Apache Spark Deep Learning Cookbook

How to do it...

1. You are now ready to generate new words, one at a time. First, encode the seed text to integers using the same tokenizer that was used when training the model, which is done using the following code: encoded = tokenizer.texts_to_sequences([seed_text])[0]

2. The model can predict the next word directly by calling model.predict_classes(), which will return the index of the word with the highest probability:

 prediction = model.predict_classes(encoded, verbose=0)

3. Look up the index in the Tokenizers mapping to get the associated word, as shown in the following code:

 out_word = '' for word, index in tokenizer.word_index.items(): ...