featuretools.primitives.ExponentialWeightedAverage#

class featuretools.primitives.ExponentialWeightedAverage(com=None, span=None, halflife=None, alpha=None, ignore_na=False)[source]#

Computes the exponentially weighted moving average for a series of numbers

Description:

Returns the exponentially weighted moving average for a series of numbers. Exactly one of center of mass (com), span, half-life, and alpha must be provided. Missing values can be ignored when calculating weights by setting ‘ignore_na’ to True.

Parameters:
  • com (float) – Specify decay in terms of center of mass for com >= 0. Default is None.

  • span (float) – Specify decay in terms of span for span >= 1. Default is None.

  • halflife (float) – Specify decay in terms of half-life for halflife > 0. Default is None.

  • alpha (float) – Specify smoothing factor alpha directly. Alpha should be greater than 0 and less than or equal to 1. Default is None.

  • ignore_na (bool) – Ignore missing values when calculating weights. Default is False.

Examples

>>> exponential_weighted_average = ExponentialWeightedAverage(com=0.5)
>>> exponential_weighted_average([1, 2, 3, 4]).tolist()
[1.0, 1.75, 2.615384615384615, 3.55]

Missing values can be ignored >>> ewma_ignorena = ExponentialWeightedAverage(com=0.5, ignore_na=True) >>> ewma_ignorena([1, 2, 3, None, 4]).tolist() [1.0, 1.75, 2.615384615384615, 2.615384615384615, 3.55]

__init__(com=None, span=None, halflife=None, alpha=None, ignore_na=False)[source]#

Methods

__init__([com, span, halflife, alpha, ignore_na])

flatten_nested_input_types(input_types)

Flattens nested column schema inputs into a single list.

generate_name(base_feature_names)

generate_names(base_feature_names)

get_args_string()

get_arguments()

get_description(input_column_descriptions[, ...])

get_filepath(filename)

get_function()

Attributes

base_of

base_of_exclude

commutative

default_value

Default value this feature returns if no data found.

description_template

input_types

woodwork.ColumnSchema types of inputs

max_stack_depth

name

Name of the primitive

number_output_features

Number of columns in feature matrix associated with this feature

return_type

ColumnSchema type of return

stack_on

stack_on_exclude

stack_on_self

uses_calc_time

uses_full_dataframe