哥斯拉mining过程

数据导入

setwd("D:/R")

或者直接getwd（）放入学校路径

A=read.csv('',header=TRUE)    有表头true  无 false

数据清理

#1.空值

data=data[complete.cases(data),]#去空值

data=data[!complete.cases(wine),]#显示空值

#2.去重复值

data=unique(data)

#3.查看缺失值

c=is.na(data)

#4.标记缺失值

data()    列出已载入的包中的所有数据集。

data(package = .packages(all.available = TRUE))       列出已安装的包中的所有数据集。

y = rep(c(1, 2, 3), c(20, 20, 20))

生成20个1 20个2 20个3

y=c(rep(-1,10),rep(1,10))

rep  重复函数    -1 重复出现十次

rnorm()函数产生一系列的随机数，随机数个数，均值和标准差都可以设定

sample 有无放回生成随机数https://blog.csdn.net/Heidlyn/article/details/56013509

cor() 函数计算两两变量之间的相关系数的矩阵

数据中心化：  scale(data,center=T,scale=F)

数据标准化：  scale(data,center=T,scale=T) 或默认参数scale(data)

进行pca之前一般先变量标准化

决策树 分类树 剪枝条

决策树（https://blog.csdn.net/u010089444/article/details/53241218）

ID3算法        选择信息增益最大的方向进行分支标准

https://blog.csdn.net/xiaohukun/article/details/78055132

信息增益：    信息熵-条件熵

在决策树算法的学习过程中，信息增益是特征选择的一个重要指标，它定义为一个特征能够为分类系统带来多少信息，带来的信息越多，说明该特征越重要，相应的信息增益也就越大。

https://www.zhihu.com/question/22104055

信息熵越大说明事件的无序程度越高

信息熵越小说明事件的有序程度越高

https://blog.csdn.net/wxn704414736/article/details/80512705

CART

gini越小 越纯

最小的切分点最为最优切分点    使用该切分点将数据切分为两个子集https://blog.csdn.net/wsp_1138886114/article/details/80955528

生成树枝+剪枝

https://www.cnblogs.com/karlpearson/p/6224148.html

监督学习【分类 回归  支持向量机】

非监督学习【聚类 主成分】

https://blog.csdn.net/chenKFKevin/article/details/70547549

无监督学习：仅有x值 来

两种主要类型无监督学习：聚类分析，主成分分析

定性的响应变量，定性变量也称为分类变量。

线性回归的因变量（Y）是连续变量，自变量（X）可以是连续变量，也可以是分类变量

logistic 回归与线性回归恰好相反，因变量一定要是分类变量，不可能是连续变量。分类变量既可以是二分类，也可以是多分类，多分类中既可以是有序，也可以是无序。

最小二乘法（https://www.zhihu.com/question/37031188）    

竖直投影下来 计算(y-ybar)^2最小

pca  降维工具

协方差矩阵——PCA实现的关键  

cov()  计算协方差in R

https://www.zhihu.com/question/41120789

pinkyjie.com/2011/02/24/covariance-pca/

prcomp(data,scale=TRUE)    scale对数据进行标准化处理

prcomp    pca主成分分析函数

混淆矩阵

https://www.zhihu.com/question/36883196

马氏距离。ROC曲线

蒙特卡洛仿真

支持向量机    （文本分类问题）

https://www.zhihu.com/question/21094489

knn 

kmeans 

https://zhuanlan.zhihu.com/p/31580379

Version:1.0StartHTML:0000000107EndHTML:0000000974StartFragment:0000000127EndFragment:0000000956

X=rbind(matrix(rnorm(20*50,mean = 0),nrow = 20)，matrix(rnorm(20*50,mean = 0.7),nrow = 20)，matrix(rnorm(20*50,mean = 1.4),nrow = 20))

X.pca=prcomp(X)

plot(X.pca[,1:2],col=c(rep(1,20),rep(2,20),rep(3,20)))

res=kmeans(X，centers=3)

true_class=c(rep(1,20),rep(2,20),rep(3,30))

table(res$cluster,true_class)

wine.case

https://www.kaggle.com/xvivancos/tutorial-clustering-wines-with-k-means

https://www.kaggle.com/maitree/wine-quality-selection

cov_sdc=cov(wine)

eigen(cov_sdc)

res.pca <- PCA(wine[,-12], graph = TRUE)

eig.val <- get_eigenvalue(res.pca)

eig.val

#数据导入

wine=read.csv()

wine= read.csv('winequality-white.csv'，header=TRUE)

wine=winequality_white

#data cleaning

wine = wine[complete.cases(wine),]

#PCA

library(stringr)

library(FactoMineR)

#绘图

res.pca <- PCA(wine[,-12], graph = TRUE)#delete Y=quality, plot the PCA graph

sdc=scale(wine)

pca.d=prcomp(sdc)

summary(pca.d)

#PCA降维

wine=wine[,-9:-11]

#查看定性变量分布，确定定性变量

hist(wine$quality)

#分类

wine0 = wine[wine$quality==3,]

wine1 = wine[wine$quality==4,]

wine2 = wine[wine$quality==5,]

wine3 = wine[wine$quality==6,]

wine4 = wine[wine$quality==7,]

wine5 = wine[wine$quality==8,]

#抽样

label0= sample(c(1:10),dim(wine0[1]),replace= TRUE)

label1= sample(c(1:10),dim(wine1[1]),replace= TRUE)

label2= sample(c(1:10),dim(wine2[1]),replace= TRUE)

label3= sample(c(1:10),dim(wine3[1]),replace= TRUE)

label4= sample(c(1:10),dim(wine4[1]),replace= TRUE)

label5= sample(c(1:10),dim(wine5[1]),replace= TRUE)

wine0_train = wine0[label0<=5,]

wine0_test = wine0[label0>5,]

wine1_train = wine1[label1<=5,]

wine1_test = wine1[label1>5,]

wine2_train = wine2[label2<=5,]

wine2_test = wine2[label2>5,]

wine3_train = wine3[label3<=5,]

wine3_test = wine3[label3>5,]

wine4_train = wine4[label4<=5,]

wine4_test = wine4[label4>5,]

wine5_train = wine5[label5<=5,]

wine5_test = wine4[label5>5,]

wine_train = rbind(wine0_train,wine1_train,wine2_train,wine3_train,wine4_train,wine5_train)

wine_test = rbind(wine0_test,wine1_test,wine2_test,wine3_test,wine4_test,wine5_test)

跑

library(nnet)

re_log = multinomial(quality~.,data= wine_train) 

将数据变为定性变量

wine_train$quality = as.factor(wine_train$quality)

######################################

library(rpart)

library(rattle)

library(rpart.plot)

#########################################

ID3  方法生成树枝（信息增益）

re_id3 <-rpart(quality~.,data=wine_train,method="class", parms=list(split="information"))

plot(re_id3)

########################################

CART 方法生成树枝（基尼系数）

re_CART = rpart(quality~.,data= wine_train,method = "class",parms = list(split="gini"),control=rpart.control(cp=0.000001))

plot(re_CART,main = "CART")

找到复杂度最小的值

min = which.min(re_CART$cptable[,4])

剪枝

re_CART_f = prune(re_CART,cp=re_CART$cptable[min,1])

pred_id3 = predict(re_id3,newdata = wine_test)

pred_CART = predict(re_CART,newdata = wine_test,type="class")

table(wine_test$quality,pred_CART)

wine_train$quality= as.factor(wine_train$quality)

随机森林

•library("randomForest")

•data.index = sample(c(1,2), nrow(heart), replace = T, prob = c(0.7, 0.3))

•train_data =heart[which(data.index == 1),]

•test_data =heart[which(data.index == 2),]

•n<-length(names(train_data))

•rate=c()

网格法

for (i in 1:(n-1))

{

  mtry=i

  for(j in (1:100))

  {

  set.seed(1234)

  rf_train=randomForest(as.factor(train_data$target)~.,data=train_data,mtry=i,ntree=j)

  rate[(i-1)*100+j]=mean(rf_train$err.rate) 

  }

}

z=which.min(rate)

print(z)

展示重要性

importance<-importance(heart_rf)

barplot(heart_rf$importance[,1],main="Input variable importance measure indicator bar chart")

box（）

importance(heart_rf,type=2)

varImpPlot(x=heart_rf,sort=TRUE,n.var=nrow(heart_rf$importance),main="scatterplot") #可视化

hist(treesize(heart_rf))

check model

pred<-predict(heart_rf,newdata=data.test)

pred_out_1<-predict(object=heart_rf,newdata=data.test,type="prob")

table<-table(pred,data.test$target)

sum(diag(table))/sum(table)

plot(margin(iris_rf,data.test$target))

----------------------------------------------------------------别管

wine$quality

linear regression

library(ggplot2) # Data visualization

library(readr) # CSV file I/O, e.g. the read_csv function

library(corrgram)

library(lattice) #required for nearest neighbors

library(FNN) # nearest neighbors techniques

library(pROC) # to make ROC curve

install.packages('corrgram')

library(corrgram)

---------------------------------------------------------------------------------

linear_quality = lm(quality ~ fixed acidity+volatile acidity+citric acid+residual sugar+chlorides+free sulfur dioxide+total sulfur dioxide+density, data=wine)

corrgram(wine, lower.panel=panel.shade, upper.panel=panel.ellipse)

wine$poor <- wine$quality <= 4

wine$okay <- wine$quality == 5 | wine$quality == 6

wine$good <- wine$quality >= 7

head(wine)

summary(wine)

KNN

class_knn10 = knn(train=wine[,1:8], test=wine[,1:8], cl=wine$good, k =10)

class_knn20 = knn(train=wine[,1:8],test=wine[,1:8], cl = wine$good, k=20)

table(wine$good,class_knn10)

table(wine$good,class_knn20)

wine123=winequality_white

wine123$poor <- wine$quality <= 4

wine123$okay <- wine$quality == 5 | wine$quality == 6

wine123$good <- wine$quality >= 7

library(rpart) #for trees

tree1 = rpart(good~  alcohol + sulphates+ pH , data = wine123, method="class")

rpart.plot(tree1)

summary(tree1)

pred1 = predict(tree1,newdata=wine123,type="class")

summary(pred1)

summary(wine123$good)

比较模型的准确度

tree2 = rpart(good~  alcohol + volatile acidity +citric acid+ pH , data = wine123, method="class")

tree2 = rpart(good ~ alcohol + volatile acidity + citric acid + sulphates, data = wine123, method="class")

rpart.plot(tree2)

tree2= rpart(good ~ alcohol + volatile acidity + citric acid + sulphates, data = wine123 ,method='class')

pred2 = predict(tree2,newdata=wine123,type="class")

summary(pred2)

summary(wine123$good)

信息熵计算

LDA

决策树

p187      chp4   power function

p212     chp5     boostrap

p215     chp5     loocv

p431     chp10    kmeans

一、变量的基本定义和基础操作

1. 数值型变量的赋值

  a = 5

2. 向量赋值

  x = c(1:6) , c()为生成向量对应的函数

3. 向量中元素的访问

  x = c(1:6)

 x[3] ,中括号中的数字代表所访问的数值在向量x中的位置。

  x[-3],负数的标度表示取补集，即返回向量x中除第3位以外的其他元素。

4. 矩阵的定义

  B =matrix(c(1:10),nrow=2,ncol=5,byrow=TRUE)

matrix()未定义矩阵的函数，括号中第一个位置为写入矩阵中的元素，nrow参数位行数，ncol参数位列数，byrow=TRUE，表示数据按行的顺序书写。byrow=FALSE  按照列的顺序书写

不打byrow 按照列来输入

5. 矩阵元素的访问

  B[1,] 访问矩阵中的第一行

  B[,2]  访问矩阵中的第二列

  B[2,1]访问矩阵第二行第一列的元素

  B[,2:5]访问矩阵2到5列的元素

  B[,-4]  访问矩阵中除第4列的元素

6. 常用统计函数

  sum()求括号中对象的各个元素和

  mean()求括号中对象元素的均值

  max()  求括号中对象元素中的最大值

  min()   求括号中对象元素中的最小值

7. 其他矩阵信息的提取

  dim(B)  返回矩阵的维度，第一个值为行数，第二个值为列数

  dim(B)[1]可访问矩阵的行

  dim(B)[2] 可访问矩阵的列数   1 代表行 2代表列

  length(B)返回对象的长度，（请自行测试返回值是行还是列）