在 Python 中安排训练和测试脚本

Question

我有一个简单的 RandomForest 回归模型，它进行训练和测试，然后打印预测和模型准确性。我想编写一个 python 自动化脚本来安排这个代码，它将每月训练一次，每周自动测试一次。

型号代码：

from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import numpy as np

import pandas as pd
from main import data as df


class Model():
    def __init__(self):
        self.df = df
        self.linear_reg = LinearRegression()
        self.random_forest = RandomForestRegressor()
    def split(self, test_size):
        X = np.array(self.df[['age','experience','education','certificates']])
        y = np.array(self.df['salary'])
        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(X, y, test_size = test_size, random_state = 42)

    def fit(self):
        self.model = self.random_forest.fit(self.X_train, self.y_train)

    def predict(self):

        self.result = self.random_forest.predict(self.X_test)
        return self.result


if __name__ == '__main__':
    model_instance = Model()
    model_instance.split(0.2)
    model_instance.fit()
    model_instance.predict()
    print(model_instance.result)
    print("Accuracy: ", model_instance.model.score(model_instance.X_test, model_instance.y_test))

这是我想每月安排一次的训练部分

    def fit(self):
        self.model = self.random_forest.fit(self.X_train, self.y_train)

这是我想每周安排一次的测试部分

     def predict(self):

        self.result = self.random_forest.predict(self.X_test)
        return self.result

如何编写代码以在所述时间范围内安排训练和测试？

Answer 1

使用schedule可以实现以下解决方案：

import schedule
import time
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import numpy as np

import pandas as pd
from main import data as df

class Model():
    def __init__(self):
        self.df = df
        self.linear_reg = LinearRegression()
        self.random_forest = RandomForestRegressor()
    def split(self, test_size):
        X = np.array(self.df[['age','experience','education','certificates']])
        y = np.array(self.df['salary'])
        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(X, y, test_size = test_size, random_state = 42)

    def fit(self):
        self.model = self.random_forest.fit(self.X_train, self.y_train)

    def predict(self):

        self.result = self.random_forest.predict(self.X_test)
        print(self.result)
        print("Accuracy: ", self.model.score(self.X_test, self.y_test))


if __name__ == '__main__':
    model_instance = Model()
    model_instance.split(0.2)
    schedule.every(28).day.at("07:00").do(model_instance.fit())
    schedule.every(7).day.at("07:00").do(model_instance.predict())
    while 1:
        schedule.run_pending()
        time.sleep(1)