<?php

namespace App\Models\NetworksTraining;

use App\Events\PerceptronTrainingEnded;
use App\Models\ActivationsFunctions;
use App\Models\Perceptrons\GradientDescentPerceptron;
use App\Models\Perceptrons\NetworkPerceptron;
use App\Models\Perceptrons\Perceptron;
use App\Models\Perceptrons\SimpleBinaryPerceptron2;
use App\Models\Perceptrons\SimpleBinaryPerceptron;
use App\Services\DatasetReader\IDataSetReader;
use App\Services\IterationEventBuffer\IPerceptronIterationEventBuffer;
use App\Services\SynapticWeightsProvider\ISynapticWeightsProvider;
use App\Services\SynapticWeightsProvider\SimpleNetworkWeightsProvider;
use Illuminate\Support\Arr;

class MonoLayerPerceptronTraining extends NetworkTraining
{
    private Perceptron $network;

    private array $labels;

    public ActivationsFunctions $activationFunction = ActivationsFunctions::LINEAR;
    public ?ActivationsFunctions $presentationLayerActivationFunction = ActivationsFunctions::STEP;

    private float $epochError;

    public function __construct(
        IDataSetReader $datasetReader,
        protected float $learningRate,
        int $maxEpochs,
        ISynapticWeightsProvider $synapticWeightsProvider,
        IPerceptronIterationEventBuffer $iterationEventBuffer,
        string $sessionId,
        string $trainingId,
        private float $minError,
    ) {
        parent::__construct($datasetReader, $maxEpochs, $iterationEventBuffer, $sessionId, $trainingId);
        $networkWeightsProvider = new SimpleNetworkWeightsProvider($synapticWeightsProvider);
        $this->network = new NetworkPerceptron(
            $networkWeightsProvider->generate(
                $datasetReader->getInputSize(),
                $datasetReader->getOutputSize(),
                0, // No hidden layer
                0, // No hidden layer neurons
            ),
            $datasetReader->getInputSize(),
            GradientDescentPerceptron::class, // No hidden layer
            SimpleBinaryPerceptron2::class,
        );
        $this->labels = $datasetReader->getLabels();
    }

    public function start(): void
    {
        $this->epoch = 0;
        do {
            $this->epochError = 0;
            $this->epoch++;

            $inputsForCurrentEpoch = [];

            while ($nextRow = $this->datasetReader->getNextLine()) {
                $inputsForCurrentEpoch[] = $nextRow;
                $inputs = array_slice($nextRow, 0, -1);
                $correctOutput = (int) end($nextRow);

                $iterationError = $this->iterationFunction($inputs, $correctOutput);

                // Synaptic weights correction after each example
                $synaptic_weights = $this->network->getSynapticWeights();
                $inputs_with_bias = array_merge([1], $inputs); // Add bias input

                // Updates the weights
                $this->network->setSynapticWeights(
                    $this->getUpdatedSynapticWeights($synaptic_weights, $iterationError, $inputs_with_bias)
                );

                // Broadcast the training iteration event
                $this->addIterationToBuffer(array_sum($iterationError), $this->network->getSynapticWeights());
            }

            // Calculte the average error for the epoch with the last synaptic weights
            foreach ($inputsForCurrentEpoch as $inputsWithLabel) {
                $inputs = array_slice($inputsWithLabel, 0, -1);
                $correctOutput = (float) end($inputsWithLabel);
                $iterationError = $this->iterationFunction($inputs, $correctOutput);
                foreach ($iterationError as $error) {
                    $this->epochError += ($error ** 2) / 2; // Squared error for the example
                }
            }
            $this->epochError /= $this->datasetReader->getEpochExamplesCount(); // Average error for the epoch

            $this->datasetReader->reset(); // Reset the dataset for the next iteration
        } while ($this->epoch < $this->maxEpochs && ! $this->stopCondition());

        $this->iterationEventBuffer->flush(); // Ensure all iterations are sent to the frontend

        $this->checkPassedMaxIterations($this->epochError);
    }

    protected function stopCondition(): bool
    {
        $condition = $this->epochError <= $this->minError;
        if ($condition === true) {
            event(new PerceptronTrainingEnded('Le perceptron à atteint l\'erreur minimale', $this->sessionId, $this->trainingId));
        }

        return $condition;
    }

    private function iterationFunction(array $inputs, int $correctOutput): array
    {
        $outputs = $this->network->test($inputs);
        $desiredOutput = $this->getDesiredOutputFromCorrectOutput($correctOutput);

        $errors = [];
        foreach ($outputs as $index => $output) {
            $error = $desiredOutput[$index] - $output;
            $errors[] = $error;
        }

        return $errors;
    }

    private function getUpdatedSynapticWeights(array $synaptic_weights, array $iterationError, array $inputs): array
    {
        $updatedWeights = [];
        foreach ($synaptic_weights[0] as $neuronIndex => $neuronWeights) { // There is only one layer of weights
            $updatedNeuronWeights = [];
            foreach ($neuronWeights as $weightIndex => $weight) {
                $updatedWeight = $weight + ($this->learningRate * $iterationError[$neuronIndex] * $inputs[$weightIndex]);
                $updatedNeuronWeights[] = $updatedWeight;
            }
            $updatedWeights[] = $updatedNeuronWeights;
        }

        return [$updatedWeights];
    }

    private function getDesiredOutputFromCorrectOutput(int $correctOutput): array
    {
        $desiredOutput = array_fill(0, count($this->labels), -1);
        $labelIndex = Arr::first(array_keys($this->labels), fn($key) => $this->labels[$key] == $correctOutput);
        if ($labelIndex !== null) {
            $desiredOutput[$labelIndex] = 1;
        }

        return $desiredOutput;
    }

    public function getSynapticWeights(): array
    {
        return [[$this->network->getSynapticWeights()]];
    }
}