PHP code example of rubix / credit

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

rubix / credit example snippets

use Rubix\ML\Datasets\Labeled;
use Rubix\ML\Extractors\CSV;

$dataset = Labeled::fromIterator(new CSV('dataset.csv', true));

use Rubix\ML\Transformers\LambdaFunction;
use Rubix\ML\Transformers\MissingDataImputer;
use Rubix\ML\Transformers\FloatTypeConverter;
use Rubix\ML\Transformers\OneHotEncoder;
use Rubix\ML\Transformers\PowerTransformer;
use Rubix\ML\Transformers\ZScaleStandardizer;

$dataset->apply(new LambdaFunction(function (array &$sample) {
        if ($sample[2] === '0') {
            $sample[2] = '?';
        }
    }))
    ->apply(new MissingDataImputer())
    ->apply(new FloatTypeConverter())
    ->apply(new OneHotEncoder())
    ->apply(new PowerTransformer())
    ->apply(new ZScaleStandardizer());

[$training, $testing] = $dataset->randomize()->stratifiedSplit(0.8);

use Rubix\ML\Classifiers\LogisticRegression;
use Rubix\ML\NeuralNet\Optimizers\Stochastic;
use Rubix\ML\NeuralNet\Optimizers\Schedulers\StepDecay;

$estimator = new LogisticRegression(128, new Stochastic(new StepDecay(0.001, 100)));

use Rubix\ML\Loggers\Screen;

$logger = new Screen();

$estimator->setLogger($logger);

$estimator->setValidationDataset($testing);

$estimator->train($training);

use Rubix\ML\Extractors\CSV;

$extractor = new CSV('progress.csv', true);

$extractor->export($estimator->progress(), overwrite: true);

use Rubix\ML\CrossValidation\Reports\AggregateReport;
use Rubix\ML\CrossValidation\Reports\MulticlassBreakdown;
use Rubix\ML\CrossValidation\Reports\ConfusionMatrix;

$report = new AggregateReport([
    new MulticlassBreakdown(),
    new ConfusionMatrix(),
]);

$predictions = $estimator->predict($testing);

use Rubix\ML\Persisters\Filesystem;

$results = $report->generate($predictions, $testing->labels());

$results->toJSON()->saveTo(new Filesystem('report.json'));

use Rubix\ML\Datasets\Labeled;
use Rubix\ML\Extractors\CSV;
use Rubix\ML\Transformers\LambdaFunction;
use Rubix\ML\Transformers\MissingDataImputer;
use Rubix\ML\Transformers\FloatTypeConverter;

$dataset = Labeled::fromIterator(new CSV('dataset.csv', true));

$dataset = $dataset->apply(new LambdaFunction(function (array &$sample) {
        if ($sample[2] === '0') {
            $sample[2] = '?';
        }
    }))
    ->apply(new MissingDataImputer())
    ->apply(new FloatTypeConverter());

$stats = $dataset->describeByClassLabels();

use Rubix\ML\Persisters\Filesystem;

$stats->toJSON()->saveTo(new Filesystem('stats.json'));

use Rubix\ML\Datasets\Labeled;

$dataset = $dataset->randomize()->take(2048);

use Rubix\ML\Transformers\TSNE;

$embedder = new TSNE(
    dimensions: 2,
    rate: 20.0,
    perplexity: 20,
    exaggeration: 12.0,
    epochs: 1000,
    minGradient: 1e-7,
    evalInterval: 10,
    window: 5
);

use Rubix\ML\Transformers\OneHotEncoder;
use Rubix\ML\Transformers\PowerTransformer;
use Rubix\ML\Transformers\ZScaleStandardizer;

$dataset->apply(new OneHotEncoder())
    ->apply(new PowerTransformer())
    ->apply(new ZScaleStandardizer());

$dataset->apply($embedder);

use Rubix\ML\Extractors\CSV;

$dataset->exportTo(new CSV('embedding.csv'), overwrite: true);

sh
$ php train.php

sh
$ php explore.php

sh
$ php plot.php