Deleted cells under label encoding and tokenization to avoid confusion
The following section under Dummy encode the labels is a little confusing,
df['CATEGORY'][1] retrieves the dataframe with index = 1; as the dataframe has been randomized, index=1 does not refer to the second row and hence does not match with encoded_y
Renamed tensorflow to pytorch for pytorch alternative notebooks
Issue #, if available:
Description of changes:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.
Deleted cells under label encoding and tokenization to avoid confusion The following section under Dummy encode the labels is a little confusing, df['CATEGORY'][1] retrieves the dataframe with index = 1; as the dataframe has been randomized, index=1 does not refer to the second row and hence does not match with encoded_y
Renamed tensorflow to pytorch for pytorch alternative notebooks
Issue #, if available:
Description of changes:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.