FDA_lab2.

R
2023-08-16

#20mia1006 SANIDHYA CHAUDHARY

#LAB_2_A AND LAB_2_B

#Create a list for an employee with the following fields:EmpId,

Name,Designation, CompanyName
employee <- list(EmpId = "1",Name = "shiva",Designation = "IT
head",CompanyName = "infosys")

#Q 2. Add the fields viz., DateOfBirth, ContactNumber and MailID to theabove

list.

employee$DateOfBirth <- "2000-03-24"

employee$ContactNumber <- "9548624522"
employee$MailID <- "[email protected]"
employee

## $EmpId
## [1] "1"
##
## $Name
## [1] "shiva"
##
## $Designation
## [1] "IT head"
##
## $CompanyName
## [1] "infosys"
##
## $DateOfBirth
## [1] "2000-03-24"
##
## $ContactNumber
## [1] "9548624522"
##
## $MailID
## [1] "[email protected]"

#Q 3. Print the total number of fields and the field names.

num_fields <- length(employee)

field_names <- names(employee)
cat("Total number of fields:", num_fields, "\n")

## Total number of fields: 7

cat("Field names:", field_names, "\n")

## Field names: EmpId Name Designation CompanyName DateOfBirth ContactNumber

MailID

#Q 4. Create a data frame with the above fieldnames (5 different variables

for EmpId, Name, Designation, Company, DOB) for 5 employees.

employee_df <- data.frame(EmpId = c(001,002,003,004,005),Name =

c("shiva","shri","rohit","Sanidhya","harshit"),
Designation = c("Software Engineer","Data
Analyst","Product Manager","IT head","Marketing Head"),
CompanyName = c("infosys","JP Morgan","TCS","de
shaw","google"),
DateOfBirth = as.Date(c("1998-06-1","1988-09-
23","1995-03-10","1997-11-30","1999-06-18")))
# Print employee data frame
print(employee_df)

## EmpId Name Designation CompanyName DateOfBirth

## 1 1 shiva Software Engineer infosys 1998-06-01
## 2 2 shri Data Analyst JP Morgan 1988-09-23
## 3 3 rohit Product Manager TCS 1995-03-10
## 4 4 Sanidhya IT head de shaw 1997-11-30
## 5 5 harshit Marketing Head google 1999-06-18

#Q 5. Add the ContactNumber and MailID to this dataframe.

employee_df$ContactNumber <- c("9119086885", "9876543210", "7885265442",

"8546127596", "9578523655")
employee_df$MailID <- c("[email protected]", "[email protected]",
"[email protected]", "[email protected]", "[email protected]")
employee_df

## EmpId Name Designation CompanyName DateOfBirth ContactNumber

## 1 1 shiva Software Engineer infosys 1998-06-01 9119086885
## 2 2 shri Data Analyst JP Morgan 1988-09-23 9876543210
## 3 3 rohit Product Manager TCS 1995-03-10 7885265442
## 4 4 Sanidhya IT head de shaw 1997-11-30 8546127596
## 5 5 harshit Marketing Head google 1999-06-18 9578523655
## MailID
## 1 [email protected]
## 2 [email protected]
## 3 [email protected]
## 4 [email protected]
## 5 [email protected]
#Q 6. Add the details of employee 3 without contact number and employee 4
without mentioning mailID.

# Add a new employee record without mail ID and contact number

employee_df <- rbind(employee_df, c("06", "abhishek", "Sales head",

"accenture", "1995-06-18", NA, NA))
employee_df <- rbind(employee_df,c("07", "shreyas", "HR head", "TVS", "1999-
07-29", NA, NA))
# Print updated employee data frame
employee_df

## EmpId Name Designation CompanyName DateOfBirth ContactNumber

## 1 1 shiva Software Engineer infosys 1998-06-01 9119086885
## 2 2 shri Data Analyst JP Morgan 1988-09-23 9876543210
## 3 3 rohit Product Manager TCS 1995-03-10 7885265442
## 4 4 Sanidhya IT head de shaw 1997-11-30 8546127596
## 5 5 harshit Marketing Head google 1999-06-18 9578523655
## 6 06 abhishek Sales head accenture 1995-06-18 <NA>
## 7 07 shreyas HR head TVS 1999-07-29 <NA>
## MailID
## 1 [email protected]
## 2 [email protected]
## 3 [email protected]
## 4 [email protected]
## 5 [email protected]
## 6 <NA>
## 7 <NA>

#Q 7. Display the details of the employees after removing the missing values.

employee_df_cleaned <- na.omit(employee_df)

print(employee_df_cleaned)

## EmpId Name Designation CompanyName DateOfBirth ContactNumber

## 1 1 shiva Software Engineer infosys 1998-06-01 9119086885
## 2 2 shri Data Analyst JP Morgan 1988-09-23 9876543210
## 3 3 rohit Product Manager TCS 1995-03-10 7885265442
## 4 4 Sanidhya IT head de shaw 1997-11-30 8546127596
## 5 5 harshit Marketing Head google 1999-06-18 9578523655
## MailID
## 1 [email protected]
## 2 [email protected]
## 3 [email protected]
## 4 [email protected]
## 5 [email protected]

#Q 8. Calculate the age of all the employees and add it as an additional

field
employee_df$Age <- as.integer(difftime(Sys.Date(),
as.Date(employee_df$DateOfBirth), units = "days") / 365)
# Print updated employee data frame
print(employee_df)

## EmpId Name Designation CompanyName DateOfBirth ContactNumber

## 1 1 shiva Software Engineer infosys 1998-06-01 9119086885
## 2 2 shri Data Analyst JP Morgan 1988-09-23 9876543210
## 3 3 rohit Product Manager TCS 1995-03-10 7885265442
## 4 4 Sanidhya IT head de shaw 1997-11-30 8546127596
## 5 5 harshit Marketing Head google 1999-06-18 9578523655
## 6 06 abhishek Sales head accenture 1995-06-18 <NA>
## 7 07 shreyas HR head TVS 1999-07-29 <NA>
## MailID Age
## 1 [email protected] 25
## 2 [email protected] 34
## 3 [email protected] 28
## 4 [email protected] 25
## 5 [email protected] 24
## 6 <NA> 28
## 7 <NA> 24

#Q 9. Add the date of joining information to every employee.

employee_df$DateOfJoining <- as.Date(c("2020-01-15", "2018-08-10", "2022-03-
20", "2019-11-05", "2021-06-30","2022-05-05","2023-02-25"))
employee_df

## EmpId Name Designation CompanyName DateOfBirth ContactNumber

## 1 1 shiva Software Engineer infosys 1998-06-01 9119086885
## 2 2 shri Data Analyst JP Morgan 1988-09-23 9876543210
## 3 3 rohit Product Manager TCS 1995-03-10 7885265442
## 4 4 Sanidhya IT head de shaw 1997-11-30 8546127596
## 5 5 harshit Marketing Head google 1999-06-18 9578523655
## 6 06 abhishek Sales head accenture 1995-06-18 <NA>
## 7 07 shreyas HR head TVS 1999-07-29 <NA>
## MailID Age DateOfJoining
## 1 [email protected] 25 2020-01-15
## 2 [email protected] 34 2018-08-10
## 3 [email protected] 28 2022-03-20
## 4 [email protected] 25 2019-11-05
## 5 [email protected] 24 2021-06-30
## 6 <NA> 28 2022-05-05
## 7 <NA> 24 2023-02-25

##Q 10 10.Print the experience (in terms of years, months and day) of
employee1 at this company till Dec 31, 2022.
employee1_joining_date <- employee_df$DateOfJoining[1]
target_date <- as.Date("2022-12-31")
experience_days <- as.numeric(difftime(target_date, employee1_joining_date,
units = "days"))
# Calculate years, months, and days
experience_years <- floor(experience_days / 365.25)
remaining_days <- experience_days %% 365.25
experience_months <- floor(remaining_days / 30.44)
experience_remaining_days <- round(remaining_days %% 30.44)

# Print experience of Employee 1

cat("Experience of Employee 1 until Dec 31, 2022:",
experience_years, "years,", experience_months, "months,",
experience_remaining_days, "days\n")

## Experience of Employee 1 until Dec 31, 2022: 2 years, 11 months, 16 days

## 11.Print the age of employee2 at the time of joining in his company

employee2_joining_date <- employee_df$DateOfJoining[2]

employee2_dob <- employee_df$DateOfBirth[2]
age_at_joining <- as.integer(difftime(employee2_joining_date, employee2_dob,
units = "days") / 365.25)

# Print age of Employee 2 at the time of joining

cat("Age of Employee 2 at the time of joining:", age_at_joining, "years\n")

## Age of Employee 2 at the time of joining: 29 years

### LAB 2 B

##Q1 Create a list of cities in different countries. Add the population and
area (in square kilometers) for each city as additional fields.
#Print the total number of cities in the list.

# Create a list of cities with population and area

city_list <- list(
City1 = c(Name = "New York", Population = 8376000, Area = 783.84),
City2 = c(Name = "Tokyo", Population = 9273000, Area = 2187.66),
City3 = c(Name = "London", Population = 8674000, Area = 1572),
City4 = c(Name = "Mumbai", Population = 18410000, Area = 603.4)
)

# Print total number of cities in the list

cat("Total number of cities:", length(city_list), "\n")

## Total number of cities: 4

##Q2 Create a data frame to store information about books. Include columns
for Title, Author, Year of Publication, and Genre.
#Add information for 6 different books.

# Create a data frame for books

books_df <- data.frame(
Title = c("To Kill a Mockingbird", "1984", "The Great Gatsby", "Pride and
Prejudice", "The Hobbit", "The Catcher in the Rye"),
 Author = c("Harper Lee", "George Orwell", "F. Scott Fitzgerald", "Jane
Austen", "J.R.R. Tolkien", "J.D. Salinger"),
Year = c(1960, 1949, 1925, 1813, 1937, 1951),
Genre = c("Fiction", "Dystopian", "Classics", "Romance", "Fantasy",
"Coming-of-age")
)

# Print the data frame

print(books_df)

## Title Author Year Genre

## 1 To Kill a Mockingbird Harper Lee 1960 Fiction
## 2 1984 George Orwell 1949 Dystopian
## 3 The Great Gatsby F. Scott Fitzgerald 1925 Classics
## 4 Pride and Prejudice Jane Austen 1813 Romance
## 5 The Hobbit J.R.R. Tolkien 1937 Fantasy
## 6 The Catcher in the Rye J.D. Salinger 1951 Coming-of-age

##Q3 Add a new book entry to the existing data frame created in the previous
question.
# Add a new book entry to the data frame
new_book <- data.frame(
Title = "Harry Potter and the Sorcerer's Stone",
Author = "J.K. Rowling",
Year = 1997,
Genre = "Fantasy"
)
books_df <- rbind(books_df, new_book)

# Print the updated data frame

print(books_df)

## Title Author Year

Genre
## 1 To Kill a Mockingbird Harper Lee 1960
Fiction
## 2 1984 George Orwell 1949
Dystopian
## 3 The Great Gatsby F. Scott Fitzgerald 1925
Classics
## 4 Pride and Prejudice Jane Austen 1813
Romance
## 5 The Hobbit J.R.R. Tolkien 1937
Fantasy
## 6 The Catcher in the Rye J.D. Salinger 1951 Coming-
of-age
## 7 Harry Potter and the Sorcerer's Stone J.K. Rowling 1997
Fantasy

##Q4 Calculate the average year of publication for the books in the data
frame.
average_year <- mean(books_df$Year)
cat("Average year of publication:", round(average_year), "\n")

## Average year of publication: 1933

##Q5 Create a list of students with their names, ages, and favorite subjects.
Convert the list into a data frame.

# Create a list of students

students_list <- list(
Student1 = c(Name = "Ramesh", Age = 18, FavoriteSubject = "Math"),
Student2 = c(Name = "Babulal", Age = 17, FavoriteSubject = "Science"),
Student3 = c(Name = "chetan", Age = 16, FavoriteSubject = "History"),
Student4 = c(Name = "Dhruv", Age = 18, FavoriteSubject = "English")
)

# Convert the list into a data frame

students_df <- as.data.frame(students_list)

# Print the data frame

print(students_df)

## Student1 Student2 Student3 Student4

## Name Ramesh Babulal chetan Dhruv
## Age 18 17 16 18
## FavoriteSubject Math Science History English

##Q 6 Create a data frame with information about movies, including Title,
Director, Release Year, and Genre.
#Add details for at least 5 different movies.

# Create a data frame for movies

movies_df <- data.frame(
Title = c("Inception", "The Shawshank Redemption", "Avatar", "Pulp
Fiction", "Jurassic Park"),
Director = c("Christopher Nolan", "Frank Darabont", "James Cameron",
"Quentin Tarantino", "Steven Spielberg"),
ReleaseYear = c(2010, 1994, 2009, 1994, 1993),
Genre = c("Science Fiction", "Drama", "Science Fiction", "Crime",
"Adventure")
)

# Print the data frame

print(movies_df)

## Title Director ReleaseYear Genre

## 1 Inception Christopher Nolan 2010 Science Fiction
## 2 The Shawshank Redemption Frank Darabont 1994 Drama
## 3 Avatar James Cameron 2009 Science Fiction
## 4 Pulp Fiction Quentin Tarantino 1994 Crime
## 5 Jurassic Park Steven Spielberg 1993 Adventure

##Q 7 Filter the movies data frame to include only movies released after the
year 2000.

recent_movies <- subset(movies_df, ReleaseYear > 2000)

# Print the filtered data frame
print(recent_movies)

## Title Director ReleaseYear Genre

## 1 Inception Christopher Nolan 2010 Science Fiction
## 3 Avatar James Cameron 2009 Science Fiction

##Q8 Create a data frame to store information about products, including

ProductName, Price, Category, and Quantity.
#Add details for at least 6 different products.

# Create a data frame for products

products_df <- data.frame(
ProductName = c("Laptop", "Smartphone", "Headphones", "Tablet", "Camera",
"Printer"),
Price = c(1000, 700, 150, 300, 400, 200),
Category = c("Electronics", "Electronics", "Accessories", "Electronics",
"Electronics", "Office Supplies"),
Quantity = c(10, 15, 20, 8, 5, 12)
)

# Print the data frame

print(products_df)

## ProductName Price Category Quantity

## 1 Laptop 1000 Electronics 10
## 2 Smartphone 700 Electronics 15
## 3 Headphones 150 Accessories 20
## 4 Tablet 300 Electronics 8
## 5 Camera 400 Electronics 5
## 6 Printer 200 Office Supplies 12

##Q9 Add a new column to the products data frame to calculate the total cost
of each product (Price multiplied by Quantity).

products_df$TotalCost <- products_df$Price * products_df$Quantity

# Print the updated data frame
print(products_df)

## ProductName Price Category Quantity TotalCost

## 1 Laptop 1000 Electronics 10 10000
## 2 Smartphone 700 Electronics 15 10500
## 3 Headphones 150 Accessories 20 3000
## 4 Tablet 300 Electronics 8 2400
## 5 Camera 400 Electronics 5 2000
## 6 Printer 200 Office Supplies 12 2400

##Q10 Sort the products data frame in descending order based on the total
cost of each product.

sorted_products_df <- products_df[order(products_df$TotalCost, decreasing =

TRUE), ]
# Print the sorted data frame
print(sorted_products_df)

## ProductName Price Category Quantity TotalCost

## 2 Smartphone 700 Electronics 15 10500
## 1 Laptop 1000 Electronics 10 10000
## 3 Headphones 150 Accessories 20 3000
## 4 Tablet 300 Electronics 8 2400
## 6 Printer 200 Office Supplies 12 2400
## 5 Camera 400 Electronics 5 2000

##Q11 Create a nested list called student_info containing fields for Name,
Age, and Address (with fields Street, City, and PostalCode). Print the street
address of the student.

# Create a nested list for student information

student_info <- list(
Name = "John",
Age = 20,
Address = list(
Street = "123 Main St",
City = "New York",
PostalCode = "10001" ))
# Print the street address
print(student_info$Address$Street)

## [1] "123 Main St"

##Q12 Create a list numbers containing a sequence of numbers from 1 to 5.

Double each number in the list and store the result in a new list called
doubled_numbers.
#Print both lists.

numbers <- list(1, 2, 3, 4, 5)

# Double each number in the list
doubled_numbers <- lapply(numbers, function(x) x * 2)
# Print both lists
print(numbers)

## [[1]]
## [1] 1
##
## [[2]]
## [1] 2
##
## [[3]]
## [1] 3
##
## [[4]]
## [1] 4
##
## [[5]]
## [1] 5

print(doubled_numbers)

## [[1]]
## [1] 2
##
## [[2]]
## [1] 4
##
## [[3]]
## [1] 6
##
## [[4]]
## [1] 8
##
## [[5]]
## [1] 10

##Q13 Create a list grades containing student grades (A, B, C, D, F). Use the
unlist() function to convert the
#list to a vector and calculate the average grade.

grades <- list("A", "B", "C", "D", "F")

# Convert the list to a vector
grades_vector <- unlist(grades)
# Calculate the average grade
average_grade <- mean(as.numeric(factor(grades_vector), levels = c("F", "D",
"C", "B", "A")))
cat("Average grade:", average_grade, "\n")

## Average grade: 3

##Q14 Create a list ages containing age values. Use the sapply() function to
calculate the square of each age.

ages <- list(25, 30, 22, 28, 35)

# Calculate the square of each age using sapply
squared_ages <- sapply(ages, function(x) x^2)
# Print the list of squared ages
print(squared_ages)
## [1] 625 900 484 784 1225

##Q15 Create a list numbers containing numeric values. Use the Reduce()
function to calculate the
#product of all numbers in the list.

numbers <- list(2, 3, 4, 5)

# Calculate the product of all numbers using Reduce
product <- Reduce(`*`, numbers)
cat("Product of numbers:", product, "\n")

## Product of numbers: 120