Easy

IQR Outlier Detection

Easy

~15 min

code completion

IQR Outlier Detection

The interquartile range (IQR) method flags outliers without assuming any labels or a specific distribution. It is robust because the IQR itself is unaffected by the very extremes it detects.

The rule:

1. Compute $Q_{1} = 25th percentile$ and $Q_{3} = 75th percentile$

2. $IQR = Q_{3} - Q_{1}$

3. Lower fence: $Q_{1} - 1.5 \times IQR$

4. Upper fence: $Q_{3} + 1.5 \times IQR$

5. Any value outside the fences is an outlier

Example: arr = [1, 2, 3, 4, 100]

Q_{1} = 2

Q_{3} = 4

, IQR

= 2

Fences:

[- 1, 7]

100 > 7 → outlier

Your task:

Implement iqr_outlier_mask(arr) that returns an integer array where 1 = outlier and 0 = normal.

Example Tests

Single high spike flagged at position 4

Input: {"arr":[1,2,3,4,100]}

Expected: [0,0,0,0,1]

All identical values: IQR is zero, no outliers

Input: {"arr":[10,10,10,10,10]}

Expected: [0,0,0,0,0]

Single low outlier flagged at position 0

Input: {"arr":[-100,2,3,4,5]}

Expected: [1,0,0,0,0]

You can read the full problem statement above. Create a free account to run code in the browser, submit solutions, and track your progress.