Commit 2fb74c05 authored by Park Hyunwoo's avatar Park Hyunwoo
Browse files

Clean up python codes

parent 13061236

pykospacing/__init__.py

+1 −3
Original line number Diff line number Diff line 




from pykospacing.kospacing import *



__version__ = '0.01'
 
__version__ = '0.1'

pykospacing/embedding_maker.py

+9 −15
Original line number Diff line number Diff line 
__all__ = ['load_embedding', 'load_vocab', 'encoding_and_padding']







import os

from keras.preprocessing import sequence

import json

import numpy as np

from keras.preprocessing import sequence





__all__ = ['load_embedding', 'load_vocab', 'encoding_and_padding']





def load_embedding(embeddings_file):

    return(np.load(embeddings_file))





def load_vocab(vocab_path):

    with open(vocab_path, 'r') as f:

        data = json.loads(f.read())
@@ -25,7 +23,6 @@ def encoding_and_padding(word2idx_dic, sequences, **params): 
    1. making item to idx

    2. padding



    

    :word2idx_dic

    :sequences: list of lists where each element is a sequence

    :maxlen: int, maximum length
@@ -38,6 +35,3 @@ def encoding_and_padding(word2idx_dic, sequences, **params): 
    seq_idx = [[word2idx_dic.get(a, word2idx_dic['__ETC__']) for a in i] for i in sequences]

    params['value'] = word2idx_dic['__PAD__']

    return(sequence.pad_sequences(seq_idx, **params))

pykospacing/kospacing.py

+22 −29
Original line number Diff line number Diff line 
# -*- coding: utf-8 -*-

__all__ = ['spacing',]



import json, os, re, sys



os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'



import numpy as np

from keras.models import load_model



from pykospacing.embedding_maker import load_vocab, encoding_and_padding

import pkg_resources, warnings

import numpy as np

import os

import pkg_resources

import re

import warnings





model_path = pkg_resources.resource_filename('pykospacing', os.path.join("resources", "models", "kospacing"))

dic_path = pkg_resources.resource_filename('pykospacing', os.path.join("resources", "dicts", "c2v.dic"))

model = None

__all__ = ['spacing', ]

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'



model_path = pkg_resources.resource_filename('pykospacing', os.path.join('resources', 'models', 'kospacing'))

dic_path = pkg_resources.resource_filename('pykospacing', os.path.join('resources', 'dicts', 'c2v.dic'))

model = load_model(model_path)

model._make_predict_function()

w2idx, _ = load_vocab(dic_path)



class pred_spacing:



class pred_spacing:

    def __init__(self, model, w2idx):

        self.model = model

        self.w2idx = w2idx

        self.pattern = re.compile(r'\s+')



        

    def get_spaced_sent(self, raw_sent):

        #print('sent : {}'.format(raw_sent), file=sys.stdout)

        raw_sent_ = "«" + raw_sent + "»"

        raw_sent_ = raw_sent_.replace(' ', '^')

        sents_in = [raw_sent_, ]
@@ -52,14 +48,11 @@ class pred_spacing: 
        return subs







pred_spacing = pred_spacing(model, w2idx)





def spacing(sent):

    if len(sent) > 198:

        warnings.warn("One sentence can not contain more than 198 characters. : {}".format(sent))

        warnings.warn('One sentence can not contain more than 198 characters. : {}'.format(sent))

    spaced_sent = pred_spacing.get_spaced_sent(sent)

    return(spaced_sent.strip())

setup.py

+5 −17
Original line number Diff line number Diff line 
from setuptools import setup, find_packages

from setuptools import setup

from pykospacing import __version__





setup(name='pykospacing',



      version='0.1',



      version=__version__,

      url='https://github.com/haven-jeon/PyKoSpacing',



      license='GPL-3',



      author='Heewon Jeon',



      author_email='madjakarta@gmail.com',



      description='Python package for automatic Korean word spacing.',



      packages=['pykospacing', ],



      long_description=open('README.md', encoding='utf-8').read(),



      zip_safe=False,



      include_package_data=True,



      install_requires=['tensorflow >= 1.4.0, <= 1.6.0', 'keras >= 2.1.5', 'h5py >= 2.7.1'],

      )