Codes

ts

# Thu Dec 26 09:47:49 2024 ------------------------------

#This is helpful for version control and keeping track of your work

x=5+5

y=3

z=x+y

#Connecting R to external databases is essential for several reasons:

#Accessing Large Datasets:

#Working with Real-Time Data:e.g fraud detection

#Collaboration and Data Sharing:

getwd()

setwd("C:/Users/EG/Desktop/R Practice")

getwd()

ls()

rm(X)

rm(list=c("x","y"))

#HELP

help() #general help function in R

help("mean") # help on the specific function

?mean # shortcut for help("mean")

help.search("linear")

example("mean")# examples of how to use a specific function

apropos("mean")

apropos("mean", mode="function")

1
## DATA STRUCTURE

# VECTORS

#C() used to combine elements into vector

Logical <- c(TRUE, FALSE)

absent <- c(1, 3, 6, 9)

weight <- c(1.8, 2, 3.7)

Abebe <- c("He", "is", "a", "statistician")

# mode and [ ] to extract elements of a vector.

mode(weight)

absent[3:4]

# Coercion functions in R are functions that change the data type (or "class") of an object.

x<-3.45

class(x)

xxx<-as.integer(x)

class(xxx)

xxx

# FACTORS

CConduct <- c("A", "B", "B", "A")

#is.atomic(x) tests if an object x is actually a vector.

#(1)

is.atomic(CConduct)

class(CConduct)

2
cc<-factor(CConduct)

as.numeric(cc)

is.ordered(CConduct)

#(2)

performane <-c("Good", "Very good", "Excellent", "Good")

pfn<-factor(performane, ordered = TRUE, levels = c("Good", "Very good", "Excellent"))

is.ordered(pf)

#(3) : Numeric variables can be coded as factors using the levels and labels options.

Sex <-c(0,1,1,1,0,1,1,0,0)

factor(Sex,levels = c(0,1), labels=c("M","F"))

# LIST: it may contain vectors, matrices, data frames, and even other lists.

# List are the most complex of the R objects.

L <-list(1:3, "a", c(TRUE, FALSE, TRUE), c(2.3, 5.9))

str(L)

# To access elements of a list using double square brackets [[ ]]

L[[1]]

L[[4]]

# unlist() to turn a list into an atomic vector

ul<-unlist(L)

str(ul)

# atomic vector is a one-dimensional sequence of elements of the same data type

# DATA FRAMEs: is a list of equal-length vectors.

# row = individual observation and column = variables == Table

# e.g. mydata < − data.frame(col1, col2, col3,...)

3
df<-data.frame(id=1:3,grade=c("A","B","C"))

df

dim(df)

# cbind() used to combine two or more data frames or vectors by column

# rbind(): You can add new rows to an existing data frame by using rbind()

cbind(df,data.frame(gender=c("f","m","m")))

dfG<-cbind(df,data.frame(gender=c("f","m","m")))

## OR df$gender<-c("f", "m", "m")

rbind(df, data.frame(id=4, grade="B"))

rbind(dfG, data.frame(id=4, grade="B", gender="f"))

# To extract/ retrieve columns/ rows of a data frame [r,c] and $ are used

df[2]

df[ ,2]

df$id

df$grade

df[3,2]

df[2, ] #df[2]

#attach() function in R is used to make the variables within a data frame directly accessible in your R
environment without having to explicitly reference the data frame name each time

# Instead of using the $ operator or the [ operator to access columns within data frames

# iris is built in data set (others are ChickWeight , mtcars, airquality, PlantGrowth...)

# it is a data wh contain info. on 150 iris flowers.

4
plot(iris$Sepal.Length ~ iris$Petal.Length)

plot(Sepal.Length ~ Petal.Length)

attach(iris)

str(iris)

plot(Sepal.Length ~ Petal.Length)

detach(iris)

plot(Sepal.Length ~ Petal.Length)

# Data entry/ Import to R directly

infant_data<-data.frame(Age=numeric(0),gender=character(0),weight=numeric(0))

mydata<-edit(infant_data)

mydata

# to edit or enter additional data

edit(mydata)

## embeding data

#(1)

mydatatxt <-"age gender weight

25 m 166

30 f 115"

mydata1<-read.table(header = TRUE, text = mydatatxt )

#(2)

studentgrades<- "StudentID, First, Last, Math, Science, Social

011, Bob, Smith, 90, 80, 67

012, Jane, Weary, 75, , 80 "

grade <-read.table(header = TRUE, text = studentgrades )

# DETECTION OF MISSING VALUES

airquality[!complete.cases(airquality),] # show each row with NA

any(is.na(airquality$Ozone)) # whether there is a missing under the column or not

5
is.na(airquality) # show each row

colSums(is.na(airquality)) # sum of missing observation under each column

# importing Data from excel, spss and stata

install.packages("xlsx")

library(xlsx)

install.packages("haven")

install.packages("foriegn")

library(haven)

library(foreign)

# stata

practice <- read_dta("practice.dta")

View(practice)

#SPSS

Rain <- read_sav("Rain.sav")

View(Rain)

install.packages("Hmisc")

library(Hmisc)

Rain1 <- spss.get("Rain.sav",use.value.labels=TRUE)

#EXCEL

EastHar <- read_excel("EastHar.xlsx")

View(EastHar)

6
# Import from the nth sheet

library(xlsx)

EastHar<-"C:/Users/EG/Desktop/R Practice/EastHar.xlsx"

EastHar_new<-read_xlsx(EastHar,2)

## Exporting data

df

write.table(df, file = "exported1.txt", col.names=TRUE, row.names=FALSE, sep = "")

write.table(df, file = "exported2.csv", col.names=TRUE, row.names=FALSE, sep = ",")