lightgbt的simple_example

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

print('load data...')
#如果带中文字符，那么就会报错，路径不能带中文
df_train = pd.read_csv('D:/2345download/LightGBM-master/examples/regression/regression.train',header=None,sep='\t')
df_test = pd.read_csv('D:/2345download/LightGBM-master/examples/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

#create dataset for lightgbm
#传进来的是dataframe或者series
lgb_train = lgb.Dataset(X_train,y_train)
lgb_eval = lgb.Dataset(X_test,y_test,reference=lgb_train)

#specify your configureations as a dict
params = {
    'task': 'train',
    'boosting_type': 'gbdt',
    'objective': 'regression',
    'metric': {'l2', 'auc'},
    'num_leaves': 31,
    'learning_rate': 0.05,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
        }
print('Starting training...')
#train
gbm = lgb.train(params,lgb_train,
                num_boost_round=20,
                valid_sets=lgb_eval,
                early_stopping_rounds=5)
print('Save model ...')
gbm.save_model('model.txt')

print('Start predict')
y_pred = gbm.predict(X_test,num_iteration=gbm.best_iteration)
#eva
print('The rmse of prediction is:',mean_squared_error(y_test,y_pred)**0.5)

评价：这个用gbt进行分类预测的代码，官网的simple_example模型代码，bgt有很多参数。现在总结下

'num_leaves': 31,

树的深度

'bagging_fraction': 0.8,
    'bagging_freq': 5,

bagging的初始值和衰减速率

'learning_rate': 0.05,

这个是学习步长的衰减率

其余的没懂

用这个预测iris数据集，准确率100%！！！

from sklearn import datasets
import lightgbm as lgb
import numpy as np
import json
import lightgbm as lgb
import pandas as pd
from sklearn.metrics import mean_squared_error


data = datasets.load_iris()
X_train = np.vstack((data['data'][0:40],data['data'][50:90],data['data'][100:140])).tolist()
y_train = np.hstack((data['target'][0:40],data['target'][50:90],data['target'][100:140])).tolist()
X_test = np.vstack((data['data'][40:50],data['data'][90:100],data['data'][140:150])).tolist()
y_test = np.hstack((data['target'][40:50],data['target'][90:100],data['target'][140:150])).tolist()


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

#specify your configureations as a dict
params = {
    'task': 'train',
    'boosting_type': 'gbdt',
    'objective': 'regression',
    'metric': {'l2', 'auc'},
    'num_leaves': 31,
    'learning_rate': 0.05,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
        }
print('Starting training...')
#train
gbm = lgb.train(params,lgb_train,
                num_boost_round=20,
                valid_sets=lgb_eval,
                early_stopping_rounds=5)
print('Save model ...')
gbm.save_model('model.txt')

print('Start predict')
y_pred = gbm.predict(X_test,num_iteration=gbm.best_iteration)
#eva
print('The rmse of prediction is:',mean_squared_error(y_test,y_pred)**0.5)