How to use kaggle - 10 common examples

def submit_result(self, submit_msg='KakaoAutoML'):
        """
        Submit result to kaggle and wait for getting the result.
        """
        logger.info('kaggle.submit_result: initialization')
        api_client = KaggleApi()
        api_client.authenticate()
        submissions = api_client.competitionSubmissions(KaggleSubmission.CNAME)
        last_idx = submissions[0].ref if len(submissions) > 0 else -1

        # submit
        logger.info('kaggle.submit_result: trying to submit @ %s' % self.get_filepath())
        submit_result = api_client.competitionSubmit(self.get_filepath(), submit_msg, KaggleSubmission.CNAME)
        logger.info('kaggle.submit_result: submitted!')

        # wait for the updated LB
        wait_interval = 10   # in seconds
        for _ in range(60 // wait_interval * 5):
            submissions = api_client.competitionSubmissions(KaggleSubmission.CNAME)
            if len(submissions) == 0:
                continue
            if submissions[0].status == 'complete' and submissions[0].ref != last_idx:

def kernel_submit(self):
        self.info('kernel_submit updating dataset')

        folder = 'submit'
        os.makedirs(folder, exist_ok=True)

        shutil.copy(self.file, os.path.join(folder, self.file_name))

        config = api.read_config_file()
        username = config['username']
        title = f'{self.competition}-{self.kernel_suffix}-dataset'
        dataset_meta = {
            'title': f'{self.competition}-{self.kernel_suffix}-dataset',
            'id': f'{username}/{title}',
            'licenses': [{
                'name': 'CC0-1.0'
            }]
        }
        with open(f'{folder}/dataset-metadata.json', 'w') as f:
            json.dump(dataset_meta, f)

        res = api.dataset_status(dataset_meta['id'])
        if res != 'ready':
            res = api.dataset_create_new(folder=folder)
            if res.status == 'error':

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)

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)

signal = Input(shape=(seq_maxlen,))
encoded = Dense(EMBED_SIZE, init="glorot_uniform", activation="relu")(signal)
decoded = Dense(seq_maxlen, init="glorot_uniform", activation="sigmoid")(encoded)
autoencoder = Model(input=signal, output=decoded)

autoencoder.compile("adadelta", loss="binary_crossentropy")

autoencoder.fit(Xstrain, Xstrain, nb_epoch=NBR_EPOCHS, batch_size=BATCH_SIZE,
                shuffle=True, validation_data=(Xstest, Xstest))

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
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: