How to use the kaggle.vectorize_qapairs function in kaggle

BATCH_SIZE = 32
NBR_EPOCHS = 20

## extract data

print("Loading and formatting data...")
qapairs = kaggle.get_question_answer_pairs(
    os.path.join(DATA_DIR, QA_TRAIN_FILE))
question_maxlen = max([len(qapair[0]) for qapair in qapairs])
answer_maxlen = max([len(qapair[1]) for qapair in qapairs])
seq_maxlen = max([question_maxlen, answer_maxlen])

word2idx = kaggle.build_vocab([], qapairs, [])
vocab_size = len(word2idx) + 1 # include mask character 0

Xq, Xa, Y = kaggle.vectorize_qapairs(qapairs, word2idx, seq_maxlen)
Xqtrain, Xqtest, Xatrain, Xatest, Ytrain, Ytest = \
    train_test_split(Xq, Xa, Y, test_size=0.3, random_state=42)
print(Xqtrain.shape, Xqtest.shape, Xatrain.shape, Xatest.shape, 
      Ytrain.shape, Ytest.shape)

# get embeddings from word2vec
# see https://github.com/fchollet/keras/issues/853
print("Loading Word2Vec model and generating embedding matrix...")
word2vec = Word2Vec.load_word2vec_format(
    os.path.join(DATA_DIR, WORD2VEC_BIN), binary=True)
embedding_weights = np.zeros((vocab_size, WORD2VEC_EMBED_SIZE))
for word, index in word2idx.items():
    try:
        embedding_weights[index, :] = word2vec[word.lower()]
    except KeyError:
        pass  # keep as zero (not ideal, but what else can we do?)

BATCH_SIZE = 32
NBR_EPOCHS = 20

## extract data

print("Loading and formatting data...")
qapairs = kaggle.get_question_answer_pairs(
    os.path.join(DATA_DIR, QA_TRAIN_FILE))
question_maxlen = max([len(qapair[0]) for qapair in qapairs])
answer_maxlen = max([len(qapair[1]) for qapair in qapairs])
seq_maxlen = max([question_maxlen, answer_maxlen])

word2idx = kaggle.build_vocab([], qapairs, [])
vocab_size = len(word2idx) + 1 # include mask character 0

Xq, Xa, Y = kaggle.vectorize_qapairs(qapairs, word2idx, seq_maxlen)
Xqtrain, Xqtest, Xatrain, Xatest, Ytrain, Ytest = \
    train_test_split(Xq, Xa, Y, test_size=0.3, random_state=42)
print(Xqtrain.shape, Xqtest.shape, Xatrain.shape, Xatest.shape, 
      Ytrain.shape, Ytest.shape)

# get embeddings from word2vec
# see https://github.com/fchollet/keras/issues/853
print("Loading Word2Vec model and generating embedding matrix...")
word2vec = Word2Vec.load_word2vec_format(
    os.path.join(DATA_DIR, WORD2VEC_BIN), binary=True)
embedding_weights = np.zeros((vocab_size, WORD2VEC_EMBED_SIZE))
for word, index in word2idx.items():
    try:
        embedding_weights[index, :] = word2vec[word.lower()]
    except KeyError:
        pass  # keep as zero (not ideal, but what else can we do?)

BATCH_SIZE = 32
NBR_EPOCHS = 20

## extract data

print("Loading and formatting data...")
qapairs = kaggle.get_question_answer_pairs(
    os.path.join(DATA_DIR, QA_TRAIN_FILE))
question_maxlen = max([len(qapair[0]) for qapair in qapairs])
answer_maxlen = max([len(qapair[1]) for qapair in qapairs])
seq_maxlen = max([question_maxlen, answer_maxlen])

word2idx = kaggle.build_vocab([], qapairs, [])
vocab_size = len(word2idx) + 1 # include mask character 0

Xq, Xa, Y = kaggle.vectorize_qapairs(qapairs, word2idx, seq_maxlen)
Xqtrain, Xqtest, Xatrain, Xatest, Ytrain, Ytest = \
    train_test_split(Xq, Xa, Y, test_size=0.3, random_state=42)
print(Xqtrain.shape, Xqtest.shape, Xatrain.shape, Xatest.shape, 
      Ytrain.shape, Ytest.shape)

# get embeddings from word2vec
# see https://github.com/fchollet/keras/issues/853
print("Loading Word2Vec model and generating embedding matrix...")
word2vec = Word2Vec.load_word2vec_format(
    os.path.join(DATA_DIR, WORD2VEC_BIN), binary=True)
embedding_weights = np.zeros((vocab_size, WORD2VEC_EMBED_SIZE))
for word, index in word2idx.items():
    try:
        embedding_weights[index, :] = word2vec[word.lower()]
    except KeyError:
        pass  # keep as zero (not ideal, but what else can we do?)

BATCH_SIZE = 32
NBR_EPOCHS = 20

## extract data

print("Loading and formatting data...")
qapairs = kaggle.get_question_answer_pairs(
    os.path.join(DATA_DIR, QA_TRAIN_FILE))
question_maxlen = max([len(qapair[0]) for qapair in qapairs])
answer_maxlen = max([len(qapair[1]) for qapair in qapairs])
seq_maxlen = max([question_maxlen, answer_maxlen])

word2idx = kaggle.build_vocab([], qapairs, [])
vocab_size = len(word2idx) + 1 # include mask character 0

Xq, Xa, Y = kaggle.vectorize_qapairs(qapairs, word2idx, seq_maxlen)
Xqtrain, Xqtest, Xatrain, Xatest, Ytrain, Ytest = \
    train_test_split(Xq, Xa, Y, test_size=0.3, random_state=42)
print(Xqtrain.shape, Xqtest.shape, Xatrain.shape, Xatest.shape, 
      Ytrain.shape, Ytest.shape)

# get embeddings from word2vec
# see https://github.com/fchollet/keras/issues/853
print("Loading Word2Vec model and generating embedding matrix...")
word2vec = Word2Vec.load_word2vec_format(
    os.path.join(DATA_DIR, WORD2VEC_BIN), binary=True)
embedding_weights = np.zeros((vocab_size, WORD2VEC_EMBED_SIZE))
for word, index in word2idx.items():
    try:
        embedding_weights[index, :] = word2vec[word.lower()]
    except KeyError:
        pass  # keep as zero (not ideal, but what else can we do?)