问打印lm或fastLm()模型的摘要而不打印系数
EN

Stack Overflow用户

提问于 2015-10-07 02:02:44

回答 1查看 1.8K关注 0票数 3

使用我自己的数据集，我有太多的系数。我只是想打印摘要，而不是(或部分)打印系数。

示例脚本：

lm.fit <- lm(iris$Sepal.Length ~ iris$Petal.Length)
summary(lm.fit)

输出：

> summary(lm.fit)

Call:
lm(formula = iris$Sepal.Length ~ iris$Petal.Length)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.24675 -0.29657 -0.01515  0.27676  1.00269 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)        4.30660    0.07839   54.94   <2e-16 ***
iris$Petal.Length  0.40892    0.01889   21.65   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4071 on 148 degrees of freedom
Multiple R-squared:   0.76, Adjusted R-squared:  0.7583 
F-statistic: 468.6 on 1 and 148 DF,  p-value: < 2.2e-16

期望产出：

Call:
lm(formula = iris$Sepal.Length ~ iris$Petal.Length)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.24675 -0.29657 -0.01515  0.27676  1.00269 

---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4071 on 148 degrees of freedom
Multiple R-squared:   0.76, Adjusted R-squared:  0.7583 
F-statistic: 468.6 on 1 and 148 DF,  p-value: < 2.2e-16

我知道我可以调用从下面提到的summary(lm.fit)$names中选择的names。但我需要的是相反的。没有系数的摘要。

> names(summary(lm.fit))
 [1] "call"          "terms"         "residuals"     "coefficients" 
 [5] "aliased"       "sigma"         "df"            "r.squared"    
 [9] "adj.r.squared" "fstatistic"    "cov.unscaled"

这个是可能的吗？如果是，怎么做？

编辑:实际上，我需要fastLm包中的RcppArmadillo。

我只是期望lm()和fastLm()的输出是相同的。@LyzandeR提供的代码非常适合lm()。

使用@LyzandeR的示例，我搜索并创建了以下代码片段，它替换了RcppArmadillo包提供的打印摘要。

print.summary.fastLm <- function(x, ...) {
    ## Alternate print summary
    ## Prints without coefficients
    cat("\nCall:\n")
    print(x$call)
    cat("\nResiduals:\n")
    print(x$residSum)
    cat("\n")

    #printCoefmat(x$coefficients, P.values=TRUE, has.Pvalue=TRUE)
    digits <- max(3, getOption("digits") - 3)
    cat("\nResidual standard error: ", formatC(x$sigma, digits=digits), " on ",
    formatC(x$df), " degrees of freedom\n", sep="")
    cat("Multiple R-squared: ", formatC(x$r.squared, digits=digits),
    ",\tAdjusted R-squared: ",formatC(x$adj.r.squared, digits=digits),
    "\n", sep="")
    invisible(x)
}

summary

回答 1

Stack Overflow用户

回答已采纳

发布于 2015-10-07 02:23:28

我稍微修改了print.summary.lm函数，只是注释掉了打印系数的部分(注释代码行如下所示)：

print.sum2 <-
  function (x, digits = max(3L, getOption("digits") - 3L), symbolic.cor = x$symbolic.cor, 
            signif.stars = getOption("show.signif.stars"), ...) 
  {
    cat("\nCall:\n", paste(deparse(x$call), sep = "\n", collapse = "\n"), 
        "\n\n", sep = "")
    resid <- x$residuals
    df <- x$df
    rdf <- df[2L]
    cat(if (!is.null(x$weights) && diff(range(x$weights))) 
      "Weighted ", "Residuals:\n", sep = "")
    if (rdf > 5L) {
      nam <- c("Min", "1Q", "Median", "3Q", "Max")
      rq <- if (length(dim(resid)) == 2L) 
        structure(apply(t(resid), 1L, quantile), dimnames = list(nam, 
                                                                 dimnames(resid)[[2L]]))
      else {
        zz <- zapsmall(quantile(resid), digits + 1L)
        structure(zz, names = nam)
      }
      print(rq, digits = digits, ...)
    }
    else if (rdf > 0L) {
      print(resid, digits = digits, ...)
    }
    else {
      cat("ALL", df[1L], "residuals are 0: no residual degrees of freedom!")
      cat("\n")
    }
    if (length(x$aliased) == 0L) {
      #cat("\nNo Coefficients\n")
    }
    else {
      if (nsingular <- df[3L] - df[1L]) {
        #cat("\nCoefficients: (", nsingular, " not defined because of singularities)\n", sep = "")
      }
      else {
         #  cat("\nCoefficients:\n")
      }
      coefs <- x$coefficients
      if (!is.null(aliased <- x$aliased) && any(aliased)) {
        cn <- names(aliased)
        coefs <- matrix(NA, length(aliased), 4, dimnames = list(cn, 
                                                                colnames(coefs)))
        coefs[!aliased, ] <- x$coefficients
      }
      #printCoefmat(coefs, digits = digits, signif.stars = signif.stars, na.print = "NA", ...)
    }
    cat("\nResidual standard error:", format(signif(x$sigma, 
                                                    digits)), "on", rdf, "degrees of freedom")
    cat("\n")
    if (nzchar(mess <- naprint(x$na.action))) 
      cat("  (", mess, ")\n", sep = "")
    if (!is.null(x$fstatistic)) {
      cat("Multiple R-squared: ", formatC(x$r.squared, digits = digits))
      cat(",\tAdjusted R-squared: ", formatC(x$adj.r.squared, 
                                             digits = digits), "\nF-statistic:", formatC(x$fstatistic[1L], 
                                                                                         digits = digits), "on", x$fstatistic[2L], "and", 
          x$fstatistic[3L], "DF,  p-value:", format.pval(pf(x$fstatistic[1L], 
                                                            x$fstatistic[2L], x$fstatistic[3L], lower.tail = FALSE), 
                                                         digits = digits))
      cat("\n")
    }
    correl <- x$correlation
    if (!is.null(correl)) {
      p <- NCOL(correl)
      if (p > 1L) {
        cat("\nCorrelation of Coefficients:\n")
        if (is.logical(symbolic.cor) && symbolic.cor) {
          print(symnum(correl, abbr.colnames = NULL))
        }
        else {
          correl <- format(round(correl, 2), nsmall = 2, 
                           digits = digits)
          correl[!lower.tri(correl)] <- ""
          print(correl[-1, -p, drop = FALSE], quote = FALSE)
        }
      }
    }
    cat("\n")
    invisible(x)
  }

现在如果你跑：

> print.sum2(summary(lm.fit))

Call:
lm(formula = iris$Sepal.Length ~ iris$Petal.Length)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.24675 -0.29657 -0.01515  0.27676  1.00269 

Residual standard error: 0.4071 on 148 degrees of freedom
Multiple R-squared:   0.76, Adjusted R-squared:  0.7583 
F-statistic: 468.6 on 1 and 148 DF,  p-value: < 2.2e-16