From 2075d6334449b880b442d2286b57bfb093a7a7ea Mon Sep 17 00:00:00 2001
From: Michiel van Galen <m.van_galen@lumc.nl>
Date: Mon, 14 Jul 2014 16:17:23 +0200
Subject: [PATCH] Examples more goodness prepared in a notebook.
---
solutions/More_goodness_progression.ipynb | 430 ++++++++++++++++++++++
1 file changed, 430 insertions(+)
create mode 100644 solutions/More_goodness_progression.ipynb
diff --git a/solutions/More_goodness_progression.ipynb b/solutions/More_goodness_progression.ipynb
new file mode 100644
index 0000000..4119b84
--- /dev/null
+++ b/solutions/More_goodness_progression.ipynb
@@ -0,0 +1,430 @@
+{
+ "metadata": {
+ "name": "",
+ "signature": "sha256:8a9edae870851327562c4e01d6fc9a2c2a00319e9c6353ac21dada578d06d83f"
+ },
+ "nbformat": 3,
+ "nbformat_minor": 0,
+ "worksheets": [
+ {
+ "cells": [
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "GC percentage"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "def calc_gc_percent(seq):\n",
+ " at_count, gc_count = 0, 0\n",
+ " for char in seq:\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ " \n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "print \"The sequence 'CAGG' has a %GC of {:.2f}\".format(\n",
+ " calc_gc_percent(\"CAGG\"))"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "output_type": "stream",
+ "stream": "stdout",
+ "text": [
+ "The sequence 'CAGG' has a %GC of 75.00\n"
+ ]
+ }
+ ],
+ "prompt_number": 47
+ },
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "Adding user input"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "user_input = 'CACG'"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [],
+ "prompt_number": 48
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "#!/usr/bin/env python\n",
+ "import sys\n",
+ "\n",
+ "def calc_gc_percent(seq):\n",
+ " at_count, gc_count = 0, 0\n",
+ " for char in seq:\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "input_seq = user_input\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ZeroDivisionError",
+ "evalue": "float division by zero",
+ "output_type": "pyerr",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mZeroDivisionError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m<ipython-input-51-0c3101a450ef>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[0minput_seq\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0muser_input\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 15\u001b[0m print \"The sequence '{}' has a %GC of {:.2f}\".format(\n\u001b[1;32m---> 16\u001b[1;33m input_seq, calc_gc_percent(input_seq))\n\u001b[0m",
+ "\u001b[1;32m<ipython-input-51-0c3101a450ef>\u001b[0m in \u001b[0;36mcalc_gc_percent\u001b[1;34m(seq)\u001b[0m\n\u001b[0;32m 10\u001b[0m \u001b[0mgc_count\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 11\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 12\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mgc_count\u001b[0m \u001b[1;33m*\u001b[0m \u001b[1;36m100.0\u001b[0m \u001b[1;33m/\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mgc_count\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mat_count\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 13\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[0minput_seq\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0muser_input\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mZeroDivisionError\u001b[0m: float division by zero"
+ ]
+ }
+ ],
+ "prompt_number": 51
+ },
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "Adding .upper() for convenience:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "user_input = 'cacg'"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [],
+ "prompt_number": 42
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "def calc_gc_percent(seq):\n",
+ " at_count, gc_count = 0, 0\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "input_seq = user_input\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "output_type": "stream",
+ "stream": "stdout",
+ "text": [
+ "The sequence 'cacg' has a %GC of 75.00\n"
+ ]
+ }
+ ],
+ "prompt_number": 43
+ },
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "Adding a sensible docstring"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "#!/usr/bin/env python\n",
+ "import sys\n",
+ "\n",
+ "def calc_gc_percent(seq):\n",
+ " \"\"\"\n",
+ " Calculates the GC percentage of the given sequence.\n",
+ "\n",
+ " Arguments:\n",
+ " - seq - the input sequence (string).\n",
+ "\n",
+ " Returns:\n",
+ " - GC percentage (float).\n",
+ "\n",
+ " The returned value is always <= 100.0\n",
+ " \"\"\"\n",
+ " at_count, gc_count = 0, 0\n",
+ " # Change input to all caps to allow for non-capital\n",
+ " # input sequence.\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "input_seq = sys.argv[1]\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ZeroDivisionError",
+ "evalue": "float division by zero",
+ "output_type": "pyerr",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mZeroDivisionError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m<ipython-input-44-42591751c28f>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 27\u001b[0m \u001b[0minput_seq\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margv\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 28\u001b[0m print \"The sequence '{}' has a %GC of {:.2f}\".format(\n\u001b[1;32m---> 29\u001b[1;33m input_seq, calc_gc_percent(input_seq))\n\u001b[0m",
+ "\u001b[1;32m<ipython-input-44-42591751c28f>\u001b[0m in \u001b[0;36mcalc_gc_percent\u001b[1;34m(seq)\u001b[0m\n\u001b[0;32m 23\u001b[0m \u001b[0mgc_count\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 24\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 25\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mgc_count\u001b[0m \u001b[1;33m*\u001b[0m \u001b[1;36m100.0\u001b[0m \u001b[1;33m/\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mgc_count\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mat_count\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 26\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 27\u001b[0m \u001b[0minput_seq\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margv\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mZeroDivisionError\u001b[0m: float division by zero"
+ ]
+ }
+ ],
+ "prompt_number": 44
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "help(calc_gc_percent)"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": []
+ },
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "Trying unexpected input"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "user_input = 'ACTG123'"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "def calc_gc_percent(seq):\n",
+ " at_count, gc_count = 0, 0\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "input_seq = user_input\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": []
+ },
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "Adding input checks"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "user_input = 'ACTG123'"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [],
+ "prompt_number": 52
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "user_input = ''"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [],
+ "prompt_number": 54
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "def calc_gc_percent(seq):\n",
+ " \"\"\"\n",
+ " Calculates the GC percentage of the given sequence.\n",
+ "\n",
+ " Arguments:\n",
+ " - seq - the input sequence (string).\n",
+ "\n",
+ " Returns:\n",
+ " - GC percentage (float).\n",
+ "\n",
+ " The returned value is always <= 100.0\n",
+ " \"\"\"\n",
+ " at_count, gc_count = 0, 0\n",
+ " # Change input to all caps to allow for non-capital\n",
+ " # input sequence.\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ " else:\n",
+ " raise ValueError(\n",
+ " \"Unexpeced character found: {}. Only \"\n",
+ " \"ACTGs are allowed.\".format(char))\n",
+ " \n",
+ " return gc_count * 100.0 / (gc_count + at_count)\n",
+ "\n",
+ "input_seq = user_input\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))\n"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ZeroDivisionError",
+ "evalue": "float division by zero",
+ "output_type": "pyerr",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mZeroDivisionError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m<ipython-input-55-3d66cef1b29a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 28\u001b[0m \u001b[0minput_seq\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0muser_input\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 29\u001b[0m print \"The sequence '{}' has a %GC of {:.2f}\".format(\n\u001b[1;32m---> 30\u001b[1;33m input_seq, calc_gc_percent(input_seq))\n\u001b[0m",
+ "\u001b[1;32m<ipython-input-55-3d66cef1b29a>\u001b[0m in \u001b[0;36mcalc_gc_percent\u001b[1;34m(seq)\u001b[0m\n\u001b[0;32m 24\u001b[0m \"ACTGs are allowed.\".format(char))\n\u001b[0;32m 25\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 26\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mgc_count\u001b[0m \u001b[1;33m*\u001b[0m \u001b[1;36m100.0\u001b[0m \u001b[1;33m/\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mgc_count\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mat_count\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 27\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 28\u001b[0m \u001b[0minput_seq\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0muser_input\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mZeroDivisionError\u001b[0m: float division by zero"
+ ]
+ }
+ ],
+ "prompt_number": 55
+ },
+ {
+ "cell_type": "heading",
+ "level": 3,
+ "metadata": {},
+ "source": [
+ "Adding corner cases"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "user_input = ''"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [],
+ "prompt_number": 56
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "def calc_gc_percent(seq):\n",
+ " \"\"\"\n",
+ " Calculates the GC percentage of the given sequence.\n",
+ "\n",
+ " Arguments:\n",
+ " - seq - the input sequence (string).\n",
+ "\n",
+ " Returns:\n",
+ " - GC percentage (float).\n",
+ "\n",
+ " The returned value is always <= 100.0\n",
+ " \"\"\"\n",
+ " at_count, gc_count = 0, 0\n",
+ " # Change input to all caps to allow for non-capital\n",
+ " # input sequence.\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ " else:\n",
+ " raise ValueError(\n",
+ " \"Unexpeced character found: {}. Only \"\n",
+ " \"ACTGs are allowed.\".format(char))\n",
+ "\n",
+ " # Corner case handling: empty input sequence.\n",
+ " try:\n",
+ " return gc_count * 100.0 / (gc_count + at_count)\n",
+ " except ZeroDivisionError:\n",
+ " return 0.0\n",
+ "\n",
+ "input_seq = user_input\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "output_type": "stream",
+ "stream": "stdout",
+ "text": [
+ "The sequence '' has a %GC of 0.00\n"
+ ]
+ }
+ ],
+ "prompt_number": 57
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [],
+ "language": "python",
+ "metadata": {},
+ "outputs": []
+ }
+ ],
+ "metadata": {}
+ }
+ ]
+}
\ No newline at end of file
--
GitLab