#?coding:?utf-8
#?pylint:?disable?=?invalid-name?C0111
import?lightgbm?as?lgb
import?pandas?as?pd
import?numpy?as?np

#?load?or?create?your?dataset
print（‘Load?data...‘）
df_train?=?pd.read_csv（‘../binary_classification/binary.train‘?header=None?sep=‘\t‘）
df_test?=?pd.read_csv（‘../binary_classification/binary.test‘?header=None?sep=‘\t‘）
W_train?=?pd.read_csv（‘../binary_classification/binary.train.weight‘?header=None）[0]
W_test?=?pd.read_csv（‘../binary_classification/binary.test.weight‘?header=None）[0]

y_train?=?df_train[0].values
y_test?=?df_test[0].values
X_train?=?df_train.drop（0?axis=1）.values
X_test?=?df_test.drop（0?axis=1）.values

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）

#?specify?your?configurations?as?a?dict
params?=?{
????‘boosting_type‘:?‘gbdt‘
????‘objective‘:?‘binary‘
????‘metric‘:?‘binary_logloss‘
????‘num_leaves‘:?31
????‘learning_rate‘:?0.05
????‘feature_fraction‘:?0.9
????‘bagging_fraction‘:?0.8
????‘bagging_freq‘:?5
????‘verbose‘:?0
}

#?generate?a?feature?name
feature_name?=?[‘feature_‘?+?str（col）?for?col?in?range（num_feature）]

print（‘Start?training...‘）
#?feature_name?and?categorical_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]）

#?check?feature?name
print（‘Finish?first?10?rounds...‘）
print（‘7th?feature?name?is:‘?repr（lgb_train.feature_name[6]））

#?save?model?to?file
gbm.save_model（‘model.txt‘）

#?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（‘Finish?10?-?20?rounds?with?model?file...‘）

#?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（‘Finish?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（‘Finish?30?-?40?rounds?with?changing?bagging_frac