r - GLM 适合(逻辑回归)到 SQL

Question

我们经常直接为线性或逻辑回归等简单模型对数据库中的数据进行评分。将所有系数从 R 正确地传输到 SQL 总是有点棘手。我想我可以为 glm 结果做一些 R 到 SQL 的翻译。对于数字变量，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 factor 变量起作用？我想将因素放在 case ... when ... then ... end 子句中。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，但没有看到任何有用的信息。是解析 names(fit$coef) 的唯一选项吗？

Answer 1

希望此功能有所帮助。今天写的，还没有测试所有角落 - 所以小心使用:)

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)
}