2Jan_QnA(basic)

install.packages('dplyr') 

trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.5/dplyr_1.1.4.zip'
Content type 'application/zip' length 1594395 bytes (1.5 MB)
downloaded 1.5 MB

package ‘dplyr’ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\Dell\AppData\Local\Temp\RtmpWCeVTb\downloaded_packages

library(dplyr)
help(package = 'dplyr') 

x <- rep(seq(2, 3, by=0.5), times=3, each=4)
x

 [1] 2.0 2.0 2.0 2.0 2.5 2.5 2.5 2.5 3.0 3.0 3.0 3.0 2.0 2.0 2.0
[16] 2.0 2.5 2.5 2.5 2.5 3.0 3.0 3.0 3.0 2.0 2.0 2.0 2.0 2.5 2.5
[31] 2.5 2.5 3.0 3.0 3.0 3.0

cat("rank:", rank(x)) # Rank of elements.

rank: 6.5 6.5 6.5 6.5 18.5 18.5 18.5 18.5 30.5 30.5 30.5 30.5 6.5 6.5 6.5 6.5 18.5 18.5 18.5 18.5 30.5 30.5 30.5 30.5 6.5 6.5 6.5 6.5 18.5 18.5 18.5 18.5 30.5 30.5 30.5 30.5

table(x)

x
  2 2.5   3 
 12  12  12 

unique(x) 

[1] 2.0 2.5 3.0

x[-(2:4)] # All elements except two to four.

 [1] 2.0 2.5 2.5 2.5 2.5 3.0 3.0 3.0 3.0 2.0 2.0 2.0 2.0 2.5 2.5
[16] 2.5 2.5 3.0 3.0 3.0 3.0 2.0 2.0 2.0 2.0 2.5 2.5 2.5 2.5 3.0
[31] 3.0 3.0 3.0

x[x %in% c(1, 2, 5)] # Elements in the set 1, 2, 5.

 [1] 2 2 2 2 2 2 2 2 2 2 2 2

is.na(a) == Is missing is.null(a) == Is null

paste() → joining text

collapse → combining into one string

grep() → finding patterns

gsub() → replacing text

toupper() / tolower() → case change

nchar() → string length

x <- c("Data", "Science", "R")
y <- c("is", "with", "Fun")

# Join two vectors element-wise
joined <- paste(x, y, sep = " ")
joined

[1] "Data is"      "Science with" "R Fun"       

# "Data is" "Science with" "R Fun"

# Join all elements into one string
sentence <- paste(joined, collapse = " | ")
sentence

[1] "Data is | Science with | R Fun"

# "Data is | Science with | R Fun"

# Find words containing letter 'i'
grep("i", joined)

[1] 1 2

# 1 2

# Replace 'R' with 'Statistics'
replaced <- gsub("R", "Statistics", sentence)
replaced

[1] "Data is | Science with | Statistics Fun"

# "Data is | Science with | Statistics Fun"

# Convert to uppercase
upper_text <- toupper(replaced)
upper_text

[1] "DATA IS | SCIENCE WITH | STATISTICS FUN"

# "DATA IS | SCIENCE WITH | STATISTICS FUN"

# Convert to lowercase
lower_text <- tolower(upper_text)
lower_text

[1] "data is | science with | statistics fun"

# "data is | science with | statistics fun"

# Count number of characters
nchar(lower_text)

[1] 39

filter(df, a > 2) 

Error in attr(data, "tsp") <- c(start, end, frequency) : 
  object is not a matrix

Section 1: Basics

Q1.1 Install the dplyr package and load it into your R session. Then create a variable x and assign it the value 10. Print x to the console.

library('dplyr')
x <- 10
x

[1] 10

Q1.2 Create a vector containing the numbers 5, 10, 15, 20. Then extract the substring “Data” from the string “DataScience is fun”.

vec <- c(5, 10, 15, 20)
library(stringr)
str_sub("DataScience is fun", 1, 4)

[1] "Data"

Section 2: Data Structures

Q2.1 Create a list named my_list with elements: name = “Alice”, age = 30, scores = c(85, 90, 78).

my_list <- list(
  name = 'Alice',
  age = 30,
  scores = c(85, 90, 78)
)
my_list

$name
[1] "Alice"

$age
[1] 30

$scores
[1] 85 90 78

Q2.2 Create a 2x3 matrix filled with the numbers 1 through 6.

mat <- matrix(1:6, nrow=2)
mat

     [,1] [,2] [,3]
[1,]    1    3    5
[2,]    2    4    6

Q2.3 Create a data frame df with columns: ID = c(1,2,3), Name = c(“Tom”, “Jerry”, “Spike”).

df <- data.frame(
  ID = c(1,2,3),
  Name = c("Tom", "Jerry", "Spike")
)
df

Section 3: Data Manipulation

Q3.1 Using the mtcars dataset, filter rows where mpg > 20.

library(dplyr)
filter(mtcars, mpg > 20)

Q3.2 Select only the mpg and hp columns from mtcars.

select(mtcars, c(mpg,hp))

Q3.3 Add a new column kmpl to mtcars which is mpg * 0.425.

mutate(mtcars, kmpl = mpg * 0.425)

Q3.4 Calculate the mean of mpg in mtcars.

summarize(mtcars, avg_mpg = mean(mpg))

Q3.5 Arrange mtcars by wt in descending order.

arrange(mtcars, desc(wt))

Section 4: Data Visualization

Q4.1 Create a scatterplot of mpg vs wt from mtcars using ggplot2.

library(ggplot2)
ggplot(mtcars, aes(x = wt, y = mpg)) + geom_point()

Q4.2 Create a bar chart of the number of cars per cyl in mtcars.

ggplot(mtcars, aes(x = factor(cyl))) + geom_bar()

Q4.3 Create a scatterplot of mpg vs hp, colored by cyl.

ggplot(mtcars, aes(y=mpg, x=hp, color = factor(cyl))) + geom_point()

Section 5: Statistics & Probability

Q5.1 Calculate the mean, median, and standard deviation of mpg in mtcars.

# summarize(mtcars['mpg'], std=sd(mpg))
mean(mtcars$mpg)

[1] 20.09062

median(mtcars$mpg)

[1] 19.2

sd(mtcars$mpg)

[1] 6.026948

Q5.2 Find the correlation between mpg and wt.

r <- cor(mtcars['mpg'],mtcars['wt'])
r

            wt
mpg -0.8676594

Q5.3 Fit a linear model predicting mpg from wt.

model <- lm(mpg ~ wt, data = mtcars)
summary(model)

Call:
lm(formula = mpg ~ wt, data = mtcars)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.5432 -2.3647 -0.1252  1.4096  6.8727 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  37.2851     1.8776  19.858  < 2e-16 ***
wt           -5.3445     0.5591  -9.559 1.29e-10 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 3.046 on 30 degrees of freedom
Multiple R-squared:  0.7528,    Adjusted R-squared:  0.7446 
F-statistic: 91.38 on 1 and 30 DF,  p-value: 1.294e-10

Q5.4 Write a function to compute the mode of a vector.

my_mode <- function(x) {
  counts <- table(x)
  counts[which.max(counts)]
  #as.numeric(names(counts)[which.max(counts)])  # to get only mode, use this
}

my_mode(c(1, 2, 2, 3, 3, 3, 3))

3 
4 

# way 2
my_mode <- function(x) {
  names(sort(table(x), decreasing = TRUE))[1]
}

my_mode(c(1, 2, 2, 3, 3, 3))

[1] "3"

Q5.5 Simulate 10 coin tosses.

set.seed(22)
sample(c("Heads", "Tails"), 10, replace=TRUE)

 [1] "Tails" "Heads" "Tails" "Tails" "Tails" "Tails" "Tails" "Heads" "Heads" "Heads"

Section 6: Programming

Q6.1 Write an if statement that prints “Positive” if x > 0, “Negative” if x < 0, else “Zero”.

x <- -5

if (x > 0) {
  print("Positive")
} else if (x < 0) {
  print("Negative")
} else {
  print("Zero")
}

[1] "Negative"

Q6.2 Write a for loop to print squares of numbers 1 through 5.

for (i in 1:5){
  print(i^2)
}

[1] 1
[1] 4
[1] 9
[1] 16
[1] 25

Q6.3 Write a function that returns TRUE if a number is even.

even_checker <- function(x){
  x%%2==0
}
even_checker(3)

[1] FALSE

Q6.4 Use apply to calculate row sums of a matrix.

mat <- matrix(1:9, nrow = 3)
apply(mat,1,FUN=sum)

[1] 12 15 18

Section 7: Machine Learning

Q7.1 Fit a linear model to predict mpg from wt and hp in mtcars.

model <- lm(mpg~wt + hp, data=mtcars)
summary(model)

Call:
lm(formula = mpg ~ wt + hp, data = mtcars)

Residuals:
   Min     1Q Median     3Q    Max 
-3.941 -1.600 -0.182  1.050  5.854 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) 37.22727    1.59879  23.285  < 2e-16 ***
wt          -3.87783    0.63273  -6.129 1.12e-06 ***
hp          -0.03177    0.00903  -3.519  0.00145 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 2.593 on 29 degrees of freedom
Multiple R-squared:  0.8268,    Adjusted R-squared:  0.8148 
F-statistic: 69.21 on 2 and 29 DF,  p-value: 9.109e-12

Q7.2 Plot the residuals of the model.

library(ggplot2)
residuals_df <- data.frame(residuals = model$residuals)
ggplot(residuals_df, aes(x = residuals)) + geom_histogram(bins = 50)

Section 8: File I/O

Q8.1 Save the mtcars dataset as a CSV file named mtcars_data.csv.

write.csv(mtcars, "mtcars_data.csv", row.names = FALSE)

Q8.2 Read the CSV file back into R.

new_df <- read.csv("mtcars_data.csv")
new_df

Q8.3 List all files in your current working directory.

list.files()

 [1] "1Jan.nb.html"                    "1Jan.Rmd"                        "2dec.nb.html"                   
 [4] "2dec.Rmd"                        "30 Nov (2).R"                    "30 Nov (3).R"                   
 [7] "30 Nov.R"                        "data.csv"                        "final solve.nb.html"            
[10] "final solve.Rmd"                 "hjh.nb.html"                     "hjh.Rmd"                        
[13] "Intermediate R practice.nb.html" "Intermediate R practice.Rmd"     "message.txt"                    
[16] "mtcars_data.csv"                 "output.csv"                      "output.txt"                     
[19] "rsconnect"                       "Sample_Marks.xlsx"               "SampleDataGPA.csv"              

🧠 Final Challenge: Integrated Project

Q9

1. Load the iris dataset

2. Create a new column

   • Petal.Area = Petal.Length × Petal.Width

3. Filter the data

   • Keep rows where Petal.Area > 2

4. Create a scatter plot

   • X-axis: Petal.Area
   • Y-axis: Sepal.Length
   • Color points by Species

5. Fit a linear model

   • Predict Sepal.Length from Petal.Area

6. Save the filtered dataset

   • File name: iris_filtered.csv

# 1
data(iris)

# 2
iris <- mutate(iris, Petal.Area = Petal.Length * Petal.Width)

# 3
filtered_iris <- filter(iris, Petal.Area > 2)

# 4
ggplot(filtered_iris, aes(x = Petal.Area, y = Sepal.Length, color = Species)) + geom_point()

# 5
model_iris <- lm(Sepal.Length~Petal.Area, data=filtered_iris)
summary(model_iris)

Call:
lm(formula = Sepal.Length ~ Petal.Area, data = filtered_iris)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.23947 -0.28971 -0.05548  0.29046  1.02532 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  5.04735    0.12802   39.43   <2e-16 ***
Petal.Area   0.14276    0.01402   10.18   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4644 on 98 degrees of freedom
Multiple R-squared:  0.514, Adjusted R-squared:  0.5091 
F-statistic: 103.7 on 1 and 98 DF,  p-value: < 2.2e-16

# 6
write.csv(filtered_iris, "iris_filtered.csv", row.names = FALSE)