大作业初稿

#线性回归模型：建立13个变量与房价之间的预测模型，并检测模型好坏。
from sklearn.datasets import load_boston
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
boston=load_boston()#导入数据集
x = boston.data
y = boston.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)#划分训练集和测试集
lineR=LinearRegression()#线性模型
lineR.fit(x_train,y_train)
#判断模型的好坏
 
print('预测的准确率:',lineR.score(x_test,y_test))

#4. 多项式回归模型：建立13个变量与房价之间的预测模型，并检测模型好坏。
from sklearn.preprocessing import PolynomialFeatures
poly=PolynomialFeatures(degree=2)
from sklearn.linear_model import LinearRegression
lineR=LinearRegression()
x= boston.data
y = boston.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)#划分训练集和测试集
#多项式操作
x_train_poly=poly.fit_transform(x_train)
x_test_poly=poly.transform(x_test)
lineR.fit(x_train_poly,y_train)#建立模型
print('预测的准确率:',lineR.score(x_test_poly,y_test))

#图形化
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
lineR=LinearRegression()
lineR.fit(x_train_poly,y_train)
y_poly_pred=lineR.predict(x_test_poly)
plt.plot(y,y,'r')
plt.scatter(y_test,y_poly_pred)
plt.show()

#新闻文本分类
import os
import jieba
#读取文件内容
content=[]#存放新闻的内容
label=[]#存放新闻的类别
def read_txt(path):
    folder_list=os.listdir(path)#遍历data下的文件名
    for file in folder_list:
        new_path=os.path.join(path,file) #读取文件夹的名称，生成新的路径
        files=os.listdir(new_path)#存放文件的内容
        #遍历每个txt文件
        for f in files:
            with open(os.path.join(new_path,f),'r',encoding='UTF-8')as f: #打开txt文件
                temp_file=f.read()
            content.append(processing(temp_file))
            label.append(file)
            print(content)
            print(label)

#划分训练集和测试，用TF-IDF算法进行单词权值的计算
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
tfidf= TfidfVectorizer()
x_train,x_test,y_train,y_test=train_test_split(content,label,test_size=0.2)
X_train=tfidf.fit_transform(x_train)
X_test=tfidf.transform(x_test)
#构建贝叶斯模型
from sklearn.naive_bayes import MultinomialNB #用于离散特征分类，文本分类单词统计，以出现的次数作为特征值
mulp=MultinomialNB ()
mulp_NB=mulp.fit(X_train,y_train)
#对模型进行预测
y_predict=mulp.predict(X_test)
# # 从sklearn.metrics里导入classification_report做分类的性能报告
from sklearn.metrics import classification_report
print('模型的准确率为：', mulp.score(X_test, y_test))
print('classification_report:\n',classification_report(y_test, y_predict))