Daily Assignment 5
2: Create a list with the following named elements:
my_matrix, which is a 4 x 4 matrix filled with random
uniform values, my_logical which is a 100-element vector of TRUE or
FALSE values. You can do this efficiently by setting up a vector of
random values and then applying an inequality to it., my_letters, which
is a 26-element vector of all the lower-case letters in random
order.
my_data<-runif(n=16, min=0, max=20) # create a vector of 16 random uniform values between 0 and 20
my_matrix<-matrix(data=my_data,nrow=4, ncol=4) # create 4x4 matrix
print(my_matrix)## [,1] [,2] [,3] [,4]
## [1,] 9.311300 16.421334 7.106850 12.668899
## [2,] 10.150067 8.781915 19.418150 7.749743
## [3,] 7.320184 19.550999 10.916902 9.017582
## [4,] 19.979705 7.602535 3.641672 17.076048random_numbers<-runif(n=100, min=0, max=100) # assign 100 random uniform numbers to random_numbers
my_logical<- random_numbers>50 # logical statement which returns T if value > 50
my_letters<-c(letters[1:26]) # combine letters 1-26 of the alphabet into a list
my_letters<-sample(my_letters) # randomize these letters
typeof(my_letters)## [1] "character"assignment5_list<-list(my_matrix, my_logical, my_letters)
print(assignment5_list)## [[1]]
## [,1] [,2] [,3] [,4]
## [1,] 9.311300 16.421334 7.106850 12.668899
## [2,] 10.150067 8.781915 19.418150 7.749743
## [3,] 7.320184 19.550999 10.916902 9.017582
## [4,] 19.979705 7.602535 3.641672 17.076048
##
## [[2]]
## [1] FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE
## [13] TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE
## [25] TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE FALSE TRUE
## [37] FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE TRUE
## [49] TRUE FALSE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE
## [61] TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALSE
## [73] TRUE TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE FALSE
## [85] FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALSE
## [97] TRUE FALSE TRUE TRUE
##
## [[3]]
## [1] "o" "f" "r" "k" "i" "h" "c" "m" "s" "u" "b" "g" "a" "l" "y" "n" "v" "z" "t"
## [20] "j" "x" "p" "d" "e" "w" "q"Then, complete the following steps:
a: create a new list, which has the element[2,2] from the matrix, the second element of the logical vector, and the second element of the letters vector.
new_list<-list(assignment5_list[[1]][2,2],assignment5_list[[2]][2],assignment5_list[[3]][2]) # create a new list with the element [2,2] from the first compartment, the second element from the second compartment, and the second element from the third compartment
print(new_list)## [[1]]
## [1] 8.781915
##
## [[2]]
## [1] FALSE
##
## [[3]]
## [1] "f"b: use the typeof() function to confirm the underlying data types of each component in this list
typeof(assignment5_list[[1]]) # double## [1] "double"typeof(assignment5_list[[2]]) # logical## [1] "logical"typeof(assignment5_list[[3]]) # character## [1] "character"c: i) combine the underlying elements from the new list into a single atomic vector with the c() function. ii) What is the data type of this vector?
# i)
single_vector<-c(new_list[[1]],new_list[[2]],new_list[[3]]) # combine these elements into a single vector
print(single_vector)## [1] "8.78191475290805" "FALSE" "f"# ii)
typeof(single_vector)## [1] "character"# it has been coerced to character (remember data is coerced to the lowest base form in this order: logical -> integer -> double -> character)3: Create an empty data frame with two variables (= columns) and 26 observations (= rows) below:
- call the first column/variable
my_unifsand fill it with 26 random uniform values from 0 to 10 - call the second variable
my_lettersand fill it with 26 capital letters in random order.
my_unifs<-runif(n=26, min=0, max=10) # create a list of 26 random uniform numbers
print(my_unifs)## [1] 5.2370834 3.4730155 6.7812351 4.4853004 7.8295271 2.7533252 3.6025203
## [8] 2.8562958 8.5754531 9.4978003 8.1594107 4.2486706 0.7512194 9.0793182
## [15] 8.4409602 3.6029800 5.7503393 9.1163914 5.7144436 6.6285327 6.5645899
## [22] 0.6624495 8.7508541 8.9456088 7.7865269 9.1752125my_letters<-sample(letters[1:26]) # create a list of 26 letters in random order
myupper_letters<-toupper(my_letters) # capitalize these letters and assign to new name
print(myupper_letters)## [1] "Q" "G" "R" "Z" "T" "O" "U" "A" "N" "V" "E" "L" "I" "M" "W" "H" "S" "D" "C"
## [20] "B" "J" "X" "F" "P" "K" "Y"- for the first variable, use a single line of code in R to select 4 random rows and replace the numerical values in those rows with NA.
q3df<-data.frame(my_unifs, myupper_letters, stringsAsFactors = FALSE) # create a data frame of these two vectors
print(q3df)## my_unifs myupper_letters
## 1 5.2370834 Q
## 2 3.4730155 G
## 3 6.7812351 R
## 4 4.4853004 Z
## 5 7.8295271 T
## 6 2.7533252 O
## 7 3.6025203 U
## 8 2.8562958 A
## 9 8.5754531 N
## 10 9.4978003 V
## 11 8.1594107 E
## 12 4.2486706 L
## 13 0.7512194 I
## 14 9.0793182 M
## 15 8.4409602 W
## 16 3.6029800 H
## 17 5.7503393 S
## 18 9.1163914 D
## 19 5.7144436 C
## 20 6.6285327 B
## 21 6.5645899 J
## 22 0.6624495 X
## 23 8.7508541 F
## 24 8.9456088 P
## 25 7.7865269 K
## 26 9.1752125 Yset.seed(1) # keep these random values
q3df[sample(nrow(q3df), 4),1]<-NA # add NA values to 4 random rows
print(q3df)## my_unifs myupper_letters
## 1 NA Q
## 2 3.4730155 G
## 3 6.7812351 R
## 4 NA Z
## 5 7.8295271 T
## 6 2.7533252 O
## 7 NA U
## 8 2.8562958 A
## 9 8.5754531 N
## 10 9.4978003 V
## 11 8.1594107 E
## 12 4.2486706 L
## 13 0.7512194 I
## 14 9.0793182 M
## 15 8.4409602 W
## 16 3.6029800 H
## 17 5.7503393 S
## 18 9.1163914 D
## 19 5.7144436 C
## 20 6.6285327 B
## 21 6.5645899 J
## 22 0.6624495 X
## 23 8.7508541 F
## 24 8.9456088 P
## 25 NA K
## 26 9.1752125 Y- for the first variable, write a single line of R code to identify which rows have the missing values.
q3df[is.na(q3df$my_unifs),] # tell me which rows have NA values## my_unifs myupper_letters
## 1 NA Q
## 4 NA Z
## 7 NA U
## 25 NA K- re-order the entire data frame to arrange the second variable in alphabetical order.
abc_q3df<-q3df[order(q3df$myupper_letters), ] # now alphabetize this vector # descending=TRUE would flip the way it ordered it
print(abc_q3df)## my_unifs myupper_letters
## 8 2.8562958 A
## 20 6.6285327 B
## 19 5.7144436 C
## 18 9.1163914 D
## 11 8.1594107 E
## 23 8.7508541 F
## 2 3.4730155 G
## 16 3.6029800 H
## 13 0.7512194 I
## 21 6.5645899 J
## 25 NA K
## 12 4.2486706 L
## 14 9.0793182 M
## 9 8.5754531 N
## 6 2.7533252 O
## 24 8.9456088 P
## 1 NA Q
## 3 6.7812351 R
## 17 5.7503393 S
## 5 7.8295271 T
## 7 NA U
## 10 9.4978003 V
## 15 8.4409602 W
## 22 0.6624495 X
## 26 9.1752125 Y
## 4 NA Z- calculate the column mean for the first variable.
mean(abc_q3df$my_unifs, na.rm=TRUE) # what is the mean of the first variable? # na.rm=TRUE removes the NA's before it calculates the mean## [1] 6.243529- rename the second column ‘my_LETTERS’
colnames(abc_q3df)[colnames(abc_q3df) == "myupper_letters"] ="my_LETTERS" # rename the column
print(abc_q3df)## my_unifs my_LETTERS
## 8 2.8562958 A
## 20 6.6285327 B
## 19 5.7144436 C
## 18 9.1163914 D
## 11 8.1594107 E
## 23 8.7508541 F
## 2 3.4730155 G
## 16 3.6029800 H
## 13 0.7512194 I
## 21 6.5645899 J
## 25 NA K
## 12 4.2486706 L
## 14 9.0793182 M
## 9 8.5754531 N
## 6 2.7533252 O
## 24 8.9456088 P
## 1 NA Q
## 3 6.7812351 R
## 17 5.7503393 S
## 5 7.8295271 T
## 7 NA U
## 10 9.4978003 V
## 15 8.4409602 W
## 22 0.6624495 X
## 26 9.1752125 Y
## 4 NA Z