我已经在Model类中编写了这种简单的随机森林回归的小型机器学习代码。创建了此类的对象后,我打印了预测和准确性得分,并编写了代码以计划每30天训练一次并每7天进行测试。但是我遇到了一个错误
代码:
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','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(30).days.at("05:00").do(model_instance.fit())
schedule.every(7).days.at("05:00").do(model_instance.predict())
while 1:
schedule.run_pending()
time.sleep(1)
在此行schedule.every(30).days.at("05:00").do(model_instance.fit())
上,出现以下错误:the first argument must be callable
答案 0 :(得分:2)
我对schedule包不熟悉,但是我猜到do
的参数必须是可调用的。这意味着您实际上不应调用该函数。试试这个:
schedule.every(30).days.at("05:00").do(model_instance.fit)
schedule.every(7).days.at("05:00").do(model_instance.predict)
请注意,我删除了fit
和predict
之后的括号。
答案 1 :(得分:0)
我知道了。创建了用于培训和测试的单独模块,然后导入Model类,然后创建了将执行计划的功能。
培训功能:
import schedule
import time
def job():
model_instance.split(0.2)
model_instance.fit()
print("Training Completed")
schedule.every().minute.at(":17").do(job)
while True:
schedule.run_pending()
time.sleep(1)
测试功能
import schedule
import time
def job():
model_instance.predict()
print(model_instance.result)
print("Accuracy: ", model_instance.model.score(model_instance.X_test, model_instance.y_test))
print("Testing Completed")
schedule.every().minute.at(":17").do(job)
while True:
schedule.run_pending()
time.sleep(1)