time-to-botec

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

README.md (4370B)

      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 # incrmme
     22 
     23 > Compute a moving [mean error][mean-absolute-error] (ME) incrementally.
     24 
     25 <section class="intro">
     26 
     27 For a window of size `W`, the [mean error][mean-absolute-error] is defined as
     28 
     29 <!-- <equation class="equation" label="eq:mean_error" align="center" raw="\operatorname{ME} = \frac{1}{W} \sum_{i=0}^{W-1} (y_i - x_i)" alt="Equation for the mean error."> -->
     30 
     31 <div class="equation" align="center" data-raw-text="\operatorname{ME} = \frac{1}{W} \sum_{i=0}^{W-1} (y_i - x_i)" data-equation="eq:mean_error">
     32     <img src="https://cdn.jsdelivr.net/gh/stdlib-js/stdlib@634ac3689760e2f57fd51085f387d8dc5bb3b927/lib/node_modules/@stdlib/stats/incr/mme/docs/img/equation_mean_error.svg" alt="Equation for the mean error.">
     33     <br>
     34 </div>
     35 
     36 <!-- </equation> -->
     37 
     38 </section>
     39 
     40 <!-- /.intro -->
     41 
     42 <section class="usage">
     43 
     44 ## Usage
     45 
     46 ```javascript
     47 var incrmme = require( '@stdlib/stats/incr/mme' );
     48 ```
     49 
     50 #### incrmme( window )
     51 
     52 Returns an accumulator `function` which incrementally computes a moving [mean error][mean-absolute-error]. The `window` parameter defines the number of values over which to compute the moving [mean error][mean-absolute-error].
     53 
     54 ```javascript
     55 var accumulator = incrmme( 3 );
     56 ```
     57 
     58 #### accumulator( \[x, y] )
     59 
     60 If provided input values `x` and `y`, the accumulator function returns an updated [mean error][mean-absolute-error]. If not provided input values `x` and `y`, the accumulator function returns the current [mean error][mean-absolute-error].
     61 
     62 ```javascript
     63 var accumulator = incrmme( 3 );
     64 
     65 var m = accumulator();
     66 // returns null
     67 
     68 // Fill the window...
     69 m = accumulator( 2.0, 3.0 ); // [(2.0,3.0)]
     70 // returns 1.0
     71 
     72 m = accumulator( -1.0, 4.0 ); // [(2.0,3.0), (-1.0,4.0)]
     73 // returns 3.0
     74 
     75 m = accumulator( 3.0, 9.0 ); // [(2.0,3.0), (-1.0,4.0), (3.0,9.0)]
     76 // returns 4.0
     77 
     78 // Window begins sliding...
     79 m = accumulator( -7.0, 3.0 ); // [(-1.0,4.0), (3.0,9.0), (-7.0,3.0)]
     80 // returns 7.0
     81 
     82 m = accumulator( -5.0, -3.0 ); // [(3.0,9.0), (-7.0,3.0), (-5.0,-3.0)]
     83 // returns 6.0
     84 
     85 m = accumulator();
     86 // returns 6.0
     87 ```
     88 
     89 </section>
     90 
     91 <!-- /.usage -->
     92 
     93 <section class="notes">
     94 
     95 ## Notes
     96 
     97 -   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.
     98 -   As `W` (x,y) 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.
     99 -   Be careful when interpreting the [mean error][mean-absolute-error] as errors can cancel. This stated, that errors can cancel makes the [mean error][mean-absolute-error] suitable for measuring the bias in forecasts.
    100 -   **Warning**: the [mean error][mean-absolute-error] is scale-dependent and, thus, the measure should **not** be used to make comparisons between datasets having different scales.
    101 
    102 </section>
    103 
    104 <!-- /.notes -->
    105 
    106 <section class="examples">
    107 
    108 ## Examples
    109 
    110 <!-- eslint no-undef: "error" -->
    111 
    112 ```javascript
    113 var randu = require( '@stdlib/random/base/randu' );
    114 var incrmme = require( '@stdlib/stats/incr/mme' );
    115 
    116 var accumulator;
    117 var v1;
    118 var v2;
    119 var i;
    120 
    121 // Initialize an accumulator:
    122 accumulator = incrmme( 5 );
    123 
    124 // For each simulated datum, update the moving mean error...
    125 for ( i = 0; i < 100; i++ ) {
    126     v1 = ( randu()*100.0 ) - 50.0;
    127     v2 = ( randu()*100.0 ) - 50.0;
    128     accumulator( v1, v2 );
    129 }
    130 console.log( accumulator() );
    131 ```
    132 
    133 </section>
    134 
    135 <!-- /.examples -->
    136 
    137 <section class="links">
    138 
    139 [mean-absolute-error]: https://en.wikipedia.org/wiki/Mean_absolute_error
    140 
    141 </section>
    142 
    143 <!-- /.links -->