阿狗工具

1. 机器学习的训练集和验证集拆分

需要一个R包：caret

代码：

library(caret)

set.seed(12)

#按照75%的比例拆分数据集，data为原始数据框，用于拆分的列名为Name

data_index<-createDataPartition(data$Name, p=0.75)

data_train<-data[data_index$Resample1,]

data_test<-data[-data_index$Resample1,]

2. PCA降维分析

library(psych)

1) 寻找最适PCA值

parpca<-fa.parallel(data,fa="pc")

2) 假设计算出来最佳主成分个数为40，提取前40个主成分用于后续分析

ETHpca2 <- principal(ETHims,nfactors = 40)

ETHpca40 <-predict.psych(ETHpca2,ETHims)

dim(ETHpca40)

3) 画图展示前50个pc的结果

pcanum <- 50

plotdata <- data.frame(x = 1:pcanum,pc.values =parpca$pc.values[1:pcanum])ggplot(plotdata,aes(x = x,y = pc.values))+

theme_bw()+geom_point(colour ="red")+geom_line(colour ="blue")+labs(x ="Componet Number")

3. KNN分析

1) 简介 

使用caret的knn3包来进行KNN分析。KNN算法原理见：https://blog.csdn.net/weixin_45014385/article/details/123618841

ETHknn <- knn3(x = train_ETH, y = train_lab, k = 5)

寻找最佳临近数：

set.seed(123)

trcl <- trainControl(method ="cv", number = 5)

trgrid <- expand.grid(k = seq(1, 25, 2))

ETHknnFit <- train(x = train_ETH, y = train_lab,method ="knn",trControl = trcl, tuneGrid = trgrid)

2) 代码示例：

library(MASS)

data(biopsy)

str(biopsy)

biopsy<-biopsy[,-1]

names(biopsy)<-c("thick","u.size","u.shape","adhsn","s.size","nucl","chrom","n.nuc",

                "mit","class")

df<-na.omit(biopsy)

df$class<-factor(df$class,levels=c("benign","malignant"))

round(prop.table(table(df$class))*100,digits=1)

set.seed(123)

ind<-sample(1:2,nrow(df),replace=T,prob=c(0.7,0.3))

train<-df[ind==1,]

test<-df[ind==2,]

install.packages("class")

library(class)

install.packages("gmodels")

library(gmodels)

library(psych)

library(caret)

library(Metrics)

train_data<-train[,1:9]

train_class<-train[,10]

test_data<-test[,1:9]

test_class<-test[,10]

knn_result<-knn3(x=train_data,y=train_class,k=7)

test_pre<-predict(knn_result,test_data,type="class")

accuracy(test_class,test_pre)

#find proper k value

set.seed(123)

trcl<-trainControl(method="cv",number=5)

trgrid<-expand.grid(k=seq(1,50,2))

knnFit<-train(x=train_data,y=train_class,method="knn",trControl=trcl,tuneGrid=trgrid)

plot(knnFit,main="KNN")

4. 神经网络

1) 使用的R包：neuralnet

library(neuralnet)