Segmentation Faults about wildboar HOT 4 CLOSED

On Fri, 9 Aug 2019, 11:34 Mubarak Abdu-Aguye, ***@***.***> wrote: Hello, My apologies, I think I've figured it out - my data is a univariate timeseries, which was shaped as [n_samples, 431, 1] (i.e n_samples, with 431 univariate samples). Going through the issues I noticed that this inadvertently indicated that my timeseries was multivariate and had 431 dimensions...reshaping this to [n_samples, 431] fixed the problem right up. On a side note, I think its necessary to add that for the ShapeletForestClassifier, you actually don't seem to need to reshape/flatten the data? It seems to work directly on data with shape [n_samples, n_dims, n_timesteps] ? In any case, I will now close this issue. Apologies for the gaffe once again.. — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#8>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AABIZWFVHGNJ3YQC6MZAR6LQDU22PANCNFSM4IKNJD3Q> .