[Rscript]数据框的统计量汇总

1、向量是有名字的，可以使用names()查看或者unname()去除

2、构建空的向量或者空的数据框接收循环结果的时候，必须把构建步骤放在循坏之外，否则每次循环都会生成新的空的数据框，最终得到的数据框会有很多零值。

setwd("E:/天睿TERADATA/data_analysis")
rawdata<-read.csv("test_data.csv")

#筛选出待分析数据（只挑选数值型变量）,并用p_1与p_99替换异常值:
data_prepare<-function(dta){
  is_numeric_logitcal<-vector(length=ncol(dta))
  for(i in 1:ncol(dta)){
    is_numeric_logical[i]<-is.numeric(dta[,i])
  }
  newdata<-dta[,!is_numeric_logit]
  for(i in 1:ncol(dta)){
    p_1<-unname(quantile(dta[,i],0.01))
    p_99<-unname(quantile(dta[,i],0.99))
    dta[,i]<-ifelse(dta[,i]<p_1,p_1,
                     ifelse(dta[,i]>p_99,p_99,dta[,i]))
  
  }
  return(dta)
}

#导出新表：
newdata<-data_prepare(rawdata)
write.csv(newdata,"newdata.csv")

#得到统计量数据框statistic_framework
statistic_framework<-function(dta){
  data_statistic<-function(variable,na.omit=T){
    if(na.omit)
      variable<-variable[!is.na(variable)]                                 #是否忽视缺失值
    n<-length(variable)
    nmiss<-length(variable[is.na(variable)])
    nobs<-n-nmiss
    min<-min(variable)
    max<-max(variable)
    mean<-mean(variable)
    sd<-sd(variable)
    quantile_num<-c(0.01,0.02,0.03,0.04,0.05,0.1,0.15,0.2,0.25,0.3,0.35,0.4,0.45,0.5,0.55,0.6,0.65,
                    0.7,0.75,0.8,0.85,0.9,0.91,0.92,0.93,0.94,0.95,0.96,0.97,0.98,0.99,1)
    px<-vector(mode="numeric",length=length(quantile_num))
    for(i in 1:length(quantile_num)){
       px[i]<-unname(quantile(variable,quantile_num[i]))
    }
    statistic_vector<-c(n,nmiss,nobs,min,max,mean,sd,px)
    return(statistic_vector)
  }
  ncol_result<-length(data_statistic(dta[,1]))
  result<-as.data.frame(matrix(0,nrow=ncol(dta),ncol=ncol_result))
  rownames(result)<-colnames(dta)
    for(i in 1:ncol(dta)){
        result[i,]<-data_statistic(dta[,i])
    }
  colnames(result)<-c("n","nmiss","nobs","min","max","mean","sd","p_1","p_2","p_3","p_4","p_5","p_10",
                      "p_15","p_20","p_25","p_30","p_35","p_40","p_45","p_50","p_55","p_60","p_65",
                      "p_70","p_75","p_80","p_85","p_90","p_91","p_92","p_93","p_94","p_95","p_96","p_97",
                      "p_98","p_99","p_100")
  return(result)
}

#查看测试数据结果：
statistic_result<-statistic_framework(rawdata)
write.csv(statistic_result,"statistic_result.csv")