From 8b9a1473ea27dda3ebccea71464f5f7e9b4c2eae Mon Sep 17 00:00:00 2001 From: Donne Martin Date: Fri, 3 Jul 2015 19:55:56 -0400 Subject: [PATCH] Added compress challenge. --- .../compress/compress_challenge.ipynb | 173 ++++++++++++++++++ .../compress/compress_solution.ipynb | 96 ++++++---- arrays_strings/compress/test_compress.py | 24 +++ 3 files changed, 260 insertions(+), 33 deletions(-) create mode 100644 arrays_strings/compress/compress_challenge.ipynb create mode 100644 arrays_strings/compress/test_compress.py diff --git a/arrays_strings/compress/compress_challenge.ipynb b/arrays_strings/compress/compress_challenge.ipynb new file mode 100644 index 0000000..d256e96 --- /dev/null +++ b/arrays_strings/compress/compress_challenge.ipynb @@ -0,0 +1,173 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This notebook was prepared by [Donne Martin](http://donnemartin.com). Source and license info is on [GitHub](https://github.com/donnemartin/coding-challenges)." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Challenge Notebook" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Problem: Compress a string such that 'AAABCCDDDD' becomes 'A3B1C2D4'\n", + "\n", + "* [Constraints](#Constraints)\n", + "* [Test Cases](#Test-Cases)\n", + "* [Algorithm](#Algorithm)\n", + "* [Code](#Code)\n", + "* [Unit Test](#Unit-Test)\n", + "* [Solution Notebook](#Solution-Notebook)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Constraints\n", + "\n", + "*Problem statements are sometimes ambiguous. Identifying constraints and stating assumptions can help to ensure you code the intended solution.*\n", + "\n", + "* Can we assume the string is ASCII?\n", + " * Yes\n", + " * Note: Unicode strings could require special handling depending on your language\n", + "* Can you use additional data structures? \n", + " * Yes\n", + "* Is this case sensitive?\n", + " * Yes\n", + "* Do you compress even if it doesn't save space?\n", + " * No" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Test Cases\n", + "\n", + "* None -> None\n", + "* '' -> ''\n", + "* 'AABBCC' -> 'AABBCC'\n", + "* 'AAABCCDDDD' -> 'A3B1C2D4'" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Algorithm\n", + "\n", + "Refer to the [Solution Notebook](http://nbviewer.ipython.org/github/donnemartin/coding-challenges/blob/master/arrays_strings/compress/compress_solution.ipynb). If you are stuck and need a hint, the solution notebook's algorithm discussion might be a good place to start." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Code" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def compress_string(string):\n", + " # TODO: Implement me\n", + " pass" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Unit Test" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "\n", + "**The following unit test is expected to fail until you solve the challenge.**" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# %load test_compress.py\n", + "from nose.tools import assert_equal\n", + "\n", + "\n", + "class TestCompress(object):\n", + " \n", + " def test_compress(self, func):\n", + " assert_equal(func(None), None)\n", + " assert_equal(func(''), '')\n", + " assert_equal(func('AABBCC'), 'AABBCC')\n", + " assert_equal(func('AAABCCDDDD'), 'A3B1C2D4')\n", + " print('Success: test_compress')\n", + "\n", + "def main():\n", + " test = TestCompress()\n", + " test.test_compress(compress_string)\n", + " try:\n", + " test.test_compress(compress_string_alt)\n", + " except NameError:\n", + " # Alternate solutions are only defined\n", + " # in the solutions file\n", + " pass\n", + "\n", + "if __name__ == '__main__':\n", + " main()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Solution Notebook\n", + "\n", + "Review the [Solution Notebook](http://nbviewer.ipython.org/github/donnemartin/coding-challenges/blob/master/arrays_strings/compress/compress_solution.ipynb) for a discussion on algorithms and code solutions." + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.10" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/arrays_strings/compress/compress_solution.ipynb b/arrays_strings/compress/compress_solution.ipynb index 4da5513..0f8fc80 100644 --- a/arrays_strings/compress/compress_solution.ipynb +++ b/arrays_strings/compress/compress_solution.ipynb @@ -4,7 +4,14 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "This notebook was prepared by [Donne Martin](http://donnemartin.com). Source and license info is on [GitHub](https://bit.ly/code-notes)." + "This notebook was prepared by [Donne Martin](http://donnemartin.com). Source and license info is on [GitHub](https://github.com/donnemartin/coding-challenges)." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Solution Notebook" ] }, { @@ -28,9 +35,9 @@ "source": [ "## Constraints\n", "\n", - "*Problem statements are often intentionally ambiguous. Identifying constraints and stating assumptions can help to ensure you code the intended solution.*\n", + "*Problem statements are sometimes ambiguous. Identifying constraints and stating assumptions can help to ensure you code the intended solution.*\n", "\n", - "* Can I assume the string is ASCII?\n", + "* Can we assume the string is ASCII?\n", " * Yes\n", " * Note: Unicode strings could require special handling depending on your language\n", "* Can you use additional data structures? \n", @@ -47,9 +54,9 @@ "source": [ "## Test Cases\n", "\n", - "* NULL\n", + "* None -> None\n", "* '' -> ''\n", - "* 'ABC' -> 'ABC'\n", + "* 'AABBCC' -> 'AABBCC'\n", "* 'AAABCCDDDD' -> 'A3B1C2D4'" ] }, @@ -59,9 +66,7 @@ "source": [ "## Algorithm: List\n", "\n", - "Since Python strings are immutable, we'll use a list of characters instead to exercise in-place string manipulation as you would get with a C string (which is null terminated, as seen in the diagram below). Python does not use a null-terminator.\n", - "\n", - "![alt text](https://raw.githubusercontent.com/donnemartin/algorithms-data-structures/master/images/compress_string.jpg)\n", + "Since Python strings are immutable, we'll use a list of characters instead to exercise string manipulation as you would get with a C string. We'll convert the list to a string at the end of the algorithm.\n", "\n", "* Calculate the size of the compressed string\n", "* If the compressed string size is >= string size, return string\n", @@ -79,7 +84,7 @@ "\n", "Complexity:\n", "* Time: O(n)\n", - "* Space: O(2m) where m is the size of the compressed list and the resulting string copied from the list" + "* Space: O(n) additional space for the list" ] }, { @@ -138,20 +143,15 @@ "source": [ "## Algorithm: Byte Array\n", "\n", - "The byte array algorithm similar when using a list, except we will need to work with the bytearray's character codes instead of the characters as we did above when we implemented this solution with a list.\n", + "As a bonus solution, we can solve this problem with a byte array.\n", + "\n", + "The byte array algorithm similar when using a list, except we will need to work with the bytearray's character codes (using the function ord) instead of the characters as we did above when we implemented this solution with a list.\n", "\n", "Complexity:\n", "* Time: O(n)\n", "* Space: O(m) where m is the size of the compressed bytearray" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Code: Byte Array" - ] - }, { "cell_type": "code", "execution_count": 2, @@ -201,14 +201,14 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Unit Test" + "## Code: Byte Array" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "*It is important to identify and run through general and edge cases from the [Test Cases](#Test-Cases) section by hand. You generally will not be asked to write a unit test like what is shown below.*" + "## Unit Test" ] }, { @@ -217,6 +217,49 @@ "metadata": { "collapsed": false }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Overwriting test_compress.py\n" + ] + } + ], + "source": [ + "%%writefile test_compress.py\n", + "from nose.tools import assert_equal\n", + "\n", + "\n", + "class TestCompress(object):\n", + " \n", + " def test_compress(self, func):\n", + " assert_equal(func(None), None)\n", + " assert_equal(func(''), '')\n", + " assert_equal(func('AABBCC'), 'AABBCC')\n", + " assert_equal(func('AAABCCDDDD'), 'A3B1C2D4')\n", + " print('Success: test_compress')\n", + "\n", + "def main():\n", + " test = TestCompress()\n", + " test.test_compress(compress_string)\n", + " try:\n", + " test.test_compress(compress_string_alt)\n", + " except NameError:\n", + " # Alternate solutions are only defined\n", + " # in the solutions file\n", + " pass\n", + "\n", + "if __name__ == '__main__':\n", + " main()" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": false + }, "outputs": [ { "name": "stdout", @@ -228,20 +271,7 @@ } ], "source": [ - "from nose.tools import assert_equal\n", - "\n", - "class Test(object):\n", - " def test_compress(self, func):\n", - " assert_equal(func(None), None)\n", - " assert_equal(func(''), '')\n", - " assert_equal(func('ABC'), 'ABC')\n", - " assert_equal(func('AAABCCDDDD'), 'A3B1C2D4')\n", - " print('Success: test_compress')\n", - "\n", - "if __name__ == '__main__':\n", - " test = Test()\n", - " test.test_compress(compress_string)\n", - " test.test_compress(compress_string_alt)" + "%run -i test_compress.py" ] } ], diff --git a/arrays_strings/compress/test_compress.py b/arrays_strings/compress/test_compress.py new file mode 100644 index 0000000..fef9e62 --- /dev/null +++ b/arrays_strings/compress/test_compress.py @@ -0,0 +1,24 @@ +from nose.tools import assert_equal + + +class TestCompress(object): + + def test_compress(self, func): + assert_equal(func(None), None) + assert_equal(func(''), '') + assert_equal(func('AABBCC'), 'AABBCC') + assert_equal(func('AAABCCDDDD'), 'A3B1C2D4') + print('Success: test_compress') + +def main(): + test = TestCompress() + test.test_compress(compress_string) + try: + test.test_compress(compress_string_alt) + except NameError: + # Alternate solutions are only defined + # in the solutions file + pass + +if __name__ == '__main__': + main() \ No newline at end of file