Codes are fully developed in Google Colab including training and validation. It's a base example of how dataset are prepared to train in LSTM model. Feel free to use it for your project, you will need to input your own dataset. The n_steps_in and n_step_out can be re-defined by user depends on the application. Number of hidden layers and units can be also defined for better forecasting. The detail explaination of each stage is presented in my medium article : https://pangkh98.medium.com/multi-step-multivariate-time-series-forecasting-using-lstm-92c6d22cd9c2
Simply open the ipynb file in Google Colab.
Machine Learning Mastery https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/