LightGBM代码模板

一、二分类代码模板

二分类也就是我们平时的0和1二类，和逻辑回归的label一样

import lightgbm as lgb  
import pandas as pd  
import numpy as np  
import pickle  
from sklearn.metrics import roc_auc_score  
from sklearn.model_selection import train_test_split  

print("Loading Data ... ")  

# 导入数据  
train_x, train_y, test_x = load_data()  

# 用sklearn.cross_validation进行训练数据集划分，这里训练集和交叉验证集比例为7：3，可以自己根据需要设置  
X, val_X, y, val_y = train_test_split(  
    train_x,  
    train_y,  
    test_size=0.05,  
    random_state=1,  
    stratify=train_y # 这里保证分割后y的比例分布与原数据一致  
)  

X_train = X  
y_train = y  
X_test = val_X  
y_test = val_y  

# 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 = {  
    'boosting_type': 'gbdt',  
    'objective': 'binary',  
    'metric': {'binary_logloss', 'auc'},  #二进制对数损失
    'num_leaves': 5,  
    'max_depth': 6,  
    'min_data_in_leaf': 450,  
    'learning_rate': 0.1,  
    'feature_fraction': 0.9,  
    'bagging_fraction': 0.95,  
    'bagging_freq': 5,  
    'lambda_l1': 1,    
    'lambda_l2': 0.001,  # 越小l2正则程度越高  
    'min_gain_to_split': 0.2,  
    'verbose': 5,  
    'is_unbalance': True  
}  

# train  
print('Start training...')  
gbm = lgb.train(params,  
                lgb_train,  
                num_boost_round=10000,  
                valid_sets=lgb_eval,  
                early_stopping_rounds=500)  

print('Start predicting...')  

preds = gbm.predict(test_x, num_iteration=gbm.best_iteration)  # 输出的是概率结果  

# 导出结果  
threshold = 0.5  
for pred in preds:  
    result = 1 if pred > threshold else 0  

# 导出特征重要性  
importance = gbm.feature_importance()  
names = gbm.feature_name()  
with open('./feature_importance.txt', 'w+') as file:  
    for index, im in enumerate(importance):  
        string = names[index] + ', ' + str(im) + '\n'  
        file.write(string)  

里面的参数可以自己更改，又或者是配合着网格搜索法调参

下面我使用kaggle的信用卡欺诈识别数据尝试一下效果如何

 

# -*- coding: utf-8 -*-
"""
Created on Thu Feb 25 15:08:00 2021

@author: Administrator
"""

#%%导入模块
import pandas as pd 
import numpy as np
from scipy import stats
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
plt.rc("font",family="SimHei",size="12")  #解决中文无法显示的问题


#%%导入数据
creditcard = pd.read_csv('D:/信用卡欺诈检测/creditcard.csv/creditcard.csv')


#%%建模
import lightgbm as lgb  
import pandas as pd  
import numpy as np  
import pickle  
from sklearn.metrics import roc_auc_score  
from sklearn.model_selection import train_test_split  

print("Loading Data ... ")  

# 导入数据  
train_x = creditcard.iloc[:,1:-1]
train_y = creditcard['Class']

# 用sklearn.cross_validation进行训练数据集划分，这里训练集和交叉验证集比例为7：3，可以自己根据需要设置  
X, val_X, y, val_y = train_test_split(  
    train_x,  
    train_y,  
    test_size=0.05,  
    random_state=1,  
    stratify=train_y # 这里保证分割后y的比例分布与原数据一致  
)  

X_train = X  
y_train = y  
X_test = val_X  
y_test = val_y  

# 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 = {  
    'boosting_type': 'gbdt',  
    'objective': 'binary',  
    'metric': {'binary_logloss', 'auc'},  #二进制对数损失
    'num_leaves': 5,  
    'max_depth': 6,  
    'min_data_in_leaf': 450,  
    'learning_rate': 0.1,  
    'feature_fraction': 0.9,  
    'bagging_fraction': 0.95,  
    'bagging_freq': 5,  
    'lambda_l1': 1,    
    'lambda_l2': 0.001,  # 越小l2正则程度越高  
    'min_gain_to_split': 0.2,  
    'verbose': 5,  
    'is_unbalance': True  
}  

# train  
print('Start training...')  
gbm = lgb.train(params,  
                lgb_train,  
                num_boost_round=10000,  
                valid_sets=lgb_eval,  
                early_stopping_rounds=500)  

print('Start predicting...')  

preds = gbm.predict(X_test, num_iteration=gbm.best_iteration)  # 输出的是概率结果  

# 导出结果  
preds= pd.DataFrame(preds)
preds[preds>0.5] = 1
preds[preds<=0.5] = 0

#%%一些模型评估方法
from sklearn.metrics import precision_score, recall_score, f1_score,confusion_matrix
matrix = confusion_matrix(y_test, preds)
print("混淆矩阵:\n", matrix)
print("精度:", precision_score(y_test, preds))
print("召回率:", recall_score(y_test, preds))
print("f1分数:", f1_score(y_test, preds))
'''
混淆矩阵:
 [[13899   317]
 [    7    18]]
精度: 0.05373134328358209
召回率: 0.72
f1分数: 0.1
'''


# 导出特征重要性  
importance = gbm.feature_importance()  
names = gbm.feature_name()  
with open('./feature_importance.txt', 'w+') as file:  
    for index, im in enumerate(importance):  
        string = names[index] + ', ' + str(im) + '\n'  
        file.write(string)  

好像也不是特别好

 

补充：

1.LightGBM可以自动处理缺失值