Skip to main content

A dataset utils repository based on tf.data. For tensorflow 2.x only!

Project description

datasets

A dataset utils repository based on tf.data. For tensorflow>=2.0 only!

Requirements

  • python 3.6
  • tensorflow>=2.0

Installation

pip install nlp-datasets

Usage

seq2seq models

These models has an source sequence x and an target sequence y.

from nlp_datasets import Seq2SeqDataset
from nlp_datasets import SpaceTokenizer
from nlp_datasets.utils import data_dir_utils as utils

files = [
    utils.get_data_file('iwslt15.tst2013.100.envi'),
    utils.get_data_file('iwslt15.tst2013.100.envi'),
]
x_tokenizer = SpaceTokenizer()
x_tokenizer.build_from_corpus([utils.get_data_file('iwslt15.tst2013.100.en')])
y_tokenizer = SpaceTokenizer()
y_tokenizer.build_from_corpus([utils.get_data_file('iwslt15.tst2013.100.vi')])
config = {
    'train_batch_size': 2,
    'predict_batch_size': 2,
    'eval_batch_size': 2,
    'buffer_size': 100
}
dataset = Seq2SeqDataset(x_tokenizer, y_tokenizer, config)

train_dataset = dataset.build_train_dataset(files)
print(next(iter(train_dataset)))
print('=' * 120)

eval_dataset = dataset.build_eval_dataset(files)
print(next(iter(eval_dataset)))
print('=' * 120)

predict_files = [utils.get_data_file('iwslt15.tst2013.100.envi')]
predict_dataset = dataset.build_predict_dataset(predict_files)
print(next(iter(predict_dataset)))
print('=' * 120)

sequence match models

These models has two sequences as input, x and y, and has an label z.

from nlp_datasets import SeqMatchDataset
from nlp_datasets import SpaceTokenizer
from nlp_datasets.utils import data_dir_utils as utils

files = [
    utils.get_data_file('dssm.query.doc.label.txt'),
    utils.get_data_file('dssm.query.doc.label.txt'),
]
x_tokenizer = SpaceTokenizer()
x_tokenizer.build_from_vocab(utils.get_data_file('dssm.vocab.txt'))
y_tokenizer = SpaceTokenizer()
y_tokenizer.build_from_vocab(utils.get_data_file('dssm.vocab.txt'))

config = {
    'train_batch_size': 2,
    'eval_batch_size': 2,
    'predict_batch_size': 2,
    'buffer_size': 100,
}
dataset = SeqMatchDataset(x_tokenizer, y_tokenizer, config)

train_dataset = dataset.build_train_dataset(files)
print(next(iter(train_dataset)))
print('=' * 120)

eval_dataset = dataset.build_eval_dataset(files)
print(next(iter(eval_dataset)))
print('=' * 120)

predict_files = [utils.get_data_file('dssm.query.doc.label.txt')]
predict_dataset = dataset.build_predict_dataset(predict_files)
print(next(iter(predict_dataset)))
print('=' * 120)

sequence classify model

These models has a input sequence x, and a output label y.

from nlp_datasets import SeqClassifyDataset
from nlp_datasets import SpaceTokenizer
from nlp_datasets.utils import data_dir_utils as utils

files = [
    utils.get_data_file('classify.seq.label.txt')
]
x_tokenizer = SpaceTokenizer()
x_tokenizer.build_from_corpus([utils.get_data_file('classify.seq.txt')])

config = {
    'train_batch_size': 2,
    'eval_batch_size': 2,
    'predict_batch_size': 2,
    'buffer_size': 100
}
dataset = SeqClassifyDataset(x_tokenizer, config)

train_dataset = dataset.build_train_dataset(files)
print(next(iter(train_dataset)))
print('=' * 120)

eval_dataset = dataset.build_eval_dataset(files)
print(next(iter(eval_dataset)))
print('=' * 120)

predict_files = [utils.get_data_file('classify.seq.txt')]
predict_dataset = dataset.build_predict_dataset(predict_files)
print(next(iter(predict_dataset)))
print('=' * 120)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for nlp-datasets, version 1.3.0
Filename, size File type Python version Upload date Hashes
Filename, size nlp_datasets-1.3.0-py3-none-any.whl (20.8 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size nlp_datasets-1.3.0.tar.gz (8.6 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page