如何在数据框中找到两列的异常值

Question

我需要获取每种变量2和变量3的变量1的异常值总数，然后将其显示在表中。它还需要仅显示variable4大于1.5的情况。我有它的工作，但我认为我的代码有问题，因为每个的输出仅为0，这是不正确的。

当我执行boxplot.stats（df $ variable1）$ out时，会得到大量异常值。但是，当我使用下面的代码时，每个代码只说0。

high <- mean(df$variable1) + sd(df$variable1) * 3
low <- mean(df$variable1) - sd(df$variable1) * 3

df%>%
  filter(varaible4>1.5)%>%
     group_by(variable2, variable3) %>% 
       tally(variable1 < low ||variable1 > high)

表中显示了变量2和变量3的每种类型...但是计数仅表示0。

Answer 1

也许您可以使用scale代替定义high和low阈值并使用tally。

这是基于一些随机数据的实现：

library(dplyr)

df = data.frame(variable1 = runif(100,1,10),
                variable2 = round(runif(100,1,3)),
                variable3 = round(runif(100,1,3)),
                variable4 = runif(100,1,5))
df$variable1[c(5,13,95)] = 1000

df1 <- df %>% 
  filter(variable4>1.5)%>%
  group_by(variable2, variable3) %>% 
  mutate(individual_outliers = abs(scale(variable1) > 3),
         total_outliers = sum(individual_outliers))

> df1
# A tibble: 91 x 6
# Groups:   variable2, variable3 [9]
   variable1 variable2 variable3 variable4 individual_outliers total_outliers
       <dbl>     <dbl>     <dbl>     <dbl>               <int>          <int>
 1      6.86         2         3      2.82                   0              0
 2      4.89         1         2      3.27                   0              0
 3      4.19         2         3      3.03                   0              0
 4      2.05         2         3      2.31                   0              0
 5   1000            3         2      2.08                   1              1
 6      9.36         2         2      3.85                   0              0
 7      8.40         3         3      3.81                   0              0
 8      8.33         3         2      2.32                   0              1
 9      7.92         2         1      4.58                   0              0
10      8.13         3         1      2.48                   0              0
# ... with 81 more rows

Answer 2

数据：

df <- data.frame(variable1 = runif(1000,1,10),
                 variable2 = round(runif(1000,1,3)),
                 variable3 = round(runif(1000,1,3)),
                 variable4 = runif(1000,1,5),
                 variable5 = rep(LETTERS[1:4], 250),
                 variable6 = rep(LETTERS[5:9], 200), stringsAsFactors = F)

df$variable1[c(5,13,95)] = 1000

多变量离群值检测：

# Create a grouping vector: 

grouping_vars <- c("variable5", "variable6")

# Split apply combine function: 

tmp_df <- do.call(rbind, lapply(split(df[,sapply(df, is.numeric)], df[,grouping_vars]), function(x){

    # Calculate mahalanobis distance:

    md <- mahalanobis(x, colMeans(x), cov(x), inverted = FALSE)

    # Calculate the iqr of the md: 

    iqr <- quantile(md, .75) - quantile(md, .25)

    # Classify the lower threshold outliers:

    lwr <- ifelse(md > (quantile(md, .75) + (1.5 * iqr)) | (md < (quantile(md, .25) - (1.5 * iqr))),

                  "outlier",

                  "not outlier")

    # Classify the upper threshold outliers:

    upr <- ifelse(md > (quantile(md, .75) + (3 * iqr)) | (md < (quantile(md, .25) - (3 * iqr))),

                  "outlier",

                  "not outlier")

    # Bind all of the vecs together: 

    cbind(x, md, lwr, upr)

    }

   )

  )


# Extract the group from the row names:

tmp_df <- data.frame(cbind(df[,!(sapply(df, is.numeric))], 

                     grouping_vars = row.names(tmp_df), tmp_df), row.names = NULL)

df <- tmp_df[,c(names(df), setdiff(names(tmp_df), names(df)))]

单变量离群值检测：

# Use boxplot stats mean(x) +- 1.5 * IQR: 

outliers_classified <- do.call("rbind", lapply(split(df, df[,grouping_vars]), function(x){

      if(is.numeric(x)){

        ifelse(x %in% boxplot.stats(x)$out, NA, x)

      }else{

        x

      }

    }

  )

)