Factor and Data Frame in R language | R Programming Solved Assignment

Assignment 6: Factor and Data Frame in R language

1. Write a R program to find the levels of factor of a given vector.

Answer : 

v = c(1, 2, 3, 3, 4, NA, 3, 2, 4, 5, NA, 5) print("factor of vector:") print(levels(factor(v)))

2. Write a R program to create a data frame from four given vectors.

Answer :

name = c('Anastasia', 'Dima', 'Katherine', 'James', 'Emily', 'Michael', 'Matthew', 'Laura', 'Kevin', 'Jonas') score = c(12.5, 9, 16.5, 12, 9, 20, 14.5, 13.5, 8, 19) attempts = c(1, 3, 2, 3, 2, 3, 1, 1, 2, 1) qualify = c('yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes') df = data.frame(name, score, attempts, qualify) print(df)

3. Write a R program to count the number of NA values in a data frame column.

Answer :

exam_data = data.frame( name = c('Anastasia', 'Dima', 'Katherine', 'James', 'Emily', 'Michael', 'Matthew', 'Laura', 'Kevin', 'Jonas'), score = c(12.5, 9, 16.5, 12, 9, 20, 14.5, 13.5, 8, 19), attempts = c(1, NA, 2, NA, 2, NA, 1, NA, 2, 1), qualify = c('yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes') ) print("The number of NA values in attempts column:") print(sum(is.na(exam_data$attempts)))

SET A:

1. Write a R program to change the first level of a factor with another level of a given factor.

Answer :

v = c("a", "b", "a", "c", "b") f = factor(v) levels(f)[1] = "e" print(f)

2. Write a R program to create a data frame from four given vectors and display the structure and statistical summary of a data frame.

Answer ;

exam_data = data.frame( name = c('Anastasia', 'Dima', 'Katherine', 'James', 'Emily', 'Michael', 'Matthew', 'Laura', 'Kevin', 'Jonas'), score = c(12.5, 9, 16.5, 12, 9, 20, 14.5, 13.5, 8, 19), attempts = c(1, 3, 2, 3, 2, 3, 1, 1, 2, 1), qualify = c('yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes') ) print("Original dataframe:") print(exam_data) print("Structure of the said data frame:") print(str(exam_data)) print("Statistical summary and nature of the data of the said dataframe:") print(summary(exam_data))

3. Write a R program to display second row using row index and third column using column name of a data frame.

Answer :

Employees = data.frame(Name=c("Anastasia S","Dima R","Katherine S", "JAMES A","LAURA MARTIN"), Gender=c("M","M","F","F","M"), Age=c(23,22,25,26,32), Designation=c("Clerk","Manager","Exective","CEO","ASSISTANT"), SSN=c("123-34-2346","123-44-779","556-24-433","123-98-987","679-77-576") ) print("Details of the employees:") print(Employees) Employees[2:2,] Employees[, c('Age')]

4. Write a R program to create a data frame using two given vectors and display the duplicated elements and unique rows of the said data frame.

Answer :

a = c(10,20,10,10,40,50,20,30) b = c(10,30,10,20,0,50,30,30) ab = data.frame(a,b) print("Duplicate elements of the said data frame:") print(duplicated(ab)) print("Unique rows of the said data frame:") print(unique(ab))

5. Write a R program to call the (built-in) dataset airquality. Remove the variables 'Solar.R' and 'Wind' and display the data frame.

Answer :

data = airquality data[,c("Solar.R")]=NULL data[,c("Wind")]=NULL print("data.frame after removing 'Solar.R' and 'Wind' variables:") print(data)

SET B:

1. Write an R program to concatenate two given factor in a single factor and display in descending order.

Answer :

f1 <- factor(sample(LETTERS, size=6, replace=TRUE)) f2 <- factor(sample(LETTERS, size=6, replace=TRUE)) print("Original factors:") print(f1) print(f2) f = factor(c(levels(f1)[f1], levels(f2)[f2])) print("After concatenate factor becomes:") print(f) sort(f):

2. Write a R program to extract the five of the levels of factor created from a random sample from the LETTERS.

Answer : 

L = sample(LETTERS,size=50,replace=TRUE) print("Original data:") print(L) f = factor(L) print("Original factors:") print(f) print("Only five of the levels") print(table(L[1:5]))

3. Write a R program to compare two data frames to find the row(s) in first data frame that are not present in second data frame.

Answer :

DF_90 = DATA.FRAME( "ITEM" = C("ITEM1", "ITEM2", "ITEM3"), "JAN_SALE" = C(12, 14, 12), "FEB_SALE" = C(11, 12, 15), "MAR_SALE" = C(12, 14, 15) ) DF_91 = DATA.FRAME( "ITEM" = C("ITEM1", "ITEM2", "ITEM3"), "JAN_SALE" = C(12, 14, 12), "FEB_SALE" = C(11, 12, 15), "MAR_SALE" = C(12, 15, 18) ) PRINT("ROW(S) IN FIRST DATA FRAME THAT ARE NOT PRESENT IN SECOND DATA FRAME:") PRINT(SETDIFF(DF_90,DF_91))

4. Write a R program to create a data frame from four given vectors and perform the following

Answer :

exam_data = data.frame( name = c('Anastasia', 'Dima', 'Katherine', 'James', 'Emily', 'Michael', 'Matthew', 'Laura', 'Kevin', 'Jonas'), score = c(12.5, 9, 16.5, 12, 9, 20, 14.5, 13.5, 8, 19), attempts = c(1, 3, 2, 3, 2, 3, 1, 1, 2, 1), qualify = c('yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes') ) print("Original dataframe:") print(exam_data) new_exam_data = data.frame( name = c('Robert', 'Sophia'), score = c(10.5, 9), attempts = c(1, 3), qualify = c('yes', 'no') )

a. add a new column in a given data frame

Answer :

print("New data frame after adding the 'country' column:") exam_data country = c("USA","USA","USA","USA","USA","USA","USA","USA","USA","USA") print(exam_data)

b. add new row to data frame.

Answer :

exam_data = rbind(exam_data, new_exam_data) print("After adding new row(s) to an existing data frame:") print(exam_data)

c. drop specific column by name from a given data frame.

Answer :

exam_data = subset(exam_data, select = -c(name, qualify)) print(exam_data)

d. drop row by number from a given data frame.

Answer:

exam_data <- exam_data[-c(2, 4, 6), ] print(exam_data)

5. Write a R program to create a data frame from four given vectors and perform the following

Answer :

exam_data = data.frame( name = c('Anastasia', 'Dima', 'Katherine', 'James', 'Emily', 'Michael', 'Matthew', 'Laura', 'Kevin', 'Jonas'), score = c(12.5, 9, 16.5, 12, 9, 20, 14.5, 13.5, 8, 19), attempts = c(1, 3, 2, 3, 2, 3, 1, 1, 2, 1), qualify = c('yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes') ) print("Original dataframe:") print(exam_data)

a. Extract 3rd and 5th rows with 1st and 3rd columns from a given data frame.

Answer :

print("Extract 3rd and 5th rows with 1st and 3rd columns :") result = exam_data[c(3,5),c(1,3)] print(result)

b. Sort and display given data frame by specific column.

Answer :

print("dataframe after sorting 'name' and 'score' columns:") exam_data = exam_data[with(exam_data, order(name, score)), ] print(exam_data)

SET C:

1. Write a R program to create inner, outer, left, right join(merge) from given two data frames.

Answer :

df1 = data.frame(numid = c(12, 14, 10, 11)) df2 = data.frame(numid = c(13, 15, 11, 12)) print("Left outer Join:") result = merge(df1, df2, by = "numid", all.x = TRUE) print(result) print("Right outer Join:") result = merge(df1, df2, by = "numid", all.y = TRUE) print(result) print("Outer Join:") result = merge(df1, df2, by = "numid", all = TRUE) print(result) print("Cross Join:") result = merge(df1, df2, by = NULL) print(result)

2. Write a R program to save the information of a data frame in a file and display the information of the file.

Answer :

exam_data = data.frame( name = c('Anastasia', 'Dima', 'Katherine', 'James', 'Emily', 'Michael', 'Matthew', 'Laura', 'Kevin', 'Jonas'), score = c(12.5, 9, 16.5, 12, 9, 20, 14.5, 13.5, 8, 19), attempts = c(1, 3, 2, 3, 2, 3, 1, 1, 2, 1), qualify = c('yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes') ) print("Original dataframe:") print(exam_data) save(exam_data,file="data.rda") load("data.rda") file.info("data.rda")