EWVar

Exponentially weighted variance.

To calculate the variance we use the fact that Var(X) = Mean(x^2) - Mean(x)^2 and internally we use the exponentially weighted mean of x/x^2 to calculate this.

Parameters

• fading_factor – defaults to 0.5

  The closer fading_factor is to 1 the more the statistic will adapt to recent values.

Attributes

• variance (float)

  The running exponentially weighted variance.

Examples

>>> from river import stats

>>> X = [1, 3, 5, 4, 6, 8, 7, 9, 11]
>>> ewv = stats.EWVar(fading_factor=0.5)
>>> for x in X:
...     print(ewv.update(x).get())
0.0
1.0
2.75
1.4375
1.984375
3.43359375
1.7958984375
2.198974609375
3.56536865234375

Methods

get

Return the current value of the statistic.

update

Update and return the called instance.

Parameters

• x (numbers.Number)

References

---

1. Finch, T., 2009. Incremental calculation of weighted mean and variance. University of Cambridge, 4(11-5), pp.41-42. ↩

2. Exponential Moving Average on Streaming Data ↩