SVR Time Series Forecasting

[sach1n1]

Hello Guys, I am not able to figure out how to predict data beyond the data set we have.

In the example code (https://github.com/microsoft/ML-For-Beginners/tree/main/7-TimeSeries/3-SVR), we are using the test_data to actually get our y_test:

y_train_pred = model.predict(x_train).reshape(-1,1)
y_test_pred = model.predict(x_test).reshape(-1,1)

Lets take the case of the dataset in the lesson, the load data is present till 2014-12-31. Now suppose I want to predict the load for the month of January 2015, in that case what input do I give to the predict function?

Does it make sense to train the model by binding the dates (after converting to int) to the value and then train the model?

Thanks a lot