R: Statistical Analysis and Visual Display

R           # start R in Linux (installed on Roma)

?keyword    # get help on a function (guessing is ok)

?plot(type) # get help on a parameter within a function

q()         # quit

> install.packages("ggplot2")

> install.packages("histogram")

> install.packages("tm") -- the text mining library

> install.packages("stm") -- Estimation of the Structural Topic Model (topic modeling)

?read.csv   # help

> setwd("/home/csa/Pattern2.6")

df <- read.csv(inFile, header=TRUE, comment.char="#", stringsAsFactors=FALSE)

> eb<-read.csv("/Users/steen/tna/csv/Erin_Burnett.csv",header=TRUE)

> ebpositive = eb$Positive

> ebsubjective = eb$Subjective

> ng<-read.csv("/Users/steen/tna/csv/Nancy_Grace.csv",header=TRUE)

> ngpositive = ng$Positive

> ngsubjective = ng$Subjective

> List3 <- read.table("file://tmp/list3", sep=" ", header=TRUE)    # space-separated table

> heat <-read.csv("/Users/steen/tna/csv/2014-07-22_Heatmap-sentiment.csv",header=TRUE)

> SMT1Positive = heat$SMT_01_positivity

> library(ggplot2)

> library(scales)

> heatdates <- as.Date(eb$Date)

$ r -e'dat <- read.csv("/tmp/david.csv"); \

  res <- data.frame(mn1=mean(dat[,10]),sd1=sd(dat[,10]),mn2=mean(dat[,11]),sd2=sd(dat[,11])); print(res)' -

> rm(days,mydates,sdate3)

 myvars <- c("v1", "v2", "v3")

 newdata <- mydata[myvars]

 myvars <- paste("v", 1:3, sep="")

 newdata <- mydata[myvars]

 newdata <- mydata[c(1,5:10)] 

> heat <- read.csv("/Users/steen/tna/csv/2014-07-22_Heatmap-sentiment.csv", header = TRUE, as.is = TRUE)

> heat20040603 <- subset(heat,Date <= "2004-06-03")   # Works if you use as.is = TRUE

> FaF  <- subset(heat,Show = "Fox_and_Friends")  # Does not work

> library(sqldf)

> FaF <- read.csv.sql(heat, sql = 'select * from file where Show = "Fox_and_Friends"') # Fails

newdata <- subset(mydata, age >= 20 | age < 10, select=c(ID, Weight))

newdata <- subset(mydata, sex=="m" & age > 25, select=weight:income)

CNN <- subset(heat, Network=="CNN", select=Date:SMT_01_positivity)

cnnebofhm<- subset(hm, Network=="CNN" & Show=="Erin_Burnett_Out_Front")

> ls()

 > names(heat)

 [1] "Date"                "Hour"                "Country"            

 [4] "Network"             "Show"                "Caption_wc"         

 [7] "SMT_01_wc"           "SMT_01_positivity"   "SMT_01_subjectivity"

[10] "SMT_02_wc"           "SMT_02_positivity"   "SMT_02_subjectivity"

 > colnames(heat)[3]

 > str(heat)

'data.frame':   230893 obs. of  12 variables:

$ Date               : Date, format: "2004-06-01" "2004-06-02" ...

$ Hour               : int  1300 1300 1300 1300 1300 1300 1300 1300 1300 1300 ...

$ Country            : Factor w/ 13 levels "AF","BE","CA",..: 13 13 13 13 13 13 13 13 13 13 ...

$ Network            : Factor w/ 39 levels "AlJazeera","BBC",..: 39 39 39 39 39 39 39 39 39 39 ...

$ Show               : Factor w/ 1873 levels "1600_Pennsylvania_Avenue",..: 442 442 442 442 442 442 442 ...

$ Caption_wc         : int  5336 6946 8908 5366 7538 6582 7410 6261 6778 4122 ...

$ SMT_01_wc          : int  331 467 636 354 532 427 430 448 474 249 ...

$ SMT_01_positivity  : num  24.4 10.5 49.5 34.3 35.2 ...

$ SMT_01_subjectivity: num  138 202 273 174 219 ...

$ SMT_02_wc          : int  1019 1364 1778 1032 1529 1291 1384 1237 1318 733 ...

$ SMT_02_positivity  : num  13 -26.38 8.38 -1.25 2 ...

$ SMT_02_subjectivity: num  185 266 358 222 276 ...

 > heat[1]

 > heat[c(2,4)]

 > head(heat, n=10)

 > tail(heat[c(2,4)], n=10)

(today <- Sys.Date())

format(today, "%d %b %Y")  # with month as a word

(tenweeks <- seq(today, length.out=10, by="1 week")) # next ten weeks

weekdays(today)

months(tenweeks)

 heat$Date <- as.Date(heat$Date , "%Y-%m-%d")

> head(heat[1], n=1)

       Date

1 2004-06-01

> tail(heat[1], n=1)

            Date

230893 2014-07-20

mydates <- as.Date(c("2007-06-22", "2004-02-13"))

days <- mydates[1] - mydates[2]

> colnames(heat)[3] <- "Network"

for (x in c(1:10)) print(sqrt(x))

for (x in c(0:400)) print(x^2))

history()

savehistory(file = "name")

loadhistory(file = "name")

dat <- read.csv("smt2csv-02.py-output.csv", header=FALSE)

res <- data.frame(mn1=mean(dat[,10]),sd1=sd(dat[,10]),mn2=mean(dat[,11]),sd2=sd(dat[,11]))

cat smt2csv-02.py-output.csv | r -e'dat <- read.csv(file("stdin")); \

  res <- data.frame(mn1=mean(dat[,10]),sd1=sd(dat[,10]),mn2=mean(dat[,11]),sd2=sd(dat[,11])); print(res)' -

cat smt2csv-02.py-output.csv |\ r -d -e'\

  res <- data.frame(mn1=mean(dat[,10]),sd1=sd(dat[,10]),mn2=mean(dat[,11]),sd2=sd(dat[,11])); print(res)' -

> mean(ebpositive)

[1] 0.03487137

> var(ebpositive)

[1] 0.1058562

> sd(ebpositive)

[1] 0.3253556

> mean(ebsubjective)

[1] 0.2791462

> var(ebsubjective)

[1] 0.0977887

> sd(ebsubjective)

[1] 0.3127119

> mean(ngpositive)

[1] 0.02013443

> var(ngpositive)

[1] 0.1135885

> sd(ngpositive)

[1] 0.3370289

> mean(ngsubjective)

[1] 0.2875757

> var(ngsubjective)

[1] 0.09846148

> sd(ngsubjective)

[1] 0.3137857

> boxplot(eb$Positive, ng$Positive, col="lightblue")

> boxplot(eb$Subjective, ng$Subjective, col="red")

> library(histogram)

> histogram(eb$Positive)

R --vanilla --slave <delay.R               # or use --save to keep history

R --vanilla --verbose <faculty-teaching.R  # get some debugging information

x <- c(0:401)

x

Cumulative <- cumsum(x)

Cumulative <- cumsum(WordCount$V2)

names(List3)

List3$V1

TwoColumns <- paste(Record$V1,Delay$V1)

attach(List3)

plot(x,sample(x)) # plot the vector against a randomized version of itself

plot(x,sample(x)^20,xlab="x",ylab="y",main="This is my first Rtwork")

plot(y=Delay$V1,x=Record$V1)

plot(soc$N, (soc$N * soc$Students),

 ylab="Cumulative enrollment over the last four quarters",

 xlab="Number of classes taught",

 col.axis = "sky blue",

 col.lab = "grey45",

 pch = 19,        # plotting character -- 19 is a circle

 cex = 1,         # or cex 1:10/5 if you want increasing sizes

 col = green,     # If you want green circles for data

 # type = "n",    # If you don't want to plot points yet

 xlim = c(0,7),   # Set the x-axis scale

 ylim = c(0,550)) # It may be possible to use 

mtext(c("Ladder faculty teaching in ", "Comm", " and ", "Soc"),

 cex = 1.5,        # scale text size

 col = c(1,4,1,3), # 0 white, 1 black, 2 red, 3 green, 4 blue

 at = c(2,4.4,5.27,5.9),  # clumsy solution -- must be manually adjusted

 line = 2)

mtext(c("2008-2009 undergraduate classes, excluding sections and fiat lux"), line = 0.7)

text ( (soc$N - 0.3), (soc$N * soc$Students), labels = soc$Name, col = "green" )

text ( (com$N + 0.3), (com$N * com$Students), labels = com$Name, col = "blue" )

points(soc$N, (soc$N * soc$Students))

day <- Sys.Date() - 1

day <- format(day, "%d %B %Y")

title <- bquote(bold(paste("Postprocessing times on ", .(day))))

var <-  bquote(paste("string", .(var)))

plot(Delay$V1, xaxt="n", xlab="Time of recording", ylab="Delay in minutes",

main=title, col="blue")

axis(1, at=1:(length(Delay$V1)), labels=Record$V1, tick=FALSE, col="red")

plot(cumsum(WordCount$V2), xaxt="n", xlab="Dates", ylab="Words", main=title,

pch = 19, cex = -1 , col = "green", type="h")

hist(V1,ylab="Frequency",xlab="Delay in minutes", main=title)

x <- matrix(1:10,ncol=5)

write(t(x))   -- writes x to a file called data (default file name)

write(x, "", sep = "\t")   -- writes x tab-delimited to the screen (not to file)

write(x, "myfile", sep = "\t")   -- writes x tab-delimited to the file myfile

r-base*

r-block*

r-cran*

r-doc*

r-mathlib

r-other*

r-recommended

install.packages("animation")

install.packages("ggplot2")