LightGBM train with subset - from: https://github.com/microsoft/LightGBM/issues/2240#issuecomment-505305757

LightGBM train with subset.py

import numpy as np
import lightgbm as lgb



# generate simulation data
para=np.random.random((5000, 2))
data=np.zeros((10000,10))
for i in range(5000):
    mu, sigma=para[i,:]
    s=np.random.normal(mu, sigma, 1000)
    data[i,:]=np.histogram(s, bins=10, density=False,range=[-1,1])[0]


data_shuffle=data[:5000,:].copy()
for i in range(5000):
    np.random.shuffle(data_shuffle[i,:])


data[5000:,:]=data_shuffle

train_data = lgb.Dataset(data,label=[1]*5000+[0]*5000,free_raw_data=False)
train_data.save_binary('train_data.bin')


train_data = lgb.Dataset("train_data.bin")

subset_index=np.random.choice(np.arange(10000), 5000, replace=False)
subset_train_data_1=train_data.subset(subset_index).construct()


# generate new subset_index
subset_index=np.random.choice(np.arange(10000), 5000, replace=False)


subset_train_data_2=train_data.subset(subset_index).construct()


train_data_3 = lgb.Dataset(data,label=[1]*5000+[0]*5000,free_raw_data=False, reference=train_data)
subset_train_data_3=train_data_3.subset(subset_index).construct()


subset_train_data_4=lgb.Dataset(data[subset_index,:],label=np.array([1]*5000+[0]*5000)[subset_index],\
                                free_raw_data=False,reference=train_data).construct()



params = {
        'boosting_type': 'gbdt',
        'objective': 'binary',
        'metric': ["binary_error",'binary_logloss'],
        'metric_freq': 10,
        'num_leaves': 31,
        'num_threads': 1,
        'learning_rate': 0.1,
        'feature_fraction': 1,
        'boost_from_average': False,
        'verbose': 1
    }


# train using subset_train_data_1 and it works
gbm = lgb.train(params=params,
                train_set=subset_train_data_1,
                num_boost_round=10,
                valid_sets=[train_data],
                keep_training_booster=True)


#  continue training with subset_train_data_2, fail
gbm = lgb.train(params=params,
                train_set=subset_train_data_2,
                num_boost_round=10,
                valid_sets=[train_data],   
                init_model=gbm)

#  continue training with subset_train_data_3, fail
gbm = lgb.train(params=params,
                train_set=subset_train_data_3,
                num_boost_round=10,
                valid_sets=[train_data],   
                init_model=gbm)

#  continue training with subset_train_data_4, fail
gbm = lgb.train(params=params,
                train_set=subset_train_data_4,
                num_boost_round=10,
                valid_sets=[train_data],   
                init_model=gbm)