mirror of
https://github.com/donnemartin/interactive-coding-challenges.git
synced 2024-03-22 13:11:13 +08:00
264 lines
7.1 KiB
Plaintext
264 lines
7.1 KiB
Plaintext
|
{
|
||
|
"cells": [
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"<small><i>This notebook was prepared by [Donne Martin](http://donnemartin.com). Source and license info is on [GitHub](https://github.com/donnemartin/interactive-coding-challenges).</i></small>"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"# Solution Notebook"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Problem: Compress a string such that 'AAABCCDDDD' becomes 'A3BCCD4'. Only compress the string if it saves space.\n",
|
||
|
"\n",
|
||
|
"* [Constraints](#Constraints)\n",
|
||
|
"* [Test Cases](#Test-Cases)\n",
|
||
|
"* [Algorithm](#Algorithm)\n",
|
||
|
"* [Code](#Code)\n",
|
||
|
"* [Unit Test](#Unit-Test)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Constraints\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"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Test Cases\n",
|
||
|
"\n",
|
||
|
"* None -> None\n",
|
||
|
"* '' -> ''\n",
|
||
|
"* 'AABBCC' -> 'AABBCC'\n",
|
||
|
"* 'AAABCCDDDD' -> 'A3BCCD4'"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Algorithm\n",
|
||
|
"\n",
|
||
|
"Since Python strings are immutable, we'll use a list of characters to build the compressed string representation. We'll then convert the list to a string.\n",
|
||
|
"\n",
|
||
|
"* Calculate the size of the compressed string\n",
|
||
|
" * Note the constraint about compressing only if it saves space\n",
|
||
|
"* If the compressed string size is >= string size, return string\n",
|
||
|
"* Create compressed_string\n",
|
||
|
" * For each char in string\n",
|
||
|
" * If char is the same as last_char, increment count\n",
|
||
|
" * Else\n",
|
||
|
" * If the count is more than 2\n",
|
||
|
" * Append last_char to compressed_string\n",
|
||
|
" * append count to compressed_string\n",
|
||
|
" * count = 1\n",
|
||
|
" * last_char = char\n",
|
||
|
" * If count is 1\n",
|
||
|
" * Append last_char to compressed_string\n",
|
||
|
" * count = 1\n",
|
||
|
" * last_char = char\n",
|
||
|
" * If count is 2\n",
|
||
|
" * Append last_char to compressed_string\n",
|
||
|
" * Append last_char to compressed_string once more\n",
|
||
|
" * count = 1\n",
|
||
|
" * last_char = char\n",
|
||
|
" * Append last_char to compressed_string\n",
|
||
|
" * Append count to compressed_string\n",
|
||
|
" * Return compressed_string\n",
|
||
|
"\n",
|
||
|
"Complexity:\n",
|
||
|
"* Time: O(n)\n",
|
||
|
"* Space: O(n)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Code"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 4,
|
||
|
"metadata": {
|
||
|
"collapsed": false
|
||
|
},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"def compress_string(string):\n",
|
||
|
"\tif string is None or len(string) == 0:\n",
|
||
|
"\t\treturn string\n",
|
||
|
"\n",
|
||
|
"\t# Calculate the size of the compressed string\n",
|
||
|
"\tsize = 0\n",
|
||
|
"\tlast_char = string[0]\n",
|
||
|
"\tfor char in string:\n",
|
||
|
"\t\tif char != last_char:\n",
|
||
|
"\t\t\tsize += 2\n",
|
||
|
"\t\t\tlast_char = char\n",
|
||
|
"\tsize += 2\n",
|
||
|
"\n",
|
||
|
"\t# If the compressed string size is greater than\n",
|
||
|
"\t# or equal to string size, return original string\n",
|
||
|
"\tif size >= len(string):\n",
|
||
|
"\t\treturn string\n",
|
||
|
"\n",
|
||
|
"\t# Create compressed_string\n",
|
||
|
"\t# New objective:\n",
|
||
|
"\t\t# Single characters are to be left as is\n",
|
||
|
"\t\t# Double characters are to be left as are\n",
|
||
|
"\tcompressed_string = list()\n",
|
||
|
"\tcount = 0\n",
|
||
|
"\tlast_char = string[0]\n",
|
||
|
"\tfor char in string:\n",
|
||
|
"\t\tif char == last_char:\n",
|
||
|
"\t\t\tcount += 1\n",
|
||
|
"\t\telse:\n",
|
||
|
"\t\t\t# Do the old compression tricks only if count exceeds two\n",
|
||
|
"\t\t\tif count > 2:\n",
|
||
|
"\t\t\t\tcompressed_string.append(last_char)\n",
|
||
|
"\t\t\t\tcompressed_string.append(str(count))\n",
|
||
|
"\t\t\t\tcount = 1\n",
|
||
|
"\t\t\t\tlast_char = char\n",
|
||
|
"\t\t\t# If count is either 1 or 2 (or 0?)\n",
|
||
|
"\t\t\t# FIXME: CAN COUNT BE 0?\n",
|
||
|
"\t\t\telse:\n",
|
||
|
"\t\t\t\t# If count is 1, leave the char as is\n",
|
||
|
"\t\t\t\tif count == 1:\n",
|
||
|
"\t\t\t\t\tcompressed_string.append(last_char)\n",
|
||
|
"\t\t\t\t\tcount = 1\n",
|
||
|
"\t\t\t\t\tlast_char = char\n",
|
||
|
"\t\t\t\t# If count is 2, append the character twice\n",
|
||
|
"\t\t\t\telse:\n",
|
||
|
"\t\t\t\t\tcompressed_string.append(last_char)\n",
|
||
|
"\t\t\t\t\tcompressed_string.append(last_char)\n",
|
||
|
"\t\t\t\t\tcount = 1\n",
|
||
|
"\t\t\t\t\tlast_char = char\n",
|
||
|
"\tcompressed_string.append(last_char)\n",
|
||
|
"\tcompressed_string.append(str(count))\n",
|
||
|
"\n",
|
||
|
"\t# Convert the characters in the list to a string\n",
|
||
|
"\treturn \"\".join(compressed_string)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Unit Test"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 5,
|
||
|
"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'), 'A3BCCD4')\n",
|
||
|
" assert_equal(func('aaBCCEFFFFKKMMMMMMP taaammanlaarrrr seeeeeeeeek tooo'), 'aaBCCEF4KKM6P ta3mmanlaar4 se9k to3')\n",
|
||
|
" print('Success: test_compress')\n",
|
||
|
"\n",
|
||
|
"\n",
|
||
|
"def main():\n",
|
||
|
" test = TestCompress()\n",
|
||
|
" test.test_compress(compress_string)\n",
|
||
|
"\n",
|
||
|
"\n",
|
||
|
"if __name__ == '__main__':\n",
|
||
|
" main()"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 7,
|
||
|
"metadata": {
|
||
|
"collapsed": false
|
||
|
},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"name": "stdout",
|
||
|
"output_type": "stream",
|
||
|
"text": [
|
||
|
"Success: test_compress\n"
|
||
|
]
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"%run -i test_compress.py"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {
|
||
|
"collapsed": true
|
||
|
},
|
||
|
"outputs": [],
|
||
|
"source": []
|
||
|
}
|
||
|
],
|
||
|
"metadata": {
|
||
|
"kernelspec": {
|
||
|
"display_name": "Python 3",
|
||
|
"language": "python",
|
||
|
"name": "python3"
|
||
|
},
|
||
|
"language_info": {
|
||
|
"codemirror_mode": {
|
||
|
"name": "ipython",
|
||
|
"version": 3
|
||
|
},
|
||
|
"file_extension": ".py",
|
||
|
"mimetype": "text/x-python",
|
||
|
"name": "python",
|
||
|
"nbconvert_exporter": "python",
|
||
|
"pygments_lexer": "ipython3",
|
||
|
"version": "3.4.3"
|
||
|
}
|
||
|
},
|
||
|
"nbformat": 4,
|
||
|
"nbformat_minor": 0
|
||
|
}
|