Minmin_hello 2019-04-23 13:32 采纳率: 0%
浏览 1230

通过CountVectorizer和chi2特征提取,进行文本分类,准确率只有0.34正常吗

代码如下:

#encoding=utf-8

from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.svm import  SVC
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import accuracy_score,make_scorer
from sklearn.metrics import classification_report,accuracy_score
import numpy as n

categories = ['alt.atheism','talk.religion.misc','comp.graphics','sci.space']
data_train = fetch_20newsgroups(subset='train',categories=categories)
data_test = fetch_20newsgroups(subset='test',categories=categories)

count = CountVectorizer(stop_words='english',min_df=2)
train_feature = count.fit_transform(data_train.data)
print train_feature.toarray()
chi = SelectKBest(chi2,k=500)
train = chi.fit_transform(train_feature,data_train.target)
test_feature = count.fit_transform(data_test.data)
test = chi.fit_transform(test_feature,data_test.target)
# clf = MultinomialNB()
# classifier = clf.fit(train,data_train.target)
# test_accuracy = classifier.score(test,data_test.target)
# print test_accuracy

svc = SVC()
param_grid = {'kernel':('linear','poly'),'C':[0.1,1]}
grid_search = GridSearchCV(svc,param_grid=param_grid,cv=5,scoring=make_scorer(accuracy_score))
grid_search.fit(train,data_train.target)
y = grid_search.predict(test)
print grid_search.best_estimator_
print 'accuracy',accuracy_score(data_test.target,y)
print classification_report(data_test.target,y)

结果:
accuracy 0.34885439763488546
precision recall f1-score support

0 0.34 0.39 0.36 319
1 0.42 0.43 0.43 389
2 0.36 0.33 0.34 394
3 0.22 0.20 0.21 251

micro avg 0.35 0.35 0.35 1353
macro avg 0.34 0.34 0.34 1353
weighted avg 0.35 0.35 0.35 1353

求大佬指导一下 哪有问题吗

  • 写回答

1条回答 默认 最新

  • CSDN-Ada助手 CSDN-AI 官方账号 2022-09-09 19:35
    关注
    不知道你这个问题是否已经解决, 如果还没有解决的话:

    如果你已经解决了该问题, 非常希望你能够分享一下解决方案, 以帮助更多的人 ^-^
    评论

报告相同问题?

悬赏问题

  • ¥15 求差集那个函数有问题,有无佬可以解决
  • ¥15 【提问】基于Invest的水源涵养
  • ¥20 微信网友居然可以通过vx号找到我绑的手机号
  • ¥15 寻一个支付宝扫码远程授权登录的软件助手app
  • ¥15 解riccati方程组
  • ¥15 display:none;样式在嵌套结构中的已设置了display样式的元素上不起作用?
  • ¥15 使用rabbitMQ 消息队列作为url源进行多线程爬取时,总有几个url没有处理的问题。
  • ¥15 Ubuntu在安装序列比对软件STAR时出现报错如何解决
  • ¥50 树莓派安卓APK系统签名
  • ¥65 汇编语言除法溢出问题