X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=09-resolving-the-bill%2Finterleaving.ipynb;h=26ebb46c2253b83bbad5e3a53407f766a58f8e45;hb=130c870164e49bc33d63a887ecbaee95e4fa9997;hp=22140c9a938e2bfdc41609a07961e01a9c254c43;hpb=295420041326bd9e2d894dac370b17ef3ded5852;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..26ebb46 100644 --- a/09-resolving-the-bill/interleaving.ipynb +++ b/09-resolving-the-bill/interleaving.ipynb @@ -17,6 +17,18 @@ "When s3 = \"aadbbbaccc\", return false." ] }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "import random\n", + "import string" + ] + }, { "cell_type": "code", "execution_count": 2, @@ -34,10 +46,8 @@ }, { "cell_type": "code", - "execution_count": 8, - "metadata": { - "collapsed": false - }, + "execution_count": 3, + "metadata": {}, "outputs": [ { "data": { @@ -45,7 +55,7 @@ "[(0, ''), (1, 'a'), (2, 'aa'), (3, 'aab'), (4, 'aabc'), (5, 'aabcc')]" ] }, - "execution_count": 8, + "execution_count": 3, "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": 4, + "metadata": {}, "outputs": [ { "data": { @@ -79,7 +87,7 @@ " [False, False, False, False, False, False]]" ] }, - "execution_count": 11, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -92,9 +100,8 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 5, "metadata": { - "collapsed": false, "scrolled": true }, "outputs": [ @@ -139,7 +146,7 @@ " (5, 5): False}" ] }, - "execution_count": 24, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -153,7 +160,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 6, "metadata": { "collapsed": true }, @@ -167,21 +174,33 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 7, "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": 8, + "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" ] } ], @@ -191,10 +210,8 @@ }, { "cell_type": "code", - "execution_count": 39, - "metadata": { - "collapsed": false - }, + "execution_count": 9, + "metadata": {}, "outputs": [ { "name": "stdout", @@ -239,12 +256,12 @@ "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" ] }, { @@ -260,7 +277,7 @@ " (3, 3): (2, 3, 'b', 's1')}" ] }, - "execution_count": 39, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -313,23 +330,29 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 10, "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 +366,7 @@ " 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 +391,23 @@ " 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": 11, + "metadata": {}, "outputs": [ { "data": { @@ -389,7 +415,7 @@ "True" ] }, - "execution_count": 50, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -400,10 +426,8 @@ }, { "cell_type": "code", - "execution_count": 51, - "metadata": { - "collapsed": false - }, + "execution_count": 12, + "metadata": {}, "outputs": [ { "data": { @@ -426,7 +450,7 @@ " (5, 5): (4, 5, 'c', 'seq1')})" ] }, - "execution_count": 51, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -437,10 +461,81 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 13, "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": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave(s1, s2, s3t, return_backpointers=True, return_table=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, "outputs": [ { "data": { @@ -448,7 +543,7 @@ "False" ] }, - "execution_count": 52, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -459,11 +554,35 @@ }, { "cell_type": "code", - "execution_count": 54, - "metadata": { - "collapsed": false - }, + "execution_count": 15, + "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 +596,1304 @@ " (4, 3): (4, 2, 'b', 'seq2')})" ] }, - "execution_count": 54, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "is_interleave('aaaa', 'bbb', 'aaababb', return_backpointers=True, debug=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "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": 17, + "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": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'gbbdffedehgebaaeghbggcfeegfaccdhaaaachhdhhchfcfdfb'" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "make_string(50)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "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": 20, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0 0 0 adding u\n", + "0 1 -1 adding a\n", + "1 1 0 adding c\n", + "2 1 1 adding v\n", + "2 2 0 adding h\n", + "3 2 1 adding e\n", + "4 2 2 adding v\n", + "4 3 1 adding e\n", + "5 3 2 adding u\n", + "5 4 1 adding f\n", + "6 4 2 adding u\n", + "6 5 1 adding v\n", + "6 6 0 adding u\n", + "6 7 -1 adding x\n", + "6 8 -2 adding z\n", + "6 9 -3 adding u\n", + "6 10 -4 adding a\n", + "7 10 -3 adding e\n", + "8 10 -2 adding d\n", + "9 10 -1 adding h\n", + "10 10 0 adding v\n", + "10 11 -1 adding u\n", + "10 12 -2 adding h\n", + "11 12 -1 adding g\n", + "12 12 0 adding x\n", + "12 13 -1 adding e\n", + "13 13 0 adding f\n", + "14 13 1 adding w\n", + "14 14 0 adding y\n", + "14 15 -1 adding u\n", + "14 16 -2 adding d\n", + "15 16 -1 adding g\n", + "16 16 0 adding h\n", + "17 16 1 adding g\n", + "18 16 2 adding g\n", + "19 16 3 adding g\n", + "20 16 4 remaining s2 yyuz\n" + ] + }, + { + "data": { + "text/plain": [ + "('acheefaedhhgefdghggg',\n", + " 'uvvuuvuxzuvuxwyuyyuz',\n", + " 'uacvheveufuvuxzuaedhvuhgxefwyudghgggyyuz',\n", + " 40)" + ] + }, + "execution_count": 20, + "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": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "xxxx 0 0 ! ! ! True\n", + "seq2 0 1 ! a u False\n", + "seq2 0 2 ! c a False\n", + "seq2 0 3 ! h c False\n", + "seq2 0 4 ! e v False\n", + "seq2 0 5 ! e h False\n", + "seq2 0 6 ! f e False\n", + "seq2 0 7 ! a v False\n", + "seq2 0 8 ! e e False\n", + "seq2 0 9 ! d u False\n", + "seq2 0 10 ! h f False\n", + "seq2 0 11 ! h u False\n", + "seq2 0 12 ! g v False\n", + "seq2 0 13 ! e u False\n", + "seq2 0 14 ! f x False\n", + "seq2 0 15 ! d z False\n", + "seq2 0 16 ! g u False\n", + "seq2 0 17 ! h a False\n", + "seq2 0 18 ! g e False\n", + "seq2 0 19 ! g d False\n", + "seq2 0 20 ! g h False\n", + "seq1 1 0 u ! u True\n", + "seq2 1 1 u a a True\n", + "seq2 1 2 u c c True\n", + "xxxx 1 3 u h v False\n", + "xxxx 1 4 u e h False\n", + "xxxx 1 5 u e e False\n", + "xxxx 1 6 u f v False\n", + "xxxx 1 7 u a e False\n", + "xxxx 1 8 u e u False\n", + "xxxx 1 9 u d f False\n", + "xxxx 1 10 u h u False\n", + "xxxx 1 11 u h v False\n", + "xxxx 1 12 u g u False\n", + "xxxx 1 13 u e x False\n", + "xxxx 1 14 u f z False\n", + "xxxx 1 15 u d u False\n", + "xxxx 1 16 u g a False\n", + "xxxx 1 17 u h e False\n", + "xxxx 1 18 u g d False\n", + "xxxx 1 19 u g h False\n", + "xxxx 1 20 u g v False\n", + "seq1 2 0 v ! a False\n", + "xxxx 2 1 v a c False\n", + "seq1 2 2 v c v True\n", + "seq2 2 3 v h h True\n", + "seq2 2 4 v e e True\n", + "xxxx 2 5 v e v False\n", + "xxxx 2 6 v f e False\n", + "xxxx 2 7 v a u False\n", + "xxxx 2 8 v e f False\n", + "xxxx 2 9 v d u False\n", + "xxxx 2 10 v h v False\n", + "xxxx 2 11 v h u False\n", + "xxxx 2 12 v g x False\n", + "xxxx 2 13 v e z False\n", + "xxxx 2 14 v f u False\n", + "xxxx 2 15 v d a False\n", + "xxxx 2 16 v g e False\n", + "xxxx 2 17 v h d False\n", + "xxxx 2 18 v g h False\n", + "xxxx 2 19 v g v False\n", + "xxxx 2 20 v g u False\n", + "seq1 3 0 v ! c False\n", + "xxxx 3 1 v a v False\n", + "xxxx 3 2 v c h False\n", + "xxxx 3 3 v h e False\n", + "seq1 3 4 v e v True\n", + "seq2 3 5 v e e True\n", + "xxxx 3 6 v f u False\n", + "xxxx 3 7 v a f False\n", + "xxxx 3 8 v e u False\n", + "xxxx 3 9 v d v False\n", + "xxxx 3 10 v h u False\n", + "xxxx 3 11 v h x False\n", + "xxxx 3 12 v g z False\n", + "xxxx 3 13 v e u False\n", + "xxxx 3 14 v f a False\n", + "xxxx 3 15 v d e False\n", + "xxxx 3 16 v g d False\n", + "xxxx 3 17 v h h False\n", + "xxxx 3 18 v g v False\n", + "xxxx 3 19 v g u False\n", + "xxxx 3 20 v g h False\n", + "seq1 4 0 u ! v False\n", + "xxxx 4 1 u a h False\n", + "xxxx 4 2 u c e False\n", + "xxxx 4 3 u h v False\n", + "xxxx 4 4 u e e False\n", + "seq1 4 5 u e u True\n", + "seq2 4 6 u f f True\n", + "xxxx 4 7 u a u False\n", + "xxxx 4 8 u e v False\n", + "xxxx 4 9 u d u False\n", + "xxxx 4 10 u h x False\n", + "xxxx 4 11 u h z False\n", + "xxxx 4 12 u g u False\n", + "xxxx 4 13 u e a False\n", + "xxxx 4 14 u f e False\n", + "xxxx 4 15 u d d False\n", + "xxxx 4 16 u g h False\n", + "xxxx 4 17 u h v False\n", + "xxxx 4 18 u g u False\n", + "xxxx 4 19 u g h False\n", + "xxxx 4 20 u g g False\n", + "seq1 5 0 u ! h False\n", + "xxxx 5 1 u a e False\n", + "xxxx 5 2 u c v False\n", + "xxxx 5 3 u h e False\n", + "xxxx 5 4 u e u False\n", + "xxxx 5 5 u e f False\n", + "seq1 5 6 u f u True\n", + "xxxx 5 7 u a v False\n", + "xxxx 5 8 u e u False\n", + "xxxx 5 9 u d x False\n", + "xxxx 5 10 u h z False\n", + "xxxx 5 11 u h u False\n", + "xxxx 5 12 u g a False\n", + "xxxx 5 13 u e e False\n", + "xxxx 5 14 u f d False\n", + "xxxx 5 15 u d h False\n", + "xxxx 5 16 u g v False\n", + "xxxx 5 17 u h u False\n", + "xxxx 5 18 u g h False\n", + "xxxx 5 19 u g g False\n", + "xxxx 5 20 u g x False\n", + "seq1 6 0 v ! e False\n", + "xxxx 6 1 v a v False\n", + "xxxx 6 2 v c e False\n", + "xxxx 6 3 v h u False\n", + "xxxx 6 4 v e f False\n", + "xxxx 6 5 v e u False\n", + "seq1 6 6 v f v True\n", + "xxxx 6 7 v a u False\n", + "xxxx 6 8 v e x False\n", + "xxxx 6 9 v d z False\n", + "xxxx 6 10 v h u False\n", + "xxxx 6 11 v h a False\n", + "xxxx 6 12 v g e False\n", + "xxxx 6 13 v e d False\n", + "xxxx 6 14 v f h False\n", + "xxxx 6 15 v d v False\n", + "xxxx 6 16 v g u False\n", + "xxxx 6 17 v h h False\n", + "xxxx 6 18 v g g False\n", + "xxxx 6 19 v g x False\n", + "xxxx 6 20 v g e False\n", + "seq1 7 0 u ! v False\n", + "xxxx 7 1 u a e False\n", + "xxxx 7 2 u c u False\n", + "xxxx 7 3 u h f False\n", + "xxxx 7 4 u e u False\n", + "xxxx 7 5 u e v False\n", + "seq1 7 6 u f u True\n", + "xxxx 7 7 u a x False\n", + "xxxx 7 8 u e z False\n", + "xxxx 7 9 u d u False\n", + "xxxx 7 10 u h a False\n", + "xxxx 7 11 u h e False\n", + "xxxx 7 12 u g d False\n", + "xxxx 7 13 u e h False\n", + "xxxx 7 14 u f v False\n", + "xxxx 7 15 u d u False\n", + "xxxx 7 16 u g h False\n", + "xxxx 7 17 u h g False\n", + "xxxx 7 18 u g x False\n", + "xxxx 7 19 u g e False\n", + "xxxx 7 20 u g f False\n", + "seq1 8 0 x ! e False\n", + "xxxx 8 1 x a u False\n", + "xxxx 8 2 x c f False\n", + "xxxx 8 3 x h u False\n", + "xxxx 8 4 x e v False\n", + "xxxx 8 5 x e u False\n", + "seq1 8 6 x f x True\n", + "xxxx 8 7 x a z False\n", + "xxxx 8 8 x e u False\n", + "xxxx 8 9 x d a False\n", + "xxxx 8 10 x h e False\n", + "xxxx 8 11 x h d False\n", + "xxxx 8 12 x g h False\n", + "xxxx 8 13 x e v False\n", + "xxxx 8 14 x f u False\n", + "xxxx 8 15 x d h False\n", + "xxxx 8 16 x g g False\n", + "xxxx 8 17 x h x False\n", + "xxxx 8 18 x g e False\n", + "xxxx 8 19 x g f False\n", + "xxxx 8 20 x g w False\n", + "seq1 9 0 z ! u False\n", + "xxxx 9 1 z a f False\n", + "xxxx 9 2 z c u False\n", + "xxxx 9 3 z h v False\n", + "xxxx 9 4 z e u False\n", + "xxxx 9 5 z e x False\n", + "seq1 9 6 z f z True\n", + "xxxx 9 7 z a u False\n", + "xxxx 9 8 z e a False\n", + "xxxx 9 9 z d e False\n", + "xxxx 9 10 z h d False\n", + "xxxx 9 11 z h h False\n", + "xxxx 9 12 z g v False\n", + "xxxx 9 13 z e u False\n", + "xxxx 9 14 z f h False\n", + "xxxx 9 15 z d g False\n", + "xxxx 9 16 z g x False\n", + "xxxx 9 17 z h e False\n", + "xxxx 9 18 z g f False\n", + "xxxx 9 19 z g w False\n", + "xxxx 9 20 z g y False\n", + "seq1 10 0 u ! f False\n", + "xxxx 10 1 u a u False\n", + "xxxx 10 2 u c v False\n", + "xxxx 10 3 u h u False\n", + "xxxx 10 4 u e x False\n", + "xxxx 10 5 u e z False\n", + "seq1 10 6 u f u True\n", + "seq2 10 7 u a a True\n", + "seq2 10 8 u e e True\n", + "seq2 10 9 u d d True\n", + "seq2 10 10 u h h True\n", + "xxxx 10 11 u h v False\n", + "xxxx 10 12 u g u False\n", + "xxxx 10 13 u e h False\n", + "xxxx 10 14 u f g False\n", + "xxxx 10 15 u d x False\n", + "xxxx 10 16 u g e False\n", + "xxxx 10 17 u h f False\n", + "xxxx 10 18 u g w False\n", + "xxxx 10 19 u g y False\n", + "xxxx 10 20 u g u False\n", + "seq1 11 0 v ! u False\n", + "xxxx 11 1 v a v False\n", + "xxxx 11 2 v c u False\n", + "xxxx 11 3 v h x False\n", + "xxxx 11 4 v e z False\n", + "xxxx 11 5 v e u False\n", + "xxxx 11 6 v f a False\n", + "xxxx 11 7 v a e False\n", + "xxxx 11 8 v e d False\n", + "xxxx 11 9 v d h False\n", + "seq1 11 10 v h v True\n", + "xxxx 11 11 v h u False\n", + "xxxx 11 12 v g h False\n", + "xxxx 11 13 v e g False\n", + "xxxx 11 14 v f x False\n", + "xxxx 11 15 v d e False\n", + "xxxx 11 16 v g f False\n", + "xxxx 11 17 v h w False\n", + "xxxx 11 18 v g y False\n", + "xxxx 11 19 v g u False\n", + "xxxx 11 20 v g d False\n", + "seq1 12 0 u ! v False\n", + "xxxx 12 1 u a u False\n", + "xxxx 12 2 u c x False\n", + "xxxx 12 3 u h z False\n", + "xxxx 12 4 u e u False\n", + "xxxx 12 5 u e a False\n", + "xxxx 12 6 u f e False\n", + "xxxx 12 7 u a d False\n", + "xxxx 12 8 u e h False\n", + "xxxx 12 9 u d v False\n", + "seq1 12 10 u h u True\n", + "seq2 12 11 u h h True\n", + "seq2 12 12 u g g True\n", + "xxxx 12 13 u e x False\n", + "xxxx 12 14 u f e False\n", + "xxxx 12 15 u d f False\n", + "xxxx 12 16 u g w False\n", + "xxxx 12 17 u h y False\n", + "xxxx 12 18 u g u False\n", + "xxxx 12 19 u g d False\n", + "xxxx 12 20 u g g False\n", + "seq1 13 0 x ! u False\n", + "xxxx 13 1 x a x False\n", + "xxxx 13 2 x c z False\n", + "xxxx 13 3 x h u False\n", + "xxxx 13 4 x e a False\n", + "xxxx 13 5 x e e False\n", + "xxxx 13 6 x f d False\n", + "xxxx 13 7 x a h False\n", + "xxxx 13 8 x e v False\n", + "xxxx 13 9 x d u False\n", + "xxxx 13 10 x h h False\n", + "xxxx 13 11 x h g False\n", + "seq1 13 12 x g x True\n", + "seq2 13 13 x e e True\n", + "seq2 13 14 x f f True\n", + "xxxx 13 15 x d w False\n", + "xxxx 13 16 x g y False\n", + "xxxx 13 17 x h u False\n", + "xxxx 13 18 x g d False\n", + "xxxx 13 19 x g g False\n", + "xxxx 13 20 x g h False\n", + "seq1 14 0 w ! x False\n", + "xxxx 14 1 w a z False\n", + "xxxx 14 2 w c u False\n", + "xxxx 14 3 w h a False\n", + "xxxx 14 4 w e e False\n", + "xxxx 14 5 w e d False\n", + "xxxx 14 6 w f h False\n", + "xxxx 14 7 w a v False\n", + "xxxx 14 8 w e u False\n", + "xxxx 14 9 w d h False\n", + "xxxx 14 10 w h g False\n", + "xxxx 14 11 w h x False\n", + "xxxx 14 12 w g e False\n", + "xxxx 14 13 w e f False\n", + "seq1 14 14 w f w True\n", + "xxxx 14 15 w d y False\n", + "xxxx 14 16 w g u False\n", + "xxxx 14 17 w h d False\n", + "xxxx 14 18 w g g False\n", + "xxxx 14 19 w g h False\n", + "xxxx 14 20 w g g False\n", + "seq1 15 0 y ! z False\n", + "xxxx 15 1 y a u False\n", + "xxxx 15 2 y c a False\n", + "xxxx 15 3 y h e False\n", + "xxxx 15 4 y e d False\n", + "xxxx 15 5 y e h False\n", + "xxxx 15 6 y f v False\n", + "xxxx 15 7 y a u False\n", + "xxxx 15 8 y e h False\n", + "xxxx 15 9 y d g False\n", + "xxxx 15 10 y h x False\n", + "xxxx 15 11 y h e False\n", + "xxxx 15 12 y g f False\n", + "xxxx 15 13 y e w False\n", + "seq1 15 14 y f y True\n", + "xxxx 15 15 y d u False\n", + "xxxx 15 16 y g d False\n", + "xxxx 15 17 y h g False\n", + "xxxx 15 18 y g h False\n", + "xxxx 15 19 y g g False\n", + "xxxx 15 20 y g g False\n", + "seq1 16 0 u ! u False\n", + "xxxx 16 1 u a a False\n", + "xxxx 16 2 u c e False\n", + "xxxx 16 3 u h d False\n", + "xxxx 16 4 u e h False\n", + "xxxx 16 5 u e v False\n", + "xxxx 16 6 u f u False\n", + "xxxx 16 7 u a h False\n", + "xxxx 16 8 u e g False\n", + "xxxx 16 9 u d x False\n", + "xxxx 16 10 u h e False\n", + "xxxx 16 11 u h f False\n", + "xxxx 16 12 u g w False\n", + "xxxx 16 13 u e y False\n", + "seq1 16 14 u f u True\n", + "seq2 16 15 u d d True\n", + "seq2 16 16 u g g True\n", + "seq2 16 17 u h h True\n", + "seq2 16 18 u g g True\n", + "seq2 16 19 u g g True\n", + "seq2 16 20 u g g True\n", + "seq1 17 0 y ! a False\n", + "xxxx 17 1 y a e False\n", + "xxxx 17 2 y c d False\n", + "xxxx 17 3 y h h False\n", + "xxxx 17 4 y e v False\n", + "xxxx 17 5 y e u False\n", + "xxxx 17 6 y f h False\n", + "xxxx 17 7 y a g False\n", + "xxxx 17 8 y e x False\n", + "xxxx 17 9 y d e False\n", + "xxxx 17 10 y h f False\n", + "xxxx 17 11 y h w False\n", + "xxxx 17 12 y g y False\n", + "xxxx 17 13 y e u False\n", + "xxxx 17 14 y f d False\n", + "xxxx 17 15 y d g False\n", + "xxxx 17 16 y g h False\n", + "xxxx 17 17 y h g False\n", + "xxxx 17 18 y g g False\n", + "xxxx 17 19 y g g False\n", + "seq1 17 20 y g y True\n", + "seq1 18 0 y ! e False\n", + "xxxx 18 1 y a d False\n", + "xxxx 18 2 y c h False\n", + "xxxx 18 3 y h v False\n", + "xxxx 18 4 y e u False\n", + "xxxx 18 5 y e h False\n", + "xxxx 18 6 y f g False\n", + "xxxx 18 7 y a x False\n", + "xxxx 18 8 y e e False\n", + "xxxx 18 9 y d f False\n", + "xxxx 18 10 y h w False\n", + "xxxx 18 11 y h y False\n", + "xxxx 18 12 y g u False\n", + "xxxx 18 13 y e d False\n", + "xxxx 18 14 y f g False\n", + "xxxx 18 15 y d h False\n", + "xxxx 18 16 y g g False\n", + "xxxx 18 17 y h g False\n", + "xxxx 18 18 y g g False\n", + "xxxx 18 19 y g y False\n", + "seq1 18 20 y g y True\n", + "seq1 19 0 u ! d False\n", + "xxxx 19 1 u a h False\n", + "xxxx 19 2 u c v False\n", + "xxxx 19 3 u h u False\n", + "xxxx 19 4 u e h False\n", + "xxxx 19 5 u e g False\n", + "xxxx 19 6 u f x False\n", + "xxxx 19 7 u a e False\n", + "xxxx 19 8 u e f False\n", + "xxxx 19 9 u d w False\n", + "xxxx 19 10 u h y False\n", + "xxxx 19 11 u h u False\n", + "xxxx 19 12 u g d False\n", + "xxxx 19 13 u e g False\n", + "xxxx 19 14 u f h False\n", + "xxxx 19 15 u d g False\n", + "xxxx 19 16 u g g False\n", + "xxxx 19 17 u h g False\n", + "xxxx 19 18 u g y False\n", + "xxxx 19 19 u g y False\n", + "seq1 19 20 u g u True\n", + "seq1 20 0 z ! h False\n", + "xxxx 20 1 z a v False\n", + "xxxx 20 2 z c u False\n", + "xxxx 20 3 z h h False\n", + "xxxx 20 4 z e g False\n", + "xxxx 20 5 z e x False\n", + "xxxx 20 6 z f e False\n", + "xxxx 20 7 z a f False\n", + "xxxx 20 8 z e w False\n", + "xxxx 20 9 z d y False\n", + "xxxx 20 10 z h u False\n", + "xxxx 20 11 z h d False\n", + "xxxx 20 12 z g g False\n", + "xxxx 20 13 z e h False\n", + "xxxx 20 14 z f g False\n", + "xxxx 20 15 z d g False\n", + "xxxx 20 16 z g g False\n", + "xxxx 20 17 z h y False\n", + "xxxx 20 18 z g y False\n", + "xxxx 20 19 z g u False\n", + "seq1 20 20 z g z True\n", + "T . . . . . . . . . . . . . . . . . . . .\n", + "T T T . . . . . . . . . . . . . . . . . .\n", + ". . T T T . . . . . . . . . . . . . . . .\n", + ". . . . T T . . . . . . . . . . . . . . .\n", + ". . . . . T T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T T T T T . . . . . . . . . .\n", + ". . . . . . . . . . T . . . . . . . . . .\n", + ". . . . . . . . . . T T T . . . . . . . .\n", + ". . . . . . . . . . . . T T T . . . . . .\n", + ". . . . . . . . . . . . . . T . . . . . .\n", + ". . . . . . . . . . . . . . T . . . . . .\n", + ". . . . . . . . . . . . . . T T T T T T T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . 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": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'UacVheVeUfUVUXZUaedhVUhgXefWYUdghgggYYUZ'" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "show_backtrace(bp)" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T . . . . . . . . . . . . . . . . . . . .\n", + "T T T . . . . . . . . . . . . . . . . . .\n", + ". . T T T . . . . . . . . . . . . . . . .\n", + ". . . . T T . . . . . . . . . . . . . . .\n", + ". . . . . T T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T . . . . . . . . . . . . . .\n", + ". . . . . . T T T T T . . . . . . . . . .\n", + ". . . . . . . . . . T . . . . . . . . . .\n", + ". . . . . . . . . . T T T . . . . . . . .\n", + ". . . . . . . . . . . . T T T . . . . . .\n", + ". . . . . . . . . . . . . . T . . . . . .\n", + ". . . . . . . . . . . . . . T . . . . . .\n", + ". . . . . . . . . . . . . . T T T T T T T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . T\n", + "UacVheVeUfUVUXZUaedhVUhgXefWYUdghgggYYUZ\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 23, + "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": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('gfccbgegegaccfcgeehbgcafchgbfdfbggbcachfdfaccfbffb',\n", + " 'accfcfbdaabcabbbegdfffhcgcefbddegghgfdgcgdcffcfdcd',\n", + " 'acgcfcffbdcacbabcagbbbegegegadcfcffcgfeehbgchacfchggcbefbfddfbdggbegcgachhfgfdfdgcgdacccfbffcffbfdcd',\n", + " 100)" + ] + }, + "execution_count": 24, + "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": 25, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + "T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + "T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". T . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T T 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 T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . T . . T T T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . T . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T T T T T . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . T T T T . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T T T .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . T T . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T\n", + "ACgCFCfFBDcAcbABCAgBBBegegEGaDcFcfFcgFeehbgcHaCfchgGCbEFBfdDfbDggbEGcGachHfGFdfDGCGDaccCfbFFCffbFDCD\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": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1000 loops, best of 3: 1.25 ms per loop\n" + ] + } + ], + "source": [ + "%%timeit\n", + "is_interleave(s2, s1, il)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T . T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . T T . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . T T T T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . T . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . T . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . T . T T T . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T T . . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . . . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T . T T . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T . . T . . . .\n", + ". . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T T T T T\n", + "acGcfcfFbdCaCBabcaGbbbegEGEGAdCfCfFCGfEEHBGChAcFCHgGcBefbFdDFBdGGBegCgAChHFgfDFdgcgdAcCCFBffcFFBfdcd\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 27, + "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": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "show_backtrace(bp).lower() == il" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('adadhfgacgbahfchffghdfffcfcdccchedahggdffhgbacghbe', False, False)" + ] + }, + "execution_count": 29, + "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": 30, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T 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", + "a\n" + ] + }, + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 30, + "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": 31, + "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": 32, + "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": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('badbbdcadc', 'bdaadcadab', 'bdabaadbdcbadcaddacb', 20)" + ] + }, + "execution_count": 33, + "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": 34, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* b d a . . . . . . .\n", + "b . . b a . . . . . .\n", + ". . . a a d . . . . .\n", + ". . . . d . . . . . .\n", + ". . . . b d c . . . .\n", + ". . . . . . b a d . .\n", + ". . . . . . . d . . .\n", + ". . . . . . . c . . .\n", + ". . . . . . . a d . .\n", + ". . . . . . . d d a .\n", + ". . . . . . . . . c b\n", + "bdaBaADBdcBaDCAdDaCb\n", + "bdabaadbdcbadcaddacb\n", + " * *** * *** * * \n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 34, + "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": 35, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* b . . . . . . . . .\n", + "b . . . . . . . . . .\n", + "d . . . . . . . . . .\n", + "a b a . . . . . . . .\n", + ". a a d b . . . . . .\n", + ". . d . d . . . . . .\n", + ". . . . c b . . . . .\n", + ". . . . . a d c a d .\n", + ". . . . . d . . d d .\n", + ". . . . . . . . . a c\n", + ". . . . . . . . . . b\n", + "BDAbaAdbDCbAdcadDAcB\n", + "bdabaadbdcbadcaddacb\n", + "*** * ** * ** *\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 35, + "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": 36, + "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": 36, + "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": 37, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* . . . . . . . . . .\n", + "b . . . . . . . . . .\n", + "d a . . . . . . . . .\n", + "a . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + ". . . . . . . . . . .\n", + "\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 37, "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" ] }, { @@ -512,7 +1922,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.5.2" + "version": "3.5.2+" } }, "nbformat": 4,