Finding outliers with the 1.5 × IQR rule

Flag the values that lie far from the rest, and see how much they move the mean.

What to build

A program that applies the 1.5 × IQR rule.

Requirements

  • Quartiles as before: sort, take the values before and after the middle (an odd count leaves the middle out), and use the median of each half.
  • Print Q1 A and Q3 B (2 decimal places), fences L to U (2 decimal places), outliers followed by the outliers in increasing order (or outliers none), then mean with M and mean without N, the mean of all values and of the non-outliers (2 decimal places).

Input

One line: whole numbers separated by spaces.

Output

Six lines.

Constraints

4 to 1000 numbers.

Example

Input:

62 70 70 75 81 88 91 11

Output:

Q1 66.00
Q3 84.50
fences 38.25 to 112.25
outliers 11
mean with 68.50
mean without 76.71

Why it works

The quartiles are themselves resistant to extreme values, so fences built from them are not dragged out by the very outliers they are meant to catch.

Examples

Example 1 · Input
62 70 70 75 81 88 91 11
Expected output
Q1 66.00
Q3 84.50
fences 38.25 to 112.25
outliers 11
mean with 68.50
mean without 76.71
Example 2 · Input
1 2 3 4
Expected output
Q1 1.50
Q3 3.50
fences -1.50 to 6.50
outliers none
mean with 2.50
mean without 2.50

Prompts inside input() are ignored when checking, so input("n: ") is fine.

Hints

Hint 1

Find Q1 and Q3 as in the medians of the lower and upper halves, then the fences Q1 − 1.5 × IQR and Q3 + 1.5 × IQR.

Hint 2

An outlier is strictly outside the fences.

Solution

Show one correct solution (try it yourself first)
nums = sorted(int(x) for x in input().split())
n = len(nums)


def median(values):
    m = len(values) // 2
    return values[m] if len(values) % 2 else (values[m - 1] + values[m]) / 2


q1, q3 = median(nums[: n // 2]), median(nums[(n + 1) // 2 :])
iqr = q3 - q1
low, high = q1 - 1.5 * iqr, q3 + 1.5 * iqr
outliers = [x for x in nums if x < low or x > high]
kept = [x for x in nums if low <= x <= high]
print(f"Q1 {q1:.2f}")
print(f"Q3 {q3:.2f}")
print(f"fences {low:.2f} to {high:.2f}")
print("outliers", " ".join(map(str, outliers)) if outliers else "none")
print(f"mean with {sum(nums) / n:.2f}")
print(f"mean without {sum(kept) / len(kept):.2f}")

Lesson: Describing data →