Closed falcon-ram closed 2 years ago
Do I have to reshape my X_train to (1, 5210,6)?
This model aims at clustering whole multivariate time series, i.e. the input matrix should be (N, T, F) where N is the number of input series, T the length of each series (timesteps), and F the number of observed variables (features). The clustering is performed on the N inputs. I think your data set does not meet this requirement. What do you want to cluster exactly? The 5210 individual time points (i.e. 5210 points in a 6-dimensional space)? or the 6 univariate time series (i.e. 6 points in a 5210-dimensional space)?
Hello Florent, Thanks for the response. I'm actually trying to classify 5210 points in a 6-dimensional space. I'm trying to see if I can get a Machine Learning algorithm can classify up trends, down trends and neutral trends in Stock market data. After looking more carefully at the code and the input data used I realized what is going on. Thanks and regards.
Hello, Thank you very much for the code. I am having some issues using your classes with my own program (also when running the main code in DeepTemporalClustering.py). My code so far:
At this point I'm getting the above mentioned error.
The X_train shape is 5210 by 6. i.e. 5210 timesteps and 6 features.
Upon investigation it seems that this line of code in TAE.py is causing the problem:
x = Input(shape=(timesteps, input_dim), name='input_seq')
Is it necessary for the Input shape to include the timesteps? I checked online and it seems that only the features should be part of the input shape. Is this correct?Thank you and regards.