxxx 7 7 w f h False\n",
+ "xxxx 7 8 w f u False\n",
+ "xxxx 7 9 w d v False\n",
+ "xxxx 7 10 w g w False\n",
+ "xxxx 7 11 w h f False\n",
+ "xxxx 7 12 w g z False\n",
+ "xxxx 7 13 w b f False\n",
+ "xxxx 7 14 w a d False\n",
+ "xxxx 7 15 w a x False\n",
+ "xxxx 7 16 w d y False\n",
+ "xxxx 7 17 w g g False\n",
+ "xxxx 7 18 w c h False\n",
+ "xxxx 7 19 w c u False\n",
+ "xxxx 7 20 w g g False\n",
+ "seq1 8 0 w ! y False\n",
+ "xxxx 8 1 w d a False\n",
+ "xxxx 8 2 w f w False\n",
+ "xxxx 8 3 w g w False\n",
+ "seq1 8 4 w a w True\n",
+ "seq2 8 5 w g g True\n",
+ "seq2 8 6 w h h True\n",
+ "xxxx 8 7 w f u False\n",
+ "xxxx 8 8 w f v False\n",
+ "xxxx 8 9 w d w False\n",
+ "xxxx 8 10 w g f False\n",
+ "xxxx 8 11 w h z False\n",
+ "xxxx 8 12 w g f False\n",
+ "xxxx 8 13 w b d False\n",
+ "xxxx 8 14 w a x False\n",
+ "xxxx 8 15 w a y False\n",
+ "xxxx 8 16 w d g False\n",
+ "xxxx 8 17 w g h False\n",
+ "xxxx 8 18 w c u False\n",
+ "xxxx 8 19 w c g False\n",
+ "xxxx 8 20 w g b False\n",
+ "seq1 9 0 u ! a False\n",
+ "xxxx 9 1 u d w False\n",
+ "xxxx 9 2 u f w False\n",
+ "xxxx 9 3 u g w False\n",
+ "xxxx 9 4 u a g False\n",
+ "xxxx 9 5 u g h False\n",
+ "seq1 9 6 u h u True\n",
+ "xxxx 9 7 u f v False\n",
+ "xxxx 9 8 u f w False\n",
+ "xxxx 9 9 u d f False\n",
+ "xxxx 9 10 u g z False\n",
+ "xxxx 9 11 u h f False\n",
+ "xxxx 9 12 u g d False\n",
+ "xxxx 9 13 u b x False\n",
+ "xxxx 9 14 u a y False\n",
+ "xxxx 9 15 u a g False\n",
+ "xxxx 9 16 u d h False\n",
+ "xxxx 9 17 u g u False\n",
+ "xxxx 9 18 u c g False\n",
+ "xxxx 9 19 u c b False\n",
+ "xxxx 9 20 u g u False\n",
+ "seq1 10 0 v ! w False\n",
+ "xxxx 10 1 v d w False\n",
+ "xxxx 10 2 v f w False\n",
+ "xxxx 10 3 v g g False\n",
+ "xxxx 10 4 v a h False\n",
+ "xxxx 10 5 v g u False\n",
+ "seq1 10 6 v h v True\n",
+ "xxxx 10 7 v f w False\n",
+ "xxxx 10 8 v f f False\n",
+ "xxxx 10 9 v d z False\n",
+ "xxxx 10 10 v g f False\n",
+ "xxxx 10 11 v h d False\n",
+ "xxxx 10 12 v g x False\n",
+ "xxxx 10 13 v b y False\n",
+ "xxxx 10 14 v a g False\n",
+ "xxxx 10 15 v a h False\n",
+ "xxxx 10 16 v d u False\n",
+ "xxxx 10 17 v g g False\n",
+ "xxxx 10 18 v c b False\n",
+ "xxxx 10 19 v c u False\n",
+ "xxxx 10 20 v g z False\n",
+ "seq1 11 0 w ! w False\n",
+ "xxxx 11 1 w d w False\n",
+ "xxxx 11 2 w f g False\n",
+ "xxxx 11 3 w g h False\n",
+ "xxxx 11 4 w a u False\n",
+ "xxxx 11 5 w g v False\n",
+ "seq1 11 6 w h w True\n",
+ "seq2 11 7 w f f True\n",
+ "xxxx 11 8 w f z False\n",
+ "xxxx 11 9 w d f False\n",
+ "xxxx 11 10 w g d False\n",
+ "xxxx 11 11 w h x False\n",
+ "xxxx 11 12 w g y False\n",
+ "xxxx 11 13 w b g False\n",
+ "xxxx 11 14 w a h False\n",
+ "xxxx 11 15 w a u False\n",
+ "xxxx 11 16 w d g False\n",
+ "xxxx 11 17 w g b False\n",
+ "xxxx 11 18 w c u False\n",
+ "xxxx 11 19 w c z False\n",
+ "xxxx 11 20 w g a False\n",
+ "seq1 12 0 z ! w False\n",
+ "xxxx 12 1 z d g False\n",
+ "xxxx 12 2 z f h False\n",
+ "xxxx 12 3 z g u False\n",
+ "xxxx 12 4 z a v False\n",
+ "xxxx 12 5 z g w False\n",
+ "xxxx 12 6 z h f False\n",
+ "seq1 12 7 z f z True\n",
+ "seq2 12 8 z f f True\n",
+ "seq2 12 9 z d d True\n",
+ "xxxx 12 10 z g x False\n",
+ "xxxx 12 11 z h y False\n",
+ "xxxx 12 12 z g g False\n",
+ "xxxx 12 13 z b h False\n",
+ "xxxx 12 14 z a u False\n",
+ "xxxx 12 15 z a g False\n",
+ "xxxx 12 16 z d b False\n",
+ "xxxx 12 17 z g u False\n",
+ "xxxx 12 18 z c z False\n",
+ "xxxx 12 19 z c a False\n",
+ "xxxx 12 20 z g u False\n",
+ "seq1 13 0 x ! g False\n",
+ "xxxx 13 1 x d h False\n",
+ "xxxx 13 2 x f u False\n",
+ "xxxx 13 3 x g v False\n",
+ "xxxx 13 4 x a w False\n",
+ "xxxx 13 5 x g f False\n",
+ "xxxx 13 6 x h z False\n",
+ "xxxx 13 7 x f f False\n",
+ "xxxx 13 8 x f d False\n",
+ "seq1 13 9 x d x True\n",
+ "xxxx 13 10 x g y False\n",
+ "xxxx 13 11 x h g False\n",
+ "xxxx 13 12 x g h False\n",
+ "xxxx 13 13 x b u False\n",
+ "xxxx 13 14 x a g False\n",
+ "xxxx 13 15 x a b False\n",
+ "xxxx 13 16 x d u False\n",
+ "xxxx 13 17 x g z False\n",
+ "xxxx 13 18 x c a False\n",
+ "xxxx 13 19 x c u False\n",
+ "xxxx 13 20 x g x False\n",
+ "seq1 14 0 y ! h False\n",
+ "xxxx 14 1 y d u False\n",
+ "xxxx 14 2 y f v False\n",
+ "xxxx 14 3 y g w False\n",
+ "xxxx 14 4 y a f False\n",
+ "xxxx 14 5 y g z False\n",
+ "xxxx 14 6 y h f False\n",
+ "xxxx 14 7 y f d False\n",
+ "xxxx 14 8 y f x False\n",
+ "seq1 14 9 y d y True\n",
+ "seq2 14 10 y g g True\n",
+ "seq2 14 11 y h h True\n",
+ "xxxx 14 12 y g u False\n",
+ "xxxx 14 13 y b g False\n",
+ "xxxx 14 14 y a b False\n",
+ "xxxx 14 15 y a u False\n",
+ "xxxx 14 16 y d z False\n",
+ "xxxx 14 17 y g a False\n",
+ "xxxx 14 18 y c u False\n",
+ "xxxx 14 19 y c x False\n",
+ "xxxx 14 20 y g a False\n",
+ "seq1 15 0 u ! u False\n",
+ "xxxx 15 1 u d v False\n",
+ "xxxx 15 2 u f w False\n",
+ "xxxx 15 3 u g f False\n",
+ "xxxx 15 4 u a z False\n",
+ "xxxx 15 5 u g f False\n",
+ "xxxx 15 6 u h d False\n",
+ "xxxx 15 7 u f x False\n",
+ "xxxx 15 8 u f y False\n",
+ "xxxx 15 9 u d g False\n",
+ "xxxx 15 10 u g h False\n",
+ "seq1 15 11 u h u True\n",
+ "seq2 15 12 u g g True\n",
+ "seq2 15 13 u b b True\n",
+ "xxxx 15 14 u a u False\n",
+ "xxxx 15 15 u a z False\n",
+ "xxxx 15 16 u d a False\n",
+ "xxxx 15 17 u g u False\n",
+ "xxxx 15 18 u c x False\n",
+ "xxxx 15 19 u c a False\n",
+ "xxxx 15 20 u g d False\n",
+ "seq1 16 0 u ! v False\n",
+ "xxxx 16 1 u d w False\n",
+ "xxxx 16 2 u f f False\n",
+ "xxxx 16 3 u g z False\n",
+ "xxxx 16 4 u a f False\n",
+ "xxxx 16 5 u g d False\n",
+ "xxxx 16 6 u h x False\n",
+ "xxxx 16 7 u f y False\n",
+ "xxxx 16 8 u f g False\n",
+ "xxxx 16 9 u d h False\n",
+ "xxxx 16 10 u g u False\n",
+ "xxxx 16 11 u h g False\n",
+ "xxxx 16 12 u g b False\n",
+ "seq1 16 13 u b u True\n",
+ "xxxx 16 14 u a z False\n",
+ "xxxx 16 15 u a a False\n",
+ "xxxx 16 16 u d u False\n",
+ "xxxx 16 17 u g x False\n",
+ "xxxx 16 18 u c a False\n",
+ "xxxx 16 19 u c d False\n",
+ "xxxx 16 20 u g g False\n",
+ "seq1 17 0 z ! w False\n",
+ "xxxx 17 1 z d f False\n",
+ "xxxx 17 2 z f z False\n",
+ "xxxx 17 3 z g f False\n",
+ "xxxx 17 4 z a d False\n",
+ "xxxx 17 5 z g x False\n",
+ "xxxx 17 6 z h y False\n",
+ "xxxx 17 7 z f g False\n",
+ "xxxx 17 8 z f h False\n",
+ "xxxx 17 9 z d u False\n",
+ "xxxx 17 10 z g g False\n",
+ "xxxx 17 11 z h b False\n",
+ "xxxx 17 12 z g u False\n",
+ "seq1 17 13 z b z True\n",
+ "seq2 17 14 z a a True\n",
+ "xxxx 17 15 z a u False\n",
+ "xxxx 17 16 z d x False\n",
+ "xxxx 17 17 z g a False\n",
+ "xxxx 17 18 z c d False\n",
+ "xxxx 17 19 z c g False\n",
+ "xxxx 17 20 z g c False\n",
+ "seq1 18 0 u ! f False\n",
+ "xxxx 18 1 u d z False\n",
+ "xxxx 18 2 u f f False\n",
+ "xxxx 18 3 u g d False\n",
+ "xxxx 18 4 u a x False\n",
+ "xxxx 18 5 u g y False\n",
+ "xxxx 18 6 u h g False\n",
+ "xxxx 18 7 u f h False\n",
+ "xxxx 18 8 u f u False\n",
+ "xxxx 18 9 u d g False\n",
+ "xxxx 18 10 u g b False\n",
+ "xxxx 18 11 u h u False\n",
+ "xxxx 18 12 u g z False\n",
+ "xxxx 18 13 u b a False\n",
+ "seq1 18 14 u a u True\n",
+ "xxxx 18 15 u a x False\n",
+ "xxxx 18 16 u d a False\n",
+ "xxxx 18 17 u g d False\n",
+ "xxxx 18 18 u c g False\n",
+ "xxxx 18 19 u c c False\n",
+ "xxxx 18 20 u g x False\n",
+ "seq1 19 0 x ! z False\n",
+ "xxxx 19 1 x d f False\n",
+ "xxxx 19 2 x f d False\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "xxxx 19 3 x g x False\n",
+ "xxxx 19 4 x a y False\n",
+ "xxxx 19 5 x g g False\n",
+ "xxxx 19 6 x h h False\n",
+ "xxxx 19 7 x f u False\n",
+ "xxxx 19 8 x f g False\n",
+ "xxxx 19 9 x d b False\n",
+ "xxxx 19 10 x g u False\n",
+ "xxxx 19 11 x h z False\n",
+ "xxxx 19 12 x g a False\n",
+ "xxxx 19 13 x b u False\n",
+ "seq1 19 14 x a x True\n",
+ "seq2 19 15 x a a True\n",
+ "seq2 19 16 x d d True\n",
+ "seq2 19 17 x g g True\n",
+ "seq2 19 18 x c c True\n",
+ "xxxx 19 19 x c x False\n",
+ "xxxx 19 20 x g c False\n",
+ "seq1 20 0 x ! f False\n",
+ "xxxx 20 1 x d d False\n",
+ "xxxx 20 2 x f x False\n",
+ "xxxx 20 3 x g y False\n",
+ "xxxx 20 4 x a g False\n",
+ "xxxx 20 5 x g h False\n",
+ "xxxx 20 6 x h u False\n",
+ "xxxx 20 7 x f g False\n",
+ "xxxx 20 8 x f b False\n",
+ "xxxx 20 9 x d u False\n",
+ "xxxx 20 10 x g z False\n",
+ "xxxx 20 11 x h a False\n",
+ "xxxx 20 12 x g u False\n",
+ "xxxx 20 13 x b x False\n",
+ "xxxx 20 14 x a a False\n",
+ "xxxx 20 15 x a d False\n",
+ "xxxx 20 16 x d g False\n",
+ "xxxx 20 17 x g c False\n",
+ "seq1 20 18 x c x True\n",
+ "seq2 20 19 x c c True\n",
+ "seq2 20 20 x g g True\n",
+ "T T . . . . . . . . . . . . . . . . . . .\n",
+ ". T . . . . . . . . . . . . . . . . . . .\n",
+ ". T T . . . . . . . . . . . . . . . . . .\n",
+ ". . T . . . . . . . . . . . . . . . . . .\n",
+ ". . T T . . . . . . . . . . . . . . . . .\n",
+ ". . . T T . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . T T T . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . T T . . . . . . . . . . . . .\n",
+ ". . . . . . . T T T . . . . . . . . . . .\n",
+ ". . . . . . . . . T . . . . . . . . . . .\n",
+ ". . . . . . . . . T T T . . . . . . . . .\n",
+ ". . . . . . . . . . . T T T . . . . . . .\n",
+ ". . . . . . . . . . . . . T . . . . . . .\n",
+ ". . . . . . . . . . . . . T T . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . .\n",
+ ". . . . . . . . . . . . . . T T T T T . .\n",
+ ". . . . . . . . . . . . . . . . . . T T T\n"
+ ]
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s2, s1, il, return_backpointers=True, return_table=True, debug=True)\n",
+ "print(show_table(t))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 144,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'dVVfVWgYaWWWghUVWfZfdXYghUgbUZaUXadgcXcg'"
+ ]
+ },
+ "execution_count": 144,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "show_backtrace(bp)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 145,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "T T . . . . . . . . . . . . . . . . . . .\n",
+ ". T . . . . . . . . . . . . . . . . . . .\n",
+ ". T T . . . . . . . . . . . . . . . . . .\n",
+ ". . T . . . . . . . . . . . . . . . . . .\n",
+ ". . T T . . . . . . . . . . . . . . . . .\n",
+ ". . . T T . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . T T T . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . T T . . . . . . . . . . . . .\n",
+ ". . . . . . . T T T . . . . . . . . . . .\n",
+ ". . . . . . . . . T . . . . . . . . . . .\n",
+ ". . . . . . . . . T T T . . . . . . . . .\n",
+ ". . . . . . . . . . . T T T . . . . . . .\n",
+ ". . . . . . . . . . . . . T . . . . . . .\n",
+ ". . . . . . . . . . . . . T T . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . .\n",
+ ". . . . . . . . . . . . . . T T T T T . .\n",
+ ". . . . . . . . . . . . . . . . . . T T T\n",
+ "dVVfVWgYaWWWghUVWfZfdXYghUgbUZaUXadgcXcg\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 145,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s2, s1, il, return_backpointers=True, return_table=True)\n",
+ "print(show_table(t))\n",
+ "print(show_backtrace(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 151,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "('cfhgbbfabcehcbfdfcafdfecefaecfagbdfeecfdbhebgbfhee',\n",
+ " 'begacfabcgegaegefgcgaabeefahahgfhbdbhhdabbaaahhdcb',\n",
+ " 'bcfehggacfbbabcgegfaeabgceefhcbgcgaabfdfcaefedfefacehahgffhbdbahechfagdabbbdaafeahechdfdcbbhebgbfhee',\n",
+ " 100)"
+ ]
+ },
+ "execution_count": 151,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s1 = make_string(50)\n",
+ "s2 = make_string(50)\n",
+ "il = interleave(s1, s2)\n",
+ "s1, s2, il, len(il)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 152,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . T . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T T T T T T T\n",
+ "BcfEhgGACFbbABCGEGfAEabGceEFhcbGCGAABfdfcaEfEdfeFAceHAHGfFHBDBaHecHfagDAbBBdAAfeAHecHDfdCbBhebgbfhee\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 152,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s2, s1, il, return_backpointers=True, return_table=True)\n",
+ "print(show_table(t))\n",
+ "print(show_backtrace(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 157,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1000 loops, best of 3: 1.24 ms per loop\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%timeit\n",
+ "is_interleave(s2, s1, il)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 148,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . T . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . T T T T T T T T T T T T T T . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . T . . . . . . . . . T . . T T T . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . T T . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n",
+ "FCgcGdDEgebbEhBCCgEcehHDAFBebgGECehcgdfdadbeggEgFCfggGAGaAhEEHfAgGAGHeFdaDfEcbfGcBDEbHdEaaFdfBBCABHC\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 148,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s1, s2, il, return_backpointers=True, return_table=True)\n",
+ "print(show_table(t))\n",
+ "print(show_backtrace(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 115,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 115,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "show_backtrace(bp).lower() == il"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 149,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "('hchdchbfgbfhfcadcdehgebefhebedbdadfbbcdadfgbefebeb', False, False)"
+ ]
+ },
+ "execution_count": 149,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s3 = make_string(50)\n",
+ "s3, is_interleave(s1, s3, il), is_interleave(s2, s3, il)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 150,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n",
+ "FCG\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "False"
+ ]
+ },
+ "execution_count": 150,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s1, s3, il, return_backpointers=True, return_table=True)\n",
+ "print(show_table(t))\n",
+ "print(show_backtrace(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Example"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 174,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def show_annotated_table(table, bps):\n",
+ " return '\\n'.join(' '.join('*' if (i, j) == (0, 0) else bps[i, j][2] if table[i, j] else '.' for j in sorted(set([k[1] for k in table])))\n",
+ " for i in sorted(set([k[0] for k in table])))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 195,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def show_backtrace_star(bps):\n",
+ " i = max([0] + [k[0] for k in bps])\n",
+ " j = max([0] + [k[1] for k in bps])\n",
+ " chars = ''\n",
+ " stars = ''\n",
+ " if (i, j) in bps:\n",
+ " while i != 0 or j != 0:\n",
+ " chars += bps[i, j][2]\n",
+ " if bps[i, j][3] == 'seq1':\n",
+ " stars += '*'\n",
+ " else:\n",
+ " stars += ' '\n",
+ " i, j = bps[i, j][0], bps[i, j][1] \n",
+ " return ''.join(list(reversed(chars))) + '\\n' + ''.join(list(reversed(stars)))\n",
+ " else:\n",
+ " return ''"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 203,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "('ddcbcaabac', 'abcaddcbcc', 'abddcbccaaadbadccbcc', 20)"
+ ]
+ },
+ "execution_count": 203,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s1 = make_string(10, alphabet='abcd')\n",
+ "s2 = make_string(10, alphabet='abcd')\n",
+ "s3 = make_string(10, alphabet='abcd')\n",
+ "il = interleave(s1, s2)\n",
+ "s1, s2, il, len(il)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 204,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "* a b . . . . . . . .\n",
+ ". . d . . . . . . . .\n",
+ ". . d c . . . . . . .\n",
+ ". . c . . . . . . . .\n",
+ ". . b c . . . . . . .\n",
+ ". . c c a . . . . . .\n",
+ ". . . a a . . . . . .\n",
+ ". . . a a d . . . . .\n",
+ ". . . . . b . . . . .\n",
+ ". . . . . a d c . . .\n",
+ ". . . . . . c c b c c\n",
+ "abDDCBcCaAAdBAdcCbcc\n",
+ "abddcbccaaadbadccbcc\n",
+ " **** * ** ** * \n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 204,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s1, s2, il, return_backpointers=True, return_table=True)\n",
+ "print(show_annotated_table(t, bp))\n",
+ "print(show_backtrace(bp))\n",
+ "print(show_backtrace_star(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 198,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "* b . . . . . . . . .\n",
+ "b b c a . . . . . . .\n",
+ ". c . c . . . . . . .\n",
+ ". a c . . . . . . . .\n",
+ ". . b . . . . . . . .\n",
+ ". . d a a . . . . . .\n",
+ ". . a a . . . . . . .\n",
+ ". . . d a . . . . . .\n",
+ ". . . . b a d a . . .\n",
+ ". . . . . . . c . . .\n",
+ ". . . . . . . c b b b\n",
+ "bBCAcBDaADaBadaCCbbb\n",
+ "bbcacbdaadabadaccbbb\n",
+ " *** ** ** * ** \n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 198,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s2, s1, il, return_backpointers=True, return_table=True)\n",
+ "print(show_annotated_table(t, bp))\n",
+ "print(show_backtrace(bp))\n",
+ "print(show_backtrace_star(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 199,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "* b . . . . . . . . .\n",
+ "b b c . . . . . . . .\n",
+ ". c . . . . . . . . .\n",
+ ". a c . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ "bBCAc\n",
+ "bbcac\n",
+ " *** \n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "False"
+ ]
+ },
+ "execution_count": 199,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "v, bp, t = is_interleave(s1, s3, il, return_backpointers=True, return_table=True)\n",
+ "print(show_annotated_table(t, bp))\n",
+ "print(show_backtrace(bp))\n",
+ "print(show_backtrace_star(bp))\n",
+ "v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 200,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "* b . . . . . . . . .\n",
+ "b b c . . . . . . . .\n",
+ ". c . . . . . . . . .\n",
+ ". a c . . . . . . . .\n",
+ ". . b . . . . . . . .\n",
+ ". . d . . . . . . . .\n",
+ ". . a . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ ". . . . . . . . . . .\n",
+ "bBCAcBDA\n",
+ "bbcacbda\n",
+ " *** ***\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "False"
+ ]
+ },
+ "execution_count": 200,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "is_interleave('aaaa', 'bbb', 'aaababb', return_backpointers=True)"
+ "v, bp, t = is_interleave(s2, s3, il, return_backpointers=True, return_table=True)\n",
+ "print(show_annotated_table(t, bp))\n",
+ "print(show_backtrace(bp))\n",
+ "print(show_backtrace_star(bp))\n",
+ "v"
]
},
{
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.5.2"
+ "version": "3.5.2+"
}
},
"nbformat": 4,
--- /dev/null
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Subsequence strings\n",
+ "\n",
+ "Given two strings `a` and `b`, is `a` a subsequence of `b`?\n",
+ "\n",
+ "For example,\n",
+ "Given:\n",
+ "a = \"aabcc\",\n",
+ "b = \"dabaabcacb\",\n",
+ "\n",
+ "return True : dAbAaBCaCb\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "s1 = \"aabcc\"\n",
+ "s2t = \"dabaabcacb\"\n",
+ "s2f = \"dabacc\"\n",
+ "\n",
+ "s2 = s2t"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "`dp_table[i, j]` is True if first `i` characters of `s1` can be found in first `j` characters of `s2`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{(0, 0): False,\n",
+ " (0, 1): False,\n",
+ " (0, 2): False,\n",
+ " (0, 3): False,\n",
+ " (0, 4): False,\n",
+ " (0, 5): False,\n",
+ " (0, 6): False,\n",
+ " (0, 7): False,\n",
+ " (0, 8): False,\n",
+ " (0, 9): False,\n",
+ " (0, 10): False,\n",
+ " (1, 0): False,\n",
+ " (1, 1): False,\n",
+ " (1, 2): False,\n",
+ " (1, 3): False,\n",
+ " (1, 4): False,\n",
+ " (1, 5): False,\n",
+ " (1, 6): False,\n",
+ " (1, 7): False,\n",
+ " (1, 8): False,\n",
+ " (1, 9): False,\n",
+ " (1, 10): False,\n",
+ " (2, 0): False,\n",
+ " (2, 1): False,\n",
+ " (2, 2): False,\n",
+ " (2, 3): False,\n",
+ " (2, 4): False,\n",
+ " (2, 5): False,\n",
+ " (2, 6): False,\n",
+ " (2, 7): False,\n",
+ " (2, 8): False,\n",
+ " (2, 9): False,\n",
+ " (2, 10): False,\n",
+ " (3, 0): False,\n",
+ " (3, 1): False,\n",
+ " (3, 2): False,\n",
+ " (3, 3): False,\n",
+ " (3, 4): False,\n",
+ " (3, 5): False,\n",
+ " (3, 6): False,\n",
+ " (3, 7): False,\n",
+ " (3, 8): False,\n",
+ " (3, 9): False,\n",
+ " (3, 10): False,\n",
+ " (4, 0): False,\n",
+ " (4, 1): False,\n",
+ " (4, 2): False,\n",
+ " (4, 3): False,\n",
+ " (4, 4): False,\n",
+ " (4, 5): False,\n",
+ " (4, 6): False,\n",
+ " (4, 7): False,\n",
+ " (4, 8): False,\n",
+ " (4, 9): False,\n",
+ " (4, 10): False,\n",
+ " (5, 0): False,\n",
+ " (5, 1): False,\n",
+ " (5, 2): False,\n",
+ " (5, 3): False,\n",
+ " (5, 4): False,\n",
+ " (5, 5): False,\n",
+ " (5, 6): False,\n",
+ " (5, 7): False,\n",
+ " (5, 8): False,\n",
+ " (5, 9): False,\n",
+ " (5, 10): False}"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "dp_table = {(i, j): False\n",
+ " for i in range(len(s1)+1)\n",
+ " for j in range(len(s2)+1)}\n",
+ "dp_table"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def show_table(table):\n",
+ " return '\\n'.join(\n",
+ " ' '.join(str(table[i, j])[0] for j in sorted(set([k[1] for k in table])))\n",
+ " for i in sorted(set([k[0] for k in table]))) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "F F F F F F F F F F F\n",
+ "F F F F F F F F F F F\n",
+ "F F F F F F F F F F F\n",
+ "F F F F F F F F F F F\n",
+ "F F F F F F F F F F F\n",
+ "F F F F F F F F F F F\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(show_table(dp_table))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "aaaa aaababb\n",
+ "aa 0 0 ! ! True\n",
+ "aa 0 1 ! ! True\n",
+ "aa 0 2 ! ! True\n",
+ "aa 0 3 ! ! True\n",
+ "aa 0 4 ! ! True\n",
+ "aa 0 5 ! ! True\n",
+ "aa 0 6 ! ! True\n",
+ "aa 0 7 ! ! True\n",
+ "s1 1 1 a a True\n",
+ "s2 1 2 a a True\n",
+ "s1 1 2 a a True\n",
+ "s2 1 3 a a True\n",
+ "s1 1 3 a a True\n",
+ "s2 1 4 a b True\n",
+ "s2 1 5 a a True\n",
+ "s1 1 5 a a True\n",
+ "s2 1 6 a b True\n",
+ "s2 1 7 a b True\n",
+ "s1 2 2 a a True\n",
+ "s2 2 3 a a True\n",
+ "s1 2 3 a a True\n",
+ "s2 2 4 a b True\n",
+ "s2 2 5 a a True\n",
+ "s1 2 5 a a True\n",
+ "s2 2 6 a b True\n",
+ "s2 2 7 a b True\n",
+ "s1 3 3 a a True\n",
+ "s2 3 4 a b True\n",
+ "s2 3 5 a a True\n",
+ "s1 3 5 a a True\n",
+ "s2 3 6 a b True\n",
+ "s2 3 7 a b True\n",
+ "xx 4 4 a b False\n",
+ "s1 4 5 a a True\n",
+ "s2 4 6 a b True\n",
+ "s2 4 7 a b True\n",
+ "T T T T T T T T\n",
+ "F T T T T T T T\n",
+ "F F T T T T T T\n",
+ "F F F T T T T T\n",
+ "F F F F F T T T\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "{(1, 1): (0, 0, 'a', 's1'),\n",
+ " (1, 2): (0, 1, 'a', 's1'),\n",
+ " (1, 3): (0, 2, 'a', 's1'),\n",
+ " (1, 4): (1, 3, 'b', 's2'),\n",
+ " (1, 5): (0, 4, 'a', 's1'),\n",
+ " (1, 6): (1, 5, 'b', 's2'),\n",
+ " (1, 7): (1, 6, 'b', 's2'),\n",
+ " (2, 2): (1, 1, 'a', 's1'),\n",
+ " (2, 3): (1, 2, 'a', 's1'),\n",
+ " (2, 4): (2, 3, 'b', 's2'),\n",
+ " (2, 5): (1, 4, 'a', 's1'),\n",
+ " (2, 6): (2, 5, 'b', 's2'),\n",
+ " (2, 7): (2, 6, 'b', 's2'),\n",
+ " (3, 3): (2, 2, 'a', 's1'),\n",
+ " (3, 4): (3, 3, 'b', 's2'),\n",
+ " (3, 5): (2, 4, 'a', 's1'),\n",
+ " (3, 6): (3, 5, 'b', 's2'),\n",
+ " (3, 7): (3, 6, 'b', 's2'),\n",
+ " (4, 5): (3, 4, 'a', 's1'),\n",
+ " (4, 6): (4, 5, 'b', 's2'),\n",
+ " (4, 7): (4, 6, 'b', 's2')}"
+ ]
+ },
+ "execution_count": 47,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s2 = s2f\n",
+ "\n",
+ "s1 = 'aaaa'\n",
+ "s2 = 'aaababb'\n",
+ "\n",
+ "print(s1, s2)\n",
+ "\n",
+ "dp_table = {(i, j): False\n",
+ " for i in range(len(s1)+1)\n",
+ " for j in range(len(s2)+1)}\n",
+ "\n",
+ "backpointers = {}\n",
+ "\n",
+ "for i in range(len(s1)+1):\n",
+ " for j in range(i, len(s2)+1):\n",
+ " if i == 0 or j == 0:\n",
+ " dp_table[i, j] = True\n",
+ " print('aa', i, j, '!', '!', dp_table[i, j])\n",
+ " else:\n",
+ " # extend by character from s2\n",
+ " if dp_table[i, j-1]:\n",
+ " dp_table[i, j] = True\n",
+ " backpointers[i, j] = (i, j-1, s2[j-1], 's2')\n",
+ " print('s2', i, j, s1[i-1], s2[j-1], dp_table[i, j]) \n",
+ " # extend by character from s1\n",
+ " if dp_table[i-1, j-1] and s1[i-1] == s2[j-1]:\n",
+ " dp_table[i, j] = True\n",
+ " backpointers[i, j] = (i-1, j-1, s1[i-1], 's1') \n",
+ " print('s1', i, j, s1[i-1], s2[j-1], dp_table[i, j])\n",
+ " if not dp_table[i, j]:\n",
+ " print('xx', i, j, s1[i-1], s2[j-1], dp_table[i, j])\n",
+ "\n",
+ "print(show_table(dp_table))\n",
+ "backpointers"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def show_backtrace(bps):\n",
+ " i = max([0] + [k[0] for k in bps])\n",
+ " j = max([0] + [k[1] for k in bps])\n",
+ " chars = ''\n",
+ " if (i, j) in bps:\n",
+ " while i != 0 or j != 0:\n",
+ " if bps[i, j][3] == 's1':\n",
+ " chars += bps[i, j][2].upper()\n",
+ " else:\n",
+ " chars += bps[i, j][2]\n",
+ " i, j = bps[i, j][0], bps[i, j][1] \n",
+ " return ''.join(list(reversed(chars)))\n",
+ " else:\n",
+ " return ''"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'AAAbAbb'"
+ ]
+ },
+ "execution_count": 60,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "show_backtrace(backpointers)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def is_subseq(seq1, seq2, return_backpointers=False, debug=False):\n",
+ " \"\"\"Return true if seq1 is a subsequence of seq2.\n",
+ " If return_backpointers, also return the set of backpointers to\n",
+ " reconstruct the subsequence\"\"\"\n",
+ " \n",
+ " # dp_table[i, j] is True if first i characters of seq1 can\n",
+ " # be found in the first j characters of seq2\n",
+ " \n",
+ " dp_table = {(i, j): False\n",
+ " for i in range(len(seq1)+1)\n",
+ " for j in range(len(seq2)+1)}\n",
+ "\n",
+ " backpointers = {}\n",
+ " \n",
+ " for i in range(len(seq1)+1):\n",
+ " for j in range(i, len(seq2)+1):\n",
+ " if i == 0 or j == 0:\n",
+ " dp_table[i, j] = True\n",
+ " if debug: print('aa', i, j, '!', '!', dp_table[i, j])\n",
+ " else:\n",
+ " # extend by character from s2\n",
+ " if dp_table[i, j-1]:\n",
+ " dp_table[i, j] = True\n",
+ " backpointers[i, j] = (i, j-1, seq2[j-1], 's2')\n",
+ " if debug: print('s2', i, j, seq1[i-1], seq2[j-1], dp_table[i, j]) \n",
+ " # extend by character from s1\n",
+ " if dp_table[i-1, j-1] and seq1[i-1] == seq2[j-1]:\n",
+ " dp_table[i, j] = True\n",
+ " backpointers[i, j] = (i-1, j-1, seq1[i-1], 's1') \n",
+ " if debug: print('s1', i, j, seq1[i-1], seq2[j-1], dp_table[i, j])\n",
+ " if not dp_table[i, j]:\n",
+ " if debug: print('xx', i, j, seq1[i-1], seq2[j-1], dp_table[i, j]) \n",
+ " \n",
+ " if return_backpointers:\n",
+ " return dp_table[len(seq1), len(seq2)], backpointers\n",
+ " else:\n",
+ " return dp_table[len(seq1), len(seq2)]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "is_subseq(s1, s2t)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 55,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "tf, bps = is_subseq(s1, s2t, return_backpointers=True)\n",
+ "tf"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'AABCaCb'"
+ ]
+ },
+ "execution_count": 56,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "show_backtrace(bps)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "False"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "is_subseq(s1, s2f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "aa 0 0 ! ! True\n",
+ "aa 0 1 ! ! True\n",
+ "aa 0 2 ! ! True\n",
+ "aa 0 3 ! ! True\n",
+ "aa 0 4 ! ! True\n",
+ "aa 0 5 ! ! True\n",
+ "aa 0 6 ! ! True\n",
+ "aa 0 7 ! ! True\n",
+ "s1 1 1 a a True\n",
+ "s2 1 2 a a True\n",
+ "s1 1 2 a a True\n",
+ "s2 1 3 a a True\n",
+ "s1 1 3 a a True\n",
+ "s2 1 4 a b True\n",
+ "s2 1 5 a a True\n",
+ "s1 1 5 a a True\n",
+ "s2 1 6 a b True\n",
+ "s2 1 7 a b True\n",
+ "s1 2 2 a a True\n",
+ "s2 2 3 a a True\n",
+ "s1 2 3 a a True\n",
+ "s2 2 4 a b True\n",
+ "s2 2 5 a a True\n",
+ "s1 2 5 a a True\n",
+ "s2 2 6 a b True\n",
+ "s2 2 7 a b True\n",
+ "s1 3 3 a a True\n",
+ "s2 3 4 a b True\n",
+ "s2 3 5 a a True\n",
+ "s1 3 5 a a True\n",
+ "s2 3 6 a b True\n",
+ "s2 3 7 a b True\n",
+ "xx 4 4 a b False\n",
+ "s1 4 5 a a True\n",
+ "s2 4 6 a b True\n",
+ "s2 4 7 a b True\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "(True,\n",
+ " {(1, 1): (0, 1, 'a', 's1'),\n",
+ " (1, 2): (0, 2, 'a', 's1'),\n",
+ " (1, 3): (0, 3, 'a', 's1'),\n",
+ " (1, 4): (1, 3, 'b', 's2'),\n",
+ " (1, 5): (0, 5, 'a', 's1'),\n",
+ " (1, 6): (1, 5, 'b', 's2'),\n",
+ " (1, 7): (1, 6, 'b', 's2'),\n",
+ " (2, 2): (1, 2, 'a', 's1'),\n",
+ " (2, 3): (1, 3, 'a', 's1'),\n",
+ " (2, 4): (2, 3, 'b', 's2'),\n",
+ " (2, 5): (1, 5, 'a', 's1'),\n",
+ " (2, 6): (2, 5, 'b', 's2'),\n",
+ " (2, 7): (2, 6, 'b', 's2'),\n",
+ " (3, 3): (2, 3, 'a', 's1'),\n",
+ " (3, 4): (3, 3, 'b', 's2'),\n",
+ " (3, 5): (2, 5, 'a', 's1'),\n",
+ " (3, 6): (3, 5, 'b', 's2'),\n",
+ " (3, 7): (3, 6, 'b', 's2'),\n",
+ " (4, 5): (3, 5, 'a', 's1'),\n",
+ " (4, 6): (4, 5, 'b', 's2'),\n",
+ " (4, 7): (4, 6, 'b', 's2')})"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "is_subseq('aaaa', 'aaababb', return_backpointers=True, debug=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.5.2+"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
projects / ou-summer-of-code-2017.git / commitdiff