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 #########################################
NLTK的探索的更多相关文章
- 探索 Python、机器学习和 NLTK 库 开发一个应用程序,使用 Python、NLTK 和机器学习对 RSS 提要进行分类
挑战:使用机器学习对 RSS 提要进行分类 最近,我接到一项任务,要求为客户创建一个 RSS 提要分类子系统.目标是读取几十个甚至几百个 RSS 提要,将它们的许多文章自动分类到几十个预定义的主题领域 ...
- NLTK在自然语言处理
nltk-data.zip 本文主要是总结最近学习的论文.书籍相关知识,主要是Natural Language Pracessing(自然语言处理,简称NLP)和Python挖掘维基百科Infobox ...
- NLTK学习笔记(五):分类和标注词汇
目录 词性标注器 标注语料库 表示已经标注的标识符:nltk.tag.str2tuple('word/类型') 读取已经标注的语料库 名词.动词.形容词等 尝试找出每个名词类型中最频繁的名词 探索已经 ...
- 使用Python中的NLTK和spaCy删除停用词与文本标准化
概述 了解如何在Python中删除停用词与文本标准化,这些是自然语言处理的基本技术 探索不同的方法来删除停用词,以及讨论文本标准化技术,如词干化(stemming)和词形还原(lemmatizatio ...
- 【探索】机器指令翻译成 JavaScript
前言 前些时候研究脚本混淆时,打算先学一些「程序流程」相关的概念.为了不因太枯燥而放弃,决定想一个有趣的案例,可以边探索边学. 于是想了一个话题:尝试将机器指令 1:1 翻译 成 JavaScript ...
- 【探索】利用 canvas 实现数据压缩
前言 HTTP 支持 GZip 压缩,可节省不少传输资源.但遗憾的是,只有下载才有,上传并不支持.如果上传也能压缩,那就完美了.特别适合大量文本提交的场合,比如博客园,就是很好的例子. 虽然标准不支持 ...
- 探索C#之6.0语法糖剖析
阅读目录: 自动属性默认初始化 自动只读属性默认初始化 表达式为主体的函数 表达式为主体的属性(赋值) 静态类导入 Null条件运算符 字符串格式化 索引初始化 异常过滤器when catch和fin ...
- Mysql事务探索及其在Django中的实践(二)
继上一篇<Mysql事务探索及其在Django中的实践(一)>交代完问题的背景和Mysql事务基础后,这一篇主要想介绍一下事务在Django中的使用以及实际应用给我们带来的效率提升. 首先 ...
- Linux学习之探索文件系统
Linux,一起学习进步- ls With it, we can see directory contents and determine a variety of important file ...
随机推荐
- java接口的意义
java当中继承一个接口,要重写他的方法的话,那为什么还要多此一举的去实现一个接口呢? 直接把方法写在类当中不就可以了?就是说去掉类名后面的Implements 接口 ,可以不可以呢? 接口的最主要的 ...
- NTP时钟同步学习记录
--1 要点回顾 . 1. NTP唯一配置文件:/etc/ntp.conf . 2. NTP系统日志记录:/var/log/ntp . 3. ntp.conf简要介绍 - 利用 restrict 来管 ...
- Django之模板语言(二)-----Filter
1.其他常用的模板语言: 通过模板语言可以让前端页面显示数据,数据可以是基本数据类型,也可以是对象亦或者对象的列表,结合着模板中的for.if等配合使用. 要注意前端页面中,出现没有后端数据的情况,随 ...
- 架构发展史Spring Cloud
转自:https://www.iteye.com/news/32734 Spring Cloud作为一套微服务治理的框架,几乎考虑到了微服务治理的方方面面,之前也写过一些关于Spring Cloud文 ...
- 2018-8-10-dotnet-从入门到放弃的-500-篇文章合集
title author date CreateTime categories dotnet 从入门到放弃的 500 篇文章合集 lindexi 2018-08-10 19:16:52 +0800 2 ...
- php 随意参数方法的使用
1, 用到的PHP函数: func_get_arg() / func_get_args()/ func_num_args 2, func_get_arg(index) :根据索引取得参数具体值 ...
- vector以及array和数组
//比较数组.vector.array #include <iostream> #include <vector> #include <array> #includ ...
- HZOI20190828模拟32题解
题面:https://www.cnblogs.com/Juve/articles/11428730.html chinese: 考虑$\sum\limits_{i=0}^{n*m}i*f_i$的意义: ...
- 软件-浏览器-GoogleChrome:Google Chrome
ylbtech-软件-浏览器-GoogleChrome:Google Chrome Google Chrome是一款由Google公司开发的网页浏览器,该浏览器基于其他开源软件撰写,包括WebKit, ...
- Leetcode438.Find All Anagrams in a String找到字符串中所有字母异位词
给定一个字符串 s 和一个非空字符串 p,找到 s 中所有是 p 的字母异位词的子串,返回这些子串的起始索引. 字符串只包含小写英文字母,并且字符串 s 和 p 的长度都不超过 20100. 说明: ...