# Introduction to R
# Clean up everything
rm(list=ls())
# Get working directory
d <- getwd()
d
## [1] "F:/BSMMU/Spatial Data Analysis in R"
# Setting path of working directory
setwd(d)
getwd()
## [1] "F:/BSMMU/Spatial Data Analysis in R"
# Checking r-version
print(version$version.string)
## [1] "R version 4.1.1 (2021-08-10)"
#==================================
# Lesson-2: Basic data types in R
#==================================
# **Followings are vector data. A vector is a one-dimensional array or structure**
# Numeric values
# Integer values
# Character values
# Logical values
# Factors
# Missing values
# Time
# Numeric values===============================================================
a <- 7 # one element
show(a)
## [1] 7
print(a)
## [1] 7
a
## [1] 7
class(a)
## [1] "numeric"
length(a) # to see how many elements or observations
## [1] 1
rm(a) # Remove any variable or file
# try this function show(a)
# Integer values================================================================
b <- 7L
b
## [1] 7
class(b)
## [1] "integer"
# Character values=============================================================
x <- "Proloy"
x
## [1] "Proloy"
class(x)
## [1] "character"
# Logical values ==============================================================
x <- FALSE
y<- TRUE
x
## [1] FALSE
y
## [1] TRUE
class(x)
## [1] "logical"
class (y)
## [1] "logical"
# Factors======================================================================
countries <- c('Bangladesh', 'Bangladesh', 'India', 'Afghanistan', 'India')
countries
## [1] "Bangladesh" "Bangladesh" "India" "Afghanistan" "India"
class(countries)
## [1] "character"
# converting character values into factor values
f1 <- as.factor(countries)
f1
## [1] Bangladesh Bangladesh India Afghanistan India
## Levels: Afghanistan Bangladesh India
class(f1)
## [1] "factor"
# Missing values===============================================================
m <- c(2, NA, 5, 2, NA, 2) # NA ("Not Available") (e.g. missing value = .)
is.na(m) # To check NA or missing values
## [1] FALSE TRUE FALSE FALSE TRUE FALSE
class(m)
## [1] "numeric"
which(is.na(m)) # Get positions of NA
## [1] 2 5
n <- c(5, 9, NaN, 3, 8, NA, NaN) # NaN ("Not a Number") (e.g. 0 / 0)
is.nan(n) # To check NaN values
## [1] FALSE FALSE TRUE FALSE FALSE FALSE TRUE
class(n)
## [1] "numeric"
which(is.nan(n)) # Get positions of NaN
## [1] 3 7
# Time========================================================================
d<- Sys.Date()
d
## [1] "2022-12-18"
class(d)
## [1] "Date"
#================================
#Lesson-3: Basic data structures
#================================
# **In the previous lesson we learned one dimensional data structure (vector). In this lesson, we will learn multi-dimensional data structures that can store basic data or vector data**
# Matrix========================================================================
# **A two-dimensional rectangular layout is called a matrix. We can create a matrix with two rows and three columns using following codes**
m <- matrix(ncol=3, nrow=2)
m
## [,1] [,2] [,3]
## [1,] NA NA NA
## [2,] NA NA NA
# All values were missing (NA) in above matrix. Let's make a matrix with values 1 to 6
m <- matrix(data=c(1:6), ncol=3, nrow=2, byrow = TRUE) # Arguments,
# like parameters, are information passed to functions.
m
## [,1] [,2] [,3]
## [1,] 1 2 3
## [2,] 4 5 6
m <- matrix(data=c(1:6), ncol=3, nrow=2, byrow = FALSE)
# By default elements are arranged sequentially by column.
m
## [,1] [,2] [,3]
## [1,] 1 3 5
## [2,] 2 4 6
# switching the number of columns and rows and using the t (transpose) function
t(m)
## [,1] [,2]
## [1,] 1 2
## [2,] 3 4
## [3,] 5 6
# A matrix can only store a single data type. If you try to mix character and numeric values, all values will become character values (as the other way around may not be possible)
vchar <- c("a", "b")
class(vchar)
## [1] "character"
vnumb <- c(1,2)
class(vnumb)
## [1] "numeric"
matrix(c(vchar,vnumb), ncol=2, nrow=2, byrow = FALSE)
## [,1] [,2]
## [1,] "a" "1"
## [2,] "b" "2"
# Define the column and row names in matrix m
m <- matrix(data=c(1:6), ncol=3, nrow=2, byrow = FALSE)
m
## [,1] [,2] [,3]
## [1,] 1 3 5
## [2,] 2 4 6
rownames(m) = c("row1", "row2") # Row names are less important.
colnames(m) = c("ID", "X", "Y")
m
## ID X Y
## row1 1 3 5
## row2 2 4 6
class(m)
## [1] "matrix" "array"
# List =========================================================================
# **A list in R is similar to your to-do list at work or school a list is some kind super data type**
v <- c(1:10)
m <- matrix(data=c(1:6), ncol = 3, nrow=2)
c <- "abc"
l<- list(v, m, c)
# Naming of list elements
names(l) <- c("first", "second", "third")
print(l)
## $first
## [1] 1 2 3 4 5 6 7 8 9 10
##
## $second
## [,1] [,2] [,3]
## [1,] 1 3 5
## [2,] 2 4 6
##
## $third
## [1] "abc"
class(l)
## [1] "list"
# Data frame ===================================================================
# It is rectangular like a matrix, but unlike matrices a data.frame can have columns (variables) of different data types such as numeric, character, factor
# Let's create a data frame with the following four variables or vectors
ID <- as.integer(c(1,2,3,4))
name <- c("name1", "name2", "name3", "name4")
sex <- as.factor(c("Female","Male","Male","Female"))
age <- as.numeric(c(36, 27, 37, 32))
df <- data.frame(ID, name, sex, age, stringsAsFactors=FALSE)
print(df)
## ID name sex age
## 1 1 name1 Female 36
## 2 2 name2 Male 27
## 3 3 name3 Male 37
## 4 4 name4 Female 32
class(df)
## [1] "data.frame"
# to see the data structure
str(df)
## 'data.frame': 4 obs. of 4 variables:
## $ ID : int 1 2 3 4
## $ name: chr "name1" "name2" "name3" "name4"
## $ sex : Factor w/ 2 levels "Female","Male": 1 2 2 1
## $ age : num 36 27 37 32
#================================
# Lesson-4: Indexing
#================================
# Vector========================================================================
# Access element(s) of a vector
b <- c(10:15)
b
## [1] 10 11 12 13 14 15
# Get the first element of a vector
b[1]
## [1] 10
# Get all elements except the second
b[-2]
## [1] 10 12 13 14 15
# use an index to change values
b[1] <- 11
b[3:6] <- -99
b
## [1] 11 11 -99 -99 -99 -99
# Matrix========================================================================
# values of matrices can be accessed through indexing
m <- matrix(1:9, nrow=3, ncol=3, byrow=TRUE)
colnames(m) <- c('a', 'b', 'c')
m
## a b c
## [1,] 1 2 3
## [2,] 4 5 6
## [3,] 7 8 9
# use two numbers in a double index, the first for the row number(s) and the second for the column number(s).
m[2,2]
## b
## 5
# entire column
m[ ,2]
## [1] 2 5 8
# two columns
m[, c('a', 'c')]
## a c
## [1,] 1 3
## [2,] 4 6
## [3,] 7 9
# setting values
m[1,1] <- 5
# List==========================================================================
v <- c(1:10)
m <- matrix(data=c(1:6), ncol = 3, nrow=2)
c <- "abc"
l<- list(v, m, c)
# Naming of list elements
names(l) <- c("first", "second", "third")
print(l)
## $first
## [1] 1 2 3 4 5 6 7 8 9 10
##
## $second
## [,1] [,2] [,3]
## [1,] 1 3 5
## [2,] 2 4 6
##
## $third
## [1] "abc"
class(l)
## [1] "list"
# the elements can be extracted by using the $ (dollar) operator
l$first
## [1] 1 2 3 4 5 6 7 8 9 10
l$second
## [,1] [,2] [,3]
## [1,] 1 3 5
## [2,] 2 4 6
l$third
## [1] "abc"
l[["first"]]
## [1] 1 2 3 4 5 6 7 8 9 10
# Data frame ===================================================================
# create a data.frame from matrix m
m <- matrix(1:9, nrow=3, ncol=3, byrow=TRUE)
colnames(m) <- c('a', 'b', 'c')
d <- data.frame(m)
class(d)
## [1] "data.frame"
# extract a column by column number
d[,2]
## [1] 2 5 8
# use the column name to get values
d[, 'b']
## [1] 2 5 8
d[ , 'b', drop=FALSE]
## b
## 1 2
## 2 5
## 3 8
# Which ========================================================================
# When we need to find indices of the elements in a vector that have values above 15?. The function which() gives us the entries of a logical vector that are true.
x <- 10:20
i <- which(x > 15)
print(i)
## [1] 7 8 9 10 11
x[i]
## [1] 16 17 18 19 20
# %in% =========================================================================
# A very useful operator that allows you to ask whether a set of values is present in a vector is %in%.
x <- c(10:20)
j <- c(7,9,11,13)
j %in% x
## [1] FALSE FALSE TRUE TRUE
which(j %in% x)
## [1] 3 4
# Match=========================================================================
# The function match() looks for entries in a vector and returns the index needed to access them
# Another handy similar function is match
match(j, x)
## [1] NA NA 2 4
#================================
# Lesson-5: Algebra
#================================
# Vector algebra ==============================================================
# Two vectors:
a <- 1:5
b <- 6:10
# Multiplication works element by element:
d <- a*b
# Logical comparisons
a == 2
## [1] FALSE TRUE FALSE FALSE FALSE
b > 6 & b < 8
## [1] FALSE TRUE FALSE FALSE FALSE
b > 9 | a < 2
## [1] TRUE FALSE FALSE FALSE TRUE
b >= 9
## [1] FALSE FALSE FALSE TRUE TRUE
a <= 2
## [1] TRUE TRUE FALSE FALSE FALSE
b >= 9 | a <= 2
## [1] TRUE TRUE FALSE TRUE TRUE
b >= 9 & a <= 2
## [1] FALSE FALSE FALSE FALSE FALSE
# Functions
sqrt(a)
## [1] 1.000000 1.414214 1.732051 2.000000 2.236068
exp(a)
## [1] 2.718282 7.389056 20.085537 54.598150 148.413159
min(a)
## [1] 1
max(a)
## [1] 5
range(a)
## [1] 1 5
sum(a)
## [1] 15
mean(a)
## [1] 3
median(a)
## [1] 3
prod(a)
## [1] 120
sd(a)
## [1] 1.581139
# Random numbers
r <- runif(10) # for uniform distributed numbers
r <- rnorm(10, mean=10, sd =2) # for randomly distributed numbers
# To be able to exactly reproduce examples or data analysis we often want to assure that we take exactly the same "random" sample each time we run our code.
set.seed(n)
# Matrices
# Create an example matrix
m <- matrix(1:6, ncol=3, nrow=2, byrow=TRUE)
print(m)
## [,1] [,2] [,3]
## [1,] 1 2 3
## [2,] 4 5 6
#to multiply all values of m with 5,
m*5
## [,1] [,2] [,3]
## [1,] 5 10 15
## [2,] 20 25 30
# multiply two matrices
m*m
## [,1] [,2] [,3]
## [1,] 1 4 9
## [2,] 16 25 36
# We can also do math with a matrix and a vector
m * 1:2
## [,1] [,2] [,3]
## [1,] 1 2 3
## [2,] 8 10 12
#================================
# Lesson-6: Data Exploration
#================================
# Summary and Table=============================================================
d <- data.frame(id=1:10, name=c('Bob', 'Bobby', '???', 'Bob', 'Bab', 'Jim', 'Jim', 'jim', '', 'Jim'), score1=c(8, 10, 7, 9, 2, 5, 1, 6, 3, 4),
score2=c(3,4,5,-999,5,5,-999,2,3,4), stringsAsFactors=FALSE)
print(d)
## id name score1 score2
## 1 1 Bob 8 3
## 2 2 Bobby 10 4
## 3 3 ??? 7 5
## 4 4 Bob 9 -999
## 5 5 Bab 2 5
## 6 6 Jim 5 5
## 7 7 Jim 1 -999
## 8 8 jim 6 2
## 9 9 3 3
## 10 10 Jim 4 4
str(d)
## 'data.frame': 10 obs. of 4 variables:
## $ id : int 1 2 3 4 5 6 7 8 9 10
## $ name : chr "Bob" "Bobby" "???" "Bob" ...
## $ score1: num 8 10 7 9 2 5 1 6 3 4
## $ score2: num 3 4 5 -999 5 5 -999 2 3 4
summary(d)
## id name score1 score2
## Min. : 1.00 Length:10 Min. : 1.00 Min. :-999.00
## 1st Qu.: 3.25 Class :character 1st Qu.: 3.25 1st Qu.: 2.25
## Median : 5.50 Mode :character Median : 5.50 Median : 3.50
## Mean : 5.50 Mean : 5.50 Mean :-196.70
## 3rd Qu.: 7.75 3rd Qu.: 7.75 3rd Qu.: 4.75
## Max. :10.00 Max. :10.00 Max. : 5.00
# Use $ symbol to extract variable from dataset
i <- d$score2 == -999
d$score2[i] <- NA
summary(d)
## id name score1 score2
## Min. : 1.00 Length:10 Min. : 1.00 Min. :2.000
## 1st Qu.: 3.25 Class :character 1st Qu.: 3.25 1st Qu.:3.000
## Median : 5.50 Mode :character Median : 5.50 Median :4.000
## Mean : 5.50 Mean : 5.50 Mean :3.875
## 3rd Qu.: 7.75 3rd Qu.: 7.75 3rd Qu.:5.000
## Max. :10.00 Max. :10.00 Max. :5.000
## NA's :2
# character (and integer) variables,
unique(d$name)
## [1] "Bob" "Bobby" "???" "Bab" "Jim" "jim" ""
table(d$name)
##
## ??? Bab Bob Bobby jim Jim
## 1 1 1 2 1 1 3
# to replace 'Bab' and 'Bobby' with 'Bob'
d$name[d$name %in% c('Bab', 'Bobby')] <- 'Bob'
table(d$name)
##
## ??? Bob jim Jim
## 1 1 4 1 3
# to replace 'jim' with 'Jim'
d$name[d$name %in% 'jim'] <- 'Jim'
table(d$name)
##
## ??? Bob Jim
## 1 1 4 4
d$name[d$name == '???'] <- NA
table(d$name)
##
## Bob Jim
## 1 4 4
# To force table to also count the NA values.
table(d$name, useNA='ifany')
##
## Bob Jim <NA>
## 1 4 4 1
d$name[9]
## [1] ""
# Note that there is one 'empty' value in the dataset. to replace 'empty' value with NA (missing value)
d$name[d$name == ''] <- NA
table(d[ c('name', 'score2')])
## score2
## name 2 3 4 5
## Bob 0 1 1 1
## Jim 1 0 1 1
# Quantile, range, and mean=====================================================
quantile(d$score1)
## 0% 25% 50% 75% 100%
## 1.00 3.25 5.50 7.75 10.00
range(d$score1)
## [1] 1 10
mean(d$score1)
## [1] 5.5
# you may need to use na.rm=TRUE if there are NA values
# quantile(d$score2)
quantile(d$score2, na.rm=TRUE)
## 0% 25% 50% 75% 100%
## 2 3 4 5 5
range(d$score2)
## [1] NA NA
range(d$score2, na.rm=TRUE)
## [1] 2 5
# Plots=========================================================================
# sets up the canvas for two rows and columns
par(mfrow=c(2,2))
# Scatter plot with two variables
plot(d$score1, d$score2)
# Boxplot of two variables
boxplot(d[, c('score1', 'score2')])
plot(sort(d$score1))
hist(d$score2)
# ========================
# Read and write files
# ========================
# To read first we need to know the full path (directory) name and the name of the file for path delimiters we need to use the forward-slash "/". For example, "C:/projects/research/data/obs.csv".
df <- read.csv("F:/BSMMU/Spatial Data Analysis in R/participants.csv")
print(df)
## RegTime Full.Name
## 1 26/10/2022 16:41:45 Taslima Chowdhury
## 2 26/10/2022 16:42:35 Anika Tasnim
## 3 26/10/2022 16:42:49 Shahana Sultana
## 4 26/10/2022 17:01:08 Tanjela Bushra
## 5 26/10/2022 19:17:17 Md. Redwanul Islam
## 6 30/10/2022 11:11:30 Kamrun Nahar
## 7 4/11/2022 10:05 Evana Binthe Alam
## 8 6/11/2022 7:54 Marium Salwa
## 9 7/12/2022 22:45 Dr Ashekur Rahman Mullick
## 10 7/12/2022 22:45 Nabhira Aftabi Binte Islam
## 11 7/12/2022 23:02 Sabrina Mousum
## 12 8/12/2022 0:10 Ayesha Tabassum Swarna
## 13 8/12/2022 10:03 Sumaiya Samad Deepa
## 14 11/12/2022 15:53 Md Maruf Haque KHan
## 15 12/12/2022 13:11 Tanjela Bushra
## 16 13/12/2022 14:24:11 Nilima Barman
## Previous.Software.Experience.on...Excel.
## 1 Yes
## 2 Yes
## 3 Yes
## 4 Yes
## 5 Yes
## 6 Yes
## 7 Yes
## 8 Yes
## 9 Yes
## 10 Yes
## 11 Yes
## 12 Yes
## 13 Yes
## 14 Yes
## 15 Yes
## 16 Yes
## Previous.Software.Experience.on...SPSS.
## 1 Yes
## 2 Yes
## 3 Yes
## 4 Yes
## 5 Yes
## 6 Yes
## 7 Yes
## 8 Yes
## 9 Yes
## 10 Yes
## 11 Yes
## 12 Yes
## 13 Yes
## 14 Yes
## 15 Yes
## 16 Yes
## Previous.Software.Experience.on...Stata.
## 1 No
## 2 No
## 3 No
## 4 No
## 5 No
## 6 No
## 7 No
## 8 No
## 9 No
## 10 No
## 11 No
## 12 No
## 13 No
## 14 No
## 15 No
## 16 No
## Previous.Software.Experience.on...R. Previous.Software.Experience.on...SAS.
## 1 No No
## 2 No No
## 3 No No
## 4 No No
## 5 No No
## 6 No No
## 7 No No
## 8 No No
## 9 No No
## 10 No No
## 11 No No
## 12 No No
## 13 No No
## 14 No Yes
## 15 No No
## 16 No No
## Age Gender Major.at.Bachelor.or.master.s.level Do.you.have.personal.laptop
## 1 36-40 Female Others Yes
## 2 31-35 Female Others Yes
## 3 36-40 Female Others Yes
## 4 31-35 Female Others Yes
## 5 26-30 Male Anthropology Yes
## 6 36-40 Female Others Yes
## 7 31-35 Female Others Yes
## 8 31-35 Female Others Yes
## 9 31-35 Male Others Yes
## 10 36-40 Female Biostatistics Yes
## 11 31-35 Female Others Yes
## 12 31-35 Female Others Yes
## 13 26-30 Female Others Yes
## 14 36-40 Male Others Yes
## 15 31-35 Female Others Yes
## 16 36-40 Female Others Yes
class(df)
## [1] "data.frame"
str(df)
## 'data.frame': 16 obs. of 11 variables:
## $ RegTime : chr "26/10/2022 16:41:45" "26/10/2022 16:42:35" "26/10/2022 16:42:49" "26/10/2022 17:01:08" ...
## $ Full.Name : chr "Taslima Chowdhury" "Anika Tasnim" "Shahana Sultana" "Tanjela Bushra " ...
## $ Previous.Software.Experience.on...Excel.: chr "Yes" "Yes" "Yes" "Yes" ...
## $ Previous.Software.Experience.on...SPSS. : chr "Yes" "Yes" "Yes" "Yes" ...
## $ Previous.Software.Experience.on...Stata.: chr "No" "No" "No" "No" ...
## $ Previous.Software.Experience.on...R. : chr "No" "No" "No" "No" ...
## $ Previous.Software.Experience.on...SAS. : chr "No" "No" "No" "No" ...
## $ Age : chr "36-40" "31-35" "36-40" "31-35" ...
## $ Gender : chr "Female" "Female" "Female" "Female" ...
## $ Major.at.Bachelor.or.master.s.level : chr "Others" "Others" "Others" "Others" ...
## $ Do.you.have.personal.laptop : chr "Yes" "Yes" "Yes" "Yes" ...
write.csv(df, "F:/BSMMU/Spatial Data Analysis in R/participants_data.csv")
# to see file.path
getwd()
## [1] "F:/BSMMU/Spatial Data Analysis in R"
# Cleaning stuff
colnames(df) <- c("reg", "name", "excel", "spss", "stata", "r", "sas", "age", "sex","major", "laptop")
str(df)
## 'data.frame': 16 obs. of 11 variables:
## $ reg : chr "26/10/2022 16:41:45" "26/10/2022 16:42:35" "26/10/2022 16:42:49" "26/10/2022 17:01:08" ...
## $ name : chr "Taslima Chowdhury" "Anika Tasnim" "Shahana Sultana" "Tanjela Bushra " ...
## $ excel : chr "Yes" "Yes" "Yes" "Yes" ...
## $ spss : chr "Yes" "Yes" "Yes" "Yes" ...
## $ stata : chr "No" "No" "No" "No" ...
## $ r : chr "No" "No" "No" "No" ...
## $ sas : chr "No" "No" "No" "No" ...
## $ age : chr "36-40" "31-35" "36-40" "31-35" ...
## $ sex : chr "Female" "Female" "Female" "Female" ...
## $ major : chr "Others" "Others" "Others" "Others" ...
## $ laptop: chr "Yes" "Yes" "Yes" "Yes" ...
df$excel <- as.factor(df$excel)
df$spss <- as.factor(df$spss)
df$stata <- as.factor(df$stata)
df$r <- as.factor(df$r)
df$sas <- as.factor(df$sas)
df$age <- as.factor(df$age)
df$sex <- as.factor(df$sex)
df$major <- as.factor(df$major)
df$laptop <- as.factor(df$laptop)
df <- df[-1]
df
## name excel spss stata r sas age sex
## 1 Taslima Chowdhury Yes Yes No No No 36-40 Female
## 2 Anika Tasnim Yes Yes No No No 31-35 Female
## 3 Shahana Sultana Yes Yes No No No 36-40 Female
## 4 Tanjela Bushra Yes Yes No No No 31-35 Female
## 5 Md. Redwanul Islam Yes Yes No No No 26-30 Male
## 6 Kamrun Nahar Yes Yes No No No 36-40 Female
## 7 Evana Binthe Alam Yes Yes No No No 31-35 Female
## 8 Marium Salwa Yes Yes No No No 31-35 Female
## 9 Dr Ashekur Rahman Mullick Yes Yes No No No 31-35 Male
## 10 Nabhira Aftabi Binte Islam Yes Yes No No No 36-40 Female
## 11 Sabrina Mousum Yes Yes No No No 31-35 Female
## 12 Ayesha Tabassum Swarna Yes Yes No No No 31-35 Female
## 13 Sumaiya Samad Deepa Yes Yes No No No 26-30 Female
## 14 Md Maruf Haque KHan Yes Yes No No Yes 36-40 Male
## 15 Tanjela Bushra Yes Yes No No No 31-35 Female
## 16 Nilima Barman Yes Yes No No No 36-40 Female
## major laptop
## 1 Others Yes
## 2 Others Yes
## 3 Others Yes
## 4 Others Yes
## 5 Anthropology Yes
## 6 Others Yes
## 7 Others Yes
## 8 Others Yes
## 9 Others Yes
## 10 Biostatistics Yes
## 11 Others Yes
## 12 Others Yes
## 13 Others Yes
## 14 Others Yes
## 15 Others Yes
## 16 Others Yes
df$ID <- 1:nrow(df)
df
## name excel spss stata r sas age sex
## 1 Taslima Chowdhury Yes Yes No No No 36-40 Female
## 2 Anika Tasnim Yes Yes No No No 31-35 Female
## 3 Shahana Sultana Yes Yes No No No 36-40 Female
## 4 Tanjela Bushra Yes Yes No No No 31-35 Female
## 5 Md. Redwanul Islam Yes Yes No No No 26-30 Male
## 6 Kamrun Nahar Yes Yes No No No 36-40 Female
## 7 Evana Binthe Alam Yes Yes No No No 31-35 Female
## 8 Marium Salwa Yes Yes No No No 31-35 Female
## 9 Dr Ashekur Rahman Mullick Yes Yes No No No 31-35 Male
## 10 Nabhira Aftabi Binte Islam Yes Yes No No No 36-40 Female
## 11 Sabrina Mousum Yes Yes No No No 31-35 Female
## 12 Ayesha Tabassum Swarna Yes Yes No No No 31-35 Female
## 13 Sumaiya Samad Deepa Yes Yes No No No 26-30 Female
## 14 Md Maruf Haque KHan Yes Yes No No Yes 36-40 Male
## 15 Tanjela Bushra Yes Yes No No No 31-35 Female
## 16 Nilima Barman Yes Yes No No No 36-40 Female
## major laptop ID
## 1 Others Yes 1
## 2 Others Yes 2
## 3 Others Yes 3
## 4 Others Yes 4
## 5 Anthropology Yes 5
## 6 Others Yes 6
## 7 Others Yes 7
## 8 Others Yes 8
## 9 Others Yes 9
## 10 Biostatistics Yes 10
## 11 Others Yes 11
## 12 Others Yes 12
## 13 Others Yes 13
## 14 Others Yes 14
## 15 Others Yes 15
## 16 Others Yes 16
data.table::setcolorder(df, neworder = "ID")
df
## ID name excel spss stata r sas age sex
## 1 1 Taslima Chowdhury Yes Yes No No No 36-40 Female
## 2 2 Anika Tasnim Yes Yes No No No 31-35 Female
## 3 3 Shahana Sultana Yes Yes No No No 36-40 Female
## 4 4 Tanjela Bushra Yes Yes No No No 31-35 Female
## 5 5 Md. Redwanul Islam Yes Yes No No No 26-30 Male
## 6 6 Kamrun Nahar Yes Yes No No No 36-40 Female
## 7 7 Evana Binthe Alam Yes Yes No No No 31-35 Female
## 8 8 Marium Salwa Yes Yes No No No 31-35 Female
## 9 9 Dr Ashekur Rahman Mullick Yes Yes No No No 31-35 Male
## 10 10 Nabhira Aftabi Binte Islam Yes Yes No No No 36-40 Female
## 11 11 Sabrina Mousum Yes Yes No No No 31-35 Female
## 12 12 Ayesha Tabassum Swarna Yes Yes No No No 31-35 Female
## 13 13 Sumaiya Samad Deepa Yes Yes No No No 26-30 Female
## 14 14 Md Maruf Haque KHan Yes Yes No No Yes 36-40 Male
## 15 15 Tanjela Bushra Yes Yes No No No 31-35 Female
## 16 16 Nilima Barman Yes Yes No No No 36-40 Female
## major laptop
## 1 Others Yes
## 2 Others Yes
## 3 Others Yes
## 4 Others Yes
## 5 Anthropology Yes
## 6 Others Yes
## 7 Others Yes
## 8 Others Yes
## 9 Others Yes
## 10 Biostatistics Yes
## 11 Others Yes
## 12 Others Yes
## 13 Others Yes
## 14 Others Yes
## 15 Others Yes
## 16 Others Yes
str(df)
## 'data.frame': 16 obs. of 11 variables:
## $ ID : int 1 2 3 4 5 6 7 8 9 10 ...
## $ name : chr "Taslima Chowdhury" "Anika Tasnim" "Shahana Sultana" "Tanjela Bushra " ...
## $ excel : Factor w/ 1 level "Yes": 1 1 1 1 1 1 1 1 1 1 ...
## $ spss : Factor w/ 1 level "Yes": 1 1 1 1 1 1 1 1 1 1 ...
## $ stata : Factor w/ 1 level "No": 1 1 1 1 1 1 1 1 1 1 ...
## $ r : Factor w/ 1 level "No": 1 1 1 1 1 1 1 1 1 1 ...
## $ sas : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 1 1 1 1 ...
## $ age : Factor w/ 3 levels "26-30","31-35",..: 3 2 3 2 1 3 2 2 2 3 ...
## $ sex : Factor w/ 2 levels "Female","Male": 1 1 1 1 2 1 1 1 2 1 ...
## $ major : Factor w/ 3 levels "Anthropology",..: 3 3 3 3 1 3 3 3 3 2 ...
## $ laptop: Factor w/ 1 level "Yes": 1 1 1 1 1 1 1 1 1 1 ...