Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Master #54

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Master #54

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3,282 changes: 3,282 additions & 0 deletions LinkedIn/03_02_loadingtext.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

291 changes: 291 additions & 0 deletions LinkedIn/03_03_findinganagrams.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,291 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 03_03: Finding Anagrams"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import math\n",
"import collections\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as pp\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"words = sorted({line.strip().lower() for line in open('words.txt', 'r')})"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sorted(\"aaron\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sorted(\"elvis\") == sorted(\"lives\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sorted(\"elvis\") == sorted(\"sings\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'-'.join(sorted(\"aaron\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"''.join(sorted(\"aaron\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# compute the signature string for a word\n",
"\n",
"def signature(word):\n",
" return ''.join(sorted(word))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# brute-force anagram search: compare myword's signature\n",
"# with the signatures of all words in the dictionary\n",
"\n",
"def find_anagram(myword):\n",
" mysig = signature(myword)\n",
" \n",
" for word in words:\n",
" if mysig == signature(word):\n",
" print(word)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"find_anagram('dictionary')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%time find_anagram('dictionary')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# make a dict that maps each signature to the set of words with that signature;\n",
"# each signature will map to at least one word\n",
"\n",
"words_by_sig = collections.defaultdict(set)\n",
"\n",
"for word in words:\n",
" words_by_sig[signature(word)].add(word)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"words_by_sig"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# keep only the key/value pairs where the set has more than one element;\n",
"# this is now a regular dict\n",
"\n",
"anagrams_by_sig = {sig: wordset for sig, wordset in words_by_sig.items() if len(wordset) > 1}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"anagrams_by_sig"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# smart anagram search: look up myword's signature, return set\n",
"\n",
"def find_anagram_fast(myword):\n",
" sig = signature(myword)\n",
" \n",
" return anagrams_by_sig[sig]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"find_anagram_fast('tops')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"find_anagram_fast('michele')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# handle case when myword's signature is not found, returning the empty set\n",
"\n",
"def find_anagram_fast(myword):\n",
" sig = signature(myword)\n",
"\n",
" try:\n",
" return anagrams_by_sig[sig]\n",
" except KeyError:\n",
" return set()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"find_anagram_fast('Michele')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%time find_anagram_fast('Michele')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# list of signatures, sorted by length, longest first\n",
"sorted(anagrams_by_sig.keys(), key=len, reverse=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# list of anagram sets, sorted by signature length\n",
"[anagrams_by_sig[sig] for sig in sorted(anagrams_by_sig.keys(), key=len, reverse=True)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# list of anagram sets, sorted by their length, largest first\n",
"sorted(anagrams_by_sig.values(), key=len, reverse=True)"
]
}
],
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading