## create tcorpus of 5 bush and obama docs
tc = create_tcorpus(sotu_texts[c(1:5,801:805),], doc_col='id')
## subset to keep only tokens where token_id <= 20 (i.e.first 20 tokens)
tcs1 = subset(tc, token_id < 20)
tcs1
## subset to keep only documents where president is Barack Obama
tcs2 = subset(tc, subset_meta = president == 'Barack Obama')
tcs2
Run the code above in your browser using DataLab