基于N-HiTS神经层次插值模型的时间序列预测——cross validation交叉验证与ray tune超参数优化

news2025/1/5 17:39:01

论文链接：https://arxiv.org/pdf/2201.12886v3

$\begin{aligned} &\text{\large \color{#CDA59E}N-HiTS: Neural Hierarchical Interpolation for TimeSeries Forecasting}\\ \end{aligned}$
NHITS builds upon NBEATS and specializes its partial outputs in the different frequencies of the time series through hierarchical interpolation and multi-rate input processing. On the long-horizon forecasting task NHITS improved accuracy by 25% on AAAI’s best paper award the Informer, while being 50x faster.

References
-Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio (2019). “N-BEATS: Neural basis expansion analysis for interpretable time series forecasting”.
-Cristian Challu, Kin G. Olivares, Boris N. Oreshkin, Federico Garza, Max Mergenthaler-Canseco, Artur Dubrawski (2023). “NHITS: Neural Hierarchical Interpolation for Time Series Forecasting”. Accepted at the Thirty-Seventh AAAI Conference on Artificial Intelligence.
-Zhou, H.; Zhang, S.; Peng, J.; Zhang, S.; Li, J.; Xiong, H.; and Zhang, W. (2020). “Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting”. Association for the Advancement of Artificial Intelligence Conference 2021 (AAAI 2021).

在这里插入图片描述

前言

系列专栏:【深度学习：算法项目实战】✨︎
涉及医疗健康、财经金融、商业零售、食品饮料、运动健身、交通运输、环境科学、社交媒体以及文本和图像处理等诸多领域，讨论了各种复杂的深度神经网络思想，如卷积神经网络、循环神经网络、生成对抗网络、门控循环单元、长短期记忆、自然语言处理、深度强化学习、大型语言模型和迁移学习。

NHITS是一种解决时间序列长期预测中波动性和计算复杂性的模型。它采用了分层插值和多率数据采样技术，通过构建分层结构来降低计算成本并提高预测精度‌。相较于最新的Transformer架构，NHITS在平均精度上提升了16%，同时计算时间减少了50倍‌。这种模型能够更有效地处理时间序列数据，为时间序列分析提供了新的方法。

具体来说，NHITS通过结合新的分层插值和多率数据采样技术，解决了长期预测中的两个常见挑战：预测的波动性和计算复杂性。这些技术使NHITS能够依次组装其预测，强调具有不同频率和尺度的分量，同时分解输入信号并合成预测‌。这种独特的处理方式使得NHITS在长期预测任务中表现出色。

文章目录

1. 数据集加载
2. 数据预处理
3. 数据可视化
4. 定义超参数
5. 构建模型
6. 交叉验证
7. 预测结果
8. 模型评估

import pandas as pd
import matplotlib.pyplot as plt

from ray import tune
from neuralforecast.auto import AutoNHITS
from neuralforecast.core import NeuralForecast
from neuralforecast.losses.numpy import mae, mse, mape, rmse

from datasetsforecast.long_horizon import LongHorizon

1. 数据集加载

datasetsforecast 是一个用于处理时间序列预测相关数据集的库。它的主要目的是方便用户获取、加载和预处理适合于时间序列预测任务的数据集。在时间序列分析和预测领域，拥有高质量、合适的数据集是非常关键的一步，这个库能够帮助我们更高效地开展工作。

# Change this to your own data to try the model
Y_df, X_df, _ = LongHorizon.load(directory='./', group='ETTm2')

2. 数据预处理

Y_df['ds'] = pd.to_datetime(Y_df['ds'])

# For this excercise we are going to take 20% of the DataSet
n_time = len(Y_df.ds.unique())
val_size = int(.2 * n_time)
test_size = int(.2 * n_time)

Y_df.groupby('unique_id').head(2)

3. 数据可视化

# We are going to plot the temperature of the transformer
# and marking the validation and train splits
u_id = 'HUFL'
x_plot = pd.to_datetime(Y_df[Y_df.unique_id==u_id].ds)
y_plot = Y_df[Y_df.unique_id==u_id].y.values

x_val = x_plot[n_time - val_size - test_size]
x_test = x_plot[n_time - test_size]

fig = plt.figure(figsize=(10, 5))
fig.tight_layout()

plt.plot(x_plot, y_plot)
plt.xlabel('Date', fontsize=17)
plt.ylabel('HUFL [15 min temperature]', fontsize=17)

plt.axvline(x_val, color='black', linestyle='-.')
plt.axvline(x_test, color='black', linestyle='-.')
plt.text(x_val, 5, '  Validation', fontsize=12)
plt.text(x_test, 5, '  Test', fontsize=12)

plt.grid()

HUFL

4. 定义超参数

Ray Tune 是一个用于超参数优化的库，它是基于 Ray 框架的一部分。Ray 是一个开源的分布式计算框架，旨在简化并行和分布式Python编程。Ray Tune 专门设计用来帮助开发者高效地搜索机器学习模型的超参数空间，以找到性能最佳的模型配置

horizon = 96 # 24hrs = 4 * 15 min.

# Use your own config or AutoNHITS.default_config
nhits_config = {
       "learning_rate": tune.choice([1e-3]),                                     # Initial Learning rate
       "max_steps": tune.choice([1000]),                                         # Number of SGD steps
       "input_size": tune.choice([5 * horizon]),                                 # input_size = multiplier * horizon
       "batch_size": tune.choice([7]),                                           # Number of series in windows
       "windows_batch_size": tune.choice([256]),                                 # Number of windows in batch
       "n_pool_kernel_size": tune.choice([[2, 2, 2], [16, 8, 1]]),               # MaxPool's Kernel size
       "n_freq_downsample": tune.choice([[168, 24, 1], [24, 12, 1], [1, 1, 1]]), # Interpolation expressivity ratios
       "activation": tune.choice(['ReLU']),                                      # Type of non-linear activation
       "n_blocks":  tune.choice([[1, 1, 1]]),                                    # Blocks per each 3 stacks
       "mlp_units":  tune.choice([[[512, 512], [512, 512], [512, 512]]]),        # 2 512-Layers per block for each stack
       "interpolation_mode": tune.choice(['linear']),                            # Type of Multi-step interpolation
       "val_check_steps": tune.choice([100]),                                    # Compute validation every 100 epochs
       "random_seed": tune.randint(3, 5),
    }

5. 构建模型

nf = NeuralForecast(
    models = [
        AutoNHITS(h=horizon,
                  config=nhits_config,
                  num_samples=5
                  )
    ],
    freq='15min')

6. 交叉验证

交叉验证方法 cross_validation 将返回模型在测试集上的预测结果。

Y_hat_df = nf.cross_validation(df=Y_df, val_size=val_size,
                               test_size=test_size, n_windows=None)

nf.models[0].results.get_best_result().config

{'learning_rate': 0.001,
 'max_steps': 1000,
 'input_size': 480,
 'batch_size': 7,
 'windows_batch_size': 256,
 'n_pool_kernel_size': [2, 2, 2],
 'n_freq_downsample': [1, 1, 1],
 'activation': 'ReLU',
 'n_blocks': [1, 1, 1],
 'mlp_units': [[512, 512], [512, 512], [512, 512]],
 'interpolation_mode': 'linear',
 'val_check_steps': 100,
 'random_seed': 3,
 'h': 96,
 'loss': MAE(),
 'valid_loss': MAE()}

7. 预测结果

y_true = Y_hat_df.y.values
y_hat = Y_hat_df['AutoNHITS'].values

n_series = len(Y_df.unique_id.unique())

y_true = y_true.reshape(n_series, -1, horizon)
y_hat = y_hat.reshape(n_series, -1, horizon)

print('Parsed results')
print('2. y_true.shape (n_series, n_windows, n_time_out):\t', y_true.shape)
print('2. y_hat.shape  (n_series, n_windows, n_time_out):\t', y_hat.shape)

Parsed results
2. y_true.shape (n_series, n_windows, n_time_out):	 (7, 11425, 96)
2. y_hat.shape  (n_series, n_windows, n_time_out):	 (7, 11425, 96)

fig, axs = plt.subplots(nrows=3, ncols=1, figsize=(10, 11))
fig.tight_layout()

series = ['HUFL','HULL','LUFL','LULL','MUFL','MULL','OT']
series_idx = 3

for idx, w_idx in enumerate([200, 300, 400]):
  axs[idx].plot(y_true[series_idx, w_idx,:],label='True')
  axs[idx].plot(y_hat[series_idx, w_idx,:],label='Forecast')
  axs[idx].grid()
  axs[idx].set_ylabel(series[series_idx]+f' window {w_idx}',
                      fontsize=17)
  if idx==2:
    axs[idx].set_xlabel('Forecast Horizon', fontsize=17)
plt.legend()
plt.show()
#plt.savefig('./results/HUFL_window.png', dpi=300)
plt.close()

在这里插入图片描述

8. 模型评估

以下代码使用了一些常见的评估指标：平均绝对误差（MAE）、平均绝对百分比误差（MAPE）、均方误差（MSE）、均方根误差（RMSE）来衡量模型预测的性能。这里我们将调用 neuralforecast.losses.numpy 模块中的 mae, mse, mape, rmse 函数来对模型的预测效果进行评估。

mae = mae(Y_hat_df['y'], Y_hat_df['AutoNHITS'])
print(f"MAE: {mae:.4f}")

mape = mape(Y_hat_df['y'], Y_hat_df['AutoNHITS'])
print(f"MAPE: {mape * 100:.4f}%")

mse = mse(Y_hat_df['y'], Y_hat_df['AutoNHITS'])
print(f"MSE: {mse:.4f}")

rmse = rmse(Y_hat_df['y'], Y_hat_df['AutoNHITS'])
print(f"RMSE: {rmse:.4f}")