ezmsg.sigproc.ewma

Functions

ewma_step(sample, zi, alpha, beta=None)

Do an exponentially weighted moving average step.

Parameters:

• sample (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The new sample.

• zi (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The output of the previous step.

• alpha (float) – Fading factor.

• beta (float | None) – Persisting factor. If None, it is calculated as 1-alpha.

Returns:

alpha * sample + beta * zi

Classes

class EWMASettings(time_constant: float = 1.0, axis: str | None = None)

Bases: Settings

Parameters:

• time_constant (float)

• axis (str | None)

time_constant: float = 1.0

axis: str | None = None

__init__(time_constant=1.0, axis=None)

Parameters:

• time_constant (float)

• axis (str | None)

Return type:

None

class EWMAState

Bases: object

alpha: float

zi: ndarray[tuple[Any, ...], dtype[_ScalarT]] | None = None

class EWMATransformer(*args, **kwargs)

Bases: BaseStatefulTransformer[EWMASettings, AxisArray, AxisArray, EWMAState]

class EWMAUnit(*args, settings=None, **kwargs)

Bases: BaseTransformerUnit[EWMASettings, AxisArray, AxisArray, EWMATransformer]

Parameters:

settings (Settings | None)

SETTINGS

alias of EWMASettings

class EWMA_Deprecated(alpha, max_len)

Bases: object

Grabbed these methods from https://stackoverflow.com/a/70998068 and other answers in that topic, but they ended up being slower than the scipy.signal.lfilter method. Additionally, compute and compute2 suffer from potential errors as the vector length increases and beta**n approaches zero.

Parameters:

• alpha (float)

• max_len (int)

__init__(alpha, max_len)

Parameters:

• alpha (float)

• max_len (int)

compute(arr, out=None)

Parameters:

• arr (ndarray[tuple[Any, ...], dtype[_ScalarT]])

• out (ndarray[tuple[Any, ...], dtype[_ScalarT]] | None)

Return type:

ndarray[tuple[Any, …], dtype[_ScalarT]]

compute2(arr)

Compute the Exponentially Weighted Moving Average (EWMA) of the input array.

Parameters:

arr (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The input array to be smoothed.

Returns:

The smoothed array.

Return type:

ndarray[tuple[Any, …], dtype[_ScalarT]]

compute_sample(new_sample)

Parameters:

new_sample (ndarray[tuple[Any, ...], dtype[_ScalarT]])

Return type:

ndarray[tuple[Any, …], dtype[_ScalarT]]

ewma_step(sample, zi, alpha, beta=None)

Do an exponentially weighted moving average step.

Parameters:

• sample (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The new sample.

• zi (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The output of the previous step.

• alpha (float) – Fading factor.

• beta (float | None) – Persisting factor. If None, it is calculated as 1-alpha.

Returns:

alpha * sample + beta * zi

class EWMA_Deprecated(alpha, max_len)

Bases: object

Grabbed these methods from https://stackoverflow.com/a/70998068 and other answers in that topic, but they ended up being slower than the scipy.signal.lfilter method. Additionally, compute and compute2 suffer from potential errors as the vector length increases and beta**n approaches zero.

Parameters:

• alpha (float)

• max_len (int)

__init__(alpha, max_len)

Parameters:

• alpha (float)

• max_len (int)

compute(arr, out=None)

Parameters:

• arr (ndarray[tuple[Any, ...], dtype[_ScalarT]])

• out (ndarray[tuple[Any, ...], dtype[_ScalarT]] | None)

Return type:

ndarray[tuple[Any, …], dtype[_ScalarT]]

compute2(arr)

Compute the Exponentially Weighted Moving Average (EWMA) of the input array.

Parameters:

arr (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The input array to be smoothed.

Returns:

The smoothed array.

Return type:

ndarray[tuple[Any, …], dtype[_ScalarT]]

compute_sample(new_sample)

Parameters:

new_sample (ndarray[tuple[Any, ...], dtype[_ScalarT]])

Return type:

ndarray[tuple[Any, …], dtype[_ScalarT]]

class EWMASettings(time_constant: float = 1.0, axis: str | None = None)

Bases: Settings

Parameters:

• time_constant (float)

• axis (str | None)

time_constant: float = 1.0

axis: str | None = None

__init__(time_constant=1.0, axis=None)

Parameters:

• time_constant (float)

• axis (str | None)

Return type:

None

class EWMAState

Bases: object

alpha: float

zi: ndarray[tuple[Any, ...], dtype[_ScalarT]] | None = None

class EWMATransformer(*args, **kwargs)

Bases: BaseStatefulTransformer[EWMASettings, AxisArray, AxisArray, EWMAState]

class EWMAUnit(*args, settings=None, **kwargs)

Bases: BaseTransformerUnit[EWMASettings, AxisArray, AxisArray, EWMATransformer]

Parameters:

settings (Settings | None)

SETTINGS

alias of EWMASettings