# 默认版本
pip install lightgbm
# MPI版本
pip install lightgbm --install-option=--mpi
# GPU版本
pip install lightgbm --install-option=--gpu
2 调用方法
在Python语言中LightGBM提供了两种调用方式，分为为原生的API和Scikit-learn API，两种方式都可以完成训练和验证。当然原生的API更加灵活，看个人习惯来进行选择。
2.1 定义数据集
df_train = pd.read_csv('https://cdn.coggle.club/LightGBM/examples/binary_classification/binary.train', header=None, sep='\t')
df_test = pd.read_csv('https://cdn.coggle.club/LightGBM/examples/binary_classification/binary.test', header=None, sep='\t')
W_train = pd.read_csv('https://cdn.coggle.club/LightGBM/examples/binary_classification/binary.train.weight', header=None)[0]
W_test = pd.read_csv('https://cdn.coggle.club/LightGBM/examples/binary_classification/binary.test.weight', header=None)[0]
y_train = df_train[0]
y_test = df_test[0]
X_train = df_train.drop(0, axis=1)
X_test = df_test.drop(0, axis=1)
num_train, num_feature = X_train.shape
# create dataset for lightgbm
# if you want to re-use data, remember to set free_raw_data=False
lgb_train = lgb.Dataset(X_train, y_train,
weight=W_train, free_raw_data=False)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train,
weight=W_test, free_raw_data=False)
# generate feature names
feature_name = ['feature_' + str(col) for col in range(num_feature)]
gbm = lgb.train(params,
lgb_train,
num_boost_round=10,
valid_sets=lgb_train, # eval training data
feature_name=feature_name,
categorical_feature=[21])
2.3 模型保存与加载
# save model to file
gbm.save_model('model.txt')
print('Dumping model to JSON...')
model_json = gbm.dump_model()
with open('model.json', 'w+') as f:
json.dump(model_json, f, indent=4)
2.4 查看特征重要性
# feature names
print('Feature names:', gbm.feature_name())
# feature importances
print('Feature importances:', list(gbm.feature_importance()))
2.5 继续训练
# continue training
# init_model accepts:
# 1. model file name
# 2. Booster()
gbm = lgb.train(params,
lgb_train,
num_boost_round=10,
init_model='model.txt',
valid_sets=lgb_eval)
print('Finished 10 - 20 rounds with model file...')
2.6 动态调整模型超参数
# decay learning rates
# learning_rates accepts:
# 1. list/tuple with length = num_boost_round
# 2. function(curr_iter)
gbm = lgb.train(params,
lgb_train,
num_boost_round=10,
init_model=gbm,
learning_rates=lambda iter: 0.05 * (0.99 ** iter),
valid_sets=lgb_eval)
print('Finished 20 - 30 rounds with decay learning rates...')
# change other parameters during training
gbm = lgb.train(params,
lgb_train,
num_boost_round=10,
init_model=gbm,
valid_sets=lgb_eval,
callbacks=[lgb.reset_parameter(bagging_fraction=[0.7] * 5 + [0.6] * 5)])
print('Finished 30 - 40 rounds with changing bagging_fraction...')
2.7 自定义损失函数
# self-defined objective function
# f(preds: array, train_data: Dataset) -> grad: array, hess: array
# log likelihood loss
def loglikelihood(preds, train_data):
labels = train_data.get_label()
preds = 1. / (1. + np.exp(-preds))
grad = preds - labels
hess = preds * (1. - preds)
return grad, hess
# self-defined eval metric
# f(preds: array, train_data: Dataset) -> name: string, eval_result: float, is_higher_better: bool
# binary error
# NOTE: when you do customized loss function, the default prediction value is margin
# This may make built-in evalution metric calculate wrong results
# For example, we are doing log likelihood loss, the prediction is score before logistic transformation
# Keep this in mind when you use the customization
def binary_error(preds, train_data):
labels = train_data.get_label()
preds = 1. / (1. + np.exp(-preds))
return 'error', np.mean(labels != (preds > 0.5)), False
gbm = lgb.train(params,
lgb_train,
num_boost_round=10,
init_model=gbm,
fobj=loglikelihood,
feval=binary_error,
valid_sets=lgb_eval)
print('Finished 40 - 50 rounds with self-defined objective function and eval metric...')
2.8 调参方法
For Faster Speed
Use bagging by setting bagging_fraction and bagging_freq
Use feature sub-sampling by setting feature_fraction
Use small max_bin
Use save_binary to speed up data loading in future learning
Use parallel learning, refer to Parallel Learning Guide <./Parallel-Learning-Guide.rst>__
For Better Accuracy
Use large max_bin (may be slower)
Use small learning_rate with large num_iterations
Use large num_leaves (may cause over-fitting)
Use bigger training data
Try dart
Deal with Over-fitting
Use small max_bin
Use small num_leaves
Use min_data_in_leaf and min_sum_hessian_in_leaf
Use bagging by set bagging_fraction and bagging_freq
Use feature sub-sampling by set feature_fraction
Use bigger training data
Try lambda_l1, lambda_l2 and min_gain_to_split for regularization
Try max_depth to avoid growing deep tree
Try extra_trees
Try increasing path_smooth
lg = lgb.LGBMClassifier(silent=False)
param_dist = {"max_depth": [4,5, 7],
"learning_rate" : [0.01,0.05,0.1],
"num_leaves": [300,900,1200],
"n_estimators": [50, 100, 150]
grid_search = GridSearchCV(lg, n_jobs=-1, param_grid=param_dist, cv = 5, scoring="roc_auc", verbose=5)
grid_search.fit(train,y_train)
grid_search.best_estimator_, grid_search.best_score_
贝叶斯优化
import warnings
import time
warnings.filterwarnings("ignore")
from bayes_opt import BayesianOptimization
def lgb_eval(max_depth, learning_rate, num_leaves, n_estimators):
params = {
"metric" : 'auc'
params['max_depth'] = int(max(max_depth, 1))
params['learning_rate'] = np.clip(0, 1, learning_rate)
params['num_leaves'] = int(max(num_leaves, 1))
params['n_estimators'] = int(max(n_estimators, 1))
cv_result = lgb.cv(params, d_train, nfold=5, seed=0, verbose_eval =200,stratified=False)
return 1.0 * np.array(cv_result['auc-mean']).max()
lgbBO = BayesianOptimization(lgb_eval, {'max_depth': (4, 8),
'learning_rate': (0.05, 0.2),
'num_leaves' : (20,1500),
'n_estimators': (5, 200)}, random_state=0)
lgbBO.maximize(init_points=5, n_iter=50,acq='ei')
print(lgbBO.max)
