2024-06-18 10:49:43 +08:00
|
|
|
|
# from joblib import load
|
|
|
|
|
|
#
|
|
|
|
|
|
# model = load('AgentPPO/reward_data.pkl')
|
|
|
|
|
|
#
|
|
|
|
|
|
# data = model['mean_episode_reward']
|
|
|
|
|
|
# print(data)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# import torch
|
|
|
|
|
|
#
|
|
|
|
|
|
# model_path = 'AgentDDPG/actor.pth'
|
|
|
|
|
|
#
|
|
|
|
|
|
# checkpoint = torch.load(model_path, map_location=torch.device('cuda'))
|
|
|
|
|
|
#
|
|
|
|
|
|
# # 如果.pth文件保存的是整个模型（包含模型结构和参数）
|
|
|
|
|
|
# model = checkpoint # 这里假设checkpoint直接就是模型实例，有时候可能需要model.load_state_dict(checkpoint['state_dict'])
|
|
|
|
|
|
|
|
|
|
|
|
# 如果.pth文件仅保存了state_dict（模型参数）
|
|
|
|
|
|
# model = YourModelClass() # 实例化你的模型
|
|
|
|
|
|
# model.load_state_dict(checkpoint)
|
|
|
|
|
|
|
|
|
|
|
|
# print(model)
|
|
|
|
|
|
|
2024-06-24 11:07:53 +08:00
|
|
|
|
# import pickle
|
|
|
|
|
|
#
|
|
|
|
|
|
# a = 'DDPG'
|
|
|
|
|
|
# b = 'PPO'
|
|
|
|
|
|
# c = 'SAC'
|
|
|
|
|
|
# d = 'TD3'
|
|
|
|
|
|
#
|
|
|
|
|
|
# a1 = '/reward_data.pkl'
|
|
|
|
|
|
# a2 = '/loss_data.pkl'
|
|
|
|
|
|
# a3 = '/test_data.pkl'
|
|
|
|
|
|
#
|
|
|
|
|
|
# filename = './Agent' + a + a3
|
|
|
|
|
|
#
|
|
|
|
|
|
# # 使用 'rb' 模式打开文件，读取二进制数据
|
|
|
|
|
|
# with open(filename, 'rb') as f:
|
|
|
|
|
|
# data = pickle.load(f)
|
|
|
|
|
|
#
|
|
|
|
|
|
# print(data)
|
2024-06-18 10:49:43 +08:00
|
|
|
|
|
2024-06-24 11:07:53 +08:00
|
|
|
|
import pandas as pd
|
2024-06-18 10:49:43 +08:00
|
|
|
|
|
2024-06-24 11:07:53 +08:00
|
|
|
|
# Load the CSV file
|
|
|
|
|
|
file_path = 'data/prices_m.csv'
|
|
|
|
|
|
price_df = pd.read_csv(file_path)
|
|
|
|
|
|
# Check the columns
|
|
|
|
|
|
print(price_df.columns)
|
2024-06-18 10:49:43 +08:00
|
|
|
|
|
