python 贝叶斯优化调参 代码实现

环境安装

pip 的可以使用这个
$ pip install bayesian-optimization
conda的可以使用这个
$ conda install -c conda-forge bayesian-optimization

优化类的实现

# 导入包
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
import catboost as cb
from bayes_opt import BayesianOptimization


class optimizationClass():
    # 初始化的时候把数据集传进来
    def __init__(self,df):
        self.df = df 
        
     # 定义一个评估指标的函数评估模型好坏   
    def reg_calculate(self,true, prediction): 
        mse = metrics.mean_squared_error(true, prediction)
        rmse = np.sqrt(mse)
        mae = metrics.mean_absolute_error(true, prediction)
        mape = np.mean(np.abs((true - prediction) / true)) * 100
        r2 = metrics.r2_score(true, prediction)
        rmsle = np.sqrt(metrics.mean_squared_log_error(true, prediction))
        # print("mse: {}, rmse: {}, mae: {}, mape: {}, r2: {}, rmsle: {}".format(mse, rmse, mae, mape, r2, rmsle))
        # return mse, rmse, mae, mape, r2, rmsle
        return {"mse": mse, "rmse": rmse, "mae": mae, "mape": mape, "r2": r2, "rmsle": rmsle}    
    
    # 优化函数 参数为你需要调参的 hyper Parameter 这里用catBoost作为样例
    def optimization_function(self,iterations,learning_rate,depth,l2_leaf_reg):
        parameterDict = {"iterations":int(iterations),"learning_rate": float(learning_rate), "depth": int(depth),
                         "l2_leaf_reg":float(l2_leaf_reg),
                         "task_type":"CPU","logging_level":"Silent"}
        CB_Regressor=cb.CatBoostRegressor(**parameterDict)
        CB_Regressor.fit(self.df["X_train"], self.df["Y_train"])
        Y_pre=CB_Regressor.predict(self.df["X_test"])
        resDict =self.reg_calculate(self.df["Y_test"],Y_pre)
        return resDict["r2"]
    # 定义一下模型
    def run(self, init_points=2,n_iter=3):
        cb_bo = BayesianOptimization(
        self.optimization_function,
        {'iterations': (200, 5000),
        'learning_rate': (1e-6, 1e-2),
        'depth': (2, 15),
        'l2_leaf_reg': (0, 5)}
        )
        cb_bo.maximize(
                        init_points=init_points,
                        n_iter=n_iter)
        print("Final result:", cb_bo.max)
#         

# 如何使用 

Opt = optimizationClass(df = {"X_train":X_Train, "X_test":X_Test, "Y_train":Y_Train, "Y_test":Y_Test})
Opt.run()

boston Estate Dataset Example:

from sklearn import datasets  # 导入库

boston = datasets.load_boston()  # 导入波士顿房价数据
print(boston.keys())  # 查看键(属性)     ['data','target','feature_names','DESCR', 'filename'] 
print(boston.data.shape,boston.target.shape)  # 查看数据的形状 (506, 13) (506,)
print(boston.feature_names)  # 查看有哪些特征 这里共13种
print(boston.DESCR)  # described 描述这个数据集的信息 
print(boston.filename)  # 文件路径 


from sklearn.model_selection import train_test_split
# check data shape
print("boston.data.shape %s , boston.target.shape %s"%(boston.data.shape,boston.target.shape))
train = boston.data  # sample
target = boston.target  # target
# 切割数据样本集合测试集
X_train, X_test, Y_train, Y_test = train_test_split(train, target, test_size=0.2)  # 20%测试集；80%训练集


op = optimizationClass({"X_train":X_train,"X_test":X_test,"Y_train":Y_train,"Y_test":Y_test})
op.run(init_points=20,n_iter=30)

輸出結果：

|   iter    |  target   |   depth   | iterat... | l2_lea... | learni... |
-------------------------------------------------------------------------
|  1        |  0.9282   |  11.81    |  4.533e+0 |  3.429    |  0.004794 |
|  2        |  0.9276   |  5.078    |  4.344e+0 |  3.845    |  0.002252 |
|  3        |  0.9346   |  7.365    |  2.657e+0 |  3.246    |  0.006347 |
|  4        |  0.9209   |  11.48    |  2.92e+03 |  3.517    |  0.002591 |
|  5        |  0.499    |  10.03    |  419.6    |  4.096    |  0.001719 |
|  6        |  0.9343   |  8.34     |  2.694e+0 |  4.258    |  0.007294 |
|  7        |  0.9249   |  8.519    |  854.2    |  2.287    |  0.006147 |
|  8        |  0.9332   |  9.853    |  3.582e+0 |  2.197    |  0.007308 |
|  9        |  0.9279   |  4.312    |  4.274e+0 |  1.338    |  0.007123 |
|  10       |  0.5959   |  11.42    |  1.607e+0 |  0.1317   |  0.000427 |
|  11       |  0.8569   |  4.669    |  331.7    |  0.8752   |  0.006876 |
|  12       |  0.9156   |  14.84    |  4.485e+0 |  3.21     |  0.005824 |
|  13       |  0.4344   |  2.786    |  1.692e+0 |  1.453    |  0.000322 |
|  14       |  0.9264   |  6.568    |  4.434e+0 |  4.968    |  0.001957 |
|  15       |  0.5893   |  14.47    |  344.0    |  0.09192  |  0.002032 |
|  16       |  0.9308   |  5.575    |  3.734e+0 |  4.577    |  0.004715 |
|  17       |  0.9091   |  14.26    |  2.902e+0 |  0.823    |  0.003099 |
|  18       |  0.9212   |  12.85    |  2.764e+0 |  0.6054   |  0.0057   |
|  19       |  0.9308   |  8.671    |  4.675e+0 |  1.319    |  0.008707 |
|  20       |  0.8202   |  11.81    |  1.814e+0 |  2.959    |  0.001198 |
|  21       |  0.9159   |  10.66    |  4.572e+0 |  4.217    |  0.001212 |
|  22       |  0.9269   |  10.75    |  840.0    |  0.2402   |  0.008043 |
|  23       |  0.9254   |  11.77    |  2.675e+0 |  1.939    |  0.003613 |
|  24       |  0.743    |  3.133    |  287.7    |  3.102    |  0.00504  |
|  25       |  0.8311   |  9.778    |  2.659e+0 |  3.956    |  0.000840 |
|  26       |  0.8424   |  6.952    |  2.146e+0 |  3.603    |  0.001016 |
|  27       |  0.8028   |  7.485    |  201.4    |  3.991    |  0.009137 |
|  28       |  0.7884   |  12.78    |  4.139e+0 |  0.01309  |  0.000319 |
|  29       |  0.8163   |  6.678    |  2.703e+0 |  0.9174   |  0.000598 |
|  30       |  0.9211   |  3.304    |  2.852e+0 |  3.181    |  0.00489  |
|  31       |  0.9315   |  10.15    |  4.572e+0 |  4.742    |  0.009919 |
|  32       |  0.9153   |  2.532    |  2.65e+03 |  2.52     |  0.006542 |
|  33       |  0.9266   |  11.07    |  2.685e+0 |  1.156    |  0.004197 |
|  34       |  0.9246   |  3.542    |  4.578e+0 |  1.338    |  0.004215 |
|  35       |  0.9176   |  3.253    |  4.567e+0 |  1.612    |  0.002075 |
|  36       |  0.9258   |  3.051    |  2.911e+0 |  0.6876   |  0.007575 |
|  37       |  0.9319   |  7.894    |  4.546e+0 |  5.0      |  0.01     |
|  38       |  0.9141   |  2.334    |  2.683e+0 |  4.422    |  0.006926 |
|  39       |  0.9252   |  11.3     |  3.595e+0 |  0.0      |  0.009926 |
|  40       |  0.7408   |  2.598    |  4.687e+0 |  3.924    |  0.000349 |
|  41       |  0.9133   |  13.61    |  4.663e+0 |  0.165    |  0.002419 |
|  42       |  0.8717   |  2.679    |  4.664e+0 |  2.919    |  0.000942 |
|  43       |  0.9046   |  2.163    |  3.59e+03 |  4.122    |  0.003341 |
|  44       |  0.9187   |  2.043    |  2.663e+0 |  0.9121   |  0.006893 |
|  45       |  0.9034   |  3.795    |  3.72e+03 |  1.496    |  0.001378 |
|  46       |  0.9202   |  2.537    |  4.259e+0 |  2.654    |  0.008496 |
|  47       |  0.8981   |  14.64    |  4.267e+0 |  1.603    |  0.001094 |
|  48       |  0.9271   |  7.045    |  4.358e+0 |  2.492    |  0.00139  |
|  49       |  0.9319   |  6.785    |  4.449e+0 |  3.364    |  0.005274 |
|  50       |  0.856    |  9.51     |  4.467e+0 |  3.623    |  0.000571 |
=========================================================================
Final result: {'target': 0.9346381784461701, 'params': {'depth': 7.3647831970412785, 'iterations': 2657.0839817870524, 'l2_leaf_reg': 3.245530918527948, 'learning_rate': 0.006347041199650392}}

Refercence:
BayesianOptimization 库的官方文档
https://blog.csdn.net/ningyanggege/article/details/89003698