TECHNO INDIA UNIVERSITY

SESSION: - 2023-2025
NAME: -SHASWATI PAUL
YEAR: - 2ND
BATCH: -MCA 2C
STUDENT ID: - 231001271220
SUBJECT: - R Programming Lab
 ASSIGNMENT 10

Topic:Datafile Handling in R
Attempt to solve the problems given below as directed:
1. Develop a generalised R script for creating a .CSV file out of a
dataframe formed with cbind() function.
Code:-
# Generalized Script
create_csv_from_cbind <- function(data1, data2, filename) {
# Create a dataframe using cbind()
df <- as.data.frame(cbind(data1, data2))

# Write the dataframe to a .CSV file

write.csv(df, file = filename, row.names = FALSE)

cat("CSV file", filename, "has been created successfully.\n")

}

# Example Usage
data1 <- c(1, 2, 3, 4)
data2 <- c("A", "B", "C", "D")
create_csv_from_cbind(data1, data2, "output.csv")
Output:-
2. Develop an R script to do the following:
(a) create a dataframe with any set of data of your choice
(b) write the dataframe to a .CSV file
(c) Read the .csv file using the scan() function such that only the
row-data of the dataframe are displayed with one row in one
line.
Code:-
# Create a dataframe
df <- data.frame(
Name = c("John", "Alice", "Bob"),
Age = c(25, 30, 22),
Department = c("HR", "IT", "Sales")
)

# Write the dataframe to a .CSV file

write.csv(df, "data.csv", row.names = FALSE)

# Read the .CSV file using scan() (row-data only)

scanned_data <- scan(file = "data.csv", what = "", sep = "\n", skip = 1)
cat("Row Data from the CSV file:\n")
print(scanned_data)
Output:-

3. Develop an R script to perform the following:

• Accepts a text-file name as input
• Accepts vectors of input one by one each containing multiple
lines of text
• Writes each of the vectors using writeLine() function
• Shows one of line data at a time until the end of file.
Code:-
# Function to accept vectors and write to a text file
write_vectors_to_file <- function(filename, ...) {
# Collect vectors as input
vectors <- list(...)

# Write vectors to file

file_conn <- file(filename, "w")
for (vector in vectors) {
writeLines(vector, file_conn)
}
close(file_conn)
 # Read and display each line of the file
file_conn <- file(filename, "r")
while (length(line <- readLines(file_conn, n = 1, warn = FALSE)) > 0) {
print(line)
}
close(file_conn)
}

# Example Usage
vector1 <- c("Line 1 from Vector 1", "Line 2 from Vector 1")
vector2 <- c("Line 1 from Vector 2", "Line 2 from Vector 2")
write_vectors_to_file("output.txt", vector1, vector2)
Output:-

4. Develop an R script to create a text file to write the records of employees

of a company comprising EMP-ID,EMP-Name,Deptt,Dateof-Joining and
Date-Of-birth to determine and print EMP-ID,EMPName,Deptt.Years-
served and Age-on-01-01-2022 for those employ1
ees who will either complete 60 years in age or 40 years in service.Assume
that the dates are in mm-dd-yyyy format.
Code:-
# Install and load required packages
if (!requireNamespace("lubridate", quietly = TRUE)) {
install.packages("lubridate")
}
library(lubridate)
# Function to process employee data
process_employees <- function(filename) {
# Create employee data
employees <- data.frame(
EMP_ID = c(101, 102, 103),
EMP_Name = c("John Doe", "Alice Smith", "Robert Brown"),
Dept = c("HR", "IT", "Sales"),
Date_Joining = c("01-15-1982", "03-10-1990", "05-12-2000"),
Date_Birth = c("12-10-1962", "01-20-1970", "06-15-1980")
)

# Write employee data to file

write.csv(employees, filename, row.names = FALSE)

# Read and process the data

df <- read.csv(filename)
df$Years_Served <- as.integer(2022 - year(mdy(df$Date_Joining)))
df$Age_2022 <- as.integer(2022 - year(mdy(df$Date_Birth)))

# Filter employees meeting the criteria

eligible <- subset(df, Age_2022 >= 60 | Years_Served >= 40)
print(eligible[, c("EMP_ID", "EMP_Name", "Dept", "Years_Served",
"Age_2022")])
}

# Example Usage
process_employees("employee_data.csv")
Output:-

5. Develop an R script to create a text file to write the records of employees

of a company comprising EMP-ID,EMP-Name,Deptt and
Basic Pay and then to create another file containing salary data of
all the employees with the following specifications:
• Each salary record will consist of EMP-ID,EMP-Name,Deptt
,Basic Pay,DA,MA,HRA,Gross-Pay,PF,PT,IT and Net-Pay.
• DA is calculated @109% of the basic pay subject to minimum
of Rs. 10000.
• MA is calculated @21% of basic pay subject to a minimum of
Rs.3000 and a maximum of Rs.7000.
• HRA is calculated @35% of the basic pay subject to a maximum
of Rs.20,000.
• Gross-Pay is the sum of Basic Pay,DA,MA,HRA.
• PT is Rs. 100 for employees having Gross-Pay <50000, otherwise, it is Rs.
200.
• PF is 12.5% of the Gross-Pay
• IT is calculated @10% for having the Gross-Pay that exceeds
70,000 but less than 100,000;otherwise, it is 20% of the GrossPay.
• Net Pay is calculated by subtracting PF,PT and IT from the
Gross-Pay.
• Show the names of the employees in abbreviated form like Amal
Kumar Biswas as A.K. Biswas
• Format the Net-pay rounded to nearest rupees by taking the
upper value.
Code:-
# Install and load required packages
if (!requireNamespace("stringr", quietly = TRUE)) {
install.packages("stringr")
}
library(stringr)

# Function to process salary data

process_salary <- function(filename) {
# Create employee data
employees <- data.frame(
EMP_ID = c(101, 102, 103),
EMP_Name = c("John Doe", "Alice Smith", "Robert Brown"),
Dept = c("HR", "IT", "Sales"),
Basic_Pay = c(40000, 60000, 80000)
)

# Calculate salary components

employees$DA <- pmax(employees$Basic_Pay * 0.109, 10000)
employees$MA <- pmin(pmax(employees$Basic_Pay * 0.21, 3000), 7000)
employees$HRA <- pmin(employees$Basic_Pay * 0.35, 20000)
employees$Gross_Pay <- rowSums(employees[, c("Basic_Pay", "DA", "MA",
"HRA")])
employees$PF <- employees$Gross_Pay * 0.125
employees$PT <- ifelse(employees$Gross_Pay < 50000, 100, 200)
 employees$IT <- ifelse(employees$Gross_Pay > 70000 &
employees$Gross_Pay < 100000,
employees$Gross_Pay * 0.1, employees$Gross_Pay * 0.2)
employees$Net_Pay <- ceiling(employees$Gross_Pay - employees$PF -
employees$PT - employees$IT)

# Format names
employees$EMP_Name <- sapply(employees$EMP_Name, function(x) {
name_parts <- strsplit(x, " ")[[1]]
paste(paste0(substr(name_parts[-length(name_parts)], 1, 1), "."),
name_parts[length(name_parts)])
})

# Write to file
write.csv(employees, filename, row.names = FALSE)

print(employees)
}

# Example Usage
process_salary("salary_data.csv")
Output:-

6. An excel data file contains 5 sheets of data about the students of

five different classes. Develop an R script to read each of the sheets
in different .csv files to print total number of students,number of
boys,number of girls, average age of the boys and average age of
the girls for each of the classes by assuming any data structure you
deem suitable.
Code:-
# Install and load required packages
if (!requireNamespace("readxl", quietly = TRUE)) {
install.packages("readxl")
}
library(readxl)

# Function to process Excel data

process_excel_data <- function(filename) {
# Check if the file exists
if (!file.exists(filename)) {
stop(paste("Error: File", filename, "does not exist. Please check the file
path."))
}

# Try to read the file and handle any errors

tryCatch({
sheets <- excel_sheets(filename)
results <- list()

for (sheet in sheets) {

data <- read_excel(filename, sheet = sheet)

# Check if the required columns exist

 if (!all(c("Gender", "Age") %in% colnames(data))) {
stop(paste("Error: Sheet", sheet, "is missing required columns 'Gender'
and/or 'Age'."))
}

# Split into boys and girls

boys <- subset(data, Gender == "Male")
girls <- subset(data, Gender == "Female")

# Collect results for each sheet

results[[sheet]] <- list(
Total_Students = nrow(data),
Boys = nrow(boys),
Girls = nrow(girls),
Avg_Age_Boys = ifelse(nrow(boys) > 0, mean(boys$Age, na.rm = TRUE),
NA),
Avg_Age_Girls = ifelse(nrow(girls) > 0, mean(girls$Age, na.rm = TRUE),
NA)
)
}

# Print the results

print(results)
}, error = function(e) {
cat("An error occurred:", e$message, "\n")
})
}

# Example Usage
# Provide the correct file path to your Excel file
file_path <- "C:/Users/shasw/OneDrive/Desktop/Shaswati Paul Final
Documents/students_data.xlsx"
process_excel_data(file_path)
Output:-