How to use the kaggle.get_question_answer_pairs function in kaggle

DATA_DIR = "../data/comp_data"
MODEL_DIR = "../data/models"
WORD2VEC_BIN = "GoogleNews-vectors-negative300.bin.gz"
WORD2VEC_EMBED_SIZE = 300

QA_TRAIN_FILE = "8thGr-NDMC-Train.csv"

QA_EMBED_SIZE = 64
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

DATA_DIR = "../data/comp_data"
MODEL_DIR = "../data/models"
WORD2VEC_BIN = "GoogleNews-vectors-negative300.bin.gz"
WORD2VEC_EMBED_SIZE = 300

QA_TRAIN_FILE = "8thGr-NDMC-Train.csv"
STORY_FILE = "studystack_qa_cleaner_no_qm.txt"

QA_EMBED_SIZE = 64
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

DATA_DIR = "../data/comp_data"
MODEL_DIR = "../data/models"
WORD2VEC_BIN = "GoogleNews-vectors-negative300.bin.gz"
WORD2VEC_EMBED_SIZE = 300

QA_TRAIN_FILE = "8thGr-NDMC-Train.csv"

QA_EMBED_SIZE = 64
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
print("Loading Word2Vec model and generating embedding matrix...")

QA_EMBED_SIZE = 64
BATCH_SIZE = 128
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])

# Even though we don't use the test set for classification, we still need
# to consider any additional vocabulary words from it for when we use the
# model for prediction (against the test set).
tqapairs = kaggle.get_question_answer_pairs(
    os.path.join(DATA_DIR, QA_TEST_FILE), is_test=True)    
tq_maxlen = max([len(qapair[0]) for qapair in tqapairs])
ta_maxlen = max([len(qapair[1]) for qapair in tqapairs])

seq_maxlen = max([question_maxlen, answer_maxlen, tq_maxlen, ta_maxlen])

word2idx = kaggle.build_vocab([], qapairs, tqapairs)
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

DATA_DIR = "../data/comp_data"
MODEL_DIR = "../data/models"
WORD2VEC_BIN = "GoogleNews-vectors-negative300.bin.gz"
WORD2VEC_EMBED_SIZE = 300

QA_TRAIN_FILE = "8thGr-NDMC-Train.csv"

QA_EMBED_SIZE = 64
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

DATA_DIR = "../data/comp_data"
QA_TRAIN_FILE = "8thGr-NDMC-Train.csv"
STORY_FILE = "studystack_qa_cleaner_no_qm.txt"
STORY_WEIGHTS = "lstm-story-weights.txt"
STORY_BIAS = "lstm-story-bias.txt"

EMBED_SIZE = 64
BATCH_SIZE = 256
NBR_EPOCHS = 20

stories = kaggle.get_stories(os.path.join(DATA_DIR, STORY_FILE))
story_maxlen = max([len(words) for words in stories])

# this part is only required to get the maximum sequence length
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([story_maxlen, question_maxlen, answer_maxlen])

word2idx = kaggle.build_vocab(stories, qapairs, [])
vocab_size = len(word2idx)

Xs = kaggle.vectorize_stories(stories, word2idx, seq_maxlen)
Xstrain, Xstest = train_test_split(Xs, test_size=0.3, random_state=42)
print(Xstrain.shape, Xstest.shape)

inputs = Input(shape=(seq_maxlen, vocab_size))
encoded = LSTM(EMBED_SIZE)(inputs)
decoded = RepeatVector(seq_maxlen)(encoded)
decoded = LSTM(vocab_size, return_sequences=True)(decoded)

DATA_DIR = "../data/comp_data"
MODEL_DIR = "../data/models"
WORD2VEC_BIN = "studystack.bin"
WORD2VEC_EMBED_SIZE = 300

QA_TRAIN_FILE = "8thGr-NDMC-Train.csv"
QA_TEST_FILE = "8thGr-NDMC-Test.csv"

QA_EMBED_SIZE = 64
BATCH_SIZE = 128
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])

# Even though we don't use the test set for classification, we still need
# to consider any additional vocabulary words from it for when we use the
# model for prediction (against the test set).
tqapairs = kaggle.get_question_answer_pairs(
    os.path.join(DATA_DIR, QA_TEST_FILE), is_test=True)    
tq_maxlen = max([len(qapair[0]) for qapair in tqapairs])
ta_maxlen = max([len(qapair[1]) for qapair in tqapairs])

seq_maxlen = max([question_maxlen, answer_maxlen, tq_maxlen, ta_maxlen])

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