reducelronplateau_criterion=args.monitor.split("_")[-1],
callbacks=[early_stopping, model_checkpoint, LRHistory(n_epochs=args.n_epochs)],
metrics=[Accuracy],
)
start = time()
trainer.fit(
X_train={"X_tab": X_train, "target": y_train},
X_val={"X_tab": X_test, "target": y_test},
n_epochs=args.n_epochs,
batch_size=args.batch_size,
validation_freq=args.eval_every,
)
runtime = time() - start
y_pred = trainer.predict(X_tab=X_test)
acc = accuracy_score(y_test, y_pred)
if args.save_results:
suffix = str(datetime.now()).replace(" ", "_").split(".")[:-1][0]
filename = "_".join(["adult_tabtransformer_best", suffix]) + ".p"
results_d = {}
results_d["args"] = args
results_d["acc"] = acc
results_d["early_stopping"] = early_stopping
results_d["trainer_history"] = trainer.history
results_d["trainer_lr_history"] = trainer.lr_history
results_d["runtime"] = runtime
with open(RESULTS_DIR / filename, "wb") as f:
pickle.dump(results_d, f)
def run_experiment_and_save(
model,
model_name,
results_dir,
models_dir,
args,
X_train,
X_test,
y_train,
y_test,
fl_exp_indx: int = 0,
):
try:
if args.focal_loss:
alpha, gamma = load_focal_loss_params(results_dir, fl_exp_indx)
focal_loss = True
else:
alpha = 0.25
gamma = 2
focal_loss = False
except AttributeError:
alpha = 0.25
gamma = 2
focal_loss = False
optimizers = set_optimizer(model, args)
steps_per_epoch = (X_train.shape[0] // args.batch_size) + 1
lr_schedulers = set_lr_scheduler(optimizers, steps_per_epoch, args)
early_stopping = EarlyStopping(
monitor=args.monitor,
min_delta=args.early_stop_delta,
patience=args.early_stop_patience,
)
model_checkpoint = ModelCheckpoint(
filepath=str(models_dir / "best_model"),
monitor=args.monitor,
save_best_only=True,
max_save=1,
)
trainer = Trainer(
model,
objective="binary_focal_loss" if focal_loss else "binary",
optimizers=optimizers,
lr_schedulers=lr_schedulers,
reducelronplateau_criterion=args.monitor.split("_")[-1],
callbacks=[early_stopping, model_checkpoint, LRHistory(n_epochs=args.n_epochs)],
metrics=[Accuracy, F1Score],
alpha=alpha,
gamma=gamma,
)
start = time()
trainer.fit(
X_train={"X_tab": X_train, "target": y_train},
X_val={"X_tab": X_test, "target": y_test},
n_epochs=args.n_epochs,
batch_size=args.batch_size,
validation_freq=args.eval_every,
)
runtime = time() - start
y_pred = trainer.predict(X_tab=X_test)
acc = accuracy_score(y_test, y_pred)
auc = roc_auc_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
print(f"Accuracy: {acc}. F1: {f1}. ROC_AUC: {auc}")
print(confusion_matrix(y_test, y_pred))
if args.save_results:
suffix = str(datetime.now()).replace(" ", "_").split(".")[:-1][0]
filename = "_".join(["bankm", model_name, "best", suffix]) + ".p"
results_d = {}
results_d["args"] = args
results_d["acc"] = acc
results_d["auc"] = auc
results_d["f1"] = f1
results_d["early_stopping"] = early_stopping
results_d["trainer_history"] = trainer.history
results_d["trainer_lr_history"] = trainer.lr_history
results_d["runtime"] = runtime
with open(results_dir / filename, "wb") as f:
pickle.dump(results_d, f)
def run_experiment_and_save(
model,
model_name,
results_dir,
models_dir,
args,
X_train,
X_test,
y_train,
y_test,
):
optimizers = set_optimizer(model, args)
steps_per_epoch = (X_train.shape[0] // args.batch_size) + 1
lr_schedulers = set_lr_scheduler(optimizers, steps_per_epoch, args)
early_stopping = EarlyStopping(
monitor=args.monitor,
min_delta=args.early_stop_delta,
patience=args.early_stop_patience,
)
model_checkpoint = ModelCheckpoint(
filepath=str(models_dir / "best_model"),
monitor=args.monitor,
save_best_only=True,
max_save=1,
)
trainer = Trainer(
model,
objective="regression",
optimizers=optimizers,
lr_schedulers=lr_schedulers,
reducelronplateau_criterion=args.monitor.split("_")[-1],
callbacks=[
early_stopping, model_checkpoint,
LRHistory(n_epochs=args.n_epochs)
],
)
start = time()
trainer.fit(
X_train={
"X_tab": X_train,
"target": y_train
},
X_val={
"X_tab": X_test,
"target": y_test
},
n_epochs=args.n_epochs,
batch_size=args.batch_size,
validation_freq=args.eval_every,
)
runtime = time() - start
y_pred = trainer.predict(X_tab=X_test)
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
r2 = r2_score(y_test, y_pred)
print(f"rmse with the best model: {rmse}")
if args.save_results:
suffix = str(datetime.now()).replace(" ", "_").split(".")[:-1][0]
filename = "_".join(["fb_comments", model_name, "best", suffix]) + ".p"
results_d = {}
results_d["args"] = args
results_d["rmse"] = rmse
results_d["r2"] = r2
results_d["early_stopping"] = early_stopping
results_d["trainer_history"] = trainer.history
results_d["trainer_lr_history"] = trainer.lr_history
results_d["runtime"] = runtime
with open(results_dir / filename, "wb") as f:
pickle.dump(results_d, f)
from utils import load_pickle, save_pickle
PRJ_DIR = os.path.dirname(__file__)
TEST_DATA_PATH = os.path.join(PRJ_DIR, 'data/test.csv')
MODEL_DIR = os.path.join(PRJ_DIR, 'model')
MODEL_PATH = os.path.join(MODEL_DIR, 'model.pth')
WIDE_PROC_PATH = os.path.join(MODEL_DIR, 'wide_proc.pickle')
DEEP_PROC_PATH = os.path.join(MODEL_DIR, 'deep_proc.pickle')
if __name__ == '__main__':
# 데이터 불러오기
test_df = pd.read_csv(TEST_DATA_PATH)
# Trinaer 불러오기
trainer = Trainer(model=MODEL_PATH, objective='binary')
trainer.batch_size = 256
# Preprocessor 불러오기
wide_processor = load_pickle(WIDE_PROC_PATH)
deep_processor = load_pickle(DEEP_PROC_PATH)
x_wide = wide_processor.transform(test_df)
x_deep = deep_processor.transform(test_df)
# 예측
y_pred = trainer.predict(X_wide=x_wide, X_tab=x_deep)
y = test_df['income_label']
print(f"Accuracy: {accuracy_score(y, y_pred)}")