#include <neuralnet/train.h>

#include <neuralnet/matrix.h>
#include <neuralnet/neuralnet.h>
#include "activation.h"
#include "neuralnet_impl.h"

#include "test.h"
#include "test_util.h"

#include <assert.h>

TEST_CASE(neuralnet_train_sigmoid_test) {
  const int num_layers = 1;
  const int layer_sizes[] = { 1, 1 };
  const nnActivation layer_activations[] = { nnSigmoid };

  nnNeuralNetwork* net = nnMakeNet(num_layers, layer_sizes, layer_activations);
  assert(net);

  // Train.

  // Try to learn the sigmoid function.
  #define N 3
  R inputs[N];
  R targets[N];
  for (int i = 0; i < N; ++i) {
    inputs[i] = lerp(-1, +1, (R)i / (R)(N-1));
    targets[i] = sigmoid(inputs[i]);
  }

  nnMatrix inputs_matrix  = nnMatrixMake(N, 1);
  nnMatrix targets_matrix = nnMatrixMake(N, 1);
  nnMatrixInit(&inputs_matrix, inputs);
  nnMatrixInit(&targets_matrix, targets);

  nnTrainingParams params = {
    .learning_rate = 0.9,
    .max_iterations = 100,
    .seed = 0,
    .weight_init = nnWeightInit01,
    .debug = false,
  };

  nnTrain(net, &inputs_matrix, &targets_matrix, &params);

  const R weight = nnMatrixAt(&net->weights[0], 0, 0);
  const R expected_weight = 1.0;
  printf("\nTrained network weight: %f, Expected: %f\n", weight, expected_weight);
  TEST_TRUE(double_eq(weight, expected_weight, WEIGHT_EPS));

  // Test.

  nnQueryObject* query = nnMakeQueryObject(net, /*num_inputs=*/1);

  const R test_input[] = { 0.3 };
  R test_output[1];
  nnQueryArray(net, query, test_input, test_output);

  const R expected_output = 0.574442516811659;  // sigmoid(0.3)
  printf("Output: %f, Expected: %f\n", test_output[0], expected_output);
  TEST_TRUE(double_eq(test_output[0], expected_output, OUTPUT_EPS));

  nnDeleteQueryObject(&query);
  nnDeleteNet(&net);
}