LightGBM分类代码

安宇雨 - 随手采集
2019-04-12 01:23:01
随手采集
0000-未整理-等待研究

代码

import json
import lightgbm as lgb
import pandas as pd
from sklearn.metrics import roc_auc_score

path = "/Users/shuubiasahi/Documents/githup/LightGBM/examples/regression/"
print("load data")
df_train = pd.read_csv(path + "regression.train", header=None, sep='\t')
df_test = pd.read_csv(path + "regression.train", header=None, sep='\t')
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
# create dataset for lightgbm
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)
# specify your configurations as a dict
params = {

'task': 'train',
'boosting_type': 'gbdt',
'objective': 'binary',
'metric': {'l2', 'auc'},
'num_leaves': 31,
'learning_rate': 0.05,
'feature_fraction': 0.9,
'bagging_fraction': 0.8,
'bagging_freq': 5,
'verbose': 0

}
print('Start training...')
# train
gbm = lgb.train(params,

            lgb_train,
            num\_boost\_round=20,
            valid_sets=lgb_eval,
            early\_stopping\_rounds=5)

print('Save model...')
# save model to file
gbm.save_model('lightgbm/model.txt')
print('Start predicting...')
# predict
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)
# eval
print(y_pred)
print('The roc of prediction is:', roc_auc_score(y_test, y_pred))
print('Dump model to JSON...')
# dump model to json (and save to file)
model_json = gbm.dump_model()
with open('lightgbm/model.json', 'w+') as f:

json.dump(model_json, f, indent=4)

print('Feature names:', gbm.feature_name())
print('Calculate feature importances...')
# feature importances
print('Feature importances:', list(gbm.feature_importance()))

原网址: 访问
创建于: 2019-04-12 01:23:01
目录: default
标签: 无

未标明原创文章均为采集，版权归作者所有，转载无需和我联系，请注明原出处，南摩阿彌陀佛，知识，不只知道，要得到