nlg_seq_prep_func.py

# create sequences of length 5 tokens
def create_seq(text, seq_len = 5):
    
    sequences = []

    # if the number of tokens in 'text' is greater than 5
    if len(text.split()) > seq_len:
      for i in range(seq_len, len(text.split())):
        # select sequence of tokens
        seq = text.split()[i-seq_len:i+1]
        # add to the list
        sequences.append(" ".join(seq))

      return sequences

    # if the number of tokens in 'text' is less than or equal to 5
    else:
      
      return [text]