ValueError: The numbers of series in X and Y are different.
Opened this issue · 3 comments
The shape of X is (54, 337)
and the shape of y is (54,)
.
But I am getting error. I am using the following code
from tsaug import TimeWarp, Crop, Quantize, Drift, Reverse
my_augmenter = (
TimeWarp() * 5 # random time warping 5 times in parallel
+ Crop(size=300) # random crop subsequences with length 300
+ Quantize(n_levels=[10, 20, 30]) # random quantize to 10-, 20-, or 30- level sets
+ Drift(max_drift=(0.1, 0.5)) @ 0.8 # with 80% probability, random drift the signal up to 10% - 50%
+ Reverse() @ 0.5 # with 50% probability, reverse the sequence
)
data, labels = my_augmenter.augment(data, labels)
The Y in tsaug
is considered as point-wise label to X. In other words, if Y is present, then it is assumed for segmentation purpose. I guess your problem is a classification problem as you have 54 time series (each of which has 337 time points) and your label is per series instead of per time point. If so, you only need to augment X and assume the classification labels invariant.
The Y in
tsaug
is considered as point-wise label to X. In other words, if Y is present, then it is assumed for segmentation purpose. I guess your problem is a classification problem as you have 54 time series (each of which has 337 time points) and your label is per series instead of per time point. If so, you only need to augment X and assume the classification labels invariant.
After doing this, shape of X is (270, 300)
and the shape of y is (54,)
. So how can I make the shape of y equal in length of X? Is each row is augmented exactly the 5
times? or there are some rows augmented more and some less.
Yes, every row is augmented exactly 5 times.