print("Loading IMDB data...")
(train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts)
print("Using %d training examples" % n_texts)
train_docs = [nlp.tokenizer(text) for text in train_texts]
train_gold = [GoldParse(doc, cats=cats) for doc, cats in
zip(train_docs, train_cats)]
train_data = list(zip(train_docs, train_gold))
After Change
print("Loading IMDB data...")
(train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts)
print("Using %d training examples" % n_texts)
train_data = list(zip(train_texts,
[{"cats": cats} for cats in train_cats]))
// get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "textcat"]
with nlp.disable_pipes(*other_pipes): // only train textcat
