1 导入数据

# 导入数据
setwd("E:\\FOR_Study\\Daniel_File\\about_Study\\Junior\\Data_Science\\Data")
load("ch2_sample.RData")# 文件名读入
data <- read.table("v6.csv", header = T, sep = ",")

2 数据离散化

# 连续数据离散化
brks <-c (-1, -0.01, 2000, 6000, 10000, 20000, 50000, Inf)
labels <- c("Missing", "0-2000", "2000-6000", "6000-10000","10000-20000", "20000-50000", "above 50000")
dpus$WAGP.fix <- cut(dpus$WAGP.fix, breaks=brks, labels, include.lowest=T)x <- table(cut(HExer, c(-Inf, 7, 10, Inf)))# 按条件筛选记录
data <- subset(data,with(data,(bmi>=10)&(bmi<=133)&(age>=18)&(age<=150)&(glucose_max<=900)&(data$glucose_min<=900)&(tempc_min>=30)&(ph_min>=6)))

3 数据集划分

# 单次划分
set.seed(128767)
custdata_fix$gp <- runif(dim(custdata_fix)[1])
train_set <- subset(custdata_fix,custdata_fix$gp <= 0.9)
test_set <- subset(custdata_fix,custdata_fix$gp > 0.9)

4 常用函数

# ROC评价指标
library('ROCR')
calcAUC <-function(predcol,outcol) {perf <-performance(prediction(predcol,outcol==pos),'auc')as.numeric(perf@y.values)
}# 最大似然指标
loglikelihood<-function(y, py) {    pysmooth<-ifelse(py==0, 1e-12, ifelse(py==1, 1-1e-12, py))sum(y * log(pysmooth) + (1-y)*log(1 -pysmooth))   
}# 常见指标封装
accuracyMeasures<-function(pred, truth, name="model",value) {   dev.norm<--2*loglikelihood(as.numeric(truth), pred)/length(pred)ctable<-table(truth==1,pred=(pred>value))accuracy <-sum(diag(ctable))/sum(ctable)precision <-ctable[2,2]/sum(ctable[,2])recall <-ctable[2,2]/sum(ctable[2,])f1 <-2*precision*recall/(precision+recall)data.frame(model=name, accuracy=accuracy,precision=precision,recall=recall, f1=f1, dev.norm)  
}# roc曲线
library(ggplot2)
plotROC<-function(predcol,outcol) {perf<-performance(prediction(predcol,outcol==pos),'tpr','fpr')pf<-data.frame(FalsePositiveRate=perf@x.values[[1]],TruePositiveRate=perf@y.values[[1]])ggplot() + geom_line(data=pf,aes(x=FalsePositiveRate,y=TruePositiveRate)) +geom_line(aes(x=c(0,1),y=c(0,1)))
}

5 which函数

which能够帮助定位索引号，如返回当前列表中最大值对应的索引。

country[which(prob_age2030_god == max(prob_age2030_god))] 

如找列名对应的索引

which(names(data) == 'v225') 

6 group by函数

planes <- group_by(data_select, Market)
Market_category <- summarise(planes,         sum_sales = sum(Sales),sum_quantity = sum(Quantity),sum_profit = sum(Profit))     #求和
Market_category