MSWon

def One_hot(data):

  index_dict = {value:index for index,value in enumerate(set(data))}
  result = []
  
  for value in data:
    
    one_hot = np.zeros(len(index_dict))
    index = index_dict[value]
    one_hot[index] = 1

MSWon

def Zero_padding(train_batch_X, Batch_size, Maxseq_length, Vector_size):
  
  zero_pad = np.zeros((Batch_size, Maxseq_length, Vector_size))
  
  for i in range(Batch_size):
    zero_pad[i,:np.shape(train_batch_X[i])[0],:np.shape(train_batch_X[i])[1]] = train_batch_X[i]
    
  return zero_pad

MSWon

def read_data(filename):    
    with open(filename, 'r',encoding='utf-8') as f:
        data = [line.split('\t') for line in f.read().splitlines()]        
        data = data[1:]   # header 제외 #    
    return data 

MSWon

from konlpy.tag import Twitter

def tokenize(doc):

    return ['/'.join(t) for t in pos_tagger.pos(doc, norm=True, stem=True)]

MSWon

library(rvest)
library(stringr)

## 인피니티워 네이버 평점 페이지 주소 ##
main_url = "https://movie.naver.com/movie/bi/mi/pointWriteFormList.nhn?code=136315&type=after&onlyActualPointYn=N&order=newest&page="


reply_list = character()
star_list = numeric()
date_list = character()

MSWon

library(rvest)
library(stringr)

url = "http://news.naver.com/main/read.nhn?mode=LSD&mid=shm&sid1=100&oid=421&aid=0003064130" ## with image

sess <- read_html(url)
node <- html_node(sess,"#articleBodyContents img")
imgurl <- html_attr(node,"src")

download.file(imgurl, destfile = "image_test.jpeg" , method = 'curl')

MSWon

import numpy as np
import tensorflow as tf

X = tf.placeholder(tf.float32, [None, 2, 3])
seq_length = tf.placeholder(tf.int32, [None])

X_batch = np.array([
          [[0,1,2], [9,8,7]], ## data 1
          [[3,4,5], [0,0,0]], ## data 2
          [[6,7,8], [6,5,4]], ## data 3

MSWon

import os
import tensorflow as tf

os.environ['CUDA_VISIBLE_DEVICES'] = "1"

config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)

MSWon

from keras.preprocessing.sequence import pad_sequences

train_seq = [[1,2,3],[4,7,9,1]]
pad_sequences(train_seq, maxlen = 5, padding = "post")

MSWon

import re

test = "What do you need?"
re.sub("do", "", test)
## "What  you need?" ##