mirror of
https://github.com/donnemartin/interactive-coding-challenges.git
synced 2024-03-22 13:11:13 +08:00
9636459124
Make hash_function private.
283 lines
7.3 KiB
Python
283 lines
7.3 KiB
Python
{
|
|
"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/interactive-coding-challenges)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Solution Notebook"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Problem: Implement a hash table with set, get, and remove methods.\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",
|
|
"* For simplicity, are the keys integers only?\n",
|
|
" * Yes\n",
|
|
"* For collision resolution, can we use chaining?\n",
|
|
" * Yes\n",
|
|
"* Do we have to worry about load factors?\n",
|
|
" * No\n",
|
|
"* Do we have to validate inputs?\n",
|
|
" * No\n",
|
|
"* Can we assume this fits memory?\n",
|
|
" * Yes"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Test Cases\n",
|
|
"\n",
|
|
"* `get` no matching key -> KeyError exception\n",
|
|
"* `get` matching key -> value\n",
|
|
"* `set` no matchin gkey -> new key, value\n",
|
|
"* `set` matching key -> update value\n",
|
|
"* `remove` no matching key -> KeyError exception\n",
|
|
"* `remove` matching key -> remove key, value"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Algorithm\n",
|
|
"\n",
|
|
"### Hash Function\n",
|
|
"\n",
|
|
"* Return key % table size\n",
|
|
"\n",
|
|
"Complexity:\n",
|
|
"* Time: O(1)\n",
|
|
"* Space: O(1)\n",
|
|
"\n",
|
|
"### Set\n",
|
|
"\n",
|
|
"* Get hash index for lookup\n",
|
|
"* If key exists, replace\n",
|
|
"* Else, add\n",
|
|
"\n",
|
|
"Complexity:\n",
|
|
"* Time: O(1) average and best, O(n) worst\n",
|
|
"* Space: O(1) space for newly added element\n",
|
|
"\n",
|
|
"### Get\n",
|
|
"\n",
|
|
"* Get hash index for lookup\n",
|
|
"* If key exists, return value\n",
|
|
"* Else, raise KeyError\n",
|
|
"\n",
|
|
"Complexity:\n",
|
|
"* Time: O(1) average and best, O(n) worst\n",
|
|
"* Space: O(1)\n",
|
|
"\n",
|
|
"### Remove\n",
|
|
"\n",
|
|
"* Get hash index for lookup\n",
|
|
"* If key exists, delete the item\n",
|
|
"* Else, raise KeyError\n",
|
|
"\n",
|
|
"Complexity:\n",
|
|
"* Time: O(1) average and best, O(n) worst\n",
|
|
"* Space: O(1)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Code"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"class Item(object):\n",
|
|
"\n",
|
|
" def __init__(self, key, value):\n",
|
|
" self.key = key\n",
|
|
" self.value = value\n",
|
|
"\n",
|
|
"\n",
|
|
"class HashTable(object):\n",
|
|
"\n",
|
|
" def __init__(self, size):\n",
|
|
" self.size = size\n",
|
|
" self.table = [[] for _ in range(self.size)]\n",
|
|
"\n",
|
|
" def _hash_function(self, key):\n",
|
|
" return key % self.size\n",
|
|
"\n",
|
|
" def set(self, key, value):\n",
|
|
" hash_index = self._hash_function(key)\n",
|
|
" for item in self.table[hash_index]:\n",
|
|
" if item.key == key:\n",
|
|
" item.value = value\n",
|
|
" return\n",
|
|
" self.table[hash_index].append(Item(key, value))\n",
|
|
"\n",
|
|
" def get(self, key):\n",
|
|
" hash_index = self._hash_function(key)\n",
|
|
" for item in self.table[hash_index]:\n",
|
|
" if item.key == key:\n",
|
|
" return item.value\n",
|
|
" raise KeyError('Key not found')\n",
|
|
"\n",
|
|
" def remove(self, key):\n",
|
|
" hash_index = self._hash_function(key)\n",
|
|
" for index, item in enumerate(self.table[hash_index]):\n",
|
|
" if item.key == key:\n",
|
|
" del self.table[hash_index][index]\n",
|
|
" return\n",
|
|
" raise KeyError('Key not found')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Unit Test"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Overwriting test_hash_map.py\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%writefile test_hash_map.py\n",
|
|
"from nose.tools import assert_equal, assert_raises\n",
|
|
"\n",
|
|
"\n",
|
|
"class TestHashMap(object):\n",
|
|
"\n",
|
|
" # TODO: It would be better if we had unit tests for each\n",
|
|
" # method in addition to the following end-to-end test\n",
|
|
" def test_end_to_end(self):\n",
|
|
" hash_table = HashTable(10)\n",
|
|
"\n",
|
|
" print(\"Test: get on an empty hash table index\")\n",
|
|
" assert_raises(KeyError, hash_table.get, 0)\n",
|
|
"\n",
|
|
" print(\"Test: set on an empty hash table index\")\n",
|
|
" hash_table.set(0, 'foo')\n",
|
|
" assert_equal(hash_table.get(0), 'foo')\n",
|
|
" hash_table.set(1, 'bar')\n",
|
|
" assert_equal(hash_table.get(1), 'bar')\n",
|
|
"\n",
|
|
" print(\"Test: set on a non empty hash table index\")\n",
|
|
" hash_table.set(10, 'foo2')\n",
|
|
" assert_equal(hash_table.get(0), 'foo')\n",
|
|
" assert_equal(hash_table.get(10), 'foo2')\n",
|
|
"\n",
|
|
" print(\"Test: set on a key that already exists\")\n",
|
|
" hash_table.set(10, 'foo3')\n",
|
|
" assert_equal(hash_table.get(0), 'foo')\n",
|
|
" assert_equal(hash_table.get(10), 'foo3')\n",
|
|
"\n",
|
|
" print(\"Test: remove on a key that already exists\")\n",
|
|
" hash_table.remove(10)\n",
|
|
" assert_equal(hash_table.get(0), 'foo')\n",
|
|
" assert_raises(KeyError, hash_table.get, 10)\n",
|
|
"\n",
|
|
" print(\"Test: remove on a key that doesn't exist\")\n",
|
|
" assert_raises(KeyError, hash_table.remove, -1)\n",
|
|
"\n",
|
|
" print('Success: test_end_to_end')\n",
|
|
"\n",
|
|
"\n",
|
|
"def main():\n",
|
|
" test = TestHashMap()\n",
|
|
" test.test_end_to_end()\n",
|
|
"\n",
|
|
"\n",
|
|
"if __name__ == '__main__':\n",
|
|
" main()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Test: get on an empty hash table index\n",
|
|
"Test: set on an empty hash table index\n",
|
|
"Test: set on a non empty hash table index\n",
|
|
"Test: set on a key that already exists\n",
|
|
"Test: remove on a key that already exists\n",
|
|
"Test: remove on a key that doesn't exist\n",
|
|
"Success: test_end_to_end\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"run -i test_hash_map.py"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.5.0"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0
|
|
}
|