NLTK朴素贝叶斯,文本分类代码示例 采样 SMSSpamCollection数据集下载

https://stackoverflow.com/

文本分类代码 编译通过

 

import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import csv
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
import sklearn.metrics as metrics
from sklearn import tree
from sklearn.linear_model import SGDClassifier
from sklearn.svm import LinearSVC
from sklearn.ensemble import RandomForestClassifier


# 文本清洗预处理
def preprocessing(text):
    # text = text.encode("gbk").decode("utf8")
    # tokons to word 句子标记解析  单词标记解析
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]
    # print("单词标记解析：", tokens)
    # 停用词删除
    stop = stopwords.words('english')
    tokens = [token for token in tokens if token not in stop]
    # print("停用词删除", tokens)
    # 单词字数小于3删除 并转换成小写
    tokens = [word.lower() for word in tokens if len(word) >= 3]
    # print("字数小于3删除", tokens)
    # lemmatize
    # 把（文中的词）按屈折变化形式（或异体形式）进行归类
    lemter = WordNetLemmatizer()