Reference:
https://stackoverflow.com/questions/59394947/how-to-fix-resourceexhaustederror-oom-when-allocating-tensor/59395251#:~:text=OOM%20stands%20for%20%22out%20of,in%20your%20Dense%20%2C%20Conv2D%20layers

https://cloud.google.com/automl-tables/docs/data-best-practices#time

https://cloud.google.com/ai-platform/prediction/docs/batch-predict

This approach ensures that the model is able to accurately interpret the categorical data in the test set. As the training set already contains one-hot encoded data, it is important to apply the same encoding to the test set so the model can interpret the data accurately. Reference: https://machinelearningmastery.com/how-to-one-hot-encode-sequence-data-in-python/https://machinelearningmastery.com/how-to-use-one-hot-encoding-for-categorical-data/.
When working with categorical input variables, it's important to ensure that the same preprocessing steps are applied to both the training and test sets. One-hot encoding is a common method used to convert categorical variables into numerical values, which can then be used as inputs to machine learning models. By applying one-hot encoding to the test set, you will ensure that the test data has the same format as the training data and that the model can make accurate predictions.