Ray Tune模型调参：以一个简单的二分类模型为例

以Titanic乘客生存预测任务为例，进一步熟悉Ray Tune调参工具。

titanic数据集的目标是根据乘客信息预测他们在Titanic号撞击冰山沉没后能否生存。

本示例的基础代码参考了下面两篇文章：

• 1-1,结构化数据建模流程范例（一个不错的PyTorch教程）

• How to use Tune with PyTorch

也可以看一下上一篇文章：PyTorch + Ray Tune 调参

教程中的原始代码如下：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import torch
from torch import nn
from torch.utils.data import Dataset,DataLoader,TensorDataset
from sklearn.metrics import accuracy_score
import datetime

dftrain_raw = pd.read_csv('train.csv')
dftest_raw = pd.read_csv('test.csv')
dftrain_raw.head(10)

def preprocessing(dfdata):

    dfresult= pd.DataFrame()

    #Pclass
    dfPclass = pd.get_dummies(dfdata['Pclass'])
    dfPclass.columns = ['Pclass_' +str(x) for x in dfPclass.columns ]
    dfresult = pd.concat([dfresult,dfPclass],axis = 1)

    #Sex
    dfSex = pd.get_dummies(dfdata['Sex'])
    dfresult = pd.concat([dfresult,dfSex],axis = 1)

    #Age
    dfresult['Age'] = dfdata['Age'].fillna(0)
    dfresult['Age_null'] = pd.isna(dfdata['Age']).astype('int32')

    #SibSp,Parch,Fare
    dfresult['SibSp'] = dfdata['SibSp']
    dfresult['Parch'] = dfdata['Parch']
    dfresult['Fare'] = dfdata['Fare']

    #Carbin
    dfresult['Cabin_null'] =  pd.isna(dfdata['Cabin']).astype('int32')

    #Embarked
    dfEmbarked = pd.get_dummies(dfdata['Embarked'],dummy_na=True)
    dfEmbarked.columns = ['Embarked_' + str(x) for x in dfEmbarked.columns]
    dfresult = pd.concat([dfresult,dfEmbarked],axis = 1)

    return(dfresult)


x_train = preprocessing(dftrain_raw).values
y_train = dftrain_raw[['Survived']].values

x_test = preprocessing(dftest_raw).values
y_test = dftest_raw[['Survived']].values

print("x_train.shape =", x_train.shape )
print("x_test.shape =", x_test.shape )

print("y_train.shape =", y_train.shape )
print("y_test.shape =", y_test.shape )

dl_train = DataLoader(TensorDataset(torch.tensor(x_train).float(),torch.tensor(y_train).float()),
                     shuffle = True, batch_size = 8)
dl_valid = DataLoader(TensorDataset(torch.tensor(x_test).float(),torch.tensor(y_test).float()),
                     shuffle = False, batch_size = 8)


def create_net():
    net = nn.Sequential()
    net.add_module("linear1", nn.Linear(15, 20))
    net.add_module("relu1", nn.ReLU())
    net.add_module("linear2", nn.Linear(20, 15))
    net.add_module("relu2", nn.ReLU())
    net.add_module("linear3", nn.Linear(15, 1))
    net.add_module("sigmoid", nn.Sigmoid())
    return net


net = create_net()
print(net)

loss_func = nn.BCELoss()
optimizer = torch.optim.Adam(params=net.parameters(),lr = 0.01)
metric_func = lambda y_pred,y_true: accuracy_score(y_true.data.numpy(),y_pred.data.numpy()>0.5)
metric_name = "accuracy"

epochs = 10
log_step_freq = 30

dfhistory = pd.DataFrame(columns = ["epoch","loss",metric_name,"val_loss","val_"+metric_name])
print("Start