def test_deadline_stopper():
deadline = DeadlineStopper(0.0001)
gp_minimize(bench3, [(-1.0, 1.0)], callback=deadline, n_calls=10, random_state=1)
assert len(deadline.iter_time) == 1
assert np.sum(deadline.iter_time) > deadline.total_time
deadline = DeadlineStopper(60)
gp_minimize(bench3, [(-1.0, 1.0)], callback=deadline, n_calls=10, random_state=1)
assert len(deadline.iter_time) == 10
assert np.sum(deadline.iter_time) < deadline.total_time
def bayes_search(estimator,
search_spaces,
X,
y,
fit_params=None,
scoring=None,
n_jobs=1,
cv=None,
n_points=1,
n_iter=50,
refit=False,
random_state=9527,
verbose=0,
deadline=60):
optimizer = BayesSearchCV(estimator,
search_spaces,
scoring=scoring,
cv=cv,
n_points=n_points,
n_iter=n_iter,
n_jobs=n_jobs,
return_train_score=False,
refit=refit,
optimizer_kwargs={'base_estimator': 'GP'},
random_state=random_state)
best_parmas = BatchTrainer.hyperopt_search(
optimizer,
X,
y,
fit_params=fit_params,
title='BayesSearchCV',
callbacks=[VerboseCallback(verbose),
DeadlineStopper(deadline)])
return best_parmas
def tune_with_bayes(X_train, y_train):
roc_auc = make_scorer(roc_auc_score,
greater_is_better=True,
needs_threshold=True)
time_split = TimeSeriesSplit(n_splits=10)
cboost = CatBoostClassifier(thread_count=2, od_type='Iter', verbose=False)
search_spaces = {
'iterations': Integer(10, 1000),
'depth': Integer(1, 8),
'learning_rate': Real(0.01, 1.0, 'log-uniform'),
'random_strength': Real(1e-9, 10, 'log-uniform'),
'bagging_temperature': Real(0.0, 1.0),
'border_count': Integer(1, 255),
'l2_leaf_reg': Integer(2, 30),
'scale_pos_weight': Real(0.01, 1.0, 'uniform')
}
opt = BayesSearchCV(cboost,
search_spaces,
scoring=roc_auc,
cv=time_split,
n_iter=100,
n_jobs=1,
return_train_score=False,
refit=True,
optimizer_kwargs={'base_estimator': 'GP'},
random_state=17)
best_params = report_performance(
opt,
X_train,
y_train,
'CatBoost',
callbacks=[VerboseCallback(100),
DeadlineStopper(60 * 10)])
best_params['iterations'] = 1000
tuned_model = CatBoostClassifier(**best_params,
od_type='Iter',
one_hot_max_size=10)
# tuned_model = CatBoostClassifier(**best_params,task_type = "GPU",od_type='Iter',one_hot_max_size=10)
tuned_model.fit(X_train, y_train)
return tuned_model
def xgboost_grid(x, y):
try:
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=42)
except:
x = list(x)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=42)
params = {
"objective": ['reg:squarederror'],
"colsample_bytree": [0.25, 0.5, 0.75],
"learning_rate": [0.01, 0.1, 0.2, 0.3],
"max_depth": [10, 20, 50],
"gamma": [i * 0.05 for i in range(0, 5)],
"lambda": [i * 0.05 for i in range(0, 4)],
"alpha": [i * 0.05 for i in range(0, 4)],
"eta": [i * 0.05 for i in range(0, 4)],
"n_estimators": [400, 4000],
"tree_method": ["gpu_hist"]
}
xgb_temp = xgb.XGBRegressor()
reg = GridSearchCV(xgb_temp, params, verbose=5, cv=3)
time_to_stop = 60 * 60
ckpt_loc = "../data/train/bayes/ckpt_bayes_xgboost.pkl"
checkpoint_callback = CheckpointSaver(ckpt_loc)
reg.fit(x_train,
y_train,
callback=[DeadlineStopper(time_to_stop), checkpoint_callback])
print(reg.best_params_)
print(reg.best_score_)
return reg
# 'boosting_type':['Ordered'],
# 'learning_rate': Real(0.05, 1.0, 'uniform'),
# 'border_count': Integer(1, 25),
# 'fold_len_multiplier': Real(1.1, 1.16, prior='uniform')}
# Setting up BayesSearchCV
opt = BayesSearchCV(
clf,
search_spaces,
scoring=roc_auc,
cv=skf,
n_iter=5,
n_points=100,
n_jobs=
1, # use just 1 job with CatBoost in order to avoid segmentation fault
return_train_score=False,
refit=True,
optimizer_kwargs={'base_estimator': 'ET'}, #'GP', 'RF', 'ET'
random_state=57)
# Running the optimization
best_params = report_perf(
opt,
X,
y,
'CatBoost',
callbacks=[VerboseCallback(20),
DeadlineStopper(60 * 30)])
print("Notebook Runtime: %0.2f Minutes" % ((time.time() - notebookstart) / 60))
def xgboost_bayes_basic(x, y, csv_loc="../data/train/bayes.csv"):
global csv_loc_bayes
csv_loc_bayes = csv_loc
try:
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=42)
except:
x = list(x)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=42)
xgb_temp = xgb.XGBRegressor()
reg = BayesSearchCV(xgb_temp, {
"colsample_bytree": Real(0.5, 0.99),
"max_depth": Integer(5, 25),
"lambda": Real(0, 0.25),
"learning_rate": Real(0.1, 0.25),
"alpha": Real(0, 0.2),
"eta": Real(0, 0.1),
"gamma": Real(0, 0.1),
"n_estimators": Integer(500, 5000),
"objective": ["reg:squarederror"],
"tree_method": ["gpu_hist"]
},
n_iter=10000,
verbose=4,
cv=3)
time_to_stop = 60 * 60 * 47
now = datetime.now()
year = now.strftime("%Y")
month = now.strftime("%m")
day = now.strftime("%d")
hour = now.strftime("%H")
minute = now.strftime("%M")
sec = now.strftime("%S")
#ckpt_loc = "../data/train/bayes/ckpt_bayes_xgboost" + str(year) + "_"+ str(month) + "_" + str(day) + "_" + \
# str(hour) + "_" + str(minute) + "_" + str(sec) + ".pkl"
#checkpoint_callback = CheckpointSaver(ckpt_loc)
#reg.fit(x_train, y_train, callback=[DeadlineStopper(time_to_stop), checkpoint_callback])
custom_scorer = custom_skopt_scorer
reg.fit(x_train,
y_train,
callback=[DeadlineStopper(time_to_stop),
custom_scorer(x, y)])
#reg.fit(x_train, y_train, callback=[DeadlineStopper(time_to_stop)])
score = str(mean_squared_error(reg.predict(x_test), y_test))
print("MSE score: " + str(score))
score = str(mean_absolute_error(reg.predict(x_test), y_test))
print("MAE score: " + str(score))
score = str(r2_score(reg.predict(x_test), y_test))
print("r2 score: " + str(score))
return reg