Quantile¶

Running quantile.

Uses the P² algorithm, which is also known as the "Piecewise-Parabolic quantile estimator". The code is inspired by LiveStat's implementation ².

Parameters¶

q

Type → float

Default → 0.5

Determines which quantile to compute, must be comprised between 0 and 1.

Attributes¶

name

Examples¶

from river import stats
import numpy as np

np.random.seed(42 * 1337)
mu, sigma = 0, 1
s = np.random.normal(mu, sigma, 500)

median = stats.Quantile(0.5)
for x in s:
   _ = median.update(x)
print(f'The estimated value of the 50th (median) quantile is {median.get():.4f}')

The estimated value of the 50th (median) quantile is -0.0275

print(f'The real value of the 50th (median) quantile is {np.median(s):.4f}')

The real value of the 50th (median) quantile is -0.0135

percentile_17 = stats.Quantile(0.17)
for x in s:
   _ = percentile_17.update(x)
print(f'The estimated value of the 17th quantile is {percentile_17.get():.4f}')

The estimated value of the 17th quantile is -0.8652

print(f'The real value of the 17th quantile is {np.percentile(s,17):.4f}')

The real value of the 17th quantile is -0.9072

Methods¶

get

Return the current value of the statistic.

update

Update and return the called instance.

Parameters

x — 'numbers.Number'