期末大作业

#1.回归模型预测波士顿房价
#导入load_boston数据
from sklearn.datasets import load_boston
data = load_boston()
#多元线性回归模型

from sklearn.model_selection import train_test_split

# 训练集与测试集划分为7:3
x_train,x_test,y_train,y_test = train_test_split(data.data,data.target,test_size=0.3)
print(x_train.shape,y_train.shape)

#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
#线性回归模型公式：y=^bx+^a
from sklearn.linear_model import LinearRegression
mlr = LinearRegression()
mlr.fit(x_train,y_train)
print('系数b',mlr.coef_,"\n截距a",mlr.intercept_)

#检测模型的好坏
from sklearn.metrics import regression
y_predict = mlr.predict(x_test)
#计算模型的预测指标
print('线性回归模型判断指数')
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))
#打印模型分数
print("模型的分数：",mlr.score(x_test,y_test))

#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。
# 多项式回归模型公式y = a0 + a1 * x + a2 * (x**2) + ... + an * (x ** n) + e
from sklearn.preprocessing import PolynomialFeatures
#多项式的训练集与测试集
poly2 =PolynomialFeatures(degree=2)
x_poly_train = poly2.fit_transform(x_train)
x_poly_test = poly2.transform(x_test)

#多项回归模型
mlrp=LinearRegression()
mlrp.fit(x_poly_train,y_train)

#预测值
y_predict2 = mlrp.predict(x_poly_test)
#检测模型预测指数的好坏
print("多项式回归模型判断指数")
print("预测的均方误差：",regression.mean_squared_error(y_test,y_predict2))
print("预测平均绝对误差：",regression.mean_absolute_error(y_test,y_predict2))
#打印模型分数
print("模型的分数：",mlrp.score(x_poly_test,y_test))

#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
#        i=1
        #遍历每个txt文件
        for f in files:
#            if i>50:
#                break
            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)
#            i+=1
#            print(content)
#            print(label)
            
#对数据进行预处理
with open(r'C:\Users\ASUS\Desktop\stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')
def processing(texts):
    # 去掉非法的字符
    texts = "".join([char for char in texts if char.isalpha()])
    # 用jieba分词
    texts = [text for text in jieba.cut(texts,cut_all=True) if len(text) >=2]
    # 去掉停用词
    texts = " ".join([text for text in texts if text not in stopwords])
    return texts
if __name__== '__main__':
    path=r'C:\Users\ASUS\Desktop\0369'
    read_txt(path)

#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))

# 将预测结果和实际结果进行对比
import collections
import matplotlib.pyplot as plt

# 统计测试集和预测集的各类新闻个数
testCount = collections.Counter(y_test)
predCount = collections.Counter(y_predict)
print('实际：',testCount,'\n', '预测', predCount)

# 建立标签列表，实际结果列表，预测结果列表，
nameList = list(testCount.keys())
testList = list(testCount.values())
predictList = list(predCount.values())
x = list(range(len(nameList)))
print("新闻类别：",nameList,'\n',"实际：",testList,'\n',"预测：",predictList)