gistfile1.txt

{
 "metadata": {
  "name": "hw3-solutions-3"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "from cStringIO import StringIO\n\n# load sequences in from a file handle, 'fp' -- the result of an 'open'.\ndef load_sequences(fp):\n    sequences = {}\n\n    name = None\n    seq = \"\"\n\n    for line in fp:\n        # new record?                                                               \n        if line.startswith('>'):            # new sequence records start with >\n            sequences[name] = seq           # save current record                   \n\n            name = line                     # the new record name is this line!     \n            name = name[1:]                 # strip off the '>'                     \n            name = name.strip()             # remove leading & trailing whitespace  \n            seq = \"\"                        # start 'seq' over again.\n        else:\n            line = line.strip()             # NOT a new record; remove whitespace.  \n            if line:                        # if any sequence at all...             \n                seq += line                 # add to my current sequence.           \n\n    return sequences",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\">a\nACTG\n>b\nAGCT\n>c\nTGCA\n>d\nTTTT\n>e\nGGGG\n>f\nCCCC\n\n\"\"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = load_sequences(data_fp)\nprint results\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\nassert results['a'] == 'ACTG'\nassert results['c'] == 'TGCA'\nassert results['e'] == 'GGGG'\n\nprint 'my spot checks tell me that everything is working! good luck!'",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{'a': 'ACTG', None: '', 'c': 'TGCA', 'b': 'AGCT', 'e': 'GGGG', 'd': 'TTTT'}\nmy spot checks tell me that everything is working! good luck!\n"
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "## Test cell 1 -- test multiline sequences"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\">a\nACTG\n>b\nAGCT\nAGCT\n>c\nTGCA\n\n\n\"\"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = load_sequences(data_fp)\nprint results\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\nassert results['b'] == 'AGCTAGCT'\n\nprint 'my spot checks tell me that everything is working! good luck!'",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{'a': 'ACTG', None: '', 'b': 'AGCTAGCT'}\nmy spot checks tell me that everything is working! good luck!\n"
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "## Test cell 2 -- test blank lines after sequences"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\">a\nACTG\n\n\n>b\nAGCT\n>c\nTGCA\n>d\nTTTT\n>e\nGGGG\n>f\nCCCC\n\n\"\"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = load_sequences(data_fp)\nprint results\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\nassert results['a'] == 'ACTG'\n\nprint 'my spot checks tell me that everything is working! good luck!'",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{'a': 'ACTG', None: '', 'c': 'TGCA', 'b': 'AGCT', 'e': 'GGGG', 'd': 'TTTT'}\nmy spot checks tell me that everything is working! good luck!\n"
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "## Test cell 3 -- "
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = load_sequences(data_fp)\nassert results == {}\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\n\n\nprint 'my spot checks tell me that everything is working! good luck!'",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "my spot checks tell me that everything is working! good luck!\n"
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "## Bug #1 -- empty sequence always created if there are any sequences"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\">a\nACTG\n>b\nAGCT\n>c\nTGCA\n>d\nTTTT\n>e\nGGGG\n>f\nCCCC\n\n\"\"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = load_sequences(data_fp)\nprint results\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\nassert None not in results\n\n",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "ename": "AssertionError",
       "evalue": "",
       "output_type": "pyerr",
       "traceback": [
        "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
        "\u001b[1;32m<ipython-input-13-96e0c0482260>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m     20\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m \u001b[1;31m# check a few things; here is where you want to edit/change the assert statements to check for new things\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 22\u001b[1;33m \u001b[1;32massert\u001b[0m \u001b[0mNone\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mresults\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     23\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
        "\u001b[1;31mAssertionError\u001b[0m: "
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{'a': 'ACTG', None: '', 'c': 'TGCA', 'b': 'AGCT', 'e': 'GGGG', 'd': 'TTTT'}\n"
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "## Bug #2 -- last sequence is always omitted"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\">a\nACTG\n>b\nAGCT\n>c\nTGCA\n>d\nTTTT\n>e\nGGGG\n>f\nCCCC\n\n\"\"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = load_sequences(data_fp)\nprint results\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\nassert results['f'] == 'CCCC'\n",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "ename": "KeyError",
       "evalue": "'f'",
       "output_type": "pyerr",
       "traceback": [
        "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
        "\u001b[1;32m<ipython-input-15-c56d38a83f5c>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m     20\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m \u001b[1;31m# check a few things; here is where you want to edit/change the assert statements to check for new things\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 22\u001b[1;33m \u001b[1;32massert\u001b[0m \u001b[0mresults\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'f'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m'CCCC'\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
        "\u001b[1;31mKeyError\u001b[0m: 'f'"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{'a': 'ACTG', None: '', 'c': 'TGCA', 'b': 'AGCT', 'e': 'GGGG', 'd': 'TTTT'}\n"
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "from cStringIO import StringIO\n\n# load sequences in from a file handle, 'fp' -- the result of an 'open'.\ndef FIXED_load_sequences(fp):\n    sequences = {}\n\n    name = None\n    seq = \"\"\n\n    for line in fp:\n        # new record?                                                               \n        if line.startswith('>'):            # new sequence records start with >\n            if name is not None:\n                sequences[name] = seq       ### save current record **if it's not the first time through the code **                  \n    \n            name = line                     # the new record name is this line!     \n            name = name[1:]                 # strip off the '>'                     \n            name = name.strip()             # remove leading & trailing whitespace  \n            seq = \"\"                        # start 'seq' over again.\n        else:\n            line = line.strip()             # NOT a new record; remove whitespace.  \n            if line:                        # if any sequence at all...             \n                seq += line                 # add to my current sequence.\n    \n    if name is not None:                    ### **add final sequence to the dict**\n        sequences[name] = seq\n\n    return sequences",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# a first, simple test example; this is the data you will want to change.\ndata = \"\"\">a\nACTG\n>b\nAGCT\n>c\nTGCA\n>d\nTTTT\n>e\nGGGG\n>f\nCCCC\n\n\"\"\"\ndata_fp = StringIO(data) # make the data _look_ like it's coming from a file, even though it's really an in-memory string.\n\nresults = FIXED_load_sequences(data_fp)\nprint results\n\n# check a few things; here is where you want to edit/change the assert statements to check for new things\nassert None not in results\nassert results['f'] == 'CCCC'\n",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{'a': 'ACTG', 'c': 'TGCA', 'b': 'AGCT', 'e': 'GGGG', 'd': 'TTTT', 'f': 'CCCC'}\n"
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}