lightgbm
This commit is contained in:
152
train/train_lightgbm.py
Normal file
152
train/train_lightgbm.py
Normal file
@@ -0,0 +1,152 @@
|
||||
import argparse
|
||||
import csv
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import joblib
|
||||
import numpy as np
|
||||
import lightgbm as lgb
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
from sklearn.metrics import mean_absolute_error
|
||||
|
||||
# =========================================================
|
||||
# Hyper Parameters
|
||||
# =========================================================
|
||||
|
||||
TRAIN_SIZE = 0
|
||||
VALID_SIZE = 0
|
||||
|
||||
RANDOM_STATE = 42
|
||||
|
||||
# LightGBM 특정 하이퍼파라미터
|
||||
PARAMS = {
|
||||
'objective': 'regression',
|
||||
'metric': 'mae',
|
||||
'verbosity': -1,
|
||||
'boosting_type': 'gbdt',
|
||||
'random_state': RANDOM_STATE,
|
||||
'learning_rate': 0.02, # 더 정밀한 학습을 위해 하향
|
||||
'num_leaves': 63, # 더 복잡한 패턴 학습을 위해 상향
|
||||
'feature_fraction': 0.9,
|
||||
'bagging_fraction': 0.8,
|
||||
'bagging_freq': 5,
|
||||
'n_estimators': 3000 # 학습량 대폭 상향
|
||||
}
|
||||
|
||||
CONTINUE_TRAINING = True
|
||||
ERROR_TOLERANCE = 0.1
|
||||
|
||||
# =========================================================
|
||||
# 파일명
|
||||
# =========================================================
|
||||
|
||||
FEATURES_FILENAME = "features.json"
|
||||
MEASURE_FILENAME = "measure.csv"
|
||||
MODEL_FILENAME = "model_lgbm.pkl"
|
||||
SCALER_FILENAME = "scaler_lgbm.pkl"
|
||||
FEATURE_NAMES_FILENAME = "features_lgbm.txt"
|
||||
|
||||
IGNORE_KEYS = {"songno", "difficulty"}
|
||||
|
||||
def safe_float(value):
|
||||
if value is None: return 0.0
|
||||
x = float(value)
|
||||
return x if math.isfinite(x) else 0.0
|
||||
|
||||
def train_model(working_dir: str, data_dir: str):
|
||||
random.seed(RANDOM_STATE)
|
||||
|
||||
features_path = os.path.join(working_dir, FEATURES_FILENAME)
|
||||
measure_path = os.path.join(data_dir, MEASURE_FILENAME)
|
||||
model_path = os.path.join(working_dir, MODEL_FILENAME)
|
||||
scaler_path = os.path.join(working_dir, SCALER_FILENAME)
|
||||
feature_names_path = os.path.join(working_dir, FEATURE_NAMES_FILENAME)
|
||||
|
||||
with open(features_path, "r", encoding="utf-8") as f:
|
||||
feature_data = json.load(f)
|
||||
|
||||
if len(feature_data) == 0:
|
||||
raise ValueError("features.json is empty")
|
||||
|
||||
feature_map = {(str(item["songno"]), str(item["difficulty"])): item for item in feature_data}
|
||||
feature_names = sorted([k for k in feature_data[0].keys() if k not in IGNORE_KEYS])
|
||||
|
||||
dataset = []
|
||||
with open(measure_path, "r", encoding="utf-8") as f:
|
||||
reader = csv.reader(f)
|
||||
next(reader, None)
|
||||
for row in reader:
|
||||
if len(row) < 3: continue
|
||||
measure, songno, diff = safe_float(row[0]), str(row[1]), str(row[2])
|
||||
key = (songno, diff)
|
||||
if key in feature_map:
|
||||
features = [safe_float(feature_map[key].get(k, 0)) for k in feature_names]
|
||||
dataset.append((features, measure))
|
||||
|
||||
random.shuffle(dataset)
|
||||
if len(dataset) < (TRAIN_SIZE + VALID_SIZE):
|
||||
raise ValueError(f"Not enough dataset ({len(dataset)} < {TRAIN_SIZE + VALID_SIZE})")
|
||||
|
||||
train_dataset = dataset[:TRAIN_SIZE]
|
||||
valid_dataset = dataset[TRAIN_SIZE:TRAIN_SIZE + VALID_SIZE]
|
||||
|
||||
X_train = np.array([x for x, _ in train_dataset], dtype=np.float32)
|
||||
y_train = np.array([y for _, y in train_dataset], dtype=np.float32)
|
||||
X_valid = np.array([x for x, _ in valid_dataset], dtype=np.float32)
|
||||
y_valid = np.array([y for _, y in valid_dataset], dtype=np.float32)
|
||||
|
||||
print(f"Train Size: {len(X_train)} | Valid Size: {len(X_valid)} | Features: {len(feature_names)}")
|
||||
|
||||
if CONTINUE_TRAINING and os.path.exists(scaler_path):
|
||||
print("Loading existing scaler...")
|
||||
scaler = joblib.load(scaler_path)
|
||||
else:
|
||||
print("Creating new scaler...")
|
||||
scaler = StandardScaler()
|
||||
scaler.fit(X_train)
|
||||
|
||||
X_train = scaler.transform(X_train)
|
||||
X_valid = scaler.transform(X_valid)
|
||||
|
||||
if CONTINUE_TRAINING and os.path.exists(model_path):
|
||||
print("Loading existing model for incremental training...")
|
||||
model = joblib.load(model_path)
|
||||
model.fit(
|
||||
X_train, y_train,
|
||||
eval_set=[(X_valid, y_valid)],
|
||||
init_model=model,
|
||||
callbacks=[lgb.early_stopping(stopping_rounds=100)]
|
||||
)
|
||||
else:
|
||||
print("Creating new LightGBM model...")
|
||||
model = lgb.LGBMRegressor(**PARAMS)
|
||||
model.fit(
|
||||
X_train, y_train,
|
||||
eval_set=[(X_valid, y_valid)],
|
||||
callbacks=[lgb.early_stopping(stopping_rounds=100)]
|
||||
)
|
||||
|
||||
pred = model.predict(X_valid)
|
||||
mae = mean_absolute_error(y_valid, pred)
|
||||
accuracy = np.sum(np.abs(pred - y_valid) <= ERROR_TOLERANCE) / len(y_valid)
|
||||
|
||||
print(f"\nMAE: {mae:.4f} | Accuracy (±{ERROR_TOLERANCE}): {accuracy:.4f}")
|
||||
|
||||
joblib.dump(model, model_path)
|
||||
joblib.dump(scaler, scaler_path)
|
||||
with open(feature_names_path, "w", encoding="utf-8") as f:
|
||||
for name in feature_names: f.write(name + "\n")
|
||||
|
||||
print(f"\nSaved to {working_dir}: {MODEL_FILENAME}, {SCALER_FILENAME}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--workingDir", required=True)
|
||||
parser.add_argument("--dataDir", required=True)
|
||||
parser.add_argument("--trainSize", required=True, type=int)
|
||||
parser.add_argument("--validSize", required=True, type=int)
|
||||
args = parser.parse_args()
|
||||
|
||||
TRAIN_SIZE, VALID_SIZE = args.trainSize, args.validSize
|
||||
train_model(args.workingDir, args.dataDir)
|
||||
@@ -1,313 +0,0 @@
|
||||
import argparse
|
||||
import csv
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
import joblib
|
||||
import numpy as np
|
||||
|
||||
from xgboost import XGBRegressor
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
from sklearn.metrics import mean_absolute_error
|
||||
|
||||
# =========================================================
|
||||
# Hyper Parameters
|
||||
# =========================================================
|
||||
|
||||
TEST_SIZE = 0.2
|
||||
RANDOM_STATE = 42
|
||||
|
||||
N_ESTIMATORS = 500
|
||||
MAX_DEPTH = 6
|
||||
LEARNING_RATE = 0.05
|
||||
SUBSAMPLE = 0.8
|
||||
COLSAMPLE_BYTREE = 0.8
|
||||
|
||||
CONTINUE_TRAINING = True
|
||||
|
||||
# 예측 성공으로 간주할 허용 오차
|
||||
ERROR_TOLERANCE = 0.1
|
||||
|
||||
# =========================================================
|
||||
# 파일명
|
||||
# =========================================================
|
||||
|
||||
FEATURES_FILENAME = "features.json"
|
||||
MEASURE_FILENAME = "measure.csv"
|
||||
|
||||
MODEL_FILENAME = "model.pkl"
|
||||
SCALER_FILENAME = "scaler.pkl"
|
||||
FEATURE_NAMES_FILENAME = "features.txt"
|
||||
|
||||
# =========================================================
|
||||
# 무시할 key
|
||||
# =========================================================
|
||||
|
||||
IGNORE_KEYS = {
|
||||
"songno",
|
||||
"difficulty"
|
||||
}
|
||||
|
||||
|
||||
def safe_float(value):
|
||||
if value is None:
|
||||
return 0.0
|
||||
|
||||
x = float(value)
|
||||
|
||||
if not math.isfinite(x):
|
||||
return 0.0
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def train_model(
|
||||
working_dir: str,
|
||||
data_dir: str
|
||||
):
|
||||
# =====================================================
|
||||
# path
|
||||
# =====================================================
|
||||
|
||||
features_path = os.path.join(
|
||||
working_dir,
|
||||
FEATURES_FILENAME
|
||||
)
|
||||
|
||||
measure_path = os.path.join(
|
||||
data_dir,
|
||||
MEASURE_FILENAME
|
||||
)
|
||||
|
||||
model_path = os.path.join(
|
||||
working_dir,
|
||||
MODEL_FILENAME
|
||||
)
|
||||
|
||||
scaler_path = os.path.join(
|
||||
working_dir,
|
||||
SCALER_FILENAME
|
||||
)
|
||||
|
||||
feature_names_path = os.path.join(
|
||||
working_dir,
|
||||
FEATURE_NAMES_FILENAME
|
||||
)
|
||||
|
||||
# =====================================================
|
||||
# features.json
|
||||
# =====================================================
|
||||
|
||||
with open(features_path, "r", encoding="utf-8") as f:
|
||||
feature_data = json.load(f)
|
||||
|
||||
if len(feature_data) == 0:
|
||||
raise ValueError("features.json is empty")
|
||||
|
||||
# =====================================================
|
||||
# feature map
|
||||
# =====================================================
|
||||
|
||||
feature_map = {}
|
||||
|
||||
for item in feature_data:
|
||||
key = (
|
||||
str(item["songno"]),
|
||||
str(item["difficulty"])
|
||||
)
|
||||
|
||||
feature_map[key] = item
|
||||
|
||||
# =====================================================
|
||||
# feature names
|
||||
# =====================================================
|
||||
|
||||
feature_names = sorted([
|
||||
k for k in feature_data[0].keys()
|
||||
if k not in IGNORE_KEYS
|
||||
])
|
||||
|
||||
# =====================================================
|
||||
# measure.csv
|
||||
# =====================================================
|
||||
|
||||
X = []
|
||||
y = []
|
||||
|
||||
with open(measure_path, "r", encoding="utf-8") as f:
|
||||
reader = csv.reader(f)
|
||||
next(reader, None)
|
||||
|
||||
for row in reader:
|
||||
if len(row) < 3:
|
||||
continue
|
||||
|
||||
measure = safe_float(row[0])
|
||||
songno = str(row[1])
|
||||
diff = str(row[2])
|
||||
|
||||
key = (songno, diff)
|
||||
|
||||
if key not in feature_map:
|
||||
print(
|
||||
f"[WARN] feature not found: "
|
||||
f"{songno} {diff}"
|
||||
)
|
||||
continue
|
||||
|
||||
feature_item = feature_map[key]
|
||||
|
||||
features = [
|
||||
safe_float(feature_item.get(k, 0))
|
||||
for k in feature_names
|
||||
]
|
||||
|
||||
X.append(features)
|
||||
y.append(measure)
|
||||
|
||||
if len(X) == 0:
|
||||
raise ValueError("No training data")
|
||||
|
||||
X = np.array(X, dtype=np.float32)
|
||||
y = np.array(y, dtype=np.float32)
|
||||
|
||||
print(f"Dataset Size: {len(X)}")
|
||||
print(f"Feature Count: {len(feature_names)}")
|
||||
|
||||
# =====================================================
|
||||
# split
|
||||
# =====================================================
|
||||
|
||||
X_train, X_valid, y_train, y_valid = train_test_split(
|
||||
X,
|
||||
y,
|
||||
test_size=TEST_SIZE,
|
||||
random_state=RANDOM_STATE
|
||||
)
|
||||
|
||||
# =====================================================
|
||||
# scaler
|
||||
# =====================================================
|
||||
|
||||
if CONTINUE_TRAINING and os.path.exists(scaler_path):
|
||||
print("Loading existing scaler...")
|
||||
|
||||
scaler = joblib.load(scaler_path)
|
||||
|
||||
else:
|
||||
print("Creating new scaler...")
|
||||
|
||||
scaler = StandardScaler()
|
||||
scaler.fit(X_train)
|
||||
|
||||
X_train = scaler.transform(X_train)
|
||||
X_valid = scaler.transform(X_valid)
|
||||
|
||||
# =====================================================
|
||||
# model
|
||||
# =====================================================
|
||||
|
||||
if CONTINUE_TRAINING and os.path.exists(model_path):
|
||||
print("Loading existing model...")
|
||||
|
||||
model = joblib.load(model_path)
|
||||
|
||||
previous_booster = model.get_booster()
|
||||
|
||||
model.fit(
|
||||
X_train,
|
||||
y_train,
|
||||
xgb_model=previous_booster
|
||||
)
|
||||
|
||||
else:
|
||||
print("Creating new model...")
|
||||
|
||||
model = XGBRegressor(
|
||||
n_estimators=N_ESTIMATORS,
|
||||
max_depth=MAX_DEPTH,
|
||||
learning_rate=LEARNING_RATE,
|
||||
subsample=SUBSAMPLE,
|
||||
colsample_bytree=COLSAMPLE_BYTREE,
|
||||
objective="reg:squarederror",
|
||||
random_state=RANDOM_STATE
|
||||
)
|
||||
|
||||
model.fit(X_train, y_train)
|
||||
|
||||
# =====================================================
|
||||
# evaluate
|
||||
# =====================================================
|
||||
|
||||
pred = model.predict(X_valid)
|
||||
|
||||
mae = mean_absolute_error(y_valid, pred)
|
||||
|
||||
correct = np.sum(
|
||||
np.abs(pred - y_valid) <= ERROR_TOLERANCE
|
||||
)
|
||||
|
||||
accuracy = correct / len(y_valid)
|
||||
|
||||
print(f"\nMAE: {mae:.4f}")
|
||||
print(
|
||||
f"Accuracy "
|
||||
f"(±{ERROR_TOLERANCE}): "
|
||||
f"{accuracy:.4f}"
|
||||
)
|
||||
|
||||
# =====================================================
|
||||
# feature importance
|
||||
# =====================================================
|
||||
|
||||
print("\nFeature Importance:")
|
||||
|
||||
importance = model.feature_importances_
|
||||
|
||||
pairs = list(zip(feature_names, importance))
|
||||
pairs.sort(key=lambda x: x[1], reverse=True)
|
||||
|
||||
for name, score in pairs:
|
||||
print(f"{name:25} {score:.6f}")
|
||||
|
||||
# =====================================================
|
||||
# save
|
||||
# =====================================================
|
||||
|
||||
joblib.dump(model, model_path)
|
||||
joblib.dump(scaler, scaler_path)
|
||||
|
||||
with open(feature_names_path, "w", encoding="utf-8") as f:
|
||||
for name in feature_names:
|
||||
f.write(name + "\n")
|
||||
|
||||
print("\nSaved:")
|
||||
print(model_path)
|
||||
print(scaler_path)
|
||||
print(feature_names_path)
|
||||
|
||||
|
||||
# =========================================================
|
||||
# main
|
||||
# =========================================================
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
parser.add_argument(
|
||||
"--workingDir",
|
||||
required=True
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--dataDir",
|
||||
required=True
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
train_model(
|
||||
args.workingDir,
|
||||
args.dataDir
|
||||
)
|
||||
Reference in New Issue
Block a user