Fork, of Peter Norvig's spell checker example.
Added a front-end. Deployed at http://mrcactu5.herokuapp.com/spell
Starting ground for even more interesting spell-checking. Very interesting use of conditional probability. A friend asks if it can be used to predict slang.
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <title>Spell-Checker</title> | |
| <!-- Bootstrap --> | |
| <link href="/static/bootstrap.min.css" rel="stylesheet" media="screen"> | |
| </head> | |
| <body> | |
| <div class="row"><div class="span12"><h1>Spell Checker</h1></div></div> | |
| <script src="http://code.jquery.com/jquery-latest.js"></script> | |
| <script src="/static/bootstrap.min.js"></script> | |
| <div class="row"> | |
| <div class="span3"> | |
| <form class="navbar-form pull-left" action="/spell" method="POST"> | |
| <input type="text" class="span2" name="word"> | |
| <button type="submit" class="btn">Submit</button> | |
| </form> | |
| </div> | |
| <div class="span1"> | |
| <table> | |
| %if word: | |
| %for wd in word: | |
| <tr><td>{{wd}}</td></tr> | |
| %else: | |
| </table> | |
| </div> | |
| </div> | |
| </body> | |
| </html> |
| from bottle import route, run, template, static_file, get, post, request | |
| import spellcheck | |
| @route('/spell') | |
| def spell_form(): | |
| return template('spell',word=None) | |
| @post('/spell') | |
| def spell_submit(): | |
| word = spellcheck.correct(request.forms.get('word')) | |
| return template('spell', word=word) | |
| run(host='localhost', port=8080) |
| import re, collections | |
| def words(text): return re.findall('[a-z]+', text.lower()) | |
| def train(features): | |
| model = collections.defaultdict(lambda: 1) | |
| for f in features: | |
| model[f] += 1 | |
| return model | |
| NWORDS = train(words(file('big.txt').read())) | |
| alphabet = 'abcdefghijklmnopqrstuvwxyz' | |
| def edits1(word): | |
| s = [(word[:i], word[i:]) for i in range(len(word) + 1)] | |
| deletes = [a + b[1:] for a, b in s if b] | |
| transposes = [a + b[1] + b[0] + b[2:] for a, b in s if len(b)>1] | |
| replaces = [a + c + b[1:] for a, b in s for c in alphabet if b] | |
| inserts = [a + c + b for a, b in s for c in alphabet] | |
| return set(deletes + transposes + replaces + inserts) | |
| def known_edits2(word): | |
| return set(e2 for e1 in edits1(word) for e2 in edits1(e1) if e2 in NWORDS) | |
| def known(words): return set(w for w in words if w in NWORDS) | |
| def correct(word): | |
| c = known([word]) or known(edits1(word)) or known_edits2(word) or [word] | |
| return max(c, key=NWORDS.get) |
