X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=09-resolving-the-bill%2Finterleaving.ipynb;h=f93a848a813bd8310b661aa357438701eb2ad324;hb=f436853f44a91f167acea634e756ef5da8781c7a;hp=22140c9a938e2bfdc41609a07961e01a9c254c43;hpb=63b5f6c0b7b6c18464cce2bc888cf26491b5e603;p=ou-summer-of-code-2017.git diff --git a/09-resolving-the-bill/interleaving.ipynb b/09-resolving-the-bill/interleaving.ipynb index 22140c9..f93a848 100644 --- a/09-resolving-the-bill/interleaving.ipynb +++ b/09-resolving-the-bill/interleaving.ipynb @@ -19,7 +19,19 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "import random\n", + "import string" + ] + }, + { + "cell_type": "code", + "execution_count": 4, "metadata": { "collapsed": true }, @@ -34,10 +46,8 @@ }, { "cell_type": "code", - "execution_count": 8, - "metadata": { - "collapsed": false - }, + "execution_count": 5, + "metadata": {}, "outputs": [ { "data": { @@ -45,7 +55,7 @@ "[(0, ''), (1, 'a'), (2, 'aa'), (3, 'aab'), (4, 'aabc'), (5, 'aabcc')]" ] }, - "execution_count": 8, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -58,15 +68,13 @@ "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": 6, + "metadata": {}, "outputs": [ { "data": { @@ -79,7 +87,7 @@ " [False, False, False, False, False, False]]" ] }, - "execution_count": 11, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -92,9 +100,8 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 7, "metadata": { - "collapsed": false, "scrolled": true }, "outputs": [ @@ -139,7 +146,7 @@ " (5, 5): False}" ] }, - "execution_count": 24, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -153,7 +160,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 8, "metadata": { "collapsed": true }, @@ -167,21 +174,33 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 9, "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": 10, + "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" + ". . . . . .\n", + ". . . . . .\n", + ". . . . . .\n", + ". . . . . .\n", + ". . . . . .\n", + ". . . . . .\n" ] } ], @@ -191,16 +210,14 @@ }, { "cell_type": "code", - "execution_count": 39, - "metadata": { - "collapsed": false - }, + "execution_count": 11, + "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "aabcc dbbca aadbbbaccc\n", + "aabcc dbbca aadbbcbcac\n", "aa 0 0 ! ! ! True\n", "s2 0 1 ! d a False\n", "s2 0 2 ! b a False\n", @@ -212,39 +229,39 @@ "xx 1 2 a b d False\n", "xx 1 3 a b b False\n", "xx 1 4 a c b False\n", - "xx 1 5 a a b False\n", + "xx 1 5 a a c False\n", "s1 2 0 a ! a True\n", "s2 2 1 a d d True\n", "s2 2 2 a b b True\n", "s2 2 3 a b b True\n", - "xx 2 4 a c b False\n", - "xx 2 5 a a a False\n", + "s2 2 4 a c c True\n", + "xx 2 5 a a b False\n", "s1 3 0 b ! d False\n", "s1 3 1 b d b True\n", "s2 3 2 b b b True\n", "s1 3 2 b b b True\n", - "s2 3 3 b b b True\n", - "s1 3 3 b b b True\n", - "xx 3 4 b c a False\n", + "xx 3 3 b b c False\n", + "s1 3 4 b c b True\n", "xx 3 5 b a c False\n", "s1 4 0 c ! b False\n", "xx 4 1 c d b False\n", - "xx 4 2 c b b False\n", - "xx 4 3 c b a False\n", - "xx 4 4 c c c False\n", - "xx 4 5 c a c False\n", + "s1 4 2 c b c True\n", + "s2 4 3 c b b True\n", + "s2 4 4 c c c True\n", + "s1 4 4 c c c True\n", + "s2 4 5 c a a True\n", "s1 5 0 c ! b False\n", - "xx 5 1 c d b False\n", - "xx 5 2 c b a False\n", - "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" + "xx 5 1 c d c False\n", + "xx 5 2 c b b False\n", + "s1 5 3 c b c True\n", + "xx 5 4 c c a False\n", + "s1 5 5 c a c True\n", + "T . . . . .\n", + "T . . . . .\n", + "T T T T T .\n", + ". T T . T .\n", + ". . T T T T\n", + ". . . T . T\n" ] }, { @@ -255,18 +272,25 @@ " (2, 1): (2, 0, 'd', 's2'),\n", " (2, 2): (2, 1, 'b', 's2'),\n", " (2, 3): (2, 2, 'b', 's2'),\n", + " (2, 4): (2, 3, 'c', 's2'),\n", " (3, 1): (2, 1, 'b', 's1'),\n", " (3, 2): (2, 2, 'b', 's1'),\n", - " (3, 3): (2, 3, 'b', 's1')}" + " (3, 4): (2, 4, 'b', 's1'),\n", + " (4, 2): (3, 2, 'c', 's1'),\n", + " (4, 3): (4, 2, 'b', 's2'),\n", + " (4, 4): (3, 4, 'c', 's1'),\n", + " (4, 5): (4, 4, 'a', 's2'),\n", + " (5, 3): (4, 3, 'c', 's1'),\n", + " (5, 5): (4, 5, 'c', 's1')}" ] }, - "execution_count": 39, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "s3 = s3f\n", + "s3 = s3t\n", "\n", "print(s1, s2, s3)\n", "\n", @@ -313,23 +337,29 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 12, "metadata": { - "collapsed": false + "collapsed": true }, "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", @@ -343,7 +373,7 @@ " 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", @@ -368,20 +398,23 @@ " 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": 13, + "metadata": {}, "outputs": [ { "data": { @@ -389,7 +422,7 @@ "True" ] }, - "execution_count": 50, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -400,10 +433,8 @@ }, { "cell_type": "code", - "execution_count": 51, - "metadata": { - "collapsed": false - }, + "execution_count": 14, + "metadata": {}, "outputs": [ { "data": { @@ -426,7 +457,7 @@ " (5, 5): (4, 5, 'c', 'seq1')})" ] }, - "execution_count": 51, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -437,10 +468,81 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 15, "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": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave(s1, s2, s3t, return_backpointers=True, return_table=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, "outputs": [ { "data": { @@ -448,7 +550,7 @@ "False" ] }, - "execution_count": 52, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -459,11 +561,35 @@ }, { "cell_type": "code", - "execution_count": 54, - "metadata": { - "collapsed": false - }, + "execution_count": 17, + "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": [ @@ -477,13 +603,2187 @@ " (4, 3): (4, 2, 'b', 'seq2')})" ] }, - "execution_count": 54, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave('aaaa', 'bbb', 'aaababb', return_backpointers=True, debug=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "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] == '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": 19, + "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": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'fcdafhachbgaheghbbcehecbgfgbbbedcgcgcagdcgcbffdgbg'" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "make_string(50)" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "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": 22, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0 0 0 adding b\n", + "1 0 1 adding x\n", + "1 1 0 adding z\n", + "1 2 -1 adding h\n", + "2 2 0 adding v\n", + "2 3 -1 adding w\n", + "2 4 -2 adding f\n", + "3 4 -1 adding g\n", + "4 4 0 adding g\n", + "5 4 1 adding w\n", + "5 5 0 adding z\n", + "5 6 -1 adding x\n", + "5 7 -2 adding w\n", + "5 8 -3 adding w\n", + "5 9 -4 adding e\n", + "6 9 -3 adding h\n", + "7 9 -2 adding c\n", + "8 9 -1 adding x\n", + "8 10 -2 adding y\n", + "8 11 -3 adding d\n", + "9 11 -2 adding x\n", + "9 12 -3 adding a\n", + "10 12 -2 adding e\n", + "11 12 -1 adding a\n", + "12 12 0 adding z\n", + "12 13 -1 adding y\n", + "12 14 -2 adding x\n", + "12 15 -3 adding h\n", + "13 15 -2 adding x\n", + "13 16 -3 adding x\n", + "13 17 -4 adding u\n", + "13 18 -5 adding d\n", + "14 18 -4 adding w\n", + "14 19 -5 adding e\n", + "15 19 -4 adding b\n", + "16 19 -3 adding w\n", + "16 20 -4 remaining s1 eaca\n" + ] + }, + { + "data": { + "text/plain": [ + "('bhfggehcdaeahdebeaca',\n", + " 'xzvwwzxwwxyxzyxxxuww',\n", + " 'bxzhvwfggwzxwwehcxydxaeazyxhxxudwebweaca',\n", + " 40)" + ] + }, + "execution_count": 22, + "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": 23, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "xxxx 0 0 ! ! ! True\n", + "seq2 0 1 ! b b True\n", + "seq2 0 2 ! h x False\n", + "seq2 0 3 ! f z False\n", + "seq2 0 4 ! g h False\n", + "seq2 0 5 ! g v False\n", + "seq2 0 6 ! e w False\n", + "seq2 0 7 ! h f False\n", + "seq2 0 8 ! c g False\n", + "seq2 0 9 ! d g False\n", + "seq2 0 10 ! a w False\n", + "seq2 0 11 ! e z False\n", + "seq2 0 12 ! a x False\n", + "seq2 0 13 ! h w False\n", + "seq2 0 14 ! d w False\n", + "seq2 0 15 ! e e False\n", + "seq2 0 16 ! b h False\n", + "seq2 0 17 ! e c False\n", + "seq2 0 18 ! a x False\n", + "seq2 0 19 ! c y False\n", + "seq2 0 20 ! a d False\n", + "seq1 1 0 x ! b False\n", + "seq1 1 1 x b x True\n", + "xxxx 1 2 x h z False\n", + "xxxx 1 3 x f h False\n", + "xxxx 1 4 x g v False\n", + "xxxx 1 5 x g w False\n", + "xxxx 1 6 x e f False\n", + "xxxx 1 7 x h g False\n", + "xxxx 1 8 x c g False\n", + "xxxx 1 9 x d w False\n", + "xxxx 1 10 x a z False\n", + "xxxx 1 11 x e x False\n", + "xxxx 1 12 x a w False\n", + "xxxx 1 13 x h w False\n", + "xxxx 1 14 x d e False\n", + "xxxx 1 15 x e h False\n", + "xxxx 1 16 x b c False\n", + "xxxx 1 17 x e x False\n", + "xxxx 1 18 x a y False\n", + "xxxx 1 19 x c d False\n", + "xxxx 1 20 x a x False\n", + "seq1 2 0 z ! x False\n", + "seq1 2 1 z b z True\n", + "seq2 2 2 z h h True\n", + "xxxx 2 3 z f v False\n", + "xxxx 2 4 z g w False\n", + "xxxx 2 5 z g f False\n", + "xxxx 2 6 z e g False\n", + "xxxx 2 7 z h g False\n", + "xxxx 2 8 z c w False\n", + "xxxx 2 9 z d z False\n", + "xxxx 2 10 z a x False\n", + "xxxx 2 11 z e w False\n", + "xxxx 2 12 z a w False\n", + "xxxx 2 13 z h e False\n", + "xxxx 2 14 z d h False\n", + "xxxx 2 15 z e c False\n", + "xxxx 2 16 z b x False\n", + "xxxx 2 17 z e y False\n", + "xxxx 2 18 z a d False\n", + "xxxx 2 19 z c x False\n", + "xxxx 2 20 z a a False\n", + "seq1 3 0 v ! z False\n", + "xxxx 3 1 v b h False\n", + "seq1 3 2 v h v True\n", + "xxxx 3 3 v f w False\n", + "xxxx 3 4 v g f False\n", + "xxxx 3 5 v g g False\n", + "xxxx 3 6 v e g False\n", + "xxxx 3 7 v h w False\n", + "xxxx 3 8 v c z False\n", + "xxxx 3 9 v d x False\n", + "xxxx 3 10 v a w False\n", + "xxxx 3 11 v e w False\n", + "xxxx 3 12 v a e False\n", + "xxxx 3 13 v h h False\n", + "xxxx 3 14 v d c False\n", + "xxxx 3 15 v e x False\n", + "xxxx 3 16 v b y False\n", + "xxxx 3 17 v e d False\n", + "xxxx 3 18 v a x False\n", + "xxxx 3 19 v c a False\n", + "xxxx 3 20 v a e False\n", + "seq1 4 0 w ! h False\n", + "xxxx 4 1 w b v False\n", + "seq1 4 2 w h w True\n", + "seq2 4 3 w f f True\n", + "seq2 4 4 w g g True\n", + "seq2 4 5 w g g True\n", + "xxxx 4 6 w e w False\n", + "xxxx 4 7 w h z False\n", + "xxxx 4 8 w c x False\n", + "xxxx 4 9 w d w False\n", + "xxxx 4 10 w a w False\n", + "xxxx 4 11 w e e False\n", + "xxxx 4 12 w a h False\n", + "xxxx 4 13 w h c False\n", + "xxxx 4 14 w d x False\n", + "xxxx 4 15 w e y False\n", + "xxxx 4 16 w b d False\n", + "xxxx 4 17 w e x False\n", + "xxxx 4 18 w a a False\n", + "xxxx 4 19 w c e False\n", + "xxxx 4 20 w a a False\n", + "seq1 5 0 w ! v False\n", + "xxxx 5 1 w b w False\n", + "xxxx 5 2 w h f False\n", + "xxxx 5 3 w f g False\n", + "xxxx 5 4 w g g False\n", + "seq1 5 5 w g w True\n", + "xxxx 5 6 w e z False\n", + "xxxx 5 7 w h x False\n", + "xxxx 5 8 w c w False\n", + "xxxx 5 9 w d w False\n", + "xxxx 5 10 w a e False\n", + "xxxx 5 11 w e h False\n", + "xxxx 5 12 w a c False\n", + "xxxx 5 13 w h x False\n", + "xxxx 5 14 w d y False\n", + "xxxx 5 15 w e d False\n", + "xxxx 5 16 w b x False\n", + "xxxx 5 17 w e a False\n", + "xxxx 5 18 w a e False\n", + "xxxx 5 19 w c a False\n", + "xxxx 5 20 w a z False\n", + "seq1 6 0 z ! w False\n", + "xxxx 6 1 z b f False\n", + "xxxx 6 2 z h g False\n", + "xxxx 6 3 z f g False\n", + "xxxx 6 4 z g w False\n", + "seq1 6 5 z g z True\n", + "xxxx 6 6 z e x False\n", + "xxxx 6 7 z h w False\n", + "xxxx 6 8 z c w False\n", + "xxxx 6 9 z d e False\n", + "xxxx 6 10 z a h False\n", + "xxxx 6 11 z e c False\n", + "xxxx 6 12 z a x False\n", + "xxxx 6 13 z h y False\n", + "xxxx 6 14 z d d False\n", + "xxxx 6 15 z e x False\n", + "xxxx 6 16 z b a False\n", + "xxxx 6 17 z e e False\n", + "xxxx 6 18 z a a False\n", + "xxxx 6 19 z c z False\n", + "xxxx 6 20 z a y False\n", + "seq1 7 0 x ! f False\n", + "xxxx 7 1 x b g False\n", + "xxxx 7 2 x h g False\n", + "xxxx 7 3 x f w False\n", + "xxxx 7 4 x g z False\n", + "seq1 7 5 x g x True\n", + "xxxx 7 6 x e w False\n", + "xxxx 7 7 x h w False\n", + "xxxx 7 8 x c e False\n", + "xxxx 7 9 x d h False\n", + "xxxx 7 10 x a c False\n", + "xxxx 7 11 x e x False\n", + "xxxx 7 12 x a y False\n", + "xxxx 7 13 x h d False\n", + "xxxx 7 14 x d x False\n", + "xxxx 7 15 x e a False\n", + "xxxx 7 16 x b e False\n", + "xxxx 7 17 x e a False\n", + "xxxx 7 18 x a z False\n", + "xxxx 7 19 x c y False\n", + "xxxx 7 20 x a x False\n", + "seq1 8 0 w ! g False\n", + "xxxx 8 1 w b g False\n", + "xxxx 8 2 w h w False\n", + "xxxx 8 3 w f z False\n", + "xxxx 8 4 w g x False\n", + "seq1 8 5 w g w True\n", + "xxxx 8 6 w e w False\n", + "xxxx 8 7 w h e False\n", + "xxxx 8 8 w c h False\n", + "xxxx 8 9 w d c False\n", + "xxxx 8 10 w a x False\n", + "xxxx 8 11 w e y False\n", + "xxxx 8 12 w a d False\n", + "xxxx 8 13 w h x False\n", + "xxxx 8 14 w d a False\n", + "xxxx 8 15 w e e False\n", + "xxxx 8 16 w b a False\n", + "xxxx 8 17 w e z False\n", + "xxxx 8 18 w a y False\n", + "xxxx 8 19 w c x False\n", + "xxxx 8 20 w a h False\n", + "seq1 9 0 w ! g False\n", + "xxxx 9 1 w b w False\n", + "xxxx 9 2 w h z False\n", + "xxxx 9 3 w f x False\n", + "xxxx 9 4 w g w False\n", + "seq1 9 5 w g w True\n", + "seq2 9 6 w e e True\n", + "seq2 9 7 w h h True\n", + "seq2 9 8 w c c True\n", + "xxxx 9 9 w d x False\n", + "xxxx 9 10 w a y False\n", + "xxxx 9 11 w e d False\n", + "xxxx 9 12 w a x False\n", + "xxxx 9 13 w h a False\n", + "xxxx 9 14 w d e False\n", + "xxxx 9 15 w e a False\n", + "xxxx 9 16 w b z False\n", + "xxxx 9 17 w e y False\n", + "xxxx 9 18 w a x False\n", + "xxxx 9 19 w c h False\n", + "xxxx 9 20 w a x False\n", + "seq1 10 0 x ! w False\n", + "xxxx 10 1 x b z False\n", + "xxxx 10 2 x h x False\n", + "xxxx 10 3 x f w False\n", + "xxxx 10 4 x g w False\n", + "xxxx 10 5 x g e False\n", + "xxxx 10 6 x e h False\n", + "xxxx 10 7 x h c False\n", + "seq1 10 8 x c x True\n", + "xxxx 10 9 x d y False\n", + "xxxx 10 10 x a d False\n", + "xxxx 10 11 x e x False\n", + "xxxx 10 12 x a a False\n", + "xxxx 10 13 x h e False\n", + "xxxx 10 14 x d a False\n", + "xxxx 10 15 x e z False\n", + "xxxx 10 16 x b y False\n", + "xxxx 10 17 x e x False\n", + "xxxx 10 18 x a h False\n", + "xxxx 10 19 x c x False\n", + "xxxx 10 20 x a x False\n", + "seq1 11 0 y ! z False\n", + "xxxx 11 1 y b x False\n", + "xxxx 11 2 y h w False\n", + "xxxx 11 3 y f w False\n", + "xxxx 11 4 y g e False\n", + "xxxx 11 5 y g h False\n", + "xxxx 11 6 y e c False\n", + "xxxx 11 7 y h x False\n", + "seq1 11 8 y c y True\n", + "seq2 11 9 y d d True\n", + "xxxx 11 10 y a x False\n", + "xxxx 11 11 y e a False\n", + "xxxx 11 12 y a e False\n", + "xxxx 11 13 y h a False\n", + "xxxx 11 14 y d z False\n", + "xxxx 11 15 y e y False\n", + "xxxx 11 16 y b x False\n", + "xxxx 11 17 y e h False\n", + "xxxx 11 18 y a x False\n", + "xxxx 11 19 y c x False\n", + "xxxx 11 20 y a u False\n", + "seq1 12 0 x ! x False\n", + "xxxx 12 1 x b w False\n", + "xxxx 12 2 x h w False\n", + "xxxx 12 3 x f e False\n", + "xxxx 12 4 x g h False\n", + "xxxx 12 5 x g c False\n", + "xxxx 12 6 x e x False\n", + "xxxx 12 7 x h y False\n", + "xxxx 12 8 x c d False\n", + "seq1 12 9 x d x True\n", + "seq2 12 10 x a a True\n", + "seq2 12 11 x e e True\n", + "seq2 12 12 x a a True\n", + "xxxx 12 13 x h z False\n", + "xxxx 12 14 x d y False\n", + "xxxx 12 15 x e x False\n", + "xxxx 12 16 x b h False\n", + "xxxx 12 17 x e x False\n", + "xxxx 12 18 x a x False\n", + "xxxx 12 19 x c u False\n", + "xxxx 12 20 x a d False\n", + "seq1 13 0 z ! w False\n", + "xxxx 13 1 z b w False\n", + "xxxx 13 2 z h e False\n", + "xxxx 13 3 z f h False\n", + "xxxx 13 4 z g c False\n", + "xxxx 13 5 z g x False\n", + "xxxx 13 6 z e y False\n", + "xxxx 13 7 z h d False\n", + "xxxx 13 8 z c x False\n", + "xxxx 13 9 z d a False\n", + "xxxx 13 10 z a e False\n", + "xxxx 13 11 z e a False\n", + "seq1 13 12 z a z True\n", + "xxxx 13 13 z h y False\n", + "xxxx 13 14 z d x False\n", + "xxxx 13 15 z e h False\n", + "xxxx 13 16 z b x False\n", + "xxxx 13 17 z e x False\n", + "xxxx 13 18 z a u False\n", + "xxxx 13 19 z c d False\n", + "xxxx 13 20 z a w False\n", + "seq1 14 0 y ! w False\n", + "xxxx 14 1 y b e False\n", + "xxxx 14 2 y h h False\n", + "xxxx 14 3 y f c False\n", + "xxxx 14 4 y g x False\n", + "xxxx 14 5 y g y False\n", + "xxxx 14 6 y e d False\n", + "xxxx 14 7 y h x False\n", + "xxxx 14 8 y c a False\n", + "xxxx 14 9 y d e False\n", + "xxxx 14 10 y a a False\n", + "xxxx 14 11 y e z False\n", + "seq1 14 12 y a y True\n", + "xxxx 14 13 y h x False\n", + "xxxx 14 14 y d h False\n", + "xxxx 14 15 y e x False\n", + "xxxx 14 16 y b x False\n", + "xxxx 14 17 y e u False\n", + "xxxx 14 18 y a d False\n", + "xxxx 14 19 y c w False\n", + "xxxx 14 20 y a e False\n", + "seq1 15 0 x ! e False\n", + "xxxx 15 1 x b h False\n", + "xxxx 15 2 x h c False\n", + "xxxx 15 3 x f x False\n", + "xxxx 15 4 x g y False\n", + "xxxx 15 5 x g d False\n", + "xxxx 15 6 x e x False\n", + "xxxx 15 7 x h a False\n", + "xxxx 15 8 x c e False\n", + "xxxx 15 9 x d a False\n", + "xxxx 15 10 x a z False\n", + "xxxx 15 11 x e y False\n", + "seq1 15 12 x a x True\n", + "seq2 15 13 x h h True\n", + "xxxx 15 14 x d x False\n", + "xxxx 15 15 x e x False\n", + "xxxx 15 16 x b u False\n", + "xxxx 15 17 x e d False\n", + "xxxx 15 18 x a w False\n", + "xxxx 15 19 x c e False\n", + "xxxx 15 20 x a b False\n", + "seq1 16 0 x ! h False\n", + "xxxx 16 1 x b c False\n", + "xxxx 16 2 x h x False\n", + "xxxx 16 3 x f y False\n", + "xxxx 16 4 x g d False\n", + "xxxx 16 5 x g x False\n", + "xxxx 16 6 x e a False\n", + "xxxx 16 7 x h e False\n", + "xxxx 16 8 x c a False\n", + "xxxx 16 9 x d z False\n", + "xxxx 16 10 x a y False\n", + "xxxx 16 11 x e x False\n", + "xxxx 16 12 x a h False\n", + "seq1 16 13 x h x True\n", + "xxxx 16 14 x d x False\n", + "xxxx 16 15 x e u False\n", + "xxxx 16 16 x b d False\n", + "xxxx 16 17 x e w False\n", + "xxxx 16 18 x a e False\n", + "xxxx 16 19 x c b False\n", + "xxxx 16 20 x a w False\n", + "seq1 17 0 x ! c False\n", + "xxxx 17 1 x b x False\n", + "xxxx 17 2 x h y False\n", + "xxxx 17 3 x f d False\n", + "xxxx 17 4 x g x False\n", + "xxxx 17 5 x g a False\n", + "xxxx 17 6 x e e False\n", + "xxxx 17 7 x h a False\n", + "xxxx 17 8 x c z False\n", + "xxxx 17 9 x d y False\n", + "xxxx 17 10 x a x False\n", + "xxxx 17 11 x e h False\n", + "xxxx 17 12 x a x False\n", + "seq1 17 13 x h x True\n", + "xxxx 17 14 x d u False\n", + "xxxx 17 15 x e d False\n", + "xxxx 17 16 x b w False\n", + "xxxx 17 17 x e e False\n", + "xxxx 17 18 x a b False\n", + "xxxx 17 19 x c w False\n", + "xxxx 17 20 x a e False\n", + "seq1 18 0 u ! x False\n", + "xxxx 18 1 u b y False\n", + "xxxx 18 2 u h d False\n", + "xxxx 18 3 u f x False\n", + "xxxx 18 4 u g a False\n", + "xxxx 18 5 u g e False\n", + "xxxx 18 6 u e a False\n", + "xxxx 18 7 u h z False\n", + "xxxx 18 8 u c y False\n", + "xxxx 18 9 u d x False\n", + "xxxx 18 10 u a h False\n", + "xxxx 18 11 u e x False\n", + "xxxx 18 12 u a x False\n", + "seq1 18 13 u h u True\n", + "seq2 18 14 u d d True\n", + "xxxx 18 15 u e w False\n", + "xxxx 18 16 u b e False\n", + "xxxx 18 17 u e b False\n", + "xxxx 18 18 u a w False\n", + "xxxx 18 19 u c e False\n", + "xxxx 18 20 u a a False\n", + "seq1 19 0 w ! y False\n", + "xxxx 19 1 w b d False\n", + "xxxx 19 2 w h x False\n", + "xxxx 19 3 w f a False\n", + "xxxx 19 4 w g e False\n", + "xxxx 19 5 w g a False\n", + "xxxx 19 6 w e z False\n", + "xxxx 19 7 w h y False\n", + "xxxx 19 8 w c x False\n", + "xxxx 19 9 w d h False\n", + "xxxx 19 10 w a x False\n", + "xxxx 19 11 w e x False\n", + "xxxx 19 12 w a u False\n", + "xxxx 19 13 w h d False\n", + "seq1 19 14 w d w True\n", + "seq2 19 15 w e e True\n", + "seq2 19 16 w b b True\n", + "xxxx 19 17 w e w False\n", + "xxxx 19 18 w a e False\n", + "xxxx 19 19 w c a False\n", + "xxxx 19 20 w a c False\n", + "seq1 20 0 w ! d False\n", + "xxxx 20 1 w b x False\n", + "xxxx 20 2 w h a False\n", + "xxxx 20 3 w f e False\n", + "xxxx 20 4 w g a False\n", + "xxxx 20 5 w g z False\n", + "xxxx 20 6 w e y False\n", + "xxxx 20 7 w h x False\n", + "xxxx 20 8 w c h False\n", + "xxxx 20 9 w d x False\n", + "xxxx 20 10 w a x False\n", + "xxxx 20 11 w e u False\n", + "xxxx 20 12 w a d False\n", + "xxxx 20 13 w h w False\n", + "xxxx 20 14 w d e False\n", + "xxxx 20 15 w e b False\n", + "seq1 20 16 w b w True\n", + "seq2 20 17 w e e True\n", + "seq2 20 18 w a a True\n", + "seq2 20 19 w c c True\n", + "seq2 20 20 w a a True\n", + "T T . . . . . . . . . . . . . . . . . . .\n", + ". T . . . . . . . . . . . . . . . . . . .\n", + ". T T . . . . . . . . . . . . . . . . . .\n", + ". . T . . . . . . . . . . . . . . . . . .\n", + ". . T T T T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T T T T . . . . . . . . . . . .\n", + ". . . . . . . . T . . . . . . . . . . . .\n", + ". . . . . . . . T T . . . . . . . . . . .\n", + ". . . . . . . . . T T T T . . . . . . . .\n", + ". . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . T T . . . . . . .\n", + ". . . . . . . . . . . . . T . . . . . . .\n", + ". . . . . . . . . . . . . T . . . . . . .\n", + ". . . . . . . . . . . . . T T . . . . . .\n", + ". . . . . . . . . . . . . . T T T . . . .\n", + ". . . . . . . . . . . . . . . . T T 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": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'bXZhVWfggWZXWWehcXYdXaeaZYXhXXUdWebWeaca'" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "show_backtrace(bp)" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T T . . . . . . . . . . . . . . . . . . .\n", + ". T . . . . . . . . . . . . . . . . . . .\n", + ". T T . . . . . . . . . . . . . . . . . .\n", + ". . T . . . . . . . . . . . . . . . . . .\n", + ". . T T T T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . T T T T . . . . . . . . . . . .\n", + ". . . . . . . . T . . . . . . . . . . . .\n", + ". . . . . . . . T T . . . . . . . . . . .\n", + ". . . . . . . . . T T T T . . . . . . . .\n", + ". . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . T T . . . . . . .\n", + ". . . . . . . . . . . . . T . . . . . . .\n", + ". . . . . . . . . . . . . T . . . . . . .\n", + ". . . . . . . . . . . . . T T . . . . . .\n", + ". . . . . . . . . . . . . . T T T . . . .\n", + ". . . . . . . . . . . . . . . . T T T T T\n", + "bXZhVWfggWZXWWehcXYdXaeaZYXhXXUdWebWeaca\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 25, + "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": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('baffeeecaecbfghedbgbddbcdchbefeddgdbecbaacbdedbeca',\n", + " 'affdffbahedebhaagaaahebdeechbfhedcdgcccdcgfbdhaghe',\n", + " 'affbaffedeecfaefcbbfaghhededebbhgaagbdaaadbhebdeechbcdchfbehfedcdgecddcgcdcgdfbbdehacgbhaaecbdedbeca',\n", + " 100)" + ] + }, + "execution_count": 26, + "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": 27, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + "T T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . T . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . T . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T T T T T . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T T T T T T\n", + "AFFbaffeDeecFaeFcbBfAghHedEDEbBHgAAGbdAAAdbHEBDEECHBcdchFbeHfEDCDGeCddCgCDCGdFbBDeHAcGbHaaEcbdedbeca\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 27, + "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": 28, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1000 loops, best of 3: 1.48 ms per loop\n" + ] + } + ], + "source": [ + "%%timeit\n", + "is_interleave(s2, s1, il)" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . T . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . T T T T T T T T T T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . T . . T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T T . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . T T . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . T . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . T T T . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + "affBAFFEdEECfAEfCbBFaGhHedEDebBhGaagBDaaaDBhebdeechbCDCHfBEhFedcdgEcDDcGcdcgDfbBdEhaCgBhAAeCBDEDBECA\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 29, + "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": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "show_backtrace(bp).lower() == il" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('bgcbeceebhdgegdfehfccbfbagadhbddfbbgecdhegdaegdheh', False, False)" + ] + }, + "execution_count": 31, + "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": 32, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "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", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 32, + "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": "code", + "execution_count": 33, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def is_interleave_recursive(s1, s2, s3):\n", + " if not s1:\n", + " return s2 == s3\n", + " elif not s2:\n", + " return s1 == s3\n", + " else:\n", + " if s1[-1] == s2[-1] and s1[-1] == s3[-1]:\n", + " return is_interleave_recursive(s1[:-1], s2, s3[:-1]) or is_interleave(s1, s2[:-1], s3[:-1])\n", + " elif s1[-1] == s3[-1]:\n", + " return is_interleave_recursive(s1[:-1], s2, s3[:-1])\n", + " elif s2[-1] == s3[-1]:\n", + " return is_interleave(s1, s2[:-1], s3[:-1])\n", + " else:\n", + " return False" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "import uuid" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def is_subseq_recursive_dot(s1, s2):\n", + " node_id = uuid.uuid4().hex\n", + " node_string = 'n{} [label=\"{}\\\\n{}\"];'.format(node_id, s1, s2)\n", + "# print(s1, s2, node_string)\n", + " if not s1:\n", + " return node_id, ['n{} [label=\"-\\\\n{}\\\\nTrue\"];'.format(node_id, s2)]\n", + " elif len(s1) > len(s2):\n", + " return node_id, ['n{} [label=\"{}\\\\n{}\\\\nFalse\"];'.format(node_id, s1, s2)]\n", + " else:\n", + " if s1[-1] == s2[-1]:\n", + " node1_id, node1_graph = is_subseq_recursive_dot(s1[:-1], s2[:-1])\n", + " node2_id, node2_graph = is_subseq_recursive_dot(s1, s2[:-1])\n", + " return node_id, ([node_string, \n", + " 'n{} -> n{};'.format(node_id, node1_id), \n", + " 'n{} -> n{};'.format(node_id, node2_id)] + \n", + " node1_graph + node2_graph)\n", + " else:\n", + " node1_id, node1_graph = is_subseq_recursive_dot(s1, s2[:-1])\n", + " return node_id, ([node_string, \n", + " 'n{} -> n{};'.format(node_id, node1_id)] + \n", + " node1_graph)" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def is_interleave_recursive_dot(s1, s2, s3):\n", + " \n", + "# print(s1, s2, s3)\n", + " node_id = uuid.uuid4().hex\n", + " node_string = 'n{} [label=\"{}\\\\n{}\\\\n{}\"];'.format(node_id, s1, s2, s3)\n", + "\n", + " if not s1:\n", + " if s2 == s3:\n", + " return node_id, ['n{} [label=\"-\\\\n{}\\\\n{}\\\\nTrue\"];'.format(node_id, s2, s3)]\n", + " else:\n", + " return node_id, ['n{} [label=\"-\\\\n{}\\\\n{}\\\\nFalse\"];'.format(node_id, s2, s3)]\n", + " elif not s2:\n", + " if s1 == s3:\n", + " return node_id, ['n{} [label=\"{}\\\\n-\\\\n{}\\\\nTrue\"];'.format(node_id, s1, s3)]\n", + " else:\n", + " return node_id, ['n{} [label=\"{}\\\\n-\\\\n{}\\\\nFalse\"];'.format(node_id, s1, s3)]\n", + " else:\n", + " if s1[-1] == s2[-1] and s1[-1] == s3[-1]:\n", + " node1_id, node1_graph = is_interleave_recursive_dot(s1[:-1], s2, s3[:-1])\n", + " node2_id, node2_graph = is_interleave_recursive_dot(s1, s2[:-1], s3[:-1])\n", + " return node_id, ([node_string, \n", + " 'n{} -> n{};'.format(node_id, node1_id), \n", + " 'n{} -> n{};'.format(node_id, node2_id)] + \n", + " node1_graph + node2_graph)\n", + " elif s1[-1] == s3[-1]:\n", + " node1_id, node1_graph = is_interleave_recursive_dot(s1[:-1], s2, s3[:-1])\n", + " return node_id, ([node_string, \n", + " 'n{} -> n{};'.format(node_id, node1_id)] + \n", + " node1_graph)\n", + " elif s2[-1] == s3[-1]:\n", + " node1_id, node1_graph = is_interleave_recursive_dot(s1, s2[:-1], s3[:-1])\n", + " return node_id, ([node_string, \n", + " 'n{} -> n{};'.format(node_id, node1_id)] + \n", + " node1_graph)\n", + " else:\n", + " return node_id, ['n{} [label=\"{}\\\\n{}\\\\n{}\\\\nFalse\"];'.format(node_id, s1, s2, s3)]" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s1 = \"aabcc\"\n", + "s2 = \"dbbca\"\n", + "\n", + "s3t = \"aadbbcbcac\"\n", + "s3f = \"aadbbbaccc\"" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T . . . . .\n", + "T . . . . .\n", + "T T T T T .\n", + ". T T . T .\n", + ". . T T T T\n", + ". . . T . T\n", + "AAdbbcBCaC\n" + ] + } + ], + "source": [ + "v, bp, t = is_interleave(s1, s2, s3t, return_backpointers=True, return_table=True)\n", + "print(show_table(t))\n", + "print(show_backtrace(bp))" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def show_table_md(table, s1, s2, s3):\n", + " header = '| |' + '|'.join('{}
{}'.format('
'.join(str(s2[:i])), i) for i in range(len(s2) + 1)) + '|'\n", + " separator = '|:---:' * (len(s2) + 2) + '|'\n", + " rows = []\n", + " columns = sorted(set(k[1] for k in table))\n", + " for r in range(len(s1) + 1):\n", + " row = '|**{}
{}**|'.format(r, s1[:r])\n", + " row += '|'.join('{}
T'.format(s3[:(r+c)]) if table[r, c] else '{}
.'.format(s3[:(r+c)]) for c in columns)\n", + " row += '|'\n", + " rows += [row]\n", + " return '\\n'.join([header] + [separator] + rows)" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "| |
0|d
1|d
b
2|d
b
b
3|d
b
b
c
4|d
b
b
c
a
5|\n", + "|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n", + "|**0
**|
T|a
.|aa
.|aad
.|aadb
.|aadbb
.|\n", + "|**1
a**|a
T|aa
.|aad
.|aadb
.|aadbb
.|aadbbc
.|\n", + "|**2
aa**|aa
T|aad
T|aadb
T|aadbb
T|aadbbc
T|aadbbcb
.|\n", + "|**3
aab**|aad
.|aadb
T|aadbb
T|aadbbc
.|aadbbcb
T|aadbbcbc
.|\n", + "|**4
aabc**|aadb
.|aadbb
.|aadbbc
T|aadbbcb
T|aadbbcbc
T|aadbbcbca
T|\n", + "|**5
aabcc**|aadbb
.|aadbbc
.|aadbbcb
.|aadbbcbc
T|aadbbcbca
.|aadbbcbcac
T|\n" + ] + } + ], + "source": [ + "print(show_table_md(t, s1, s2, s3t))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "| |
0|d
1|d
b
2|d
b
b
3|d
b
b
c
4|d
b
b
c
a
5|\n", + "|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n", + "|**0
**|
T|a
.|aa
.|aad
.|aadb
.|aadbb
.|\n", + "|**1
a**|a
T|aa
.|aad
.|aadb
.|aadbb
.|aadbbc
.|\n", + "|**2
aa**|aa
T|aad
T|aadb
T|aadbb
T|aadbbc
T|aadbbcb
.|\n", + "|**3
aab**|aad
.|aadb
T|aadbb
T|aadbbc
.|aadbbcb
T|aadbbcbc
.|\n", + "|**4
aabc**|aadb
.|aadbb
.|aadbbc
T|aadbbcb
T|aadbbcbc
T|aadbbcbca
T|\n", + "|**5
aabcc**|aadbb
.|aadbbc
.|aadbbcb
.|aadbbcbc
T|aadbbcbca
.|aadbbcbcac
T|" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T T T T\n", + "T . T .\n", + ". . T T\n", + ". . . T\n", + "abACaB\n" + ] + } + ], + "source": [ + "e1 = 'acb'\n", + "e2 = 'aba'\n", + "e3 = 'abacab'\n", + "v, bp, et = is_interleave(e1, e2, e3, return_backpointers=True, return_table=True)\n", + "print(show_table(et))\n", + "print(show_backtrace(bp))" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "| |
0|a
1|a
b
2|a
b
a
3|\n", + "|:---:|:---:|:---:|:---:|:---:|\n", + "|**0
**|
T|a
T|ab
T|aba
T|\n", + "|**1
a**|a
T|ab
.|aba
T|abac
.|\n", + "|**2
ac**|ab
.|aba
.|abac
T|abaca
T|\n", + "|**3
acb**|aba
.|abac
.|abaca
.|abacab
T|\n" + ] + } + ], + "source": [ + "print(show_table_md(et, e1, e2, e3))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "| |
0|a
1|a
b
2|a
b
a
3|\n", + "|:---:|:---:|:---:|:---:|:---:|\n", + "|**0
**|
T|a
T|ab
T|aba
T|\n", + "|**1
a**|a
T|ab
.|aba
T|abac
.|\n", + "|**2
ac**|ab
.|aba
.|abac
T|abaca
T|\n", + "|**3
acb**|aba
.|abac
.|abaca
.|abacab
T|" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "n825af3fb1bf441a3b97d8fbfcdce6f3d [label=\"aabcc\\ndbbca\\naadbbcbcac\"];\n", + "n825af3fb1bf441a3b97d8fbfcdce6f3d -> n944a00ca9b134f3c98aeef34526ff17d;\n", + "n944a00ca9b134f3c98aeef34526ff17d [label=\"aabc\\ndbbca\\naadbbcbca\"];\n", + "n944a00ca9b134f3c98aeef34526ff17d -> n1586862dcfb74b1a9e9f964b7de102ef;\n", + "n1586862dcfb74b1a9e9f964b7de102ef [label=\"aabc\\ndbbc\\naadbbcbc\"];\n", + "n1586862dcfb74b1a9e9f964b7de102ef -> nf59278631d8047e7b0cca670e412297b;\n", + "n1586862dcfb74b1a9e9f964b7de102ef -> nd83e9c32d1fa43bab45dc21d46830924;\n", + "nf59278631d8047e7b0cca670e412297b [label=\"aab\\ndbbc\\naadbbcb\"];\n", + "nf59278631d8047e7b0cca670e412297b -> nb0424588e9354d2aa61b587a7edfb7f6;\n", + "nb0424588e9354d2aa61b587a7edfb7f6 [label=\"aa\\ndbbc\\naadbbc\"];\n", + "nb0424588e9354d2aa61b587a7edfb7f6 -> nb73d85cfb09e43d692de22a49de48b35;\n", + "nb73d85cfb09e43d692de22a49de48b35 [label=\"aa\\ndbb\\naadbb\"];\n", + "nb73d85cfb09e43d692de22a49de48b35 -> n9e34f866ae1746d797cebd4e1fc73af9;\n", + "n9e34f866ae1746d797cebd4e1fc73af9 [label=\"aa\\ndb\\naadb\"];\n", + "n9e34f866ae1746d797cebd4e1fc73af9 -> n5c7027bfea9f494894cea01fd5e25387;\n", + "n5c7027bfea9f494894cea01fd5e25387 [label=\"aa\\nd\\naad\"];\n", + "n5c7027bfea9f494894cea01fd5e25387 -> n650da0feb2624011a20e209bada2445c;\n", + "n650da0feb2624011a20e209bada2445c [label=\"aa\\n-\\naa\\nTrue\"];\n", + "nd83e9c32d1fa43bab45dc21d46830924 [label=\"aabc\\ndbb\\naadbbcb\"];\n", + "nd83e9c32d1fa43bab45dc21d46830924 -> n1c4772b660f24d6da9194d16be602b3a;\n", + "n1c4772b660f24d6da9194d16be602b3a [label=\"aabc\\ndb\\naadbbc\"];\n", + "n1c4772b660f24d6da9194d16be602b3a -> n0393745322e447c79515cffb4afc4d5b;\n", + "n0393745322e447c79515cffb4afc4d5b [label=\"aab\\ndb\\naadbb\"];\n", + "n0393745322e447c79515cffb4afc4d5b -> na9ae42f3b7dd415886e78bb960b94184;\n", + "n0393745322e447c79515cffb4afc4d5b -> nccaf23a4e311415cbe42bedd8a3727c2;\n", + "na9ae42f3b7dd415886e78bb960b94184 [label=\"aa\\ndb\\naadb\"];\n", + "na9ae42f3b7dd415886e78bb960b94184 -> nab2d4f76a75c4c6686166212cad4b4a3;\n", + "nab2d4f76a75c4c6686166212cad4b4a3 [label=\"aa\\nd\\naad\"];\n", + "nab2d4f76a75c4c6686166212cad4b4a3 -> nee8a56cc920943e0a2593a8ee863c53c;\n", + "nee8a56cc920943e0a2593a8ee863c53c [label=\"aa\\n-\\naa\\nTrue\"];\n", + "nccaf23a4e311415cbe42bedd8a3727c2 [label=\"aab\\nd\\naadb\"];\n", + "nccaf23a4e311415cbe42bedd8a3727c2 -> ne1d3cf2b04074c10986fdefb464e5da8;\n", + "ne1d3cf2b04074c10986fdefb464e5da8 [label=\"aa\\nd\\naad\"];\n", + "ne1d3cf2b04074c10986fdefb464e5da8 -> n9091b74bc8a64b91a9e75aef6b016a64;\n", + "n9091b74bc8a64b91a9e75aef6b016a64 [label=\"aa\\n-\\naa\\nTrue\"];\n" + ] + } + ], + "source": [ + "root, graph = is_interleave_recursive_dot(s1, s2, s3t)\n", + "print('\\n'.join(graph))" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "n894a2781e978478699af2875308ec4ad [label=\"aaa\\naaa\\naaaaaa\"];\n", + "n894a2781e978478699af2875308ec4ad -> n863e03f8030547bf9f4e7a4815c4e027;\n", + "n894a2781e978478699af2875308ec4ad -> n4c492e6eb94741d2b11567b1b4c729fa;\n", + "n863e03f8030547bf9f4e7a4815c4e027 [label=\"aa\\naaa\\naaaaa\"];\n", + "n863e03f8030547bf9f4e7a4815c4e027 -> n8f044087a7324ef69d5cf2ae120c0902;\n", + "n863e03f8030547bf9f4e7a4815c4e027 -> n5510c6a96018480ba0fc2315d34a69e6;\n", + "n8f044087a7324ef69d5cf2ae120c0902 [label=\"a\\naaa\\naaaa\"];\n", + "n8f044087a7324ef69d5cf2ae120c0902 -> n6f3153ef68384ebbbe5860a48c774d55;\n", + "n8f044087a7324ef69d5cf2ae120c0902 -> n4d068ce52cf248adb3b537805a233dda;\n", + "n6f3153ef68384ebbbe5860a48c774d55 [label=\"-\\naaa\\naaa\\nTrue\"];\n", + "n4d068ce52cf248adb3b537805a233dda [label=\"a\\naa\\naaa\"];\n", + "n4d068ce52cf248adb3b537805a233dda -> nb85aee31625f4998b596d9b6ea3b77fd;\n", + "n4d068ce52cf248adb3b537805a233dda -> nec2837ce384246ffb06e3d4090adfb37;\n", + "nb85aee31625f4998b596d9b6ea3b77fd [label=\"-\\naa\\naa\\nTrue\"];\n", + "nec2837ce384246ffb06e3d4090adfb37 [label=\"a\\na\\naa\"];\n", + "nec2837ce384246ffb06e3d4090adfb37 -> n9c395901af2d4e67a7e5a370f759bce6;\n", + "nec2837ce384246ffb06e3d4090adfb37 -> nff84b0c784744901afb3ac8a5aef3c23;\n", + "n9c395901af2d4e67a7e5a370f759bce6 [label=\"-\\na\\na\\nTrue\"];\n", + "nff84b0c784744901afb3ac8a5aef3c23 [label=\"a\\n-\\na\\nTrue\"];\n", + "n5510c6a96018480ba0fc2315d34a69e6 [label=\"aa\\naa\\naaaa\"];\n", + "n5510c6a96018480ba0fc2315d34a69e6 -> n5eaaabd1caef4c3f8f6607a8bb254906;\n", + "n5510c6a96018480ba0fc2315d34a69e6 -> n6041081af67d4f57968572aa2051d1bc;\n", + "n5eaaabd1caef4c3f8f6607a8bb254906 [label=\"a\\naa\\naaa\"];\n", + "n5eaaabd1caef4c3f8f6607a8bb254906 -> n6dd23a9ed026429fb57cbf94e6283364;\n", + "n5eaaabd1caef4c3f8f6607a8bb254906 -> n3042bda75e7c4d8f8a9ccc464f0ba724;\n", + "n6dd23a9ed026429fb57cbf94e6283364 [label=\"-\\naa\\naa\\nTrue\"];\n", + "n3042bda75e7c4d8f8a9ccc464f0ba724 [label=\"a\\na\\naa\"];\n", + "n3042bda75e7c4d8f8a9ccc464f0ba724 -> n5e702eeee87042deb3157b6663b1f07a;\n", + "n3042bda75e7c4d8f8a9ccc464f0ba724 -> n37928d6516f942008c5e89b5c37098ee;\n", + "n5e702eeee87042deb3157b6663b1f07a [label=\"-\\na\\na\\nTrue\"];\n", + "n37928d6516f942008c5e89b5c37098ee [label=\"a\\n-\\na\\nTrue\"];\n", + "n6041081af67d4f57968572aa2051d1bc [label=\"aa\\na\\naaa\"];\n", + "n6041081af67d4f57968572aa2051d1bc -> nbb96e07d3c89450cb92ad725f6fc4845;\n", + "n6041081af67d4f57968572aa2051d1bc -> n0dbe764d7e4a429298f2d3583e8c84b1;\n", + "nbb96e07d3c89450cb92ad725f6fc4845 [label=\"a\\na\\naa\"];\n", + "nbb96e07d3c89450cb92ad725f6fc4845 -> nbe5a7be2ec824370a293e7aa8f3a5467;\n", + "nbb96e07d3c89450cb92ad725f6fc4845 -> ndc15a7d84b734bb793055e4712a82d5c;\n", + "nbe5a7be2ec824370a293e7aa8f3a5467 [label=\"-\\na\\na\\nTrue\"];\n", + "ndc15a7d84b734bb793055e4712a82d5c [label=\"a\\n-\\na\\nTrue\"];\n", + "n0dbe764d7e4a429298f2d3583e8c84b1 [label=\"aa\\n-\\naa\\nTrue\"];\n", + "n4c492e6eb94741d2b11567b1b4c729fa [label=\"aaa\\naa\\naaaaa\"];\n", + "n4c492e6eb94741d2b11567b1b4c729fa -> n0e78dd2900a34a7297cc0ea2bb27e30c;\n", + "n4c492e6eb94741d2b11567b1b4c729fa -> nc18fe2c53e9e4209a9af9c0678465b1f;\n", + "n0e78dd2900a34a7297cc0ea2bb27e30c [label=\"aa\\naa\\naaaa\"];\n", + "n0e78dd2900a34a7297cc0ea2bb27e30c -> n1b98c16a65994faaa980d9c530383c77;\n", + "n0e78dd2900a34a7297cc0ea2bb27e30c -> n33dbe313802045f8895d0e904d588881;\n", + "n1b98c16a65994faaa980d9c530383c77 [label=\"a\\naa\\naaa\"];\n", + "n1b98c16a65994faaa980d9c530383c77 -> n5e7c6dff46ff49f7903eb543c02fa22b;\n", + "n1b98c16a65994faaa980d9c530383c77 -> n33391a1fab3849cf9823ccc7396aa7d4;\n", + "n5e7c6dff46ff49f7903eb543c02fa22b [label=\"-\\naa\\naa\\nTrue\"];\n", + "n33391a1fab3849cf9823ccc7396aa7d4 [label=\"a\\na\\naa\"];\n", + "n33391a1fab3849cf9823ccc7396aa7d4 -> n13b4732016804c3986853f6d2fe4a28b;\n", + "n33391a1fab3849cf9823ccc7396aa7d4 -> n767be985e5a5469da7cfeea0272705b3;\n", + "n13b4732016804c3986853f6d2fe4a28b [label=\"-\\na\\na\\nTrue\"];\n", + "n767be985e5a5469da7cfeea0272705b3 [label=\"a\\n-\\na\\nTrue\"];\n", + "n33dbe313802045f8895d0e904d588881 [label=\"aa\\na\\naaa\"];\n", + "n33dbe313802045f8895d0e904d588881 -> nf59143762fc643f0bd58507b5097b837;\n", + "n33dbe313802045f8895d0e904d588881 -> n30d968450bf147b68a8d7df49177722c;\n", + "nf59143762fc643f0bd58507b5097b837 [label=\"a\\na\\naa\"];\n", + "nf59143762fc643f0bd58507b5097b837 -> ncd2168bdc52c459d821427219fb885d1;\n", + "nf59143762fc643f0bd58507b5097b837 -> nc6011f3f746f425ab01fd89e1f17cbb4;\n", + "ncd2168bdc52c459d821427219fb885d1 [label=\"-\\na\\na\\nTrue\"];\n", + "nc6011f3f746f425ab01fd89e1f17cbb4 [label=\"a\\n-\\na\\nTrue\"];\n", + "n30d968450bf147b68a8d7df49177722c [label=\"aa\\n-\\naa\\nTrue\"];\n", + "nc18fe2c53e9e4209a9af9c0678465b1f [label=\"aaa\\na\\naaaa\"];\n", + "nc18fe2c53e9e4209a9af9c0678465b1f -> n38a7aa8aab21444d8b9d50ca71871b7e;\n", + "nc18fe2c53e9e4209a9af9c0678465b1f -> n1ec1cf69ce3c4798b305338648a6e46b;\n", + "n38a7aa8aab21444d8b9d50ca71871b7e [label=\"aa\\na\\naaa\"];\n", + "n38a7aa8aab21444d8b9d50ca71871b7e -> nad5433a86522484e85d560ac7d202b3d;\n", + "n38a7aa8aab21444d8b9d50ca71871b7e -> n6bfb83c32f9e46a19e9408fc087e74ae;\n", + "nad5433a86522484e85d560ac7d202b3d [label=\"a\\na\\naa\"];\n", + "nad5433a86522484e85d560ac7d202b3d -> n292f0206736a40ac8f6045ac0d8a0a07;\n", + "nad5433a86522484e85d560ac7d202b3d -> n07c65e03d3bd473f97579a2c63f922c7;\n", + "n292f0206736a40ac8f6045ac0d8a0a07 [label=\"-\\na\\na\\nTrue\"];\n", + "n07c65e03d3bd473f97579a2c63f922c7 [label=\"a\\n-\\na\\nTrue\"];\n", + "n6bfb83c32f9e46a19e9408fc087e74ae [label=\"aa\\n-\\naa\\nTrue\"];\n", + "n1ec1cf69ce3c4798b305338648a6e46b [label=\"aaa\\n-\\naaa\\nTrue\"];\n" + ] + } + ], + "source": [ + "root, graph = is_interleave_recursive_dot('aaa', 'aaa', 'aaaaaa')\n", + "print('\\n'.join(graph))" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "nd6df1effdb85482db276ea5fea364b79 [label=\"acb\\naba\\nabacab\"];\n", + "nd6df1effdb85482db276ea5fea364b79 -> necd79ad17e9d435c9f49c1c1ae26b524;\n", + "necd79ad17e9d435c9f49c1c1ae26b524 [label=\"ac\\naba\\nabaca\"];\n", + "necd79ad17e9d435c9f49c1c1ae26b524 -> n369b759fead243e0b35621ac1dbc09de;\n", + "n369b759fead243e0b35621ac1dbc09de [label=\"ac\\nab\\nabac\"];\n", + "n369b759fead243e0b35621ac1dbc09de -> nc4a2401f9791408ba2bb7b4052c27f11;\n", + "nc4a2401f9791408ba2bb7b4052c27f11 [label=\"a\\nab\\naba\"];\n", + "nc4a2401f9791408ba2bb7b4052c27f11 -> n71b5737da5e54fcb9dfdee6085091a01;\n", + "n71b5737da5e54fcb9dfdee6085091a01 [label=\"-\\nab\\nab\\nTrue\"];\n" + ] + } + ], + "source": [ + "root, graph = is_interleave_recursive_dot(e1, e2, e3)\n", + "print('\\n'.join(graph))" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s1 = make_string(500)\n", + "s2 = make_string(500)\n", + "s3 = make_string(500)\n", + "s12 = interleave(s1, s2)\n", + "s23 = interleave(s2, s3)" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave_recursive(s1, s2, s12)" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave_recursive(s1, s2, s23)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Example" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "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": 39, + "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": 40, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0: baddacaddb\n", + "1: bcccacbacb\n", + "2: cdcddbcccacbacbaabcc\n", + "3: cdccdbadcaacbbcccaac\n", + "4: bbacccdacdacadbdbacb\n", + "5: cbaccbbcadadaaccaddb\n", + "6: cbaccbcaac\n" + ] + }, + { + "data": { + "text/plain": [ + "['bbacccdacdacadbdbacb']" + ] + }, + "execution_count": 40, + "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", + "s4 = make_string(10, alphabet='abcd')\n", + "il = interleave(s1, s2)\n", + "bs = [s3, il, interleave(s3, s4), interleave(s2, s4), interleave(s1, s3)]\n", + "random.shuffle(bs)\n", + "bs = [s1, s2] + bs\n", + "tg = [l for l in bs if is_interleave(s1, s2, l)]\n", + "print('\\n'.join(['{}: {}'.format(i, s) for i, s in enumerate(bs)]))\n", + "tg" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* b . . . . . . . . .\n", + "b b . . . . . . . . .\n", + ". a c c c . . . . . .\n", + ". . . . d a c . . . .\n", + ". . . . . . d . . . .\n", + ". . . . . . a . . . .\n", + ". . . . . . c . . . .\n", + ". . . . . . a . . . .\n", + ". . . . . . d b . . .\n", + ". . . . . . . d . . .\n", + ". . . . . . . b a c b\n", + "bBAcccDacDACADbDBacb\n", + "bbacccdacdacadbdbacb\n", + " ** * ***** ** \n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 41, + "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": 42, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "cbaccbbcadadaaccaddb\n", + " * ** * * *****\n" + ] + }, + { + "data": { + "text/plain": [ + "5" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ind = [i for i, b in enumerate(bs) if is_interleave(s1, s3, b)][0]\n", + "v, bp = is_interleave(s1, s3, bs[ind], return_backpointers=True)\n", + "print(show_backtrace_star(bp))\n", + "ind" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* b . . . . . . . . .\n", + "b b a . . . . . . . .\n", + ". . c . . . . . . . .\n", + ". . c . . . . . . . .\n", + ". . c d . . . . . . .\n", + ". . . a . . . . . . .\n", + ". . . c d a c a d . .\n", + ". . . . . . . . b d b\n", + ". . . . . . . . . . a\n", + ". . . . . . . . . . c\n", + ". . . . . . . . . . b\n", + "bBaCCCdACdacadBdbACB\n", + "bbacccdacdacadbdbacb\n", + " * *** ** * ***\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 43, + "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": 44, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* . . . . . . . . . .\n", + "b . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + "B\n", + "b\n", + "*\n" + ] + }, + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 44, + "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": 45, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* . . . . . . . . . .\n", + "b . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + "B\n", + "b\n", + "*\n" + ] + }, + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "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" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": true + }, + "source": [ + "# Make puzzle data\n", + "\n", + "## Note to self\n", + "Include some distractors in the test set, such that:\n", + "* subsequence(my_bill, distractor) is true\n", + "* subsequence(friend_bill, distractor) is true\n", + "* interleave(my_bill, friend_bill, distractor) is false\n", + "\n", + "(i.e. characters are shared between my_bill and friend_bill)\n", + "\n", + "Students are taking a greedy approach to subsequence, and saying the interleave is true if both bills are subsequences of the distractor.\n", + "\n", + "i.e. \"aaa\" and \"aab\" are both subsequences of \"aaabbb\", but cannot be interleaved to form \"aaabbb\".\n" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "my_bill = make_string(200)\n", + "friend_bill = make_string(200)\n", + "other_bills = [make_string(200) for _ in range(98)]\n", + "\n", + "target_interleaved = interleave(my_bill, friend_bill)\n", + "mine_interleaved = [interleave(my_bill, o) for o in random.sample(other_bills, 21)]\n", + "friend_interleaved = [interleave(friend_bill, o) for o in random.sample(other_bills, 13)]\n", + "other_interleaved = []\n", + "for _ in range(103):\n", + " s1, s2 = random.sample(other_bills, 2)\n", + " other_interleaved += [interleave(s1, s2)]" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "all_targets = [target_interleaved] + mine_interleaved + friend_interleaved + other_interleaved" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "CPU times: user 2.96 s, sys: 4 ms, total: 2.97 s\n", + "Wall time: 2.97 s\n" + ] + }, + { + "data": { + "text/plain": [ + "[0]" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "%time [i for i, s12 in enumerate(all_targets) if is_interleave(my_bill, friend_bill, s12)]" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "CPU times: user 660 ms, sys: 0 ns, total: 660 ms\n", + "Wall time: 658 ms\n" + ] + }, + { + "data": { + "text/plain": [ + "[0]" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "%time [i for i, s12 in enumerate(all_targets) if is_interleave_recursive(my_bill, friend_bill, s12)]" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "bill_set = all_targets + random.sample(other_bills, 8)\n", + "random.shuffle(bill_set)\n", + "bill_set = [my_bill, friend_bill] + bill_set\n", + "\n", + "# with open('09-bills.txt', 'w') as f:\n", + "# for i, b in enumerate(bill_set):\n", + "# f.write('{}: {}\\n'.format(i, b))" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def is_subseq_greedy(s1, s2):\n", + " i = j = 0\n", + " while i < len(s1) and j < len(s2):\n", + " if s1[i] == s2[j]:\n", + " i += 1\n", + " j += 1\n", + " return i == len(s1)" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def subseq_partition(s1, s2):\n", + " i = j = 0\n", + " remainder = ''\n", + " while i < len(s1) and j < len(s2):\n", + " if s1[i] == s2[j]:\n", + " i += 1\n", + " else:\n", + " remainder += s2[j]\n", + " j += 1\n", + " return i == len(s1), remainder" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(40, 40, 20, 20)" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "common = make_string(10)\n", + "padding = make_string(10)\n", + "middle = interleave(common, padding)\n", + "\n", + "pre1 = make_string(5)\n", + "suf1 = make_string(5)\n", + "\n", + "pre2 = make_string(5)\n", + "suf2 = make_string(5)\n", + "\n", + "pre = interleave(pre1, pre2)\n", + "suf = interleave(suf1, suf2)\n", + "\n", + "distractor = pre + middle + suf\n", + "\n", + "sub1 = pre1 + common + suf1\n", + "sub2 = pre2 + common + suf2\n", + "\n", + "valid = interleave(sub1, sub2)\n", + "\n", + "len(distractor), len(valid), len(sub1), len(sub2)" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(True, True)" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_subseq_greedy(sub1, distractor), is_subseq_greedy(sub2, distractor)" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(True, True)" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_subseq_greedy(sub1, valid), is_subseq_greedy(sub2, valid)" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(False, True)" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave(sub1, sub2, distractor), is_interleave(sub1, sub2, valid)" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('echgeaeeefdcebeaahaf',\n", + " 'eeahaaeeefdcebedghbg',\n", + " 'eeecahahgeaaeeebafaadgceadabefdaghbgahaf',\n", + " 'eecheagehaaaeeeeeefdcebefadahcaebfedghbg')" + ] + }, + "execution_count": 57, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sub1, sub2, distractor, valid" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 58, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "a, b = subseq_partition(sub1, distractor)\n", + "b == sub2" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('eeahaaeeefdceb', 'eeahaaeeefdcebedghbg')" + ] + }, + "execution_count": 59, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "is_interleave('aaaa', 'bbb', 'aaababb', return_backpointers=True)" + "a, b = subseq_partition(sub1, valid)\n", + "b, sub2" ] }, { @@ -512,7 +2812,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.5.2" + "version": "3.5.2+" } }, "nbformat": 4,