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))

D:\PY-chrame\venv\Scripts\python.exe D:/PY-chrame/da.py
(354, 13) (354,)
系数b [-1.09516478e-01  3.91540238e-02  5.06501937e-02  1.39431350e+00
 -2.18805816e+01  2.97403470e+00  1.05732778e-02 -1.41167412e+00
  3.15647470e-01 -1.38088168e-02 -1.05008483e+00  6.15406136e-03
 -5.53452057e-01] 
截距a 46.69144630560215
线性回归模型判断指数
预测的均方误差： 24.39136560804038
预测的平均绝对误差： 3.375744717006874
模型的分数： 0.7305566210865768
多项式回归模型判断指数
预测的均方误差： 10.004803145076025
预测平均绝对误差： 2.296647007952124
模型的分数： 0.8894802362404708

Process finished with exit code 0

2.新闻文本分类：

 

#导入数据
import os
import numpy as np
import sys
from datetime import datetime
import gc
path = 'E:\\258'

#导入jieba进行jieba分词
import jieba
# 导入停用词：
with open(r'D:\\stopsCN.txt',encoding='utf-8') as f:
    stopwords = f.read().split('\n')

def processing(tokens):
    # 去掉非字母汉字的字符
    tokens = "".join([char for char in tokens if char.isalpha()])
    # 结巴分词
    tokens = [token for token in jieba.cut(tokens,cut_all=True) if len(token) >=2]
    # 去掉停用词
    tokens = " ".join([token for token in tokens if token not in stopwords])
    return tokens

#存放数据列表
tokenList = []
#存放目标列表
targetList = []

for root,dirs,files in os.walk(path):  
    for f in files:
        filePath = os.path.join(root,f) 
        with open(filePath,encoding='utf-8') as f:
            content = f.read()
            # 获取新闻类别标签，并处理该新闻
            target = filePath.split('\\')[-2]
            targetList.append(target)
            tokenList.append(processing(content))

 

#划分数据集，并用TF-IDF来提取文本特征建立特征向量，且用高斯分布型,多项式型进行检测
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import GaussianNB,MultinomialNB
from sklearn.metrics import classification_report

#划分训练集与测试集7：3
x_train,x_test,y_train,y_test = train_test_split(tokenList,targetList,test_size=0.3,stratify=targetList)

#用TF-IDF来提取文本特征建立特征向量，
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train) 
X_test = vectorizer.transform(x_test)  
# 建立多项型模型进行检测
mnb = MultinomialNB()
module = mnb.fit(X_train, y_train)

#进行预测
y_predict = module.predict(X_test)
#交叉验证检测模型
from sklearn.model_selection import cross_val_score
scores=cross_val_score(mnb,X_test,y_test,cv=10)
print("Accuracy:%.3f"%scores.mean())
# 输出分类指标的文本报告
print("classification_report:\n",classification_report(y_predict,y_test))

 

# 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)