NLTK的探索

import nltk
import random
from nltk.corpus import movie_reviews

documents = [(list(movie_reviews.words(fileid)), category)
             for category in movie_reviews.categories()
             for fileid in movie_reviews.fileids(category)]

random.shuffle(documents)

all_words = []

for w in movie_reviews.words():
    all_words.append(w.lower())

all_words = nltk.FreqDist(all_words)

word_features = list(all_words.keys())[:3000]

def find_features(document):
    words = set(document)
    features = {}
    for w in word_features:
        features[w] = (w in words)

    return features

print((find_features(movie_reviews.words('neg/cv000_29416.txt'))))

featuresets = [(find_features(rev), category) for (rev, category) in documents]

# set that we'll train our classifier with
training_set = featuresets[:1900]

# set that we'll test against.
testing_set = featuresets[1900:]

classifier = nltk.NaiveBayesClassifier.train(training_set)

print("Classifier accuracy percent:",(nltk.classify.accuracy(classifier, testing_set))*100)

classifier.show_most_informative_features(15)

######################
Most Informative Features
insulting = True neg : pos = 10.6 : 1.0
ludicrous = True neg : pos = 10.1 : 1.0
winslet = True pos : neg = 9.0 : 1.0
detract = True pos : neg = 8.4 : 1.0
breathtaking = True pos : neg = 8.1 : 1.0
silverstone = True neg : pos = 7.6 : 1.0
excruciatingly = True neg : pos = 7.6 : 1.0
warns = True pos : neg = 7.0 : 1.0
tracy = True pos : neg = 7.0 : 1.0
insipid = True neg : pos = 7.0 : 1.0
freddie = True neg : pos = 7.0 : 1.0
damon = True pos : neg = 5.9 : 1.0
debate = True pos : neg = 5.9 : 1.0
ordered = True pos : neg = 5.8 : 1.0
lang = True pos : neg = 5.7 : 1.0

#############################
##保存和恢复模型
save_classifier = open("naivebayes.pickle","wb")
pickle.dump(classifier, save_classifier)
save_classifier.close()

classifier_f = open("naivebayes.pickle", "rb")
classifier = pickle.load(classifier_f)
classifier_f.close()

使用nltk自带的继承于ClassifierI的投票器进行集体分类评估，模型包括nltk的classifier和sklearn的一些分类模型

读取文本并统计出前3000的频繁词汇，然后标记这3000个词的好坏，具体判断标准看这3000词是否是事先有好坏标记的词袋里的词

import nltk
import random
from nltk.corpus import movie_reviews
from nltk.classify.scikitlearn import SklearnClassifier
import pickle

from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC

from nltk.classify import ClassifierI
from statistics import mode

##定义VoteClassifier继承于ClassifierI
class VoteClassifier(ClassifierI):
    def __init__(self, *classifiers):
        self._classifiers = classifiers
    
   ##返回众数，即投票最多的项
    def classify(self, features):
        votes = []
        for c in self._classifiers:
            v = c.classify(features)
            votes.append(v)
        return mode(votes)
    
    ##定义置信区间
    def confidence(self, features):
        votes = []
        for c in self._classifiers:
            v = c.classify(features)
            votes.append(v)

        choice_votes = votes.count(mode(votes))
        conf = choice_votes / len(votes)
        return conf

documents = [(list(movie_reviews.words(fileid)), category)
             for category in movie_reviews.categories()
             for fileid in movie_reviews.fileids(category)]

random.shuffle(documents)

all_words = []

for w in movie_reviews.words():
    all_words.append(w.lower())

all_words = nltk.FreqDist(all_words)
##取出现最多的前3000个词
word_features = list(all_words.keys())[:3000]
##标记词的好坏
def find_features(document):
    words = set(document)
    features = {}
    for w in word_features:
        features[w] = (w in words)

    return features

#print((find_features(movie_reviews.words('neg/cv000_29416.txt'))))

featuresets = [(find_features(rev), category) for (rev, category) in documents]

training_set = featuresets[:1900]
testing_set =  featuresets[1900:]

#classifier = nltk.NaiveBayesClassifier.train(training_set)

classifier_f = open("naivebayes.pickle","rb")
classifier = pickle.load(classifier_f)
classifier_f.close()

print("Original Naive Bayes Algo accuracy percent:", (nltk.classify.accuracy(classifier, testing_set))*100)
classifier.show_most_informative_features(15)

MNB_classifier = SklearnClassifier(MultinomialNB())
MNB_classifier.train(training_set)
print("MNB_classifier accuracy percent:", (nltk.classify.accuracy(MNB_classifier, testing_set))*100)

BernoulliNB_classifier = SklearnClassifier(BernoulliNB())
BernoulliNB_classifier.train(training_set)
print("BernoulliNB_classifier accuracy percent:", (nltk.classify.accuracy(BernoulliNB_classifier, testing_set))*100)

LogisticRegression_classifier = SklearnClassifier(LogisticRegression())
LogisticRegression_classifier.train(training_set)
print("LogisticRegression_classifier accuracy percent:", (nltk.classify.accuracy(LogisticRegression_classifier, testing_set))*100)

SGDClassifier_classifier = SklearnClassifier(SGDClassifier())
SGDClassifier_classifier.train(training_set)
print("SGDClassifier_classifier accuracy percent:", (nltk.classify.accuracy(SGDClassifier_classifier, testing_set))*100)

##SVC_classifier = SklearnClassifier(SVC())
##SVC_classifier.train(training_set)
##print("SVC_classifier accuracy percent:", (nltk.classify.accuracy(SVC_classifier, testing_set))*100)

LinearSVC_classifier = SklearnClassifier(LinearSVC())
LinearSVC_classifier.train(training_set)
print("LinearSVC_classifier accuracy percent:", (nltk.classify.accuracy(LinearSVC_classifier, testing_set))*100)

NuSVC_classifier = SklearnClassifier(NuSVC())
NuSVC_classifier.train(training_set)
print("NuSVC_classifier accuracy percent:", (nltk.classify.accuracy(NuSVC_classifier, testing_set))*100)

voted_classifier = VoteClassifier(classifier,
                                  NuSVC_classifier,
                                  LinearSVC_classifier,
                                  SGDClassifier_classifier,
                                  MNB_classifier,
                                  BernoulliNB_classifier,
                                  LogisticRegression_classifier)

print("voted_classifier accuracy percent:", (nltk.classify.accuracy(voted_classifier, testing_set))*100)

print("Classification:", voted_classifier.classify(testing_set[0][0]), "Confidence %:",voted_classifier.confidence(testing_set[0][0])*100)
print("Classification:", voted_classifier.classify(testing_set[1][0]), "Confidence %:",voted_classifier.confidence(testing_set[1][0])*100)
print("Classification:", voted_classifier.classify(testing_set[2][0]), "Confidence %:",voted_classifier.confidence(testing_set[2][0])*100)
print("Classification:", voted_classifier.classify(testing_set[3][0]), "Confidence %:",voted_classifier.confidence(testing_set[3][0])*100)
print("Classification:", voted_classifier.classify(testing_set[4][0]), "Confidence %:",voted_classifier.confidence(testing_set[4][0])*100)
print("Classification:", voted_classifier.classify(testing_set[5][0]), "Confidence %:",voted_classifier.confidence(testing_set[5][0])*100)

####################################
out：

Original Naive Bayes Algo accuracy percent: 66.0
Most Informative Features
                thematic = True              pos : neg    =      9.1 : 1.0
                secondly = True              pos : neg    =      8.5 : 1.0
                narrates = True              pos : neg    =      7.8 : 1.0
                 layered = True              pos : neg    =      7.1 : 1.0
                 rounded = True              pos : neg    =      7.1 : 1.0
                 supreme = True              pos : neg    =      7.1 : 1.0
                  crappy = True              neg : pos    =      6.9 : 1.0
               uplifting = True              pos : neg    =      6.2 : 1.0
                     ugh = True              neg : pos    =      5.3 : 1.0
                 gaining = True              pos : neg    =      5.1 : 1.0
                   mamet = True              pos : neg    =      5.1 : 1.0
                   wanda = True              neg : pos    =      4.9 : 1.0
                   onset = True              neg : pos    =      4.9 : 1.0
               fantastic = True              pos : neg    =      4.5 : 1.0
                   milos = True              pos : neg    =      4.4 : 1.0
MNB_classifier accuracy percent: 67.0
BernoulliNB_classifier accuracy percent: 67.0
LogisticRegression_classifier accuracy percent: 68.0
SGDClassifier_classifier accuracy percent: 57.99999999999999
LinearSVC_classifier accuracy percent: 67.0
NuSVC_classifier accuracy percent: 65.0
voted_classifier accuracy percent: 65.0
Classification: neg Confidence %: 100.0
Classification: pos Confidence %: 57.14285714285714
Classification: neg Confidence %: 57.14285714285714
Classification: neg Confidence %: 57.14285714285714
Classification: pos Confidence %: 57.14285714285714
Classification: pos Confidence %: 85.71428571428571

#########################################