Sentiment-Analysis-api/sentimentEngine.py at master · 4sentiSentinels/Sentiment-Analysis-api · 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
import sys
import os
import time
import nltk
import random
import pickle
import itertools
import operator
from sklearn.feature_extraction.text import TfidfVectorizer


# documents=[]

# with open("documents.pickle","rb") as fid:
#   documents=pickle.load(fid)

test_sen_all = ["I am in rvce where are you going"]


open_file = open("vectorizer.pickle", "rb")
vectorizer = pickle.load(open_file)


def most_common(L):
  # get an iterable of (item, iterable) pairs
  SL = sorted((x, i) for i, x in enumerate(L))
  # print 'SL:', SL
  groups = itertools.groupby(SL, key=operator.itemgetter(0))
  # auxiliary function to get "quality" for an item
  def _auxfun(g):
    item, iterable = g
    count = 0
    min_index = len(L)
    for _, where in iterable:
      count += 1
      min_index = min(min_index, where)
    # print 'item %r, count %r, minind %r' % (item, count, min_index)
    return count, -min_index
  # pick the highest-count/earliest item
  return max(groups, key=_auxfun)[0]

def test_vectorizer(test_docs):

    test_corpus = [d for d in test_docs]
    X = vectorizer.transform(test_corpus)
    return X

def sentiment(message):

        open_file = open("svm_linearSVM_pos_neg.pickle", "rb")
        svm_lk_pos_neg = pickle.load(open_file)
        open_file.close()
        open_file = open("svm_linearSVM_pos_neut.pickle", "rb")
        svm_lk_pos_neut = pickle.load(open_file)
        open_file.close()
        open_file = open("svm_linearSVM_neg_neut.pickle", "rb")
        svm_lk_neg_neut = pickle.load(open_file)
        open_file.close()


        X_test = test_vectorizer(message)


        pred1 = svm_lk_pos_neg.predict(X_test)

        pred2 = svm_lk_pos_neut.predict(X_test)

        pred3 = svm_lk_neg_neut.predict(X_test)

        res=[]
        res_predict=[]
        for p1,p2,p3 in zip(pred1,pred2,pred3):
          if p1==p2:
            res.append(p1)
            res_predict.append(p1)
          elif p1==p3:
            res.append(p1)
            res_predict.append(p1)
          elif p2==p3:
            res.append(p2)
            res_predict.append(p2)
          else:
            temp=[p1,p2,p3]
            res.append(random.choice(temp))
            res_predict.append("meh")


        return (most_common(res_predict))