Outliers in certain values in column R-CodePudding

Outliers data

Given Data:

Color  |   Number
Green   |  5.0 
Red     |  20.0
Green   |  5.0    
Green   |  15.0
Green   |  100.0
Red     |  7.0
Red     |  10.0
Red     |  8.0
Green   |  6.0

Want to only take values of "green"’s number only and then plot and find outliers for them. How do you do this?

CodePudding user response：

We may subset the dataset where the Color is "Green", select the 'Number' column and use boxplot and extract the outliers

boxplot(subset(Data, Color == "Green", select = Number)$Number)$out
[1] #100

data

Data <- structure(list(Color = c("Green", "Red", "Green", "Green", "Green", 
"Red", "Red", "Red", "Green"), Number = c(5L, 20L, 5L, 15L, 100L, 
7L, 10L, 8L, 6L)), class = "data.frame", row.names = c(NA, -9L
))

CodePudding user response：

Get the values for the Green color:

GreenValues = Data[Data$Color=='Green',]

Then use boxplot.stats to get the outliers:

boxplot.stats(GreenValues$Number)$out

Hope it helps.

CodePudding user response：

Interestingly, I needed to do the same thing not so long ago. On the way I found a great video explaining just that: https://youtu.be/9aDHbRb4Bf8

Here's a JS function that I made using that youtube video:

function getOutliers(input) {
  // sort array ascending
  const asc = arr => arr.sort((a, b) => a - b);

  const sum = arr => arr.reduce((a, b) => a   b, 0);

  const mean = arr => sum(arr) / arr.length;

  // sample standard deviation
  const std = (arr) => {
    const mu = mean(arr);
    const diffArr = arr.map(a => (a - mu) ** 2);
    return Math.sqrt(sum(diffArr) / (arr.length - 1));
  };

  const quantile = (arr, q) => {
    const sorted = asc(arr);
    const pos = (sorted.length - 1) * q;
    const base = Math.floor(pos);
    const rest = pos - base;
    if (sorted[base   1] !== undefined) {
      return sorted[base]   rest * (sorted[base   1] - sorted[base]);
    } else {
      return sorted[base];
    }
  };

  const q1 = quantile(input, .25);
  const q3 = quantile(input, .75);
  const range = q3 - q1;
  const min = q1 - 1.5 * range;
  const max = q3   1.5 * range;

  let smallOutlierIndexes = [];
  let smallOutliers = [];
  let largeOutlierIndexes = [];
  let largeOutliers = [];

  for (let i = 0; i < input.length; i  ) {
    if (input[i] > max) {
      largeOutlierIndexes.push(i);
      largeOutliers.push(input[i]);
    }
    if (input[i] < min) {
      smallOutlierIndexes.push(i);
      smallOutliers.push(input[i]);
    }
  }

  return { smallOutliers, smallOutlierIndexes, largeOutliers, largeOutlierIndexes, min, max };
}