Business Statistics: R tutorials

Transcription

1 Business Statistics: R tutorials Jingyu He September 29, 2017

2 Install R and RStudio R is a free software environment for statistical computing and graphics. Download free R and RStudio for Windows/Mac: R: only commandline. RStudio: RStudio is a fancy interface. Cloud computing : all Booth students can get access to computing cluster login with your Booth ID, not CNetID. Note: R is necessary and RStudio makes your life easier. Install both!

3 Great tutorials A very short introduction to R org/doc/contrib/torfs+brauer-short-r-intro.pdf try R code school Introduction to R by Google playlist?list=plou2xlyxmsik9qqfztxeybphvru-trqap The best way to learn programming is... Use it!

4 Don t be afraid... R is just a big graphics calculator!

5 Essential reference

6 Coder s best friend

7 Rstudio interface

8 R Packages People make contribution to R community. They write their own code and build a package, post online and others can download it. Install packages: install.packages("package.name") After installation, you have to load it: library(package.name) You can also install and library R packages in the Packages tab. Get package information:?package.name

9 Package management

10 Learn R in R The swirl package is for interactive quizzes. It teaches you R programming interactively. install.packages("swirl") library(swirl) swirl() I highly encourage you to go through them by yourself if you are not familiar with R. (about 3 hours).

11 swirl modules 1: Basic Building Blocks 2: Workspace and Files 3: Sequences of Numbers 4: Vectors 5: Missing Values 6: Subsetting Vectors 7: Matrices and Data Frames 8: Logic 9: Functions 10: lapply and sapply 11: vapply and tapply 12: Looking at Data 13: Simulation 14: Dates and Times 15: Base Graphics

12 Basic R commands Working directory is a folder where you put your data file and code in. How to set working directory? View current working directory: getwd() Set new working directory: setwd(" /Document/LearnR")

13 Input and output data Make sure data files are under yoru working directory! Read local files data: data = read.table("filename.txt") or data = read.csv("filename.csv") Note: Make sure the files are in your working directory, otherwise you should enter the path: data = read.table(".../.../filename.txt") Read files data from websites directly: data = read.table(" Save data in.txt file: write.table(data, file = "filename.txt")

14 Input Data: Superbowl Example

15 Find document?functionname or help(functionname)

16 Data type R is a statistical software, most of the time you work with data! Frequently used data type scalar (numerical value) characters (or strings) vector (numerical vector or characters vector) matrix (all entries should be numerical) data frame (similar to matrix, allows different type entry)

17 Numerics and characters obj1 <- 1 obj2 <- "a" obj3 <- "hello world"

18 Vector Assignment Assign a vector: x = c(2,7,5), then type x and enter, [1] Replicate the values in x: rep(x,2), [1] Assign a natural sequence: x = 1:5, [1] Assign a vector with R command seq : x = seq(from=4,length=3,by=3), [1] Vector can contain characters x = c("hello", "world")

19 Vector Subsetting Let x = c(2,7,5), Get the 2nd value in x: x[2], [1] 7 Get the 2nd and 3rd values in x: x[2:3] or x[c(2,3)], [1] 7 5 Drop the 2nd value in x: x[-2], [1] 2 5 Drop the 2nd and 3rd values in x: x[-(2:3)] or x[-c(2,3)], [1] 2

20 Matrix Assign a matrix: z = matrix(seq(1,12),4,3,byrow = FALSE), [,1] [,2] [,3] [1,] [2,] [3,] [4,] Get the last 2 rows and last 2 columns: z[3:4,2:3], [,1] [,2] [1,] 7 11 [2,] 8 12

21 Basic Operations (element-by-element.) Let x = c(2,7,5) and y = c(4,7,10). Addition: x+y, [1] Multiplication: x*y, [1] Division: x/y, [1] Exponential function: exp(x), [1] Delete the variable x: rm(x)

22 Data frame Group a collection of related vectors. Most of the time, when data is loaded, it will be organized as a data frame. Take Boston as example

23 Distribution r.., q.., d.., p.. + distribution name norm, binom, exp, unif, gamma, beta Generate 5 standard Normal random numbers: rnorm(5,mean = 0,sd = 1) Density function : dnorm(x,mean = 0,sd = 1) Quantile function : qnorm(x,mean = 0,sd = 1) CDF function pnorm(x,mean = 0,sd = 1)

24 Basic statistics: Let x = 1:10; y = rnorm(10), Mean: mean(x) [1] 5.5 Median: median(x) [1] 5.5 Maximum: max(x) [1] 10 Minimum: min(x) [1] 1

25 Variance: var(x) [1] Covariance: cov(x,y) [1] Correlation: cor(x,y) [1]

26 Graphics Generate random numbers from U(0,1) and N(0,1): x = runif(50); y = rnorm(50) Plot x vs. y: plot(x,y,xlab="uniform",ylab="normal", main="random Data",col="blue") Random Data Normal Uniform?plot to see more about plot and customize figures.

27

28 Histogram Plot the histogram of y: hist(y), Histogram of y Frequency y

29 Box plot Plot the boxplot: boxplot(x,y),