# coding: utf-8

# pylint: disable = invalid-name, C0111

import json

import lightgbm as lgb

import pandas as pd

from sklearn.metrics import mean_squared_error

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.datasets import make_classification

iris = load_iris()

data=iris.data

target = iris.target

X_train,X_test,y_train,y_test =train_test_split(data,target,test_size=0.2)

# 加載你的數(shù)據(jù)

# print('Load data...')

# df_train = pd.read_csv('../regression/regression.train', header=None, sep='\t')

# df_test = pd.read_csv('../regression/regression.test', 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

# 創(chuàng)建成lgb特征的數(shù)據(jù)集格式

lgb_train = lgb.Dataset(X_train, y_train)

lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)

# 將參數(shù)寫成字典下形式

params = {

'task': 'train',

'boosting_type': 'gbdt', # 設(shè)置提升類型

'objective': 'regression', # 目標(biāo)函數(shù)

'metric': {'l2', 'auc'}, # 評估函數(shù)

'num_leaves': 31, # 葉子節(jié)點數(shù)

'learning_rate': 0.05, # 學(xué)習(xí)速率

'feature_fraction': 0.9, # 建樹的特征選擇比例

'bagging_fraction': 0.8, # 建樹的樣本采樣比例

'bagging_freq': 5, # k 意味著每 k 次迭代執(zhí)行bagging

'verbose': 1 # <0 顯示致命的, =0 顯示錯誤 (警告), >0 顯示信息

}

print('Start training...')

# 訓(xùn)練 cv and train

gbm = lgb.train(params,lgb_train,num_boost_round=20,valid_sets=lgb_eval,early_stopping_rounds=5)

print('Save model...')

# 保存模型到文件

gbm.save_model('model.txt')

print('Start predicting...')

# 預(yù)測數(shù)據(jù)集

y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)

# 評估模型

print('The rmse of prediction is:', mean_squared_error(y_test, y_pred) ** 0.5)

快把你的結(jié)果在評論區(qū)里亮出來吧！