Var

Running variance using Welford's algorithm.

Parameters

• ddof

  Default → 1

  Delta Degrees of Freedom. The divisor used in calculations is n - ddof, where n represents the number of seen elements.

Attributes

• mean

  It is necessary to calculate the mean of the data in order to calculate its variance.

Examples

from river import stats

X = [3, 5, 4, 7, 10, 12]

var = stats.Var()
for x in X:
    var.update(x)
    print(var.get())

0.0
2.0
1.0
2.916666
7.7
12.56666

You can measure a rolling variance by using a utils.Rolling wrapper:

from river import utils

X = [1, 4, 2, -4, -8, 0]
rvar = utils.Rolling(stats.Var(ddof=1), window_size=3)
for x in X:
    rvar.update(x)
    print(rvar.get())

0.0
4.5
2.333333
17.333333
25.333333
16.0

Methods

get

Return the current value of the statistic.

revert

update

Update and return the called instance.

Parameters

• x — 'numbers.Number'
• w — defaults to 1.0

update_many

Notes

The outcomes of the incremental and parallel updates are consistent with numpy's batch processing when \(\text{ddof} \le 1\).

---

1. Wikipedia article on algorithms for calculating variance ↩

2. Chan, T.F., Golub, G.H. and LeVeque, R.J., 1983. Algorithms for computing the sample variance: Analysis and recommendations. The American Statistician, 37(3), pp.242-247. ↩

3. Schubert, E. and Gertz, M., 2018, July. Numerically stable parallel computation of (co-)variance. In Proceedings of the 30th International Conference on Scientific and Statistical Database Management (pp. 1-12). ↩