R Basics

This is an basic introduction to R programming language

# Some basic commands in R
## Creating a list of numbers named x

x=c(1:10)

## Creating another list of number named y

y=c(20:19)

# Adding them up together to form c

c=x+y

c

##  [1] 21 21 23 23 25 25 27 27 29 29

# See all objects currently available in R environment

ls()

## [1] "c" "x" "y"

# Remove c for example

rm(c)

# Checking c if available in R

ls()

## [1] "x" "y"

# It is possible to remove all objects in R

rm(list=ls())

# Re-check the objects 

ls()

## character(0)

Creating matrix in R

# Creating a matrix in R

x=matrix(c(1,2,3,4),nrow = 2,ncol = 2)

# Displaying x 

x # If we don't specify the byrow=T, it is automatically assigned under column

##      [,1] [,2]
## [1,]    1    3
## [2,]    2    4

x=matrix(c(1,2,3,4),nrow=2,ncol=2,byrow = T)

x

##      [,1] [,2]
## [1,]    1    2
## [2,]    3    4

Creating a normal distribution values using rnorm

x=rnorm(1000,10,10)

hist(x, col=rainbow(30),main="Histogram",xlab = "Values")

See whole dataset

# Using this command 
fix(mtcars)

There are few other functions in R

library(ISLR)

# Read dataset in R

df<-read.csv("https://raw.githubusercontent.com/tuyenhavan/Statistics/Dataset/LungCapData.csv",na.strings = "?",header = T,sep=";")

# Omit missing data

na.omit(df)

head(df)

Pair plot

# Scatter plots 
pairs(~df$LungCap+df$Age+df$Height)

plot(df$LungCap,df$Age)

identify(df$LungCap,df$Age,df$Gender)

## integer(0)

# College dataset

df<-College

head(df)

# Give the first column a name

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 3.4.3

## -- Attaching packages ------------------------------------------------------------- tidyverse 1.2.1 --

## v ggplot2 2.2.1     v purrr   0.2.4
## v tibble  1.3.4     v dplyr   0.7.4
## v tidyr   0.7.2     v stringr 1.2.0
## v readr   1.1.1     v forcats 0.2.0

## Warning: package 'tidyr' was built under R version 3.4.3

## Warning: package 'purrr' was built under R version 3.4.3

## Warning: package 'dplyr' was built under R version 3.4.3

## -- Conflicts ---------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

head(df)

Logistic Regression Model