For the analyze_ngram_overlap.py file, how do you get the ngram_inclusion? e.g., shard_1["ngram_inclusion"]. I want to reproduce Figure 4: Distributions of 7-gram overlap of non-member data over select domains. I am not sure where or how to get the data including n_gram.
For the analyze_ngram_overlap.py file, how do you get the ngram_inclusion? e.g., shard_1["ngram_inclusion"]. I want to reproduce Figure 4: Distributions of 7-gram overlap of non-member data over select domains. I am not sure where or how to get the data including n_gram.