params_est = {
'n_estimators': 200,
'loss': 'deviance',
'learning_rate': 0.04,
'subsample': 0.50,
'min_samples_leaf': 60,
'max_features': 4,
'random_state': 1
}
bst7 = GradientBoostingClassifier(**params_est)
bst7.fit(X_train_xgb2, y_train)
sub_data = submiss[cols].values
submiss_val = xgb.DMatrix(sub_data, missing=np.NaN)
t1 = np.asarray([[i] for i in bst1.predict(submiss_val)])
t2 = np.asarray([[i] for i in bst2.predict_proba(submiss[cols].values)[:, 1]])
t3 = np.asarray([[i] for i in bst3.predict_proba(submiss[cols].values)[:, 1]])
t4 = np.asarray(bst4.predict_proba(submiss[cols_k2].values))
t5 = np.asarray([[i] for i in bst5.predict_proba(submiss_reg)[:, 1]])
t6 = np.asarray([[
i
] for i in bst6.predict(xgb.DMatrix(submiss[xgb2_cols].values, missing=np.NaN))
])
t7 = np.asarray([[i]
for i in bst7.predict_proba(submiss[xgb2_cols].values)[:, 1]])
tst_data = np.hstack((
t1,
t2,
t3,
t4,
# Parameters
seed = 1337
nfolds = 5
test_size = 0.2
path_to_exec = "~/Documents/apps/LightGBM/lightgbm"
np.random.seed(seed) # for reproducibility
X, Y = datasets.make_classification(n_samples=1000,
n_features=100,
random_state=seed)
x_train, x_test, y_train, y_test = model_selection.train_test_split(
X, Y, test_size=test_size, random_state=seed)
# 'exec_path' is the path to lightgbm executable
clf = GBMClassifier(exec_path=path_to_exec,
num_iterations=1000,
learning_rate=0.01,
min_data_in_leaf=1,
num_leaves=5,
metric='binary_error',
early_stopping_round=20)
clf.fit(x_train, y_train, test_data=[(x_test, y_test)])
y_prob = clf.predict_proba(x_test)
y_pred = y_prob.argmax(-1)
print("Log loss: ", metrics.log_loss(y_test, y_prob))
print("Accuracy: ", metrics.accuracy_score(y_test, y_pred))
print("Best round: ", clf.best_round)
min_sum_hessian_in_leaf=1e-4,
num_iterations=5000,
num_threads=4,
early_stopping_round=EARLY_STOPPING,
drop_rate=0.0001,
max_depth=6,
lambda_l1=0.,
lambda_l2=0.,
max_bin=63,
feature_fraction=1.0,
#bagging_fraction=0.5,
#bagging_freq=3,
verbose=True)
cl.fit(X_train, y_train, test_data=[(X_test, y_test)])
#</editor-fold>
#<editor-fold desc="Генерация сабмита">
if MAKE_SUBMISSION:
print('Computing submission probabilities...')
y_submission = cl.predict_proba(x_test)[:, 1]
print('Store submission data')
submission_filename = os.path.join(submission_folder,
'submission_lightgbm.dat')
store_submission(y_submission, submission_filename)
print(
'Submission data have been stored in {}\n'.format(submission_filename))
#</editor-fold>