Math-EMA

 view release on metacpan or  search on metacpan

README  view on Meta::CPAN

NAME
    Math::EMA - compute the exponential moving average

SYNOPSIS
      use Math::EMA;
      my $avg=Math::EMA->new(alpha=>0.926119, ema=>$initial_value);
      $avg->set_param($iterations, $end_weight);
      $avg->alpha=$new_alpha;
      $avg->ema=$new_value;
      $avg->add($some_value);
      my $ema=$avg->ema;

INSTALLATION
     perl Makefile.PL
     make
     make test
     make install

README  view on Meta::CPAN

    where alpha is a number between 0 and 1.

    That means a new value influences the average with a certain weight
    (1-alpha). That weight then exponentially vanes when other values are
    added.

  How to choose alpha?
    The value of alpha determines how fast a given value vanes but it never
    completely drops out. Assume you can define a limit say after 10
    iterations the weight of a certain value should be 1% or 0.01. Then

                   _____
             _10  /     `
     alpha =  \  / 0.01   = exp( log(0.01) / 10 )
               \/

  Methods
   Math::EMA->new( key=>value, ... )
    creates a new "Math::EMA" object. Parameters are passed as "key=>value"
    pairs. Currently these keys are recognized:

README  view on Meta::CPAN

        initializes the average. If an uninitialized ema is used the first
        value being added initializes it.

   $obj->alpha
    set or retrieve the current alpha

   $obj->ema
    set or retrieve the current average

   $obj->set_param($iterations, $end_weight)
    computes alpha from the passed values. After $iterations new values a
    certain value should have a weight of $end_weight in the average.

SEE ALSO
    <http://en.wikipedia.org/wiki/Moving_average#Exponential_moving_average>

    <http://en.wikipedia.org/wiki/Exponential_smoothing#The_exponential_movi
    ng_average>

AUTHOR
    Torsten Förtsch, <torsten.foertsch@gmx.net>

lib/Math/EMA.pm  view on Meta::CPAN

=encoding utf8

=head1 NAME

Math::EMA - compute the exponential moving average

=head1 SYNOPSIS

  use Math::EMA;
  my $avg=Math::EMA->new(alpha=>0.926119, ema=>$initial_value);
  $avg->set_param($iterations, $end_weight);
  $avg->alpha=$new_alpha;
  $avg->ema=$new_value;
  $avg->add($some_value);
  my $ema=$avg->ema;

=head1 DESCRIPTION

This module computes an exponential moving average by the following formula

  avg(n+1) = (1 - alpha) * new_value + alpha * avg(n)

where alpha is a number between 0 and 1.

That means a new value influences the average with a certain weight (1-alpha).
That weight then exponentially vanes when other values are added.

=head2 How to choose alpha?

The value of alpha determines how fast a given value vanes but it never
completely drops out. Assume you can define a limit say after 10
iterations the weight of a certain value should be 1% or 0.01. Then

               _____
         _10  /     `
 alpha =  \  / 0.01   = exp( log(0.01) / 10 )
           \/

=head2 Methods

=head3 Math::EMA-E<gt>new( key=E<gt>value, ... )

lib/Math/EMA.pm  view on Meta::CPAN

=back

=head3 $obj-E<gt>alpha

set or retrieve the current alpha

=head3 $obj-E<gt>ema

set or retrieve the current average

=head3 $obj-E<gt>set_param($iterations, $end_weight)

computes alpha from the passed values. After C<$iterations> new values a
certain value should have a weight of C<$end_weight> in the average.

=head1 SEE ALSO

L<http://en.wikipedia.org/wiki/Moving_average#Exponential_moving_average>

L<http://en.wikipedia.org/wiki/Exponential_smoothing#The_exponential_moving_average>

=head1 AUTHOR

t/001.t  view on Meta::CPAN

ok $avg, 'object created';
cmp_ok sprintf('%.10f', $avg->set_param(60, 0.01) ), '==', 0.9261187281,
       'set_param';
cmp_ok sprintf('%.10f', $avg->alpha ), '==', 0.9261187281, 'retrieve alpha';

cmp_ok $avg->add(12), '==', 12, 'added the 1st value';
cmp_ok $avg->ema, '==', 12, 'ema after the 1st value';

$avg->add(0) for(1..60);

printf("# value after 60 iterations: %.10f\n", $avg->ema);
cmp_ok sprintf('%.10f', $avg->ema), '==', 0.12, 'ema after 60 iterations';