def evaluate(params, X, y):
# Initilize instance of estimator
est = LGBMRegressor(boosting='gbdt', n_jobs=-1, random_state=2018)
# Set params
est.set_params(**params)
# Calc CV score
scores = cross_val_score(estimator=est, X=X, y=y,
scoring='r2', cv=4)
score = np.mean(scores)
return score
rstate=np.random.RandomState(seed=2018))
# Print best parameters
best_params = space_eval(hyper_space, best_vals)
print("BEST PARAMETERS: " + str(best_params))
# Print best CV score
scores = [-trial['result']['loss'] for trial in trials.trials]
print("BEST CV SCORE: " + str(np.max(scores)))
# Print execution time
tdiff = trials.trials[-1]['book_time'] - trials.trials[0]['book_time']
print("ELAPSED TIME: " + str(tdiff.total_seconds() / 60))
# Set params
est.set_params(**best_params)
# Fit
est.fit(X_train, y_train)
y_pred = est.predict(X_test)
# Predict
score = r2_score(y_test, y_pred)
print("R2 SCORE ON TEST DATA: {}".format(score))
#==============================================================================
# Tree structure of hyperparameter space (Optional)
#==============================================================================
# You must change the evaluate function in order to extract learning rate
# and n_estimators from choices. Please add the following code to the start of
# evaluate function
class LightGBM(BaseModel):
"""XGBoost Class."""
def __init__(self,
tuning_metric='mse',
trials='trials',
bottom_coding=None,
transform=None,
**kwargs):
"""Initialize hyperparameters."""
super(LightGBM, self).__init__(bottom_coding=bottom_coding,
transform=transform)
self.model = LGBMRegressor
self.tuning_metric = tuning_metric
self.trials = Trials() \
if trials == 'trials' \
else MongoTrials('mongo://localhost:1234/foo_db/jobs',
exp_key='exp1')
self.set_parameters()
def set_parameters(self):
"""Set the model hyperparameter sweep."""
self.space = {
"objective":
self.tuning_metric,
"device":
"gpu",
'min_data_in_leaf':
hp.choice('min_data_in_leaf', [100, 1000, 300]),
'boosting_type':
hp.choice('boosting_type', ['gbdt']),
'num_leaves':
scope.int(hp.quniform('num_leaves', 30, 250, 1)),
'learning_rate':
hp.loguniform('learning_rate', np.log(0.01), np.log(0.2)),
'subsample_for_bin':
scope.int(hp.quniform('subsample_for_bin', 20000, 300000, 20000)),
'reg_alpha':
hp.uniform('reg_alpha', 0.0, 1.0),
'reg_lambda':
hp.uniform('reg_lambda', 0.0, 1.0),
'colsample_bytree':
hp.uniform('colsample_by_tree', 0.6, 1.0)
}
def tune(self, training_set, logger=None, saver=None):
self.training_set = training_set
objective = generate_objective(self.training_set, self.tuning_metric)
best = space_eval(
self.space,
fmin(fn=objective,
space=self.space,
trials=self.trials,
algo=tpe.suggest,
max_evals=self.max_evals))
print(f'Search space: {self.space}')
print(f'Best hyperparams: {best}')
self.model = LGBMRegressor()
self.model.set_params(**best)
self.model.fit(training_set.X, training_set.y)
def instantiate_model(self, params):
model = LGBMRegressor()
model.set_params(**params)
return model
min_child_weight=0.001, min_child_samples=20, min_split_gain=0.1, subsample=0.8, colsample_bytree=0.8, objective= 'binary', random_state=7) lgbm_param = lgbm_model.get_params() lgbm_train = lgb.Dataset(X,Y) '''使用交叉验证的方式确定最优的树数量''' cvresult = lgb.cv(lgbm_param, lgbm_train, num_boost_round=lgbm_param['n_estimators'],nfold=5,metrics='auc',early_stopping_rounds=100) best_n_estimators=len(cvresult['auc-mean']) lgbm_model.set_params(n_estimators=best_n_estimators) lgbm_model.fit(X,Y,eval_metric='auc') feat_imp = pd.Series(lgbm_model.feature_importances_,index=X.columns) feat_imp=feat_imp.sort_values(ascending=False) valid_feature_num=len(np.where(feat_imp>0)[0]) #有效变量是有feature_importance的变量（在lgbm树模型中有贡献的变量，其他的变量没有用到） print(valid_feature_num) # In[74]: '''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' ''''''''' LGB调优feature_num '''''''''''
def instantiate_model(self, params):
model = LGBMRegressor()
model.set_params(**params)
return model