s13731105

library(RTextTools)
library(tm)

#讀取資料
data(NYTimes)
data <- NYTimes[sample(1:3100, size=100, replace=FALSE),]

#建立 文本-詞語 矩陣
matrix <- create_matrix(cbind(data["Title"],data["Subject"]), language = "english", removeNumbers = TRUE, stemWords = FALSE, weighting = weightTfIdf)

s13731105

library(tm)

setwd('C:/test/001') 
#sets R's working directory to near where my files are

a  <-Corpus(DirSource("/001"), readerControl = list(language="lat"))
summary(a)
a <- tm_map(a, removeNumbers)
a <- tm_map(a , stripWhitespace)
a <- tm_map(a, removePunctuation)

s13731105

policy.HTML.page <-readLines("http://policy.unt.edu/policy/3-5")
length(policy.HTML.page)
policy.HTML.page[186:202]
id.1 <- 3 + which(policy.HTML.page =="                    TOTAL UNIVERSITY        </div>")
id.2 <- id.1+5
text.data <- policy.HTML.page[id.1:id.2]

rm(policy.HTML.page, id.1, id.2)

text.data

s13731105

library(XML)
library(RCurl)
library(tm)
library(tmcn)
library(Rwordseg)


setwd("C:/test")
d.corpus <-Corpus(DirSource("/test/doc"), readerControl = list(language="UTF-8"))
#上兩行為抓取本機文字檔, 餘皆同網路上說明文字

s13731105

library(twitteR)
library(ROAuth)
library(ggplot2)


kejriwal.list <- searchTwitter('#kejriwal', n=1000)

#twListToDF() will take a list of objects from a single twitteR class and return a data.frame version of the members
kejriwal.df =twListToDF(kejriwal.list)
write.csv(kejriwal.df, file='c:/test/kejriwal.csv', row.names=F)

s13731105

require(devtools)
install_url("http://cran.r-project.org/src/contrib/Archive/sentiment/sentiment_0.2.tar.gz")
require(sentiment)
ls("package:sentiment")

s13731105

library(devtools)
library(twitteR)

api_key <- "89a1epAjv6QL2drupmbkYDAXX"

api_secret <- "pYBHCKVWKNsuq4stoVM3HF2KBAmcCsgcLPvnY7SwyUuWBxAWfH"

access_token <- "2352914730-1Dx4Xel5WTHBZuXuLv8AEBKXkgEgSdRzFlG0jPp"

access_token_secret <- "mMLw1ryN9D2W5wurR2b68JGNvLv69zLp0xx7V6gXJedW6"