Question

我们经常在数据库中直接为线性或逻辑回归等简单模型评分数据。将所有系数从R正确传输到SQL总是有点棘手。我以为我可以为glm结果做一些R到SQL的翻译。对于数值变量，这非常简单：

library(rpart)

fit <- glm(Kyphosis ~ ., data = kyphosis, family = binomial())

coefs <- fit$coef[2:length(fit$coef)]
expr <- paste0('1/(1 + exp(-(',fit$coef[1], '+', paste0('(', 
               coefs, '*', names(coefs), ')', collapse = '+'),')))')

print(expr)

a <- with(kyphosis, eval(parse(text = expr)))
b <- predict(fit, kyphosis, type = 'response')
names(b) <- NULL
all.equal(a, b)

生成的expr为：1/(1 + exp(-(-2.03693352129613+(0.0109304821420485*Age)+(0.410601186932733*Number)+(-0.206510049753697*Start))))。

有没有办法让这个变量适用于factor变量？我想在case ... when ... then ... end条款中加入因子。假设我们有以下模型：

kyphosis$factor_variable <- rep(LETTERS[1:5],20)[1:81]
fit <- glm(Kyphosis ~ ., data = kyphosis, family = binomial())

我正在浏览fit的结构，但看不到任何有用的内容。是解析names(fit$coef)的唯一选择吗？

Answer 1

希望这个功能有所帮助。今天写了它并且没有经过各个角落的测试 - 所以要小心使用：）

glm_to_sql <- function(glmmodel) {
  xlev <- data.frame(unlist(glmmodel$xlevels))
  xlev$xlevrowname <- rownames(xlev)
  rownames(xlev) <- NULL
  colnames(xlev)[1] <- "xlevel"
  if (nrow(xlev)==0){xlev <- data.frame(xlevrowname=character(0), xlevel=character(0), stringsAsFactors=F)}

  modcoeffs <- data.frame(unlist(glmmodel$coefficients))
  modcoeffs$coeffname <- rownames(modcoeffs)
  rownames(modcoeffs) <- NULL
  colnames(modcoeffs)[1] <- "coeffvalue"

  coeffmatrix <- sqldf("select a.*,b.*,'' as sqlstr, 
                       substr(coeffname,1,instr(coeffname, xlevel)-1) as varname 
                       from modcoeffs a left join xlev b on coeffname like '%' || xlevel and xlevrowname like substr(coeffname,1,instr(coeffname, xlevel)-1) || '%'")

  for (i in 1:nrow(coeffmatrix)) {
    if(coeffmatrix$coeffname[i] == "(Intercept)") 
    {
      coeffmatrix$sqlstr[i] <- coeffmatrix$coeffvalue[i]
    } else if (is.na(coeffmatrix$xlevel[i]) ) {    
      coeffmatrix$sqlstr[i] <- paste("(",coeffmatrix$coeffvalue[i],"*",coeffmatrix$coeffname[i],")")
    } else {
      coeffmatrix$sqlstr[i] <- paste("(case when ",coeffmatrix$varname[i],"='",coeffmatrix$xlevel[i], "' THEN ",coeffmatrix$coeffvalue[i]," ELSE 0 END)",sep="")
    }

    if (i==1){x.sql0 <- coeffmatrix$sqlstr[i]} else {x.sql0 <- paste(x.sql0,"+",coeffmatrix$sqlstr[i])}
  }

  if (glmmodel$family$link == "logit") {
    x.sql <- paste("1/(1 + exp(-(",x.sql0,")))")  
  } else if (glmmodel$family$link == "identity") {
    x.sql <- x.sql0
  }

  return(x.sql)
}

GLM适合（逻辑回归）到SQL

1 个答案: