Basics Of R Programming 1

# To know the working directory which is assigned by default
getwd()
# set the working directory from where you would like to take the files
setwd("C:/Mywork/MyLearning/MyStuddocs_UrbanPro/Data") # Assign the path as per the location where you want to allocate

getwd()

# to see the list of files in your working directory- just assigned above
dir() ## Lists files in the working directory

# Creating a folder in C drive
dir.create("C:/Mywork/MyLearning/MyStuddocs_UrbanPro/Data/Nov26")

#install.packages("car")
#install.packages("Hmisc")
#install.packages("reshape")
#install.packages('pastecs')
#install.packages('gtools')
#install.packages('gmodels')
#install.packages('caret')
#install.packages('MASS')

##-----------------------------------------------------------
## Load required libraries
##-----------------------------------------------------------
# calling the libraries in each active session is very much required
#if we want to use the functions in the library

library(foreign)
library(MASS) # for stepAIC()
library(Hmisc) # for describe()
library(boot)
library(pastecs) # for stat.desc()
library(gmodels)
library(gtools)
library(lattice)
library(ggplot2)
library(caret)
library(car)
library(foreign)
library(reshape)
library(Hmisc)

version # to check what version u are using

# import world data set
world

dim(world) # check how many rows and columns

View(world) # to View the data frame

trans<-read.csv("TransactionMaster.csv")

View(trans)

cust<-read.csv("CustomerMaster.csv")

View(cust)

dim(cust)

str(cust) # to check the structure/meta data of the data frame

# carbon copy of the file

cust_copy<-cust[,]

#save as a R file

saveRDS(cust_copy,"C:/Mywork/MyLearning/MyStuddocs_UrbanPro/Data/customerdata")

# take a sample of 100 rows and all the columns and create a sample file
# 1:100 stands for 100 rows and after comma blank means all columns to pick up
cust_sample<-cust[1:100,]

dim(cust_sample)

# take all the rows and specific columns from teh source file "cust"
samplefile

# take all rows and specific column numbers 1,8,9
samplefile

# do the frequency distribution of the City variable
table(cust$City)

# do a cross table freqency distribution of City and State variable
table(cust$State,cust$City )

table(world$deathCat, world$birthCat)

# calculate average value of energy_use_percapita variable from the world
mean(world$energy_use_percapita, na.rm=T)

#calculate median value of gni_per_capita
median(world$gni_per_capita) # 50th percentile

# to check the type of the R objects
class(world)
class(cust)
class(trans)

is.vector(world)
is.factor(world)
is.data.frame(world)
is.matrix(cust)

length(world) # display the number of cloumns : partcularly use for vectors

head(trans) # display first 6 rows in console

head(trans, n = 2) # Display top 2 rows

tail(trans) # display last 6 rows of a data frame

tail(trans,n=1)

firstfewrows

View(firstfewrows)

# to store the country names in lower case letters

world$country_name<-tolower(world$country_name)

# dropping the first column from a data frame and create a new one

world_1<-world[,-c(1)]

# filter out the atlanta customers

atlantaCustomers

# filter out atlanta or hollywood customers : | OR operator & AND opearator

atlantaHollyCustomers <-cust[which(cust$City == "ATLANTA" | cust$City == "HOLLYWOOD" ) , ]

## Selecting specific cloumns
atlantaCustomers1

# filtering out data with multiple conditions

highSales_mod<-trans[which(trans$Sales_Amount >= 100 & trans$Sales_Amount <= 150 ),]

max(highSales_mod$Sales_Amount)

min(highSales_mod$Sales_Amount)

###------------------------------------------------------------
### Basic Date functions in R
###------------------------------------------------------------

Sys.Date() # Current date

today

class(today)

Sys.time() # Current date and time with time zone
time<-Sys.time()

class(time)