kendravant

# FILE: Classifying Breast Cancer as Benign or Malignant
# AUTHOR: Timothy P. Jurka

library(RTextTools);

# GET THE BREAST CANCER DATA FROM http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.names
data <- read.csv("http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",header=FALSE)
data <- data[-1]

# ADD TEXTUAL DESCRIPTORS FOR EACH MASS CHARACTERISTIC FOR THE DOCUMENT-TERM MATRIX

kendravant

rm(list = ls())
doInstall <- TRUE  # Change to FALSE if you don't want packages installed.
toInstall <- c("zoo", "tm", "ggplot2", "Snowball")
if(doInstall){install.packages(toInstall, repos = "http://cran.r-project.org")}
lapply(toInstall, library, character.only = TRUE)

# From: http://www.cnn.com/2012/10/03/politics/debate-transcript/index.html
Transcript <- readLines("https://raw.github.com/dsparks/Test_image/master/Denver_Debate_Transcript.txt")
head(Transcript, 20)

kendravant

doInstall <- TRUE
toInstall <- c("twitteR", "dismo", "maps", "ggplot2")
if(doInstall){install.packages(toInstall, repos = "http://cran.us.r-project.org")}
lapply(toInstall, library, character.only = TRUE)

searchTerm <- "#rstats"
searchResults <- searchTwitter(searchTerm, n = 1000)  # Gather Tweets 
tweetFrame <- twListToDF(searchResults)  # Convert to a nice dF

userInfo <- lookupUsers(tweetFrame$screenName)  # Batch lookup of user info