week1 A.Vishal Bharadwaj 2023-10-16 R Markdown This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

# Define variables with different data types numeric_var <- 42 character_var <- “Hello, World!” logical_var <- TRUE date_time_var <- as.POSIXct(“2023-01-15 14:30:00”)

Add the two vectors element-wise

result_vector <- vector1 + vector2

b.Create a vector

my_vector <- c(2, 4, 6, 8, 10)

Calculate the sum, mean, and product

sum_result <- sum(my_vector) mean_result <- mean(my_vector) product_result <- prod(my_vector)

c.Create a vector

my_vector <- c(3, 1, 7, 2, 9)

Find the minimum and maximum

min_value <- min(my_vector) max_value <- max(my_vector)

Access the first and second elements of the list

first_element <- my_list\(vector_element second_element <- my_list\)matrix_element

Access specific elements

element_1 <- my_matrix[2, 3] # 3rd column, 2nd row element_2 <- my_matrix[3, ] # 3rd row element_3 <- my_matrix[, 4] # 4th column

Create a DataFrame

df <- data.frame(Name = name, Age = age)

Display the DataFrame

print(df) ## Name Age ## 1 Alice 25 ## 2 Bob 30 ## 3 Charlie 35 #i. Create a DataFrame df <- data.frame(Name = c(“Alice”, “Bob”), Age = c(25, 30))

New data to insert

new_data <- data.frame(Name = c(“Charlie”, “David”), Age = c(35, 40))

Insert new rows

df <- rbind(df, new_data)

Display the updated DataFrame

print(df) ## Name Age ## 1 Alice 25 ## 2 Bob 30 ## 3 Charlie 35 ## 4 David 40 #j. Create a DataFrame df <- data.frame(Name = c(“Alice”, “Bob”), Age = c(25, 30))

Add a new column

df$Salary <- c(50000, 60000)

Display the updated DataFrame

print(df) ## Name Age Salary ## 1 Alice 25 50000 ## 2 Bob 30 60000 #k. Create a DataFrame df <- data.frame(Name = c(“Alice”, “Bob”, “Charlie”, “David”), Age = c(25, 30, 35, 40))

Extract the first 2 rows

first_two_rows <- df[1:2, ]

Display the extracted rows

print(first_two_rows) ## Name Age ## 1 Alice 25 ## 2 Bob 30 #l. Create a DataFrame df <- data.frame(Name = c(“Charlie”, “Alice”, “Bob”), Age = c(35, 25, 30))

Sort the DataFrame by the “Age” column

sorted_df <- df[order(df$Age), ]

Display the sorted DataFrame

print(sorted_df) ## Name Age ## 2 Alice 25 ## 3 Bob 30 ## 1 Charlie 35 #m. Create two DataFrames df1 <- data.frame(ID = 1:3, Name = c(“Alice”, “Bob”, “Charlie”)) df2 <- data.frame(ID = 2:4, Salary = c(50000, 60000, 70000))

Merge the DataFrames based on the “ID” column

merged_df <- merge(df1, df2, by = “ID”, all = TRUE)

Display the merged DataFrame

print(merged_df) ## ID Name Salary ## 1 1 Alice NA ## 2 2 Bob 50000 ## 3 3 Charlie 60000 ## 4 4 70000 #n. Create two DataFrames df1 <- data.frame(Name = c(“Alice”, “Bob”), Age = c(25, 30)) df2 <- data.frame(Name = c(“Charlie”, “David”), Age = c(35, 40))

Append df2 to the end of df1

appended_df <- rbind(df1, df2)

Display the appended DataFrame

print(appended_df) ## Name Age ## 1 Alice 25 ## 2 Bob 30 ## 3 Charlie 35 ## 4 David 40 #o. Load the dplyr package library(dplyr) ## ## Attaching package: ‘dplyr’ ## The following objects are masked from ‘package:stats’: ## ## filter, lag ## The following objects are masked from ‘package:base’: ## ## intersect, setdiff, setequal, union # Create a sample DataFrame df <- data.frame(Group = c(“A”, “A”, “B”, “B”, “C”), Value = c(10, 15, 25, 20, 30))

Select rows with maximum value in each group

result <- df %>% group_by(Group) %>% filter(Value == max(Value))

Display the result

print(result) ## # A tibble: 3 × 2 ## # Groups: Group [3] ## Group Value ## ## 1 A 15 ## 2 B 25 ## 3 C 30 #p. Create two dataframes df1 <- data.frame(ID = 1:4, Name = c(“Alice”, “Bob”, “Charlie”, “David”)) df2 <- data.frame(ID = 2:5, Salary = c(50000, 60000, 70000, 55000))

Merge the dataframes based on the “ID” column

merged_df <- merge(df1, df2, by = “ID”, all = TRUE)

Display the merged dataframe

print(merged_df) ## ID Name Salary ## 1 1 Alice NA ## 2 2 Bob 50000 ## 3 3 Charlie 60000 ## 4 4 David 70000 ## 5 5 55000 #q.a. Read data from the console data <- as.numeric(readline(“Enter a number:”)) ## Enter a number: print(data) ## [1] NA #q.b. reading data from csv file data=read.csv(“C:/Users/abhishek/Documents/Book1.csv”) data ## Org_Indiv First_Plus First_Name Last_Name ## 1 3-D Medical Services Llc Steven Bruce Steven Deitelzweig ## 2 Aa Doctors, Inc. Aakash Mohan Aakash Ahuja ## 3 Abbo, Lilian Margarita Lilian Margarita Lilian Abbo ## 4 Abbo, Lilian Margarita Lilian Margarita Lilian Abbo ## 5 Abbo, Lilian Margarita Lilian Margarita Lilian Abbo ## 6 Abdullah Raffee Md Pc Abdullah Abdullah Raffee ## 7 Abebe, Sheila Y Sheila Y Sheila Abebe ## 8 Abebe, Sheila Y Sheila Y Sheila Abebe ## 9 Abilene Family Foot Center Galen Chris Galen Albritton ## 10 Abolnik, Igor Z Igor Z Igor Abolnik ## 11 Abolnik, Igor Z Igor Z Igor Abolnik ## City State Category Cash Other Total ## 1 New Orleans LA Professional Advising 2625 0 2625 ## 2 Paso Robles CA Expert-Led Forums 1000 0 1000 ## 3 Miami FL Business Related Travel 0 448 448 ## 4 Miami FL Meals 0 119 119 ## 5 Miami FL Professional Advising 1800 0 1800 ## 6 Flint MI Expert-Led Forums 750 0 750 ## 7 Indianapolis IN Educational Items 0 47 47 ## 8 Indianapolis IN Expert-Led Forums 825 0 825 ## 9 Abilene TX Professional Advising 3000 0 3000 ## 10 Provo UT Business Related Travel 0 396 396 ## 11 Provo Ut Expert-Led Forums 1750 0 1750