import os

creds = {
    'twitter': (os.environ['TW_API_KEY'], os.environ['TW_API_SEC'], (os.environ['TW_ACC_KEY'], os.environ['TW_ACC_SEC'])),
    'facebook': os.environ['FB_API_KEY'],
    'google': os.environ['GG_API_KEY']
}

import pattern

from pattern.web import Twitter, Facebook, DuckDuckGo, Google, Bing, Wikipedia, Wikia, Newsfeed
from pattern.web import SEARCH, NEWS, IMAGE, SPARQL, COMMENTS, LIKES

tw = Twitter(license=creds['twitter'])
fb = Facebook(license=creds['facebook'])
ggl = Google(license=creds['google'])
# None uses credentials shared across ALL pattern users
ddg = DuckDuckGo(license=None)
bing = Bing(license=None)
wp = Wikipedia(license=None)
wa = Wikia(license=None)
nf = Newsfeed(license=None) # RSS / atom

tw.trends()

twitter_result = tw.search('ananas', count=100)
twitter_result[0]

from collections import Counter
languages = [tweet.language for tweet in twitter_result]
Counter(languages)

from pattern.web.locale import geocode

in_result = tw.search('#EngvInd', count=50, geo=geocode('New Delhi')[:2])
en_result = tw.search('#EngvInd', count=50, geo=geocode('London')[:2])

from pattern.en import sentiment

reduce(lambda x, y: x+y, [sentiment(t.text)[0] for t in in_result]) / len(in_result)

reduce(lambda x, y: x+y, [sentiment(t.text)[0] for t in en_result]) / len(en_result)

fb_result = fb.search('dragon age inquisition', type=SEARCH, count=100)
fb_result[0]

for post in fb_result:
    
    if post.likes > 0 and post.comments > 0:
        print('\n\n'.join( [l.author[1] for l in fb.search(post.id, type=LIKES)] ))
        print('-' * 10)
        print('\n\n'.join( [c.text for c in fb.search(post.id, type=COMMENTS)] ))
        break

google_result = ggl.search('dragon age inquisition', count=10)
google_result[0]

lang_id = [ggl.identify(res.text) for res in fb_result[:10]]
lang_id

ggl.translate(fb_result[0].text, input=lang_id[0][0], output='de')

from pattern.web import find_urls, find_email

s = '''
Find out more at the PUGS website (http://pugs.org.sg), or email us at idontknow@whatouremail.is!
This is a decoy URL http://pugs.org.sg.
'''

find_urls(s, unique=True), \
find_email(s, unique=True)

from pattern.web import sort, GOOGLE

terms = [
    'french',
    'german',
    'japanese',
    'chinese',
    'persian',
    'hun',
    'american',
    'russian',
    'swede',
    'polish',
    'singaporean',
    'politician',
]
sort_result = sort(terms=terms, context='dangerous', prefix=True, service=GOOGLE, license=creds['google'])

for weight, term in sort_result:
    print "%.2f" % (weight * 100) + '%', term

from pattern.en import article, referenced

article('harbour'), \
referenced('umbrella')

from pattern.en import (pluralize as pluralise, singularize as singularise)

pluralise('octopus')

pluralise('octopus', classical=False)

pluralise('I'), \
pluralise('my'), \
pluralise('her')

singularise('bacteria')

pluralise('virus')

singularise('viruses'), \
singularise('virii'), \
singularise('virus')

singularise('viri')

from pattern.en import comparative, superlative

'python is %s than ruby!' % comparative('good')

'iPython is %s python shell' % (
referenced(superlative('ideal'), article=pattern.en.DEFINITE))

from pattern.en import conjugate, lemma, lexeme, tenses

lemma('are')

tenses('be'), \
tenses('were')

lexeme('be')

conjugate('nibble', '1sgp'), \
conjugate('nibble', '3sg')

conjugate('google', tense=pattern.en.PARTICIPLE, parse=False), \
conjugate('google', tense=pattern.en.PARTICIPLE, parse=True)

from pattern.en import number

number('five thousand six hundred and eighty nine')

from pattern.en import numerals

numerals('42.128', round=2)

animals = ['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken']
orangebirds = {'carrot': 100, 'parrot': 5, 'orange': 20}

from pattern.en import quantify

quantify(animals), \
quantify(orangebirds)

from pattern.en import suggest

suggest('psuh')

suggest('carot')

from pattern.en import ngrams

ngrams('This is a sentence', n=2)

ngrams('This is a sentence', n=3)

short_s = 'When I saw the prices for some of those apartments, I was startled.'
long_s = 'Personally, I think the only unassailable definition is the one often attributed to the great editor John W Campbell: "Science fiction is what I say it is."'

from pattern.en import tag

for word, pos in tag(short_s):
    if pos[:2] == 'NN':
        print(word)

from pattern.en import parse

parsed = parse(short_s, tokenize=True, tags=True, chunks=True, relations=True, lemmata=True)
parsed

from pattern.en import pprint

pprint(parsed)

from pattern.en import parsetree

parsetree(short_s, tokenize=True, tags=True, chunks=True, relations=True, lemmata=True)

tr = parsetree(long_s, tokenize=True, tags=True, chunks=True, relations=True, lemmata=True)

print(type(tr))

[type(item) for item in tr]

type(tr[0][0])

for sentence in tr:
    for chunk in sentence.chunks:
        print(chunk.type, [(w.string, w.type) for w in chunk.words])

from pattern.en import sentiment

sg_result = tw.search('causeway', count=50, geo=geocode('Singapore')[:2])
my_result = tw.search('causeway', count=50, geo=geocode('Kuala Lumpur')[:2])

sg_sentiment = sorted(sentiment(tweet.text)[0] for tweet in sg_result)
my_sentiment = sorted(sentiment(tweet.text)[0] for tweet in my_result)

sg_avg = sum(sg_sentiment) / len(sg_sentiment)
my_avg = sum(my_sentiment) / len(my_sentiment)

sg_avg, my_avg

x = linspace(0, 50)
plot(sg_sentiment, 'r-', label='sg')
plot(x, [sg_avg for i in xrange(0, 50)], 'r--', label='sg_avg')
plot(my_sentiment, 'g-', label='my')
plot(x, [my_avg for i in xrange(0, 50)], 'g--', label='my_avg')
grid(b=True, which='both')
legend(loc='best')

from pattern.en import wordnet

birds = wordnet.synsets('bird')
birds

bird = birds[0]

'Definition', bird.gloss

'- Synonyms', bird.synonyms

'^ Hypernyms', bird.hypernyms()

'v Hyponyms', bird.hyponyms()

'^ Holonyms', bird.holonyms()

'v Meronyms', bird.meronyms()

wordnet.synsets('owl')[0].holonyms(), wordnet.synsets('amoeba')[0].holonyms()

kitty = wordnet.synsets('kitten')[0]
pup = wordnet.synsets('puppy')[0]

wordnet.ancestor(kitty, pup)

human = wordnet.synsets('human')[0]
cuy = wordnet.synsets('guinea pig')[0]

wordnet.similarity(human, cuy), \
wordnet.similarity(human, kitty)

s = 'the fluffy brown bunnies hopped across the wet grass with much gusto.'

from pattern.search import search

search('NP', parsetree(s))

from pattern.search import taxonomy

for animal in ('bunny', 'dog', 'cat', 'banana'):
    taxonomy.append(animal, type='animal')
    
search('ANIMAL', parsetree(s, lemmata=True))

from pattern.search import Pattern

pat = Pattern.fromstring('{JJ} {ANIMAL} {VP}')
match = pat.match(parsetree(s, lemmata=True))
for i in range(0,4):
    print(match.group(i))