期末大作业

一、boston房价预测

# 1.读取数据集
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
data = load_boston

# 2.训练集与测试集划分
x_train, x_test, y_train, y_test = train_test_split(data.data,data.target,test_size=0.3)

#3.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。
#建立模型
from sklearn.linear_model import LinearRegression
mlr = LinearRegression()
mlr.fit(x_train,y_train)
print('系数',mlr.coef_,"\n截距",mlr.intercept_)

#检测模型好坏
from sklearn.metrics import regression
y_predict = mlr.predict(x_test)

print('线性回归模型：')
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：",mlr.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

# 多项式化
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)

# 测模型好坏
y_predict2 = mlrp.predict(x_poly_test)

print("多项式回归模型：")
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))

print("模型的分数：",mlrp.score(x_poly_test,y_test))

#5.比较线性模型与非线性模型的性能，并说明原因
    多项式回归模型误差比线性模型小，而且是一条平滑的曲线，对样本的拟合程度较高，所以非线性模型的性能比线性的性能要好。

 

 二、中文文本分类

import os
import numpy as np
import sys
from datetime import datetime
import gc
path = 'E:\\147'

import jieba
# 导入停用词：
with open(r'E:\\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

tokenList = []
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))

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

# 划分训练集和测试集
x_train,x_test,y_train,y_test = train_test_split(tokenList,targetList,test_size=0.3,stratify=targetList)

# 文本特征提取
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)

from sklearn.naive_bayes import MultinomialNB
# 多项式朴素贝叶斯
mnb = MultinomialNB()
module = mnb.fit(X_train,y_train)

y_predict = module.predict(X_test)
# 对数据进行5次分割
scores=cross_val_score(mnb,X_test,y_test,cv=5)
print("Accuracy:%.3f"%scores.mean())
print("classification_report:\n",classification_report(y_predict,y_test))

 

targetList.append(target)
print(targetList[0:10])
tokenList.append(processing(content))
tokenList[0:10]

import collections
# 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)