愉快的学习就从翻译开始吧_Multivariate Time Series Forecasting with LSTMs in Keras_0

Multivariate Time Series Forecasting with LSTMs in Keras/Keras中多变量时序预测

Neural networks like Long Short-Term Memory (LSTM) recurrent neural networks are able to almost seamlessly model problems with multiple input variables.

像长短期记忆（LSTM）递归神经网络这样的神经网络几乎可以无缝地建模多个输入变量的问题。

This is a great benefit in time series forecasting, where classical linear methods can be difficult to adapt to multivariate or multiple input forecasting problems.

这对于时间序列预测来说是一个很大的好处，其中经典的线性方法可能难以适应多变量或多输入预测问题

In this tutorial, you will discover how you can develop an LSTM model for multivariate time series forecasting in the Keras deep learning library.

在本教程中，您将了解如何在Keras深度学习库中开发多变量时间序列预测的LSTM模型

After completing this tutorial, you will know:

完成本教程后你将了解：

• How to transform a raw dataset into something we can use for time series forecasting.
  如何转换元数据集为可用于时间序列预测的东西
• How to prepare data and fit an LSTM for a multivariate time series forecasting problem.
  如何准备数据并拟合多变量时序预测问题的LSTM
• How to make a forecast and rescale the result back into the original units.
  如何进行预测并将结果重新调整回原始单位。
  

Let’s get started.

让我们开始吧

Tutorial Overview/教程概述

This tutorial is divided into 3 parts; they are:/本教程分为三部分，他们是：

1. Air Pollution Forecasting/空气污染预测
2. Basic Data Preparation/基本数据准备
3. Multivariate LSTM Forecast Model/多变量LSTM预测模型

Python Environment/Python环境（和上一篇文章一样重复一遍）

This tutorial assumes you have a Python SciPy environment installed. You can use either Python 2 or 3 with this tutorial.

本教程假定您已安装Python SciPy环境。 本教程可以使用Python 2或3。

You must have Keras (2.0 or higher) installed with either the TensorFlow or Theano backend.

您必须安装Keras（2.0或更高版本）或TensorFlow或Theano后端。

The tutorial also assumes you have scikit-learn, Pandas, NumPy and Matplotlib installed.

本教程还假设您已安装scikit-learn，Pandas，NumPy和Matplotlib。

If you need help with your environment, see this post:

如果您需要有关您的环境的帮助，请参阅此文章：

• How to Setup a Python Environment for Machine Learning and Deep Learning with Anaconda