bryanyang0528

library("XML")
library("httr")
library("stringr")
library("igraph")
library("dplyr")

##這部分是爬網，先從網頁版ＰＴＴ中抓下每篇文章的聯結
rm(data)
data <- list()

bryanyang0528

summarise(group_by(melted, sex, treatment, variable),
          mean=mean(value), sd=sd(value))
 
melted %.% group_by(sex, treatment, variable) %.%
       summarise(mean=mean(value), sd=sd(value))

bryanyang0528

Source: local data frame [8 x 5]
Groups: sex, treatment

  sex treatment  variable         mean        sd
1   1         1 response1  0.021856280 1.0124371
2   1         1 response2  0.045928150 1.0151670
3   1         2 response1 -0.065017971 0.9825428
4   1         2 response2  0.011512867 0.9463053
5   2         1 response1 -0.005374208 1.0095468
6   2         1 response2 -0.051699624 1.0154782

bryanyang0528

Source: local data frame [4,000 x 4]
Groups: sex, treatment, variable

   sex treatment  variable       value
1    1         1 response1 -0.15668214
2    1         2 response1 -0.40934759
3    1         1 response1  0.07103731
4    1         2 response1  0.15113270
5    1         1 response1  0.30836910
6    1         2 response1 -1.41891407

bryanyang0528

## The code for the toy data is exactly the same
data <- data.frame(sex = c(rep(1, 1000), rep(2, 1000)),
                   treatment = rep(c(1, 2), 1000),
                   response1 = rnorm(2000, 0, 1),
                   response2 = rnorm(2000, 0, 1))
 
## reshape2 still does its thing:
library(reshape2)
melted <- melt(data, id.vars=c("sex", "treatment"))
 

bryanyang0528

def longTermPriority(path, maxTermLength, minFreq):
    longTerms=[]          #長詞
    longTermsFreq=[]      #長詞+次數分配
    
    for i in range(maxTermLength,1,-1): ##字詞數由大至小
        text_list = cutSentence(path,longTerms)  #呼叫cutSentence function
        #print len(text_list)
        words_freq = ngram(text_list,i, minFreq) #呼叫 ngram function
        #print i

bryanyang0528

def ngram(textLists,n,minFreq): #第一個參數放處理好的文章(LIST檔，utf-8編碼)，第二個參數放字詞的長度單位，第三個參數放至少要幾次以上
 
    words=[]     #存放擷取出來的字詞
    words_freq={}#存放字詞:計算個數 
    result= []
    for textList in textLists:
        for w in range(len(textList)-(n-1)): #要讀取的長度隨字詞長度改變
            words.append(textList[w:w+n])    #抓取長度w-(n-1)的字串

    for word in words:

bryanyang0528

import codecs
#處理編碼的套件
import operator
##處理字典檔排序的套件
 

cutlist = "<>/:：;；,、＂’，.。！？｢\"\'\\\n\r《》“”!@#$%^&*()".decode("utf-8")  ##列出標點符號，並轉換成utf-8的格式


def cutSentence(text_path, keywords): ##放入原始文章路徑, 增加斷詞的list

bryanyang0528

import codecs
#處理編碼的套件
import operator
##處理字典檔排序的套件
 

cutlist = "<>/:：;；,、＂’，.。！？｢\"\'\\\n\r《》“”!@#$%^&*()".decode("utf-8")  


#text_new =""

bryanyang0528

import codecs
#處理編碼的套件
import operator
##處理字典檔排序的套件

text = codecs.open("text.txt","r","utf-8")
#讀取存成TXT檔的文字，讀入後統一轉成UTF-8格式

text_new =""
for line in text.readlines():