期末大作业

# 多元线性回归模型
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split

# 波士顿房价数据集
data = load_boston()

# 划分数据集
x_train, x_test, y_train, y_test = train_test_split(data.data,data.target,test_size=0.3)

# 建立线性回归模型
from sklearn.linear_model import LinearRegression
bos_lg = LinearRegression()
bos_lg.fit(x_train,y_train)
print('系数',bos_lg.coef_,"\n截距",bos_lg.intercept_)

# 检测模型好坏
from sklearn.metrics import regression
y_predict = bos_lg.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：",bos_lg.score(x_test, y_test))
print('=================\n')
# 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
bos_lgp = LinearRegression()
bos_lgp.fit(x_poly_train, y_train)

# 预测
y_predict2 = bos_lgp.predict(x_poly_test)
# 检测模型好坏
# 计算模型的预测指标
print("预测的均方误差：", regression.mean_squared_error(y_test,y_predict2))
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
print("模型的分数：",bos_lgp.score(x_poly_test, y_test))

 

中文文本分类

 

#导入os包加载数据目录
import os
import jieba
path = r'D:\data'
#停词库
with open(r'd:\\stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')

import re
def processing(tokens):
    # 去掉非字母汉字的字符

    tokens = "".join([char for char in tokens if char.isalpha()])
    cc=re.compile(r'[\u4e00-\u9fa5]')           #中文的编码范围是：\u4e00-\u9fa5
    tokens="".join(cc.findall(tokens.lower()))
    #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 = []
# 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:
        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)                   #取各个文件夹的特征
        tokenList.append(processing(content))       #用def processing(tokens):处理好的


# 划分训练集测试集并建立特征向量,为建立模型做准备
# 划分训练集测试集
from sklearn.feature_extraction.text import TfidfVectorizer  #向量化
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB, MultinomialNB   #贝叶斯
from sklearn.model_selection import cross_val_score         #验证某个模型在某个训练集上的稳定性，输出k个预测精度
from sklearn.metrics import classification_report   #来分析不同类别的准确率，召回率，F1值

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，这里选择TfidfVectorizer的方式建立特征向量。不同新闻的词语使用会有较大不同。
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)

X_test = vectorizer.transform(x_test)

# 建立模型,这里用多项式朴素贝叶斯，因为样本特征的a分布大部分是多元离散值
mnb = MultinomialNB()
module = mnb.fit(X_train, y_train)

# 进行预测
y_predict = module.predict(X_test)   #用数据做特征
# 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
#显示主要分类指标的文本报告．在报告中显示每个类的精确度，召回率，F1值等信息。
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

# 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())

print("新闻类别：",nameList,'\n',"实际：",testList,'\n',"预测：",predictList)

 

 

 

　　

 

　　

#导入os包加载数据目录
import os
import jieba
path = r'D:\data'
#停词库
with open(r'd:\\stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')

import re
def processing(tokens):
    # 去掉非字母汉字的字符

tokens = "".join([char for char in tokens if char.isalpha()])
    cc=re.compile(r'[\u4e00-\u9fa5]')           #中文的编码范围是：\u4e00-\u9fa5
tokens="".join(cc.findall(tokens.lower()))
    #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 = []
# 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:
        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)                   #取各个文件夹的特征
tokenList.append(processing(content))       #用def processing(tokens):处理好的


# 划分训练集测试集并建立特征向量,为建立模型做准备
# 划分训练集测试集
from sklearn.feature_extraction.text import TfidfVectorizer  #向量化
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB, MultinomialNB   #贝叶斯
from sklearn.model_selection import cross_val_score         #验证某个模型在某个训练集上的稳定性，输出k个预测精度
from sklearn.metrics import classification_report   #来分析不同类别的准确率，召回率，F1值

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，这里选择TfidfVectorizer的方式建立特征向量。不同新闻的词语使用会有较大不同。
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)

X_test = vectorizer.transform(x_test)

# 建立模型,这里用多项式朴素贝叶斯，因为样本特征的a分布大部分是多元离散值
mnb = MultinomialNB()
module = mnb.fit(X_train, y_train)

# 进行预测
y_predict = module.predict(X_test)   #用数据做特征
# 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
#显示主要分类指标的文本报告．在报告中显示每个类的精确度，召回率，F1值等信息。
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

# 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())

print("新闻类别：",nameList,'\n',"实际：",testList,'\n',"预测：",predictList)