from nltk.probability import DictionaryProbDist
from nltk import NaiveBayesClassifier

train_samples = {
    'I hate you and you are a bad person': 'neg',
    'I love you and you are a good person': 'pos',
    'I fail at everything and I want to kill people' : 'neg',
    'I win at everything and I want to love people' : 'pos',
    'sad are things are heppening. fml' : 'neg',
    'good are things are heppening. gbu' : 'pos',
    'I am so poor' : 'neg',
    'I am so rich' : 'pos',
    'I hate you mommy ! You are my terrible person' : 'neg',
    'I love you mommy ! You are my amazing person' : 'pos',
    'I want to kill butterflies since they make me sad' : 'neg',
    'I want to chase butterflies since they make me happy' : 'pos',
    'I want to hurt bunnies' : 'neg',
    'I want to hug bunnies' : 'pos',
    'You make me frown' : 'neg',
    'You make me smile' : 'pos',
}

test_samples = [
  'You are a terrible person and everything you do is bad',
  'I love you all and you make me happy',
  'I frown whenever I see you in a poor state of mind',
  'Finally getting rich from my ideas. They make me smile.',
  'My mommy is poor',
  'I love butterflies. Yay for happy',
  'Everything is fail today and I hate stuff',
]


def gen_bow(s):
    words = s.split(' ')
    bow = {}
    for word in words:
        bow[word] = True
    return bow

label_probdist = DictionaryProbDist({'pos': 0.5, 'neg': 0.5})

true_probdist = DictionaryProbDist({True: 6})

feature_probdist = { ## need to generate this from train_samples
            ('neg', 'no'): true_probdist,
            ('neg', 'hate'): true_probdist,
            ('neg', 'fml'): true_probdist,
            ('neg', 'poor'): true_probdist,
            ('neg', 'sad'): true_probdist,
            ('neg', 'fail'): true_probdist,
            ('neg', 'kill'): true_probdist,
            ('neg', 'evil'): true_probdist,
            ('pos', 'bunnies'): true_probdist,
            ('pos', 'butteryfly'): true_probdist,
            ('pos', 'pony'): true_probdist,
            ('pos', 'love'): true_probdist,
            ('pos', 'smile'): true_probdist,
            ('pos', 'happy'): true_probdist,
            ('pos', 'amazing'): true_probdist,
            ('pos', 'yes'): true_probdist,
}


classifier = NaiveBayesClassifier(label_probdist, feature_probdist)

for sample in test_samples:
    print "%s | %s | %s" % (sample, classifier.classify(gen_bow(sample)), classifier.prob_classify(gen_bow(sample)))

classifier.show_most_informative_features()