Write way to add samples to torch TabularDataset
I have a TabularDataset and i would like to add some examples to the dataset.
dataset = TabularDataset(path=path, format="csv", fields=[('label', l_f),('data', d_f)])
# I tried this
dataset.examples = new_examples # new_examples is a list of examples
len(dataset) == len(new_examples) # This is True
I can see that the length of the dataset has changed and in examples i have the examples from new_exampels, but i don't think this is the wright way to do it because i think that it messes up the other methods in TabularDataset.
What is the wright way to add samples or to create a new dataset from a list of examples?
Topic pytorch torch nlp python
Category Data Science