nlp.py

#!/usr/local/bin/python

import datetime

from textblob import TextBlob
from textblob import Blobber

from textblob.sentiments import NaiveBayesAnalyzer

from textblob.classifiers import NaiveBayesClassifier
from textblob.classifiers import DecisionTreeClassifier
from textblob.classifiers import MaxEntClassifier
from textblob.classifiers import BaseClassifier
from textblob.classifiers import NLTKClassifier
import nltk


class MyClassifier(NLTKClassifier):
	nltk_class = nltk.classify.scikitlearn.SklearnClassifier

train = [('I love this sandwich.', 'pos'), ('this is an amazing place!', 'pos'), ('I feel very good about these beers.', 'pos'), ('this is my best work.', 'pos'), ("what an awesome view", 'pos'), ('I do not like this restaurant', 'neg'), ('I am tired of this stuff.', 'neg'), ("I can't deal with this", 'neg'), ('he is my sworn enemy!', 'neg'), ('my boss is horrible.', 'neg')]

test = [ ('the beer was good.', 'pos'), ('I do not enjoy my job', 'neg'), ("I ain't feeling dandy today.", 'neg'), ("I feel amazing!", 'pos'), ('Gary is a friend of mine.', 'pos'), ("I can't believe I'm doing this.", 'neg')]

print("train_len: %d" % len(train))
print("test_len: %d" % len(test))

print("\n\nNaiveBayesClassifier\n====================")

ts = datetime.datetime.now()
cl = NaiveBayesClassifier(train)
print("training: %s" % (str(datetime.datetime.now() - ts)))

text = 'sandwich is good'
blob = Blobber(analyzer=NaiveBayesAnalyzer())
ss = datetime.datetime.now()
blob_sent = blob(text).sentiment
print("sentiment: %s" % (str(datetime.datetime.now() - ss)))
print("blob", blob_sent)

cs = datetime.datetime.now()
sent = cl.classify(text)
print("classify: %s" % (str(datetime.datetime.now() - cs)))

sent_prob = cl.prob_classify('sandwich is good')
accuracy = cl.accuracy(test)
print ("sentiment: %s" % sent, 
	"\naccuracy: %s%%" % str(round(accuracy, 2)* 100),
	"\nprobability: %s%%" % str(round(sent_prob.prob(sent_prob.max()), 2) * 100))

print("\n\nDecisionTreeClassifier\n======================")
ts = datetime.datetime.now()
cl = DecisionTreeClassifier(train)
print("training: %s" % (str(datetime.datetime.now() - ts)))
cs = datetime.datetime.now()
sent = cl.classify('sandwich is good')
#sent_prob = cl.prob_classify('sandwich is good')
accuracy = cl.accuracy(test)
print ("Classification: %s" % sent, 
	"\naccuracy: %s%%" % str(round(accuracy, 2) * 100),
	"\nprobability: N/A")
print("classify: %s" % (str(datetime.datetime.now() - ts)))

print("\n\nMaxEntClassifier\n====================")
ts = datetime.datetime.now()
cl = MaxEntClassifier(train)
print("training: %s" % (str(datetime.datetime.now() - ts)))
cs = datetime.datetime.now()
sent = cl.classify('sandwich is good')
sent_prob = cl.prob_classify('sandwich is good')
accuracy = cl.accuracy(test)
print ("sentiment: %s" % sent, 
	"\naccuracy: %s%%" % str(round(accuracy, 2)* 100),
	"\nprobability: %s%%" % str(round(sent_prob.prob(sent_prob.max()), 2) * 100))
print("classify: %s" % (str(datetime.datetime.now() - ts)))

print("\n\nNLTKClassifier\n======================")
ts = datetime.datetime.now()
cl = MyClassifier(train)
#cl = my_classifier(train)
#cl  =  NLTKClassifier(train)
print("training: %s" % (str(datetime.datetime.now() - ts)))
cs = datetime.datetime.now()
sent = cl.classify('sandwich is good')
#sent_prob = cl.prob_classify('sandwich is good')
accuracy = cl.accuracy(test)
print ("sentiment: %s" % sent, 
	"\naccuracy: %s%%" % str(round(accuracy, 2) * 100),
	"\nprobability: N/A")
print("classify: %s" % (str(datetime.datetime.now() - ts)))