期末大作业

一、boston房价预测

#1、导入数据集
from sklearn.datasets import load_boston
boston=load_boston()
x=boston.data
y=boston.target
print(x.shape)
print(y.shape)


#2、划分数据集
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

#将数据集划分成75%的训练集和25%的测试集
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25)

#查看数据集的shape
print("train dataset's shape is :",x_train.shape)
print("test dataset's shape is :",x_test.shape)


#3、多元线性回归模型，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.linear_model import LinearRegression
import matplotlib.pyplot as plt

linR=LinearRegression()
linR.fit(x_train,y_train)
print("系数:",linR.coef_,"\n截距:",linR.intercept_)

from sklearn.metrics import regression
y_predict=linR.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))
print("模型的分数:",linR.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)
x_poly_train=poly.fit_transform(x_train)
x_poly_test=poly.transform(x_test)

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

#预测
y_predict1=lrp.predict(x_poly_test)

#检测模型好坏
print("预测的均方误差:",regression.mean_squared_error(y_test,y_predict1))
print("预测的平均绝对误差:",regression.mean_absolute_error(y_test,y_predict1))
print("模型的分数:",lrp.score(x_poly_test,y_test))

多元线性回归模型

 

多项式回归模型

5. 比较线性模型与非线性模型的性能，并说明原因

 从预测的均方误差看，多项式回归模型的均方误差比多元线性回归模型小，从预测的平均绝对误差看，多项式回归模型的平均绝对误差

比多元线性回归模型小。说明多项式回归模型更好，更贴近样本点的分布。

 

二、中文文本分类

import os
import numpy as np
import sys
from datetime import datetime
import gc
path = 'F:\\python大作业\\0369'

# 导入结巴库
import jieba
# 导入停用词
with open(r'F:\python大作业\stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')

stopwords[0:10]

 

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

tokenList = []#处理好的新闻
targetList = []#新闻的标签
# 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):#根据根目录里的文件夹名找到对应的新闻类别的文件
    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))

processing(content)

# 划分训练集测试集
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB,MultinomialNB
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
#stratify=targetList划分处理好的新闻
x_train,x_test,y_train,y_test = train_test_split(tokenList,targetList,test_size=0.2,stratify=targetList)
# 转化为特征向量
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)
# 建立模型
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))
# 将预测结果和实际结果进行对比
import collections
import matplotlib.pyplot as plt
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['FangSong'] # 指定默认字体
mpl.rcParams['axes.unicode_minus'] = False # 解决图像无法显示中文的问题

#precision表示预测的精确度，recall表示实际的精确度，f1-score=2recallprecision/(recall+precision)

# 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)