oneday88 / deeptcn Goto Github PK

BTW, what's the meaning of weight?

As mentioned in paper "Probabilistic Forecasting with Temporal Convolutional Neural Network
", the Electricity Train data has been taken only for Dec (2011, 2012, 2013) and Test data taken for Dec(2014) data. But In preprocessing code It's taking all the last three years data and processing.

Could you please clarify on the same.

Hello, I'm reproducing your experiment of electricity part. I got the dataset from ttps://archive.ics.uci.edu/ml/datasets/ElectricityLoadDiagrams20112014 , with the file type of txt. I'd like to learn about what content is in your file modelData.csv so that I can change the dataset to that frame.
Thank you very much!

https://www.microprediction.com/competitions/electricity

Hi, tried to recreate the results of DeepTCN probabilistic for the electricity data set.

I changed the pre-processing code to standardize both train/test X and Y, but now the network predicts constant values for all 24 hours... any idea why? Why do you only standardize X and not Y?

Thanks for sharing this work. I noticed that in ResidualTCN, the data isn't being masked.
https://github.com/oneday88/deepTCN/blob/master/traffic/MxnetModels/pointModels.py#L11-L18

which is commonly done in other TCN implementations to ensure that there can be no leakage from the future into the past.
For example:

• https://github.com/unit8co/darts/blob/master/darts/models/forecasting/tcn_model.py#L107-L109

How does your code ensure causality without masking? Is it done in data preprocessing instead?

Thank you for sharing your valuable efforts. I have one doubt regardinng Train-Test data preparartion. Kindly find my below highlighted comments.

As per my understanding--
X Index Y Index
27: 39 39: 51
23: 35 35: 47
19: 31 31: 43
15: 27 27: 39
11: 23 23: 35
7: 19 19: 31
3: 15 15: 27

Kindly clarify the indexing details for Train and test data.

if(i==0): ##Please confirm whether this will be i <=3
testX[i] = series_x
testY[i] = series_y
testX2[i,:,:] = covariate_X
testY2[i,:,:] = covariate_Y
if(i>2): ##Please confirm whether this will be i >3
trainX[i-3] = series_x
trainY[i-3] = series_y
trainX2[i-3] = covariate_X
trainY2[i-3] = covariate_Y
https://github.com/oneday88/kdd2019deepTCN/blob/master/parts/quantileModel/data_preprocess.ipynb