refactor: restrukturisasi folder eksperimen ke tasks modular
This commit is contained in:
matthewflrnt
@@ -0,0 +1,137 @@
|
||||
import sys
|
||||
import os
|
||||
import time
|
||||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
# Tambahkan root directory ke path agar dapat import dari src
|
||||
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..")))
|
||||
|
||||
from src.data_loader import load_mnist_for_mlp
|
||||
from src.models import create_mlp_model
|
||||
|
||||
|
||||
def main():
|
||||
print("=" * 60)
|
||||
print("TUGAS 1: MEMUAT DATASET MNIST & EKSPERIMEN MLP")
|
||||
print("=" * 60)
|
||||
|
||||
# 1. Load Data
|
||||
(x_train, y_train), (x_test, y_test) = load_mnist_for_mlp()
|
||||
print(f"Data training : {x_train.shape}")
|
||||
print(f"Data testing : {x_test.shape}")
|
||||
|
||||
# 2. Konfigurasi 3 Model MLP
|
||||
models_config = {
|
||||
"Model A - 1 Hidden Layer": [64],
|
||||
"Model B - 2 Hidden Layer": [128, 64],
|
||||
"Model C - 3 Hidden Layer": [256, 128, 64]
|
||||
}
|
||||
|
||||
results = []
|
||||
EPOCHS = 10
|
||||
BATCH_SIZE = 128
|
||||
|
||||
# 3. Training & Evaluasi
|
||||
for model_name, architecture in models_config.items():
|
||||
print("\n" + "=" * 60)
|
||||
print(model_name)
|
||||
print("=" * 60)
|
||||
|
||||
model = create_mlp_model(architecture)
|
||||
model.summary()
|
||||
|
||||
print("\nMemulai training...")
|
||||
start_time = time.time()
|
||||
|
||||
model.fit(
|
||||
x_train,
|
||||
y_train,
|
||||
epochs=EPOCHS,
|
||||
batch_size=BATCH_SIZE,
|
||||
validation_split=0.1,
|
||||
verbose=1
|
||||
)
|
||||
|
||||
total_time = time.time() - start_time
|
||||
average_time = total_time / EPOCHS
|
||||
|
||||
test_loss, test_accuracy = model.evaluate(x_test, y_test, verbose=0)
|
||||
total_parameters = model.count_params()
|
||||
|
||||
results.append({
|
||||
"model": model_name,
|
||||
"parameters": total_parameters,
|
||||
"accuracy": test_accuracy * 100,
|
||||
"time_per_epoch": average_time
|
||||
})
|
||||
|
||||
print("\nHasil:")
|
||||
print(f"Test Accuracy : {test_accuracy * 100:.2f}%")
|
||||
print(f"Jumlah Parameter : {total_parameters:,}")
|
||||
print(f"Waktu/Epoch : {average_time:.2f} detik")
|
||||
|
||||
# 4. Ringkasan Perbandingan
|
||||
print("\n\n" + "=" * 80)
|
||||
print("HASIL PERBANDINGAN 3 MODEL MLP")
|
||||
print("=" * 80)
|
||||
print(f"{'Model':<30}{'Parameter':>15}{'Accuracy':>15}{'Time/Epoch':>15}")
|
||||
print("-" * 80)
|
||||
|
||||
for res in results:
|
||||
print(
|
||||
f"{res['model']:<30}"
|
||||
f"{res['parameters']:>15,}"
|
||||
f"{res['accuracy']:>14.2f}%"
|
||||
f"{res['time_per_epoch']:>14.2f}s"
|
||||
)
|
||||
|
||||
best_model = max(results, key=lambda x: x["accuracy"])
|
||||
print("\n" + "=" * 60)
|
||||
print("MODEL DENGAN TEST ACCURACY TERTINGGI")
|
||||
print("=" * 60)
|
||||
print(f"Model : {best_model['model']}")
|
||||
print(f"Test Accuracy : {best_model['accuracy']:.2f}%")
|
||||
print(f"Jumlah Parameter : {best_model['parameters']:,}")
|
||||
print(f"Waktu Training/Epoch: {best_model['time_per_epoch']:.2f} detik")
|
||||
|
||||
# 5. Simpan Hasil ke Folder results/01_mlp
|
||||
REPORTS_DIR = os.path.join("results", "01_mlp", "reports")
|
||||
FIGURES_DIR = os.path.join("results", "01_mlp", "figures")
|
||||
os.makedirs(REPORTS_DIR, exist_ok=True)
|
||||
os.makedirs(FIGURES_DIR, exist_ok=True)
|
||||
|
||||
df_results = pd.DataFrame(results)
|
||||
csv_path = os.path.join(REPORTS_DIR, "perbandingan_mlp.csv")
|
||||
df_results.to_csv(csv_path, index=False)
|
||||
print(f"\n[OK] Ringkasan CSV disimpan ke : {csv_path}")
|
||||
|
||||
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 5))
|
||||
names = ["Model A\n(1 Layer)", "Model B\n(2 Layer)", "Model C\n(3 Layer)"]
|
||||
accs = [r["accuracy"] for r in results]
|
||||
bars1 = ax1.bar(names, accs, color=["#4C72B0", "#55A868", "#C44E52"])
|
||||
ax1.set_title("Perbandingan Test Accuracy (%)", fontsize=12, fontweight="bold")
|
||||
ax1.set_ylabel("Accuracy (%)")
|
||||
ax1.set_ylim([max(0, min(accs) - 2), 100])
|
||||
for bar in bars1:
|
||||
yval = bar.get_height()
|
||||
ax1.text(bar.get_x() + bar.get_width()/2, yval + 0.2, f"{yval:.2f}%", ha='center', va='bottom')
|
||||
|
||||
times = [r["time_per_epoch"] for r in results]
|
||||
bars2 = ax2.bar(names, times, color=["#4C72B0", "#55A868", "#C44E52"])
|
||||
ax2.set_title("Waktu Training per Epoch (detik)", fontsize=12, fontweight="bold")
|
||||
ax2.set_ylabel("Detik / Epoch")
|
||||
for bar in bars2:
|
||||
yval = bar.get_height()
|
||||
ax2.text(bar.get_x() + bar.get_width()/2, yval + 0.05, f"{yval:.2f}s", ha='center', va='bottom')
|
||||
|
||||
plt.tight_layout()
|
||||
fig_path = os.path.join(FIGURES_DIR, "perbandingan_3_model_mlp.png")
|
||||
plt.savefig(fig_path, dpi=130)
|
||||
plt.close()
|
||||
print(f"[OK] Grafik perbandingan disimpan ke: {fig_path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -0,0 +1,93 @@
|
||||
import sys
|
||||
import os
|
||||
import matplotlib
|
||||
matplotlib.use("Agg")
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
# Tambahkan root directory ke path agar dapat import dari src
|
||||
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..")))
|
||||
|
||||
from src.data_loader import load_mnist_for_mlp
|
||||
from src.models import create_mlp_model, create_regularized_mlp_model
|
||||
from src.utils import ensure_dir
|
||||
|
||||
|
||||
def main():
|
||||
print("=" * 60)
|
||||
print("TUGAS 2: EKSPERIMEN REGULARISASI (BASELINE vs BATCHNORM + DROPOUT)")
|
||||
print("=" * 60)
|
||||
|
||||
# 1. Load Data
|
||||
(x_train, y_train), (x_test, y_test) = load_mnist_for_mlp()
|
||||
|
||||
EPOCHS = 20
|
||||
BATCH_SIZE = 128
|
||||
|
||||
# 2. Baseline Model (Without Regularization)
|
||||
print("\n" + "=" * 60)
|
||||
print("TRAINING BASELINE MODEL (WITHOUT REGULARIZATION)")
|
||||
print("=" * 60)
|
||||
model_base = create_mlp_model([256, 128, 64])
|
||||
history_base = model_base.fit(
|
||||
x_train, y_train,
|
||||
epochs=EPOCHS,
|
||||
batch_size=BATCH_SIZE,
|
||||
validation_split=0.1,
|
||||
verbose=1
|
||||
)
|
||||
|
||||
# 3. Regularized Model (BatchNorm + Dropout 0.3)
|
||||
print("\n" + "=" * 60)
|
||||
print("TRAINING REGULARIZED MODEL (WITH BATCHNORM + DROPOUT)")
|
||||
print("=" * 60)
|
||||
model_reg = create_regularized_mlp_model(hidden_layers=[256, 128, 64], dropout_rate=0.3)
|
||||
history_reg = model_reg.fit(
|
||||
x_train, y_train,
|
||||
epochs=EPOCHS,
|
||||
batch_size=BATCH_SIZE,
|
||||
validation_split=0.1,
|
||||
verbose=1
|
||||
)
|
||||
|
||||
# 4. Save Model Artifact
|
||||
results_model_dir = os.path.join("results", "01_mlp", "models")
|
||||
ensure_dir(results_model_dir)
|
||||
model_reg_path = os.path.join(results_model_dir, "model_c_regularized.keras")
|
||||
model_reg.save(model_reg_path)
|
||||
print(f"\n[INFO] Model teregularisasi disimpan di: {model_reg_path}")
|
||||
|
||||
# 5. Plot Comparison Curves
|
||||
results_fig_dir = os.path.join("results", "01_mlp", "figures")
|
||||
ensure_dir(results_fig_dir)
|
||||
fig_path = os.path.join(results_fig_dir, "loss_regularization.png")
|
||||
|
||||
plt.figure(figsize=(14, 5))
|
||||
|
||||
# Subplot 1: Baseline
|
||||
plt.subplot(1, 2, 1)
|
||||
plt.plot(history_base.history['loss'], label='Training Loss', color='blue')
|
||||
plt.plot(history_base.history['val_loss'], label='Validation Loss', color='orange', linestyle='--')
|
||||
plt.title('Model C Without Regularization')
|
||||
plt.xlabel('Epoch')
|
||||
plt.ylabel('Loss')
|
||||
plt.legend()
|
||||
plt.grid(True, alpha=0.3)
|
||||
|
||||
# Subplot 2: Regularized
|
||||
plt.subplot(1, 2, 2)
|
||||
plt.plot(history_reg.history['loss'], label='Training Loss', color='blue')
|
||||
plt.plot(history_reg.history['val_loss'], label='Validation Loss', color='green', linestyle='--')
|
||||
plt.title('Model C With BatchNorm + Dropout(0.3)')
|
||||
plt.xlabel('Epoch')
|
||||
plt.ylabel('Loss')
|
||||
plt.legend()
|
||||
plt.grid(True, alpha=0.3)
|
||||
|
||||
plt.tight_layout()
|
||||
plt.savefig(fig_path, dpi=130)
|
||||
print(f"[INFO] Grafik perbandingan loss disimpan di: {fig_path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -0,0 +1,67 @@
|
||||
"""
|
||||
Tugas 3: Contoh Implementasi Berbagai Arsitektur Model Sesuai Karakteristik Data
|
||||
"""
|
||||
|
||||
import tensorflow as tf
|
||||
from tensorflow import keras
|
||||
from tensorflow.keras.layers import Conv2D, Dense, Embedding, Flatten, LSTM, MaxPooling2D
|
||||
from tensorflow.keras.models import Sequential
|
||||
from xgboost import XGBClassifier
|
||||
|
||||
|
||||
def build_models():
|
||||
print("=" * 60)
|
||||
print("TUGAS 3: CONTOH ARSITEKTUR MODEL SELECTION")
|
||||
print("=" * 60)
|
||||
|
||||
# (a) Prediksi Stok Barang dari Deret Waktu (LSTM)
|
||||
# Input shape: (samples, time_steps=12, features=1)
|
||||
model_a = Sequential([
|
||||
LSTM(32, input_shape=(12, 1)),
|
||||
Dense(1)
|
||||
], name="LSTM_Stock_Forecasting")
|
||||
model_a.compile(optimizer='adam', loss='mse')
|
||||
print("\n[Case A] Model LSTM untuk Prediksi Stok Barang (Time Series):")
|
||||
model_a.summary()
|
||||
|
||||
# (b) Klasifikasi Foto Produk Rusak vs Normal (CNN)
|
||||
# Input shape contoh citra RGB 128x128
|
||||
model_b = Sequential([
|
||||
Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)),
|
||||
MaxPooling2D((2, 2)),
|
||||
Flatten(),
|
||||
Dense(64, activation='relu'),
|
||||
Dense(1, activation='sigmoid') # binary: rusak vs normal
|
||||
], name="CNN_Defect_Classification")
|
||||
model_b.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
|
||||
print("\n[Case B] Model CNN untuk Klasifikasi Foto Produk (Computer Vision):")
|
||||
model_b.summary()
|
||||
|
||||
# (c) Analisis Sentimen Ulasan Play Store (LSTM + Embedding)
|
||||
vocab_size = 5000
|
||||
max_length = 100
|
||||
model_c = Sequential([
|
||||
Embedding(input_dim=vocab_size, output_dim=64, input_length=max_length),
|
||||
LSTM(64),
|
||||
Dense(32, activation='relu'),
|
||||
Dense(1, activation='sigmoid') # binary: positif vs negatif
|
||||
], name="LSTM_Sentiment_Analysis")
|
||||
model_c.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
|
||||
print("\n[Case C] Model LSTM + Embedding untuk Analisis Sentimen (NLP):")
|
||||
model_c.summary()
|
||||
|
||||
# (d) Prediksi Churn Pelanggan Tabular (ML Klasik - XGBoost)
|
||||
# X_train memiliki dimensi (n_samples, 15)
|
||||
model_d = XGBClassifier(
|
||||
n_estimators=100,
|
||||
max_depth=4,
|
||||
learning_rate=0.1,
|
||||
random_state=42
|
||||
)
|
||||
print("\n[Case D] Model XGBoost untuk Prediksi Churn (Tabular 15 fitur):")
|
||||
print(model_d)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
build_models()
|
||||
|
||||
Reference in New Issue
Block a user