time-to-botec

Benchmark sampling in different programming languages
Log | Files | Refs | README

README.md (5136B)


      1 <!--
      2 
      3 @license Apache-2.0
      4 
      5 Copyright (c) 2018 The Stdlib Authors.
      6 
      7 Licensed under the Apache License, Version 2.0 (the "License");
      8 you may not use this file except in compliance with the License.
      9 You may obtain a copy of the License at
     10 
     11    http://www.apache.org/licenses/LICENSE-2.0
     12 
     13 Unless required by applicable law or agreed to in writing, software
     14 distributed under the License is distributed on an "AS IS" BASIS,
     15 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     16 See the License for the specific language governing permissions and
     17 limitations under the License.
     18 
     19 -->
     20 
     21 # incrmmaape
     22 
     23 > Compute a moving [mean arctangent absolute percentage error][@kim:2016a] (MAAPE) incrementally.
     24 
     25 <section class="intro">
     26 
     27 For a window of size `W`, the [mean arctangent absolute percentage error][@kim:2016a] is defined as
     28 
     29 <!-- <equation class="equation" label="eq:mean_arctangent_absolute_percentage_error" align="center" raw="\operatorname{MAAPE}  = \frac{1}{W} \sum_{i=0}^{W-1} \operatorname{arctan}\biggl( \biggl| \frac{a_i - f_i}{a_i} \biggr| \biggr)" alt="Equation for the mean arctangent absolute percentage error."> -->
     30 
     31 <div class="equation" align="center" data-raw-text="\operatorname{MAAPE}  = \frac{1}{W} \sum_{i=0}^{W-1} \operatorname{arctan} \biggl( \biggl| \frac{a_i - f_i}{a_i} \biggr| \biggr)" data-equation="eq:mean_arctangent_absolute_percentage_error">
     32     <img src="https://cdn.jsdelivr.net/gh/stdlib-js/stdlib@677f6828831c61cabc84859897a5ee7e079d6ddf/lib/node_modules/@stdlib/stats/incr/mmaape/docs/img/equation_mean_arctangent_absolute_percentage_error.svg" alt="Equation for the mean arctangent absolute percentage error.">
     33     <br>
     34 </div>
     35 
     36 <!-- </equation> -->
     37 
     38 where `f_i` is the forecast value and `a_i` is the actual value.
     39 
     40 </section>
     41 
     42 <!-- /.intro -->
     43 
     44 <section class="usage">
     45 
     46 ## Usage
     47 
     48 ```javascript
     49 var incrmmaape = require( '@stdlib/stats/incr/mmaape' );
     50 ```
     51 
     52 #### incrmmaape( window )
     53 
     54 Returns an accumulator `function` which incrementally computes a moving [mean arctangent absolute percentage error][@kim:2016a]. The `window` parameter defines the number of values over which to compute the moving [mean arctangent absolute percentage error][@kim:2016a].
     55 
     56 ```javascript
     57 var accumulator = incrmmaape( 3 );
     58 ```
     59 
     60 #### accumulator( \[f, a] )
     61 
     62 If provided input values `f` and `a`, the accumulator function returns an updated [mean arctangent absolute percentage error][@kim:2016a]. If not provided input values `f` and `a`, the accumulator function returns the current [mean arctangent absolute percentage error][@kim:2016a].
     63 
     64 ```javascript
     65 var accumulator = incrmmaape( 3 );
     66 
     67 var m = accumulator();
     68 // returns null
     69 
     70 // Fill the window...
     71 m = accumulator( 2.0, 3.0 ); // [(2.0,3.0)]
     72 // returns ~0.32
     73 
     74 m = accumulator( 1.0, 4.0 ); // [(2.0,3.0), (1.0,4.0)]
     75 // returns ~0.48
     76 
     77 m = accumulator( 3.0, 9.0 ); // [(2.0,3.0), (1.0,4.0), (3.0,9.0)]
     78 // returns ~0.52
     79 
     80 // Window begins sliding...
     81 m = accumulator( 7.0, 3.0 ); // [(1.0,4.0), (3.0,9.0), (7.0,3.0)]
     82 // returns ~0.72
     83 
     84 m = accumulator( 5.0, 3.0 ); // [(3.0,9.0), (7.0,3.0), (5.0,3.0)]
     85 // returns ~0.70
     86 
     87 m = accumulator();
     88 // returns ~0.70
     89 ```
     90 
     91 </section>
     92 
     93 <!-- /.usage -->
     94 
     95 <section class="notes">
     96 
     97 ## Notes
     98 
     99 -   Input values are **not** type checked. If provided `NaN` or a value which, when used in computations, results in `NaN`, the accumulated value is `NaN` for **at least** `W-1` future invocations. If non-numeric inputs are possible, you are advised to type check and handle accordingly **before** passing the value to the accumulator function.
    100 -   As `W` (f,a) pairs are needed to fill the window buffer, the first `W-1` returned values are calculated from smaller sample sizes. Until the window is full, each returned value is calculated from all provided values.
    101 -   Note that, unlike the [mean absolute percentage error][@stdlib/stats/incr/mape] (MAPE), the [mean arctangent absolute percentage error][@kim:2016a] is expressed in radians on the interval \[0,π/2].
    102 
    103 </section>
    104 
    105 <!-- /.notes -->
    106 
    107 <section class="examples">
    108 
    109 ## Examples
    110 
    111 <!-- eslint no-undef: "error" -->
    112 
    113 ```javascript
    114 var randu = require( '@stdlib/random/base/randu' );
    115 var incrmmaape = require( '@stdlib/stats/incr/mmaape' );
    116 
    117 var accumulator;
    118 var v1;
    119 var v2;
    120 var i;
    121 
    122 // Initialize an accumulator:
    123 accumulator = incrmmaape( 5 );
    124 
    125 // For each simulated datum, update the moving mean arctangent absolute percentage error...
    126 for ( i = 0; i < 100; i++ ) {
    127     v1 = ( randu()*100.0 ) + 50.0;
    128     v2 = ( randu()*100.0 ) + 50.0;
    129     accumulator( v1, v2 );
    130 }
    131 console.log( accumulator() );
    132 ```
    133 
    134 </section>
    135 
    136 <!-- /.examples -->
    137 
    138 <section class="references">
    139 
    140 ## References
    141 
    142 -   Kim, Sungil, and Heeyoung Kim. 2016. "A new metric of absolute percentage error for intermittent demand forecasts." _International Journal of Forecasting_ 32 (3): 669–79. doi:[10.1016/j.ijforecast.2015.12.003][@kim:2016a].
    143 
    144 </section>
    145 
    146 <!-- /.references -->
    147 
    148 <section class="links">
    149 
    150 [@kim:2016a]: https://www.sciencedirect.com/science/article/pii/S0169207016000121
    151 
    152 [@stdlib/stats/incr/mape]: https://www.npmjs.com/package/@stdlib/stats/tree/main/incr/mape
    153 
    154 </section>
    155 
    156 <!-- /.links -->