a bug in test dataset splitting

[nobrowning]

I noticed that there is bug in the preprocessing code for 20ng(scripts/data_20ng.py)

ETM/scripts/data_20ng.py

Line 88 in 52b090b

docs_ts = [[word2id[w] for w in init_docs[idx_d+num_docs_tr].split() if w in word2id] for idx_d in range(tsSize)]

missing the idx_permute index convert

[Littleele]

in line 91 idx_permute = np.random.permutation(num_docs_tr).astype(int)
the idx_permute is num_docs_tr size, so for test set there is no need to add the index convert