合并两个包含同样行名（rowname相同或者某一列包含相同内容）的数据集
直接上code，折腾了快一下午
library(readr)
library(tidyverse)
dfov <- read_csv("Downloads/xxx/OEC GTEx TCGA/Ovary_exp_normalpluscancer_all_withID.csv")
hippogene <- read_csv("Downloads/xxx/hippogene.csv")
dfov <- data.frame(dfov)
#...
如何添加c1~c4？r1~r5?
coln = c(”c1”,”c2”,”c3”,”c4”)
rown = c(”r1”,”r2”,”r3”,”r4”,”r5”)
colnames(datamatrix) = coln
rownames(datamatrix) = rown
https://blog.csdn.net/weixin_33922670/article/details/85903958
ghirow2 <- fread("~/Downloads/ghirow2.csv")
##打开准备用于替换colnames的数据列
cnames <- as.character(ghirow2$V2)
##转换数据列（单列）为as.character! 这是关键
colnames(exp_brain) <- cnames
##转换成功
以上为自己实践揣摩出来的，享受代码之美！
subset(x, subset, select, drop = FALSE, ...)
&多条件查询
select 显示指定列
selectresult=subset(df1,name=="aa" & sex=="f",select=c(age,sex))
负号排除指定列
selectresult=subset(df1,name=="aa" & sex=="f",select=c(-age,-sex))
代码: 参数 备注
substr(s, first, last) :first和last为截取的起始位置。必须设置参数first和last，否则出错。
substring(s, first, last = 1000000): first和last为截取的起始位置。可以只设置first参数，last参数缺省时则默认为1000000，指字符串的最大长度。
data
data<-na.omit(data)
##去除所有含NA的行
data<-subset(data,value1!="NA")
##去除value1为这一列中含有NA的行
> tmp1=as.data.frame(lapply(tmp1,as.numeric))
错误: The size of the connection buffer (131072) was not large enough
to fit a complete line:
* Increase it by setting `Sys.setenv("VROOM_CONNECTION_SIZE")`
解决办法：
Sys.setenv("VROOM_CONNECTION_SIZE"=131072*6)
>df_train <- mutate(df, df_train_sixgenes$scores = df_train_sixgenes$PMCH*( -0.6294544) + df_train_sixgenes$IFNB1*( -0.3168858) + df_train_sixgenes$IGF2*( 0.1835164) + df_train_sixgenes$PYCR1*( -0.3942564))
>df_train_sixgenes$scores <- df_train_sixgenes...
> library(survminer)
> fit <- survfit(Surv(futime, fustatus)~scores_by2,data = dtrain_score)
> p <- ggsurvplot(fit, conf.int=F, pval=T, risk.table=T, legend.labs = c('High-Risk','Low-Risk'),
legend.title='Risk Score', palette = c("dodgerblue2","orchid2...
> dtrain_score$scores_by2 <- ifelse(dtrain_score$scores > median(dtrain_score$scores),'High-Risk','Low-Risk')
> dtest_score$scores_by2 <- ifelse(dtest_score$scores > median(dtest_score$scores),'High-Risk','Low-Risk')
> tmp1 <- df_train[c(1:7)]
> tmp2 <- df_train[c(colnames = 'PMCH',colnames = 'IFNB1',colnames = 'IGF2',colnames = 'PYCR1',colnames = 'FOXO1',colnames = 'PPARG')]
> tmp <- cbind(tmp1,tmp2
以上代码需要在as.data.frame中操作，matrix...
