nltk-trainer-ngram-classifier-example-timed.py

import timeit                                                                                                                                                                                                    
import pickle                                                                                                                                                                                                  
import nltk.data                                                                                                                                                                                               
from nltk.util import ngrams                                                                                                                                                                                   

t0 = timeit.default_timer()                                                                                                                                                                                               
fin = open("C:/Users/ned/Desktop/gherkin.pickle","rb")                                                                                                                                                        
classifier = pickle.load(fin)                                                                                                                                                                                  
t1 = timeit.default_timer()                                                                                                                                                                                               
load_time = t1-t0                                                                                                                                                                                              
print "LOAD TIME: ", load_time                                                                                                                                                                                 

words = ['boring', 'and', 'stupid', 'movie']                                                                                                                                                                   
ngram_list = words + list(ngrams(words, 2)) + list(ngrams(words, 3))                                                                                                                                           
feats = dict([(word, True) for word in ngram_list])                                                                                                                                                            

t0 = timeit.default_timer()                                                                                                                                                                                               
result = classifier.classify(feats)                                                                                                                                                                            
t1 = timeit.default_timer()                                                                                                                                                                                               
classify_time = t1-t0                                                                                                                                                                                          
print "CLASSIFY TIME: ", classify_time                                                                                                                                                                         

print "RESULT: ", result      

nltk-trainer-ngram-classifier-example.py

import pickle                                                                                                                                                                                            
from nltk.util import ngrams                                                                                                                                                                                   
fin = open("C:/Users/ned/Desktop/gherkin.pickle","rb")                                                                                                                                                        
classifier = pickle.load(fin)                                                                                                                                                                                 
words = ['boring', 'and', 'stupid', 'movie']                                                                                                                                                                   
ngram_list = words + list(ngrams(words, 2)) + list(ngrams(words, 3))                                                                                                                                           
feats = dict([(word, True) for word in ngram_list])                                                                                                                                                          
dist = classifier.prob_classify(feats)                                                                                                                                                                         
#for sample in dist.samples():                                                                                                                                                                                  
#    print("%s probability: %f" % (sample, dist.prob(sample))) 
sample = "pos"                                                                                                                                                                                                                               
print("%s probability: %f" % (sample, dist.prob(sample)))