does pymde support time series data?
opened this issue · comments
for example if I have a dataframe shape of (50,1000), 50 samples with time series length of 1000 each
Sure, you can embed that with PyMDE.
Is the idea that you want to embed each sample? In that case, you can convert your dataframe into a NumPy array of shape (50, 1000), and use pymde.preserve_neighbors or pymde.preserve_distances to obtain an embedding for each sample.
The documentation explains how to do things like this. Let me know if you have follow-up questions, or if something in the documentation is not clear.