| 121 | # we will need to re-pad the stories later so that each story |
| 122 | # is the same length |
| 123 | def vectorize_stories(data, word2idx, story_maxlen, query_maxlen): |
| 124 | inputs, queries, answers = [], [], [] |
| 125 | for story, query, answer in data: |
| 126 | inputs.append([[word2idx[w] for w in s] for s in story]) |
| 127 | queries.append([word2idx[w] for w in query]) |
| 128 | answers.append([word2idx[answer]]) |
| 129 | return ( |
| 130 | [pad_sequences(x, maxlen=story_maxlen) for x in inputs], |
| 131 | pad_sequences(queries, maxlen=query_maxlen), |
| 132 | np.array(answers) |
| 133 | ) |
| 134 | |
| 135 | |
| 136 | |