大作业

一、boston房价预测

#多元线性回归模型 
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
#波士顿房价数据 
data = load_boston()
#划分数据集 
 7 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
from sklearn.linear_model import LinearRegression
mlr = LinearRegression()
mlr.fit(x_train,y_train)
w = mlr.coef_
b = mlr.intercept_
print("系数",w,"\n截距",b)

#检测模型好坏

from sklearn.metrics import regression
y_predict = mlr.predict(x_test)

#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 
from sklearn.preprocessing import PolynomialFeatures 
poly2 = PolynomialFeatures(degree = 2) 
x_poly_train = poly2.fit_transform(x_train) 
x_poly_test = poly2.transform(x_test) 
#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("预测的均方差：",regression.mean_squared_error(y_test,y_predict2)) 
44 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 
46 print("模型的分数：",mlrp.score(x_poly_test,y_test))

 

多元线性回归模型结果：

多元多项式回归模型结果：

 

二、中文文本分类

path ='C:\\Users\\Administrator\\Desktop\\中文文本分类\\0369data'

import os
for root,dirs,files in os.walk(path):
    for f in files:
        fp = os.path.join(root,f)
        with open(fp,'r',encoding='utf-8') as f:
            content = f.read() # 获取文本

with open(r'C:\Users\Administrator\Desktop\中文文本分类\stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')
import jieba
def processing(tokens):
    tokens = "".join([char for char in tokens if char.isalpha()]) #去掉非字母汉字的字符
    tokens = [token for token in jieba.cut(tokens,cut_all=True) if len(token)>=2] #结巴分词(长度大于等于2)
    tokens = " ".join([token for token in tokens if token not in stopwords])#去掉停用词
    return tokens

contentList = [] #存储经过处理以后的文本
classifyList = [] #存储分类出来的新闻类别
#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 root,dirs,files in os.walk(path):
    for f in files:
        fp = os.path.join(root,f)
        with open(fp,encoding='utf-8') as f:
            content = f.read()
        #h获取新闻类别标签，并处理该新闻
        classify = fp.split("\\")[-2]
        classifyList.append(classify)
        contentList.append(processing(content))

import pandas
datas = pandas.DataFrame({
    'classifyList': classifyList,
    'contentList':  contentList
})
print(datas)


from sklearn.model_selection import train_test_split
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(contentList,classifyList,test_size=0.3,stratify = classifyList ) #划分测试集训练集


#转化为特征向量
tfv = TfidfVectorizer() #用TfidfVectorizer的方法建立特征向量
X_train = tfv.fit_transform(x_train) #对训练集建模
X_test = tfv.transform(x_test) 

#用朴素贝叶斯建立模型，处理分散型数据
mnb = MultinomialNB()
module = mnb.fit(X_train,y_train)

y_pred = module.predict(X_test) #对测试集进行预测
scores = cross_val_score(mnb,X_test,y_test,cv = 5) #输出模型精确度
print("Accuracy:%.3f"%scores.mean())
print("classification_report:\n",classification_report(y_pred,y_test))