feat: implementasi Neural Network modular dengan dataset Iris

CMakeLists.txt

@@ -8,7 +8,7 @@ project(bellshade_C
 set(CMAKE_C_STANDARD 11)
 set(CMAKE_C_STANDARD_REQUIRED YES)
 if (MSVC)
-  add_compile_definitions(_CRT_SECURE_NO_WARNIGS)
+    add_compile_definitions(_CRT_SECURE_NO_WARNINGS)
 endif (MSVC)
 
 find_library(MATH_LIBRARY m)
@@ -43,6 +43,7 @@ add_subdirectory(hashing)
 add_subdirectory(konversi)
 add_subdirectory(algoritma/sorting)
 add_subdirectory(algoritma/searching)
+add_subdirectory(project/NeuralNetwork)
 
 cmake_policy(SET CMP0054 NEW)
 cmake_policy(SET CMP0057 NEW)

project/NeuralNetwork/CMakeLists.txt

@@ -0,0 +1,16 @@
+file(GLOB NN_SOURCES RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} *.c)
+add_executable(neural_network ${NN_SOURCES})
+
+if(OpenMP_C_FOUND)
+    target_link_libraries(neural_network OpenMP::OpenMP_C)
+endif()
+
+if(MATH_LIBRARY)
+    target_link_libraries(neural_network ${MATH_LIBRARY})
+endif()
+
+set_target_properties(neural_network PROPERTIES C_STANDARD 11 C_STANDARD_REQUIRED YES)
+
+install(TARGETS neural_network DESTINATION "bin/project/NeuralNetwork")
+install(FILES dataset/iris.csv DESTINATION "bin/project/NeuralNetwork/dataset")
+

project/NeuralNetwork/iris.csv

@@ -0,0 +1,152 @@
+https://archive.ics.uci.edu/ml/datasets/iris
+sepal length in cm,sepal width in cm,petal length in cm,petal width in cm
+5.1,3.5,1.4,.2,0
+4.9,3,1.4,.2,0
+4.7,3.2,1.3,.2,0
+4.6,3.1,1.5,.2,0
+5,3.6,1.4,.2,0
+5.4,3.9,1.7,.4,0
+4.6,3.4,1.4,.3,0
+5,3.4,1.5,.2,0
+4.4,2.9,1.4,.2,0
+4.9,3.1,1.5,.1,0
+5.4,3.7,1.5,.2,0
+4.8,3.4,1.6,.2,0
+4.8,3,1.4,.1,0
+4.3,3,1.1,.1,0
+5.8,4,1.2,.2,0
+5.7,4.4,1.5,.4,0
+5.4,3.9,1.3,.4,0
+5.1,3.5,1.4,.3,0
+5.7,3.8,1.7,.3,0
+5.1,3.8,1.5,.3,0
+5.4,3.4,1.7,.2,0
+5.1,3.7,1.5,.4,0
+4.6,3.6,1,.2,0
+5.1,3.3,1.7,.5,0
+4.8,3.4,1.9,.2,0
+5,3,1.6,.2,0
+5,3.4,1.6,.4,0
+5.2,3.5,1.5,.2,0
+5.2,3.4,1.4,.2,0
+4.7,3.2,1.6,.2,0
+4.8,3.1,1.6,.2,0
+5.4,3.4,1.5,.4,0
+5.2,4.1,1.5,.1,0
+5.5,4.2,1.4,.2,0
+4.9,3.1,1.5,.2,0
+5,3.2,1.2,.2,0
+5.5,3.5,1.3,.2,0
+4.9,3.6,1.4,.1,0
+4.4,3,1.3,.2,0
+5.1,3.4,1.5,.2,0
+5,3.5,1.3,.3,0
+4.5,2.3,1.3,.3,0
+4.4,3.2,1.3,.2,0
+5,3.5,1.6,.6,0
+5.1,3.8,1.9,.4,0
+4.8,3,1.4,.3,0
+5.1,3.8,1.6,.2,0
+4.6,3.2,1.4,.2,0
+5.3,3.7,1.5,.2,0
+5,3.3,1.4,.2,0
+7,3.2,4.7,1.4,1
+6.4,3.2,4.5,1.5,1
+6.9,3.1,4.9,1.5,1
+5.5,2.3,4,1.3,1
+6.5,2.8,4.6,1.5,1
+5.7,2.8,4.5,1.3,1
+6.3,3.3,4.7,1.6,1
+4.9,2.4,3.3,1,1
+6.6,2.9,4.6,1.3,1
+5.2,2.7,3.9,1.4,1
+5,2,3.5,1,1
+5.9,3,4.2,1.5,1
+6,2.2,4,1,1
+6.1,2.9,4.7,1.4,1
+5.6,2.9,3.6,1.3,1
+6.7,3.1,4.4,1.4,1
+5.6,3,4.5,1.5,1
+5.8,2.7,4.1,1,1
+6.2,2.2,4.5,1.5,1
+5.6,2.5,3.9,1.1,1
+5.9,3.2,4.8,1.8,1
+6.1,2.8,4,1.3,1
+6.3,2.5,4.9,1.5,1
+6.1,2.8,4.7,1.2,1
+6.4,2.9,4.3,1.3,1
+6.6,3,4.4,1.4,1
+6.8,2.8,4.8,1.4,1
+6.7,3,5,1.7,1
+6,2.9,4.5,1.5,1
+5.7,2.6,3.5,1,1
+5.5,2.4,3.8,1.1,1
+5.5,2.4,3.7,1,1
+5.8,2.7,3.9,1.2,1
+6,2.7,5.1,1.6,1
+5.4,3,4.5,1.5,1
+6,3.4,4.5,1.6,1
+6.7,3.1,4.7,1.5,1
+6.3,2.3,4.4,1.3,1
+5.6,3,4.1,1.3,1
+5.5,2.5,4,1.3,1
+5.5,2.6,4.4,1.2,1
+6.1,3,4.6,1.4,1
+5.8,2.6,4,1.2,1
+5,2.3,3.3,1,1
+5.6,2.7,4.2,1.3,1
+5.7,3,4.2,1.2,1
+5.7,2.9,4.2,1.3,1
+6.2,2.9,4.3,1.3,1
+5.1,2.5,3,1.1,1
+5.7,2.8,4.1,1.3,1
+6.3,3.3,6,2.5,2
+5.8,2.7,5.1,1.9,2
+7.1,3,5.9,2.1,2
+6.3,2.9,5.6,1.8,2
+6.5,3,5.8,2.2,2
+7.6,3,6.6,2.1,2
+4.9,2.5,4.5,1.7,2
+7.3,2.9,6.3,1.8,2
+6.7,2.5,5.8,1.8,2
+7.2,3.6,6.1,2.5,2
+6.5,3.2,5.1,2,2
+6.4,2.7,5.3,1.9,2
+6.8,3,5.5,2.1,2
+5.7,2.5,5,2,2
+5.8,2.8,5.1,2.4,2
+6.4,3.2,5.3,2.3,2
+6.5,3,5.5,1.8,2
+7.7,3.8,6.7,2.2,2
+7.7,2.6,6.9,2.3,2
+6,2.2,5,1.5,2
+6.9,3.2,5.7,2.3,2
+5.6,2.8,4.9,2,2
+7.7,2.8,6.7,2,2
+6.3,2.7,4.9,1.8,2
+6.7,3.3,5.7,2.1,2
+7.2,3.2,6,1.8,2
+6.2,2.8,4.8,1.8,2
+6.1,3,4.9,1.8,2
+6.4,2.8,5.6,2.1,2
+7.2,3,5.8,1.6,2
+7.4,2.8,6.1,1.9,2
+7.9,3.8,6.4,2,2
+6.4,2.8,5.6,2.2,2
+6.3,2.8,5.1,1.5,2
+6.1,2.6,5.6,1.4,2
+7.7,3,6.1,2.3,2
+6.3,3.4,5.6,2.4,2
+6.4,3.1,5.5,1.8,2
+6,3,4.8,1.8,2
+6.9,3.1,5.4,2.1,2
+6.7,3.1,5.6,2.4,2
+6.9,3.1,5.1,2.3,2
+5.8,2.7,5.1,1.9,2
+6.8,3.2,5.9,2.3,2
+6.7,3.3,5.7,2.5,2
+6.7,3,5.2,2.3,2
+6.3,2.5,5,1.9,2
+6.5,3,5.2,2,2
+6.2,3.4,5.4,2.3,2
+5.9,3,5.1,1.8,2

project/NeuralNetwork/main.c

@@ -0,0 +1,146 @@
+
+#include "nn.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+
+int
+main(void)
+{
+  srand(time(NULL));
+
+  printf("=============[ NEURAL NETWORK - IRIS CLASSIFICATION ]============\n");
+
+  // Inisialisasi arena memory
+  struct MemoryArena arena = arena_create(1024 * 1024 * 10); // 10MB
+
+  // Load dataset iris
+  printf("・ Loading dataset iris.csv...\n");
+  struct Matrix dataset = dataset_load_from_csv(&arena, "iris.csv", 1); // Skip header
+  printf("・ Dataset loaded: %zu samples, %zu features\n", dataset.num_rows, dataset.num_columns);
+
+  // Normalisasi data input (4 kolom pertama)
+  printf("・ Normalizing input features...\n");
+  matrix_normalize_minmax(dataset, 4, 0.0f, 1.0f);
+
+  // Shuffle dataset
+  printf("・ Shuffling dataset...\n");
+  matrix_shuffle_rows(dataset);
+
+  // Split dataset: 80% training, 20% testing
+  size_t train_size = (size_t)(dataset.num_rows * 0.8f);
+  size_t test_size = dataset.num_rows - train_size;
+
+  struct Matrix train_data = matrix_create_row_slice(dataset, 0, train_size);
+  struct Matrix test_data = matrix_create_row_slice(dataset, train_size, test_size);
+
+  printf("-- Training set: %zu samples\n", train_data.num_rows);
+  printf("-- Test set: %zu samples\n", test_data.num_rows);
+
+  // Definisi arsitektur neural network
+  // Input: 4 features (sepal length, sepal width, petal length, petal width)
+  // Hidden: 8 neurons
+  // Output: 3 classes (setosa, versicolor, virginica)
+  size_t arch[] = {4, 8, 3};
+  size_t arch_count = sizeof(arch) / sizeof(arch[0]);
+
+  printf("\n・ Creating neural network with architecture: ");
+  for (size_t i = 0; i < arch_count; ++i) {
+    printf("%zu", arch[i]);
+    if (i < arch_count - 1)
+      printf(" - ");
+  }
+  printf("\n");
+
+  // Alokasi neural network
+  struct NeuralNetwork nn = neural_network_allocate(&arena, arch, arch_count);
+
+  // Initialize weights dengan nilai random
+  printf("・ Initializing random weights...\n");
+  neural_network_randomize_weights(nn, -1.0f, 1.0f);
+
+  // Test sebelum training
+  printf("\n・ Before training:\n");
+  printf("-- Training accuracy: %.2f%%\n", 100.0f * neural_network_calculate_accuracy(nn, train_data));
+  printf("-- Test accuracy: %.2f%%\n", 100.0f * neural_network_calculate_accuracy(nn, test_data));
+  printf("-- Training cost: %.4f\n", neural_network_calculate_accuracy(nn, train_data));
+
+  // Training parameters
+  size_t epochs = 1000;
+  size_t batch_size = 32;
+  float learning_rate = 0.1f;
+
+  printf("\n・ Training parameters:\n");
+  printf("-- Epochs: %zu\n", epochs);
+  printf("-- Batch size: %zu\n", batch_size);
+  printf("-- Learning rate: %.3f\n", learning_rate);
+  printf("\n======================[ STARTING TRAINING ]======================\n");
+
+  // Create separate arena for temporary calculations during training
+  struct MemoryArena temp_arena =
+      arena_create(1024 * 1024 * 5); // 5MB for temporary calculations
+
+  // Training loop
+  for (size_t epoch = 0; epoch < epochs; ++epoch) {
+    // Shuffle training data setiap epoch
+    matrix_shuffle_rows(train_data);
+
+    struct BatchProcessor batch = {0};
+    while (!batch.is_epoch_finished) {
+      batch_process_training_data(&temp_arena, &batch, batch_size, nn, train_data, learning_rate);
+      arena_reset(&temp_arena); // Only reset temporary arena
+    }
+
+    // Print progress setiap 100 epoch
+    if ((epoch + 1) % 100 == 0 || epoch == 0 || epoch == epochs - 1) {
+      float train_acc = neural_network_calculate_accuracy(nn, train_data);
+      float test_acc = neural_network_calculate_accuracy(nn, test_data);
+      float cost = neural_network_calculate_cost(nn, train_data);
+
+      printf("Epoch %4zu | Cost: %.4f | Train Acc: %.2f%% | Test Acc: %.2f%%\n",
+             epoch + 1, cost, 100.0f * train_acc, 100.0f * test_acc);
+    }
+  }
+
+  printf("======================[ TRAINING COMPLETED ]=====================\n\n");
+
+  // Final evaluation
+  printf("・ Final Results\n");
+  float final_train_acc = neural_network_calculate_accuracy(nn, train_data);
+  float final_test_acc = neural_network_calculate_accuracy(nn, test_data);
+  float final_cost = neural_network_calculate_cost(nn, train_data);
+
+  printf("-- Final training accuracy: %.2f%%\n", 100.0f * final_train_acc);
+  printf("-- Final test accuracy: %.2f%%\n", 100.0f * final_test_acc);
+  printf("-- Final training cost: %.4f\n", final_cost);
+
+  // Demo prediksi dengan beberapa sample dari test set
+  printf("\n======================[ SAMPLE PREDICTIONS ]=====================\n");
+  printf("・ Actual -> Predicted (Confidence)\n");
+  printf("・ 0 = Setosa | 1 = Versicolor | 2 = Virginica\n");
+  printf("-----------------------------------------------------------------\n");
+
+  for (size_t i = 0; i < 10 && i < test_data.num_rows; ++i) {
+    struct Row sample = matrix_get_row(test_data, i);
+    struct Row input = row_create_slice(sample, 0, 4);
+    struct Row target = row_create_slice(sample, 4, 3);
+
+    // Copy input ke network
+    row_copy_data(nn.activation_vectors[0], input);
+    neural_network_forward_pass(nn);
+
+    size_t actual = row_find_max_index(target);
+    size_t predicted = row_find_max_index(nn.activation_vectors[nn.total_layers - 1]);
+    float confidence = row_at(nn.activation_vectors[nn.total_layers - 1], predicted);
+
+    printf("   %zu    ->    %zu     (%.3f) %s\n", actual, predicted, confidence,
+           (actual == predicted) ? "✓" : "✗");
+  }
+
+  printf("\n・ Classification Complete\n");
+
+  return 0;
+}
+
+/* vim: set ts=4 sw=4 sts=4 et */
+