AltcoinTextMining/Doc2VecExample.py.txt at master · RobertMcPherson/AltcoinTextMining · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
# gensim modules
from gensim import utils
from gensim.models.doc2vec import LabeledSentence
from gensim.models import Doc2Vec

# numpy
import numpy

# random
from random import shuffle

# classifier
from sklearn.linear_model import LogisticRegression

class LabeledLineSentence(object):
    def __init__(self, sources):
        self.sources = sources

        flipped = {}

        # make sure that keys are unique
        for key, value in sources.items():
            if value not in flipped:
                flipped[value] = [key]
            else:
                raise Exception('Non-unique prefix encountered')

    def __iter__(self):
        for source, prefix in self.sources.items():
            with utils.smart_open(source) as fin:
                for item_no, line in enumerate(fin):
                    yield LabeledSentence(utils.to_unicode(line).split(), [prefix + '_%s' % item_no])

    def to_array(self):
        self.sentences = []
        for source, prefix in self.sources.items():
            with utils.smart_open(source) as fin:
                for item_no, line in enumerate(fin):
                    self.sentences.append(LabeledSentence(utils.to_unicode(line).split(), [prefix + '_%s' % item_no]))
        return self.sentences

    def sentences_perm(self):
        shuffle(self.sentences)
        return self.sentences

sources = {'test-neg.txt':'TEST_NEG', 'test-pos.txt':'TEST_POS', 'train-neg.txt':'TRAIN_NEG', 'train-pos.txt':'TRAIN_POS', 'train-unsup.txt':'TRAIN_UNS'}

sentences = LabeledLineSentence(sources)

model = Doc2Vec(min_count=1, window=10, size=100, sample=1e-4, negative=5, workers=8)

model.build_vocab(sentences.to_array())

for epoch in range(10):
    model.train(sentences.sentences_perm())

model.save('./imdb.d2v')

model = Doc2Vec.load('./imdb.d2v')

model.most_similar('good')

model['TRAIN_NEG_0']

## Classifying Sentiments

train_arrays = numpy.zeros((25000, 100))
train_labels = numpy.zeros(25000)

for i in range(12500):
    prefix_train_pos = 'TRAIN_POS_' + str(i)
    prefix_train_neg = 'TRAIN_NEG_' + str(i)
    train_arrays[i] = model[prefix_train_pos]
    train_arrays[12500 + i] = model[prefix_train_neg]
    train_labels[i] = 1
    train_labels[12500 + i] = 0


 print train_labels

test_arrays = numpy.zeros((25000, 100))
test_labels = numpy.zeros(25000)

for i in range(12500):
    prefix_test_pos = 'TEST_POS_' + str(i)
    prefix_test_neg = 'TEST_NEG_' + str(i)
    test_arrays[i] = model[prefix_test_pos]
    test_arrays[12500 + i] = model[prefix_test_neg]
    test_labels[i] = 1
    test_labels[12500 + i] = 0

classifier = LogisticRegression()

classifier.fit(train_arrays, train_labels)

classifier.score(test_arrays, test_labels)