def train(self, params_list=None):
self.read_data()
# debug mode only load part of data, to test whether the whole pipeline works
if self.debug:
self.train_X = self.train_X[:1000]
self.test = self.test[:1000]
self.train_Y = self.train_Y[:1000]
self.bayesian_iteration = 1
if not self.bayesian_optimisation:
# frid search the best parameter
params_list = {
"objective": ["regression"],
"metric": ["rmse"],
'boosting': ["gbdt"],
"num_leaves": [10, 30, 50],
"min_child_weight": [40, 50, 60],
"max_depth": [5, 7, 10],
"learning_rate": [0.01, 0.03, 0.05, 0.06],
"bagging_fraction": [0.6, 0.7, 0.8],
"feature_fraction": [0.6, 0.7, 0.8],
"bagging_frequency": [4, 5, 6],
}
super(LGBModel, self).train(params_list)
else:
func_param = self.prepare_baysian_optimization()
xp, yp, param_candidate = bayesian_optimisation(**func_param)
self.so_far_best_rmse = yp[0]
for i in range(1, len(param_candidate)):
if yp[i] < self.so_far_best_rmse:
self.so_far_best_rmse = yp[i]
self.so_far_best_params = param_candidate[i]
def train(self, params_list=None):
self.read_data()
# debug mode only load part of data, to test whether the whole pipeline works
if self.debug:
self.train_X = self.train_X[:1000]
self.test = self.test[:1000]
self.train_Y = self.train_Y[:1000]
self.bayesian_iteration = 1
if not self.bayesian_optimisation:
# frid search the best parameter
params_list = {
"objective": ["regression"],
"learning_rate" : ["0.02,0.03,0.04,0.05"],
"depth":[4,5,6,7,8],
"eval_metric":['RMSE'],
"bagging_temperature":[0.8,0.9],
"metric_period":[80,90,100],
"od_wait":[50,60]
}
super(CatBoostModel, self).train(params_list)
else:
func_param = self.prepare_baysian_optimization()
xp, yp, param_candidate = bayesian_optimisation(**func_param)
self.so_far_best_rmse = yp[0]
for i in range(1, len(param_candidate)):
if yp[i] < self.so_far_best_rmse:
self.so_far_best_rmse = yp[i]
self.so_far_best_params = param_candidate[i]
def train(self, params_list=None):
if self.debug:
params = {
"task": "reg",
"metric": "rmse",
"lr": 0.2,
"lambda": 0.005
}
self._train(params)
return
if not self.bayesian_optimisation:
# frid search the best parameter
params_list = {
"task": ["reg"],
"metric": ["rmse"],
'lr': [0.05, 0.1, 0.15, 0.2, 0.25, 0.3],
'lambda': [0.002, 0.003, 0.004, 0.005]
}
super(FFMModel, self).train(params_list)
else:
func_param = self.prepare_baysian_optimization()
xp, yp, param_candidate = bayesian_optimisation(**func_param)
self.so_far_best_rmse = yp[0]
# iterate all the result from bayesian process and choose the best one
for i in range(1, len(param_candidate)):
if yp[i] < self.so_far_best_rmse:
self.so_far_best_rmse = yp[i]
self.so_far_best_params = param_candidate[i]