期末大作业

# 多元线性回归模型
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.metrics import regression

# 波士顿房价数据集
data = load_boston()

# 划分数据集
x_train, x_test, y_train, y_test = train_test_split(data.data,data.target,test_size=0.3)

# 建立多元线性回归模型
mlr = LinearRegression()
mlr.fit(x_train,y_train)#学习
print('系数',mlr.coef_,"\n截距",mlr.intercept_)

# 检测模型好坏
y_predict = mlr.predict(x_test)#预测
# 计算模型的预测指标
print("预测的均方误差：", regression.mean_squared_error(y_test,y_predict))
print("预测的平均绝对误差：", regression.mean_absolute_error(y_test,y_predict))
# 打印模型的分数
print("模型的分数：",mlr.score(x_test, y_test))

# 多元多项式回归模型
# 多项式化
poly2 = PolynomialFeatures(degree=2)
x_poly_train = poly2.fit_transform(x_train)#先拟合数据，然后转化它将其转化为标准形式
x_poly_test = poly2.transform(x_test)#通过找中心和缩放等实现标准化

# 建立模型
mlrp = LinearRegression()
mlrp.fit(x_poly_train, y_train)

# 预测
y_predict2 = mlrp.predict(x_poly_test)
# 检测模型好坏
# 计算模型的预测指标
print("预测的均方误差：", regression.mean_squared_error(y_test,y_predict2))
print("预测的平均绝对误差：", regression.mean_absolute_error(y_test,y_predict2))
# 打印模型的分数
print("模型的分数：",mlrp.score(x_poly_test, y_test))

 

　　

 

#导入os包加载数据目录
import os
path = r'D:\shuju'
#停词库
with open(r'stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')

#对数据进行标准编码处理(encoding='utf-8')
import codecs
import jieba
#存放文件名
filePaths = []
#存放读取的数据
fileContents = []
#存放文件类型
fileClasses = []
#进行遍历实现转码读取处理并对每条新闻进行切分
for root, dirs, files in os.walk(path):#用os.walk获取需要的变量，并拼接文件路径再打开每一个文件
    for name in files:
        filePath = os.path.join(root, name)#将路径和文件串起来
        filePaths.append(filePath)#添加数据到外部容器
        fileClasses.append(filePath.split('\\')[2])
        
        f = codecs.open(filePath, 'r', 'utf-8')#获取新闻类别标签，并处理该新闻
        fileContent = f.read()
        fileContent = fileContent.replace('\n','')#去除转行符
        tokens = [token for token in jieba.cut(fileContent)]
        tokens = " ".join([token for token in tokens if token not in stopwords])#去除停用词
        f.close()
        fileContents.append(tokens)#添加关键字

 

import pandas;
all_datas = pandas.DataFrame({
    'fileClass': fileClasses,
    'fileContent': fileContents
})
print(all_datas)

　　

 

str=''
for i in range(len(fileContents)):
    str+=fileContents[i]
#TF-IDF算法
#统计词频
import jieba.analyse
keywords = jieba.analyse.extract_tags(str, topK=20, withWeight=True, allowPOS=('n','nr','ns'))
print(keywords )

 

from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
x_train,x_test,y_train,y_test = train_test_split(fileContents,fileClasses,test_size=0.3,random_state=0,stratify=fileClasses)
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)
from sklearn.naive_bayes import  MultinomialNB
clf= MultinomialNB().fit(X_train,y_train)
y_nb_pred=clf.predict(X_test)
#分类结果显示
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
 
print('nb_confusion_matrix:')
print(y_nb_pred.shape,y_nb_pred)#x_test预测结果
cm=confusion_matrix(y_test,y_nb_pred)#混淆矩阵
print('nb_classification_report:')
print(cm)

　　

 

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import GaussianNB,MultinomialNB
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report

x_train,x_test,y_train,y_test = train_test_split(fileContents,fileClasses,test_size=0.2,stratify=fileClasses)
# 转化为特征向量，这里选择TfidfVectorizer的方式建立特征向量。不同新闻的词语使用会有较大不同。
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)
# 建立模型,这里用多项式朴素贝叶斯，因为样本特征的a分布大部分是多元离散值
mnb = MultinomialNB()
module = mnb.fit(X_train, y_train)
#进行预测
y_predict = module.predict(X_test)
# 输出模型精确度
scores=cross_val_score(mnb,X_test,y_test,cv=5)
print("Accuracy:%.3f"%scores.mean())
# 输出模型评估报告
print("classification_report:\n",classification_report(y_predict,y_test))