ratsgo

def helloworld:
  print('hello world')
  return tmp

ratsgo

def lossFun(inputs, targets, hprev, cprev):
    xs, hs, cs, is_, fs, os, gs, ys, ps= {}, {}, {}, {}, {}, {}, {}, {}, {}
    hs[-1] = np.copy(hprev) # t=0일때 t-1 시점의 hidden state가 필요하므로
    cs[-1] = np.copy(cprev)
    loss = 0
    H = hidden_size
    # forward pass
    for t in range(len(inputs)):
        xs[t] = np.zeros((vocab_size, 1))
        xs[t][inputs[t]] = 1

ratsgo

import tensorflow as tf
import numpy as np
import tool as tool
import time

# data loading
data_path = 'C:/newscorpus.csv'
title, contents = tool.loading_data(data_path, eng=False, num=False, punc=False)
word_to_ix, ix_to_word = tool.make_dict_all_cut(title+contents, minlength=0, maxlength=3, jamo_delete=True)

ratsgo

import numpy as np
import pandas as pd
from collections import defaultdict

####################################################
# loading function                                 #
####################################################

def loading_data(data_path, eng=True, num=True, punc=False):
    # data example : "title","content"

ratsgo

library(rpart)
library(Matrix)
library(stringr)

####################################
# function                         #
####################################
regression.perf_eval <- function(real,hat) {
  MSE <- mean((real - hat)^2)
  RMSE <- sqrt(MSE)

ratsgo

import os
import time
import datetime
from tensorflow import flags
import tensorflow as tf
import numpy as np
import cnn_tool as tool

class TextCNN(object):
    """

ratsgo

import numpy as np
import pandas as pd
import re
import tensorflow as tf
import random


####################################################
# cut words function                               #
####################################################

ratsgo

class BranchingEntropy:
    def __init__(self, min_length=2, max_length=7):

        self.min_length = min_length
        self.max_length = max_length

        self.encoder = IntegerEncoder()

        self.L = defaultdict(lambda: defaultdict(int))
        self.R = defaultdict(lambda: defaultdict(int))

ratsgo

class CohesionProbability:
    def __init__(self, left_min_length=1, left_max_length=10, right_min_length=1, right_max_length=6):

        self.left_min_length = left_min_length
        self.left_max_length = left_max_length
        self.right_min_length = right_min_length
        self.right_max_length = right_max_length

        self.L = defaultdict(int)
        self.R = defaultdict(int)

ratsgo

library(stringr)

# prepare corpus
corpus <- matrix(c(1,2,0,0,0,0,
            3,1,0,0,0,0,
            2,0,0,0,0,0,
            3,3,2,3,2,4,
            0,0,3,2,0,0,
            0,0,4,1,0,0,
            0,0,0,0,4,3,