values = [8160,8160,6160,22684,0,0,60720,1380,1380,57128]
how can I remove outliers like 0, 57218, 60720 and 22684?
Is there a library which can do this?
values = [8160,8160,6160,22684,0,0,60720,1380,1380,57128]
how can I remove outliers like 0, 57218, 60720 and 22684?
Is there a library which can do this?
I had some problems with the other two solutions. Problems like having NaN values as q1 and q3 because of wrong indexes. The array length needs to have an -1 because of the 0 index. Then it is checked if the index is a int or decimal, in the case of a decimal the value between two indexes is extracted.
function filterOutliers (someArray) {
if (someArray.length < 4) {
return someArray;
}
let values = someArray.slice().sort((a, b) => a - b); // copy array fast and sort
let q1 = getQuantile(values, 25);
let q3 = getQuantile(values, 75);
let iqr, maxValue, minValue;
iqr = q3 - q1;
maxValue = q3 + iqr * 1.5;
minValue = q1 - iqr * 1.5;
return values.filter((x) => (x >= minValue) && (x <= maxValue));
}
function getQuantile (array, quantile) {
// Get the index the quantile is at.
let index = quantile / 100.0 * (array.length - 1);
// Check if it has decimal places.
if (index % 1 === 0) {
return array[index];
} else {
// Get the lower index.
let lowerIndex = Math.floor(index);
// Get the remaining.
let remainder = index - lowerIndex;
// Add the remaining to the lowerindex value.
return array[lowerIndex] + remainder * (array[lowerIndex + 1] - array[lowerIndex]);
}
}
Here is the implementation to filter upper outliers from a given collection. This approach follows a similar methodology as the provided answers above.
The if case will be checking the length of collection if it is 4n or 4n + 1. In that case, we need to get an average of two elements to have our quartiles.
Otherwise, in cases of 4n + 2 and 4n + 3, we directly can access the upper/lower quartile.
const outlierDetector = collection => {
const size = collection.length;
let q1, q3;
if (size < 2) {
return collection;
}
const sortedCollection = collection.slice().sort((a, b) => a - b);
if ((size - 1) / 4 % 1 === 0 || size / 4 % 1 === 0) {
q1 = 1 / 2 * (sortedCollection[Math.floor(size / 4) - 1] + sortedCollection[Math.floor(size / 4)]);
q3 = 1 / 2 * (sortedCollection[Math.ceil(size * 3 / 4) - 1] + sortedCollection[Math.ceil(size * 3 / 4)]);
} else {
q1 = sortedCollection[Math.floor(size / 4)];
q3 = sortedCollection[Math.floor(size * 3 / 4)];
}
const iqr = q3 - q1;
const maxValue = q3 + iqr * 1.5;
return sortedCollection.filter(value => value >= maxValue);
};