├── .gitattributes
├── Chapter 1 Conditionals and Control Flow.R
├── Chapter 2 Loops.R
├── Chapter 3 Functions.R
├── Chapter 4 The Apply Family.R
└── Chapter 5 Utilities.R


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto


--------------------------------------------------------------------------------
/Chapter 1 Conditionals and Control Flow.R:
--------------------------------------------------------------------------------
  1 | ###Chapter 1 Conditionals And Control Flow
  2 | 
  3 | ###Equality
  4 | # Comparison of logicals
  5 | TRUE == FALSE
  6 | 
  7 | # Comparison of numerics
  8 | -6 * 14 != 17 - 101
  9 | 
 10 | # Comparison of character strings
 11 | "useR" == "user"
 12 | 
 13 | # Compare a logical with a numeric
 14 | TRUE == 1
 15 | 
 16 | ###Greater And Less Than
 17 | # Comparison of numerics
 18 | -6*5+2 >= -10+1
 19 | 
 20 | # Comparison of character strings
 21 | "raining" <= "raining dogs"
 22 | 
 23 | # Comparison of logicals
 24 | TRUE > FALSE
 25 | 
 26 | ###Compare Vectors
 27 | # The linkedin and facebook vectors have already been created for you
 28 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
 29 | facebook <- c(17, 7, 5, 16, 8, 13, 14)
 30 | 
 31 | # Popular days
 32 | linkedin > 15
 33 | 
 34 | # Quiet days
 35 | linkedin <= 5
 36 | 
 37 | # LinkedIn more popular than Facebook
 38 | linkedin > facebook
 39 | 
 40 | ###Compare Matrices
 41 | # The social data has been created for you
 42 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
 43 | facebook <- c(17, 7, 5, 16, 8, 13, 14)
 44 | views <- matrix(c(linkedin, facebook), nrow = 2, byrow = TRUE)
 45 | 
 46 | # When does views equal 13?
 47 | views == 13
 48 | 
 49 | # When is views less than or equal to 14?
 50 | views <= 14
 51 | 
 52 | # How often does facebook equal or exceed linkedin times two?
 53 | sum(facebook >= linkedin * 2)
 54 | 
 55 | ###& And |
 56 | # The linkedin and last variable are already defined for you
 57 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
 58 | last <- tail(linkedin, 1)
 59 | 
 60 | # Is last under 5 or above 10?
 61 | last<5 | last>10
 62 | 
 63 | # Is last between 15 (exclusive) and 20 (inclusive)?
 64 | last>15 & last<=20
 65 | 
 66 | # Is last between 0 and 5 or between 10 and 15?
 67 | (last > 0 & last < 5) | (last > 10 & last < 15)
 68 | 
 69 | ###& And | (2)
 70 | # The social data (linkedin, facebook, views) has been created for you
 71 | 
 72 | # linkedin exceeds 10 but facebook below 10
 73 | linkedin>10 & facebook<10
 74 | 
 75 | # When were one or both visited at least 12 times?
 76 | linkedin>=12 | facebook>=12
 77 | 
 78 | # When is views between 11 (exclusive) and 14 (inclusive)?
 79 | views>11 & views<=14
 80 | 
 81 | ###Reverse The Result: !
 82 | x <- 5
 83 | y <- 7
 84 | !(!(x < 4) & !!!(y > 12))
 85 | 
 86 | ###Blend It All Together
 87 | # li_df is pre-loaded in Data Camp's workspace
 88 | 
 89 | # Select the second column, named day2, from li_df: second
 90 | second <- li_df$day2
 91 | 
 92 | # Build a logical vector, TRUE if value in second is extreme: extremes
 93 | extremes <- second > 25 | second < 5
 94 | 
 95 | # Count the number of TRUEs in extremes
 96 | sum(extremes)
 97 | 
 98 | # Solve it with a one-liner
 99 | sum(li_df$day2 > 25 | li_df$day2 < 5)
100 | 
101 | ###The If Statement
102 | # Variables related to your last day of recordings
103 | medium <- "LinkedIn"
104 | num_views <- 14
105 | 
106 | # Examine the if statement for medium
107 | if (medium == "LinkedIn") {
108 |   print("Showing LinkedIn information")
109 | }
110 | 
111 | # Write the if statement for num_views
112 | if (num_views>15) {
113 |   print("You're popular!")
114 | }
115 | 
116 | ###Add An Else
117 | # Variables related to your last day of recordings
118 | medium <- "LinkedIn"
119 | num_views <- 14
120 | 
121 | # Control structure for medium
122 | if (medium == "LinkedIn") {
123 |   print("Showing LinkedIn information")
124 | } else {
125 |   print("Unknown medium")
126 | }
127 | 
128 | # Control structure for num_views
129 | if (num_views > 15) {
130 |   print("You're popular!")
131 | } else {
132 |   print("Try to be more visible!")
133 | }
134 | 
135 | ###Customize Further: Else If
136 | # Variables related to your last day of recordings
137 | medium <- "LinkedIn"
138 | num_views <- 14
139 | 
140 | # Control structure for medium
141 | if (medium == "LinkedIn") {
142 |   print("Showing LinkedIn information")
143 | } else if (medium == "Facebook") {
144 |   print("Showing Facebook information")
145 | } else {
146 |   print("Unknown medium")
147 | }
148 | 
149 | # Control structure for num_views
150 | if (num_views > 15) {
151 |   print("You're popular!")
152 | } else if (num_views <= 15 & num_views > 10) {
153 |   print("Your number of views is average")
154 | } else {
155 |   print("Try to be more visible!")
156 | }
157 | 
158 | ###Else If 2.0
159 | #1.
160 | number <- 6
161 | #2.
162 | number <- 100
163 | #3.
164 | number <- 4
165 | #4.
166 | number <- 2500
167 | if (number < 10) {
168 |   if (number < 5) {
169 |     result <- "extra small"
170 |   } else {
171 |     result <- "small"
172 |   }
173 | } else if (number < 100) {
174 |   result <- "medium"
175 | } else {
176 |   result <- "large"
177 | }
178 | print(result)
179 | 
180 | ###Take Control!
181 | # Variables related to your last day of recordings
182 | li <- 15
183 | fb <- 9
184 | 
185 | # Code the control-flow construct
186 | if (li >= 15 & fb >= 15) {
187 |   sms <- 2 * (li + fb)
188 | } else if (li < 10 & fb < 10) {
189 |   sms <- 0.5 * (li + fb)
190 | } else {
191 |   sms <- li + fb
192 | }
193 | 
194 | # Print the resulting sms to the console
195 | print(sms)
196 | 


--------------------------------------------------------------------------------
/Chapter 2 Loops.R:
--------------------------------------------------------------------------------
  1 | ###Chapter 2 Loops
  2 | 
  3 | ###Write A While Loop
  4 | # Initialize the speed variable
  5 | speed <- 64
  6 | 
  7 | # Code the while loop
  8 | while (speed>30) {
  9 |   print("Slow down!")
 10 |   speed <- speed - 7
 11 | }
 12 | 
 13 | # Print out the speed variable
 14 | speed
 15 | 
 16 | ###Throw In More Conditionals
 17 | # Initialize the speed variable
 18 | speed <- 64
 19 | 
 20 | # Extend/adapt the while loop
 21 | while (speed > 30) {
 22 |   print(paste("Your speed is",speed))
 23 |   if (speed > 48) {
 24 |     print("Slow down big time!")
 25 |     speed <- speed - 11
 26 |   } else {
 27 |     print("Slow down!")
 28 |     speed <- speed - 6
 29 |   }
 30 | }
 31 | 
 32 | ###Stop The While Loop: Break
 33 | # Initialize the speed variable
 34 | speed <- 88
 35 | 
 36 | while (speed > 30) {
 37 |   print(paste("Your speed is",speed))
 38 |   
 39 |   # Break the while loop when speed exceeds 80
 40 |   if (speed > 80)
 41 |     break
 42 |   
 43 |   if (speed > 48) {
 44 |     print("Slow down big time!")
 45 |     speed <- speed - 11
 46 |   } else {
 47 |     print("Slow down!")
 48 |     speed <- speed - 6
 49 |   }
 50 | }
 51 | 
 52 | ###Build A While Loop From Scratch
 53 | # Initialize i as 1 
 54 | i <- 1
 55 | 
 56 | # Code the while loop
 57 | while (i <= 10) {
 58 |   print(i * 3)
 59 |   if ( (i * 3) %% 8 == 0) {
 60 |     break
 61 |   }
 62 |   i <- i + 1
 63 | }
 64 | 
 65 | ###Loop Over A Vector
 66 | # The linkedin vector has already been defined for you
 67 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
 68 | 
 69 | # Loop version 1
 70 | for (p in linkedin) {
 71 |   print(p)
 72 | }
 73 | 
 74 | # Loop version 2
 75 | for (i in 1:length(linkedin)) {
 76 |   print(linkedin[i])
 77 | }
 78 | 
 79 | ###Loop Over A List
 80 | # The nyc list is already specified
 81 | nyc <- list(pop = 8405837, 
 82 |             boroughs = c("Manhattan", "Bronx", "Brooklyn", "Queens", "Staten Island"), 
 83 |             capital = FALSE)
 84 | 
 85 | # Loop version 1
 86 | for (info in nyc) {
 87 |   print(info)
 88 | }
 89 | 
 90 | # Loop version 2
 91 | for (i in 1:length(nyc)) {
 92 |   print(nyc[[i]])
 93 | }
 94 | 
 95 | ###Loop Over A Matrix
 96 | # The tic-tac-toe matrix has already been defined for you
 97 | ttt <- matrix(c("O", NA, "X", NA, "O", NA, "X", "O", "X"), nrow = 3, ncol = 3)
 98 | 
 99 | # define the double for loop
100 | for (i in 1:nrow(ttt)) {
101 |   for (j in 1:ncol(ttt)) {
102 |     print(paste("On row", i, "and column", j, "the board contains", ttt[i,j]))
103 |   }
104 | }
105 | 
106 | ###Mix It Up With Control Flow
107 | # The linkedin vector has already been defined for you
108 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
109 | 
110 | # Code the for loop with conditionals
111 | for (li in linkedin) {
112 |   if (li > 10) {
113 |     print("You're popular!")
114 |   } else {
115 |     print("Be more visible!")
116 |   }
117 |   print(li)
118 | }
119 | 
120 | ###Next, You Break It
121 | # The linkedin vector has already been defined for you
122 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
123 | 
124 | # Adapt/extend the for loop
125 | for (li in linkedin) {
126 |   if (li > 10) {
127 |     print("You're popular!")
128 |   } else {
129 |     print("Be more visible!")
130 |   }
131 |   
132 |   # Add code to conditionally break iteration
133 |   if (li > 16) {
134 |     print("This is ridiculous, I'm outta here!")
135 |     break
136 |   }
137 |   
138 |   # Add code to conditionally skip iteration
139 |   if (li < 5) {
140 |     print("This is too embarrassing!")
141 |     next
142 |   }
143 |   
144 |   print(li)
145 | }
146 | 
147 | ###Build A For Loop From Scratch
148 | # Pre-defined variables
149 | rquote <- "r's internals are irrefutably intriguing"
150 | chars <- strsplit(rquote, split = "")[[1]]
151 | 
152 | # Initialize rcount
153 | rcount <- 0
154 | 
155 | # Finish the for loop
156 | for (char in chars) {
157 |   if (char == "r") {
158 |     rcount <- rcount + 1
159 |   }
160 |   if (char == "u") {
161 |     break
162 |   }
163 | }
164 | 
165 | # Print out rcount
166 | rcount
167 | 
168 | 


--------------------------------------------------------------------------------
/Chapter 3 Functions.R:
--------------------------------------------------------------------------------
  1 | ###Chapter 3 Functions
  2 | 
  3 | ###Function Documentation
  4 | # Consult the documentation on the mean() function
  5 | help(mean)
  6 | 
  7 | # Inspect the arguments of the mean() function
  8 | args(mean)
  9 | 
 10 | ###Use A Function
 11 | # The linkedin and facebook vectors have already been created for you
 12 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
 13 | facebook <- c(17, 7, 5, 16, 8, 13, 14)
 14 | 
 15 | # Calculate average number of views
 16 | avg_li = mean(linkedin)
 17 | avg_fb = mean(facebook)
 18 | 
 19 | # Inspect avg_li and avg_fb
 20 | avg_li
 21 | avg_fb
 22 | 
 23 | # Calculate the mean of linkedin minus facebook
 24 | mean(linkedin - facebook)
 25 | 
 26 | ###Use A Function (2)
 27 | # The linkedin and facebook vectors have already been created for you
 28 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
 29 | facebook <- c(17, 7, 5, 16, 8, 13, 14)
 30 | 
 31 | # Calculate the mean of the sum
 32 | avg_sum = mean(linkedin + facebook)
 33 | 
 34 | # Calculate the trimmed mean of the sum
 35 | avg_sum_trimmed = mean(linkedin + facebook, trim = 0.2)
 36 | 
 37 | # Inspect both new variables
 38 | avg_sum
 39 | avg_sum_trimmed
 40 | 
 41 | ###Use A Function (3)
 42 | # The linkedin and facebook vectors have already been created for you
 43 | linkedin <- c(16, 9, 13, 5, NA, 17, 14)
 44 | facebook <- c(17, NA, 5, 16, 8, 13, 14)
 45 | 
 46 | # Basic average of linkedin
 47 | mean(linkedin)
 48 | 
 49 | # Advanced average of linkedin
 50 | mean(linkedin, na.rm = TRUE)
 51 | 
 52 | ###Functions Inside Functions
 53 | # The linkedin and facebook vectors have already been created for you
 54 | linkedin <- c(16, 9, 13, 5, NA, 17, 14)
 55 | facebook <- c(17, NA, 5, 16, 8, 13, 14)
 56 | 
 57 | # Calculate the mean absolute deviation
 58 | mean(abs(linkedin - facebook), na.rm = TRUE)
 59 | 
 60 | ###Write Your Own Function
 61 | # Create a function pow_two()
 62 | pow_two <- function(x) {
 63 |   x ^ 2
 64 | }
 65 | 
 66 | # Use the function 
 67 | pow_two(12)
 68 | 
 69 | # Create a function sum_abs()
 70 | sum_abs <- function(x, y) {
 71 |   abs(x) + abs(y)
 72 | }
 73 | 
 74 | # Use the function
 75 | sum_abs(-2, 3)
 76 | 
 77 | ###Write Your Own Function (2)
 78 | # Define the function hello()
 79 | hello <- function() {
 80 |   print("Hi there!")
 81 |   TRUE
 82 | }
 83 | 
 84 | # Call the function hello()
 85 | hello()
 86 | 
 87 | # Define the function my_filter()
 88 | my_filter <- function(x) {
 89 |   if (x > 0) {
 90 |     return(x)
 91 |   } else {
 92 |     return(NULL)
 93 |   }
 94 | }
 95 | 
 96 | # Call the function my_filter() twice
 97 | my_filter(5)
 98 | my_filter(-5)
 99 | 
100 | ###Write Your Own Function (3)
101 | # Extend the pow_two() function
102 | pow_two <- function(x, print_info = TRUE) {
103 |   y <- x ^ 2
104 |   if (print_info) {
105 |     print(paste(x, "to the power two equals", y))
106 |   }
107 |   return(y)
108 | }
109 | 
110 | ###Function Scoping
111 | two_dice <- function() {
112 |   possibilities <- 1:6
113 |   dice1 <- sample(possibilities, size = 1)
114 |   dice2 <- sample(possibilities, size = 1)
115 |   dice1 + dice2
116 | }
117 | 
118 | ###R Passes Arguments By Value
119 | increment <- function(x, inc = 1) {
120 |   x <- x + inc
121 |   x
122 | }
123 | count <- 5
124 | a <- increment(count, 2)
125 | b <- increment(count)
126 | count <- increment(count, 2)
127 | 
128 | ###R You Functional?
129 | # The linkedin and facebook vectors have already been created for you
130 | 
131 | # Define the interpret function
132 | interpret <- function(num_views) {
133 |   if (num_views > 15) {
134 |     print("You're popular!")
135 |     return(num_views)
136 |   } else {
137 |     print("Try to be more visible!")
138 |     return(0)
139 |   }
140 | }
141 | 
142 | # Call the interpret function twice
143 | interpret(linkedin[1])
144 | interpret(facebook[2])
145 | 
146 | ###R You Functional? (2)
147 | # The linkedin and facebook vectors have already been created for you
148 | linkedin <- c(16, 9, 13, 5, 2, 17, 14)
149 | facebook <- c(17, 7, 5, 16, 8, 13, 14)
150 | 
151 | # The interpret() can be used inside interpret_all()
152 | interpret <- function(num_views) {
153 |   if (num_views > 15) {
154 |     print("You're popular!")
155 |     return(num_views)
156 |   } else {
157 |     print("Try to be more visible!")
158 |     return(0)
159 |   }
160 | }
161 | 
162 | # Define the interpret_all() function
163 | interpret_all <- function(views, return_sum = TRUE) {
164 |   count <- 0
165 |   for (v in views) {
166 |     count <- count + interpret(v)
167 |   }
168 |   if (return_sum) {
169 |     return(count)
170 |   } else {
171 |     return(NULL)
172 |   }
173 | }
174 | 
175 | # Call the interpret_all() function on both linkedin and facebook
176 | interpret_all(linkedin)
177 | interpret_all(facebook)
178 | 
179 | ###Load An R Package
180 | # The mtcars vectors have already been prepared for you
181 | wt <- mtcars$wt
182 | hp <- mtcars$hp
183 | 
184 | # Request the currently attached packages
185 | search()
186 | 
187 | # Try the qplot() function with wt and hp
188 | qplot(wt, hp)
189 | 
190 | # Load the ggplot2 package
191 | library("ggplot2")
192 | 
193 | # Retry the qplot() function
194 | qplot(wt, hp)
195 | 
196 | # Check out the currently attached packages again
197 | search()
198 | 
199 | 


--------------------------------------------------------------------------------
/Chapter 4 The Apply Family.R:
--------------------------------------------------------------------------------
  1 | ###Chapter 4 The Apply Family
  2 | 
  3 | ###Use lapply With A Built-In R Function
  4 | # The vector pioneers has already been created for you
  5 | pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
  6 | 
  7 | # Split names from birth year: split_math
  8 | split_math <- strsplit(pioneers, split = ":")
  9 | 
 10 | # Convert to lowercase strings: split_low
 11 | split_low <- lapply(split_math, tolower)
 12 | 
 13 | # Take a look at the structure of split_low
 14 | str(split_low)
 15 | 
 16 | ###Use lapply With Your Own Function
 17 | # Code from previous exercise:
 18 | pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
 19 | split <- strsplit(pioneers, split = ":")
 20 | split_low <- lapply(split, tolower)
 21 | 
 22 | # Write function select_first()
 23 | select_first <- function(x) {
 24 |   x[1]
 25 | }
 26 | 
 27 | # Apply select_first() over split_low: names
 28 | names <- lapply(split_low, select_first)
 29 | 
 30 | # Write function select_second()
 31 | select_second <- function(x) {
 32 |   x[2]
 33 | }
 34 | 
 35 | ###lapply And Anonymous Functions
 36 | # Definition of split_low
 37 | pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
 38 | split <- strsplit(pioneers, split = ":")
 39 | split_low <- lapply(split, tolower)
 40 | 
 41 | names <- lapply(split_low, function(x) { x[1] })
 42 | 
 43 | years <- lapply(split_low, function(x) { x[2] })
 44 | 
 45 | ###Use lapply With Additional Arguments
 46 | # Definition of split_low
 47 | pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
 48 | split <- strsplit(pioneers, split = ":")
 49 | split_low <- lapply(split, tolower)
 50 | 
 51 | # Replace the select_*() functions by a single function: select_el
 52 | select_el <- function(x, index) {
 53 |   x[index]
 54 | }
 55 | 
 56 | # Call the select_el() function twice on split_low: names and years
 57 | names <- lapply(split_low, select_el, index = 1)
 58 | years <- lapply(split_low, select_el, index = 2)
 59 | 
 60 | ###Apply Functions That Return NULL
 61 | lapply(split_low, function(x) {
 62 |   if (nchar(x[1]) > 5) {
 63 |     return(NULL)
 64 |   } else {
 65 |     return(x[2])
 66 |   }
 67 | })
 68 | 
 69 | ###How To Use sapply
 70 | # temp has already been defined in Data Camp's workspace
 71 | 
 72 | # Use lapply() to find each day's minimum temperature
 73 | lapply(temp, min)
 74 | 
 75 | # Use sapply() to find each day's minimum temperature
 76 | sapply(temp, min)
 77 | 
 78 | # Use lapply() to find each day's maximum temperature
 79 | lapply(temp, max)
 80 | 
 81 | # Use sapply() to find each day's maximum temperature
 82 | sapply(temp, max)
 83 | 
 84 | ###sapply With Your Own Function
 85 | # temp is already defined in the workspace
 86 | 
 87 | # Define a function calculates the average of the min and max of a vector: extremes_avg
 88 | extremes_avg <- function(x) {
 89 |   (min(x) + max(x))/2
 90 | }
 91 | 
 92 | # Apply extremes_avg() over temp using sapply()
 93 | sapply(temp, extremes_avg)
 94 | 
 95 | # Apply extremes_avg() over temp using lapply()
 96 | lapply(temp, extremes_avg)
 97 | 
 98 | ###sapply With Function Returning Vector
 99 | # temp is already available in the workspace
100 | 
101 | # Create a function that returns min and max of a vector: extremes
102 | extremes <- function(x) {
103 |   c(min = min(x), max = max(x))
104 | }
105 | 
106 | # Apply extremes() over temp with sapply()
107 | sapply(temp, extremes)
108 | 
109 | # Apply extremes() over temp with lapply()
110 | lapply(temp, extremes)
111 | 
112 | ###sapply Can't Simplify, Now What?
113 | # temp is already prepared for you in the workspace
114 | 
115 | # Create a function that returns all values below zero: below_zero
116 | below_zero <- function(x) {
117 |   return(x[x < 0])
118 | }
119 | 
120 | # Apply below_zero over temp using sapply(): freezing_s
121 | freezing_s <- sapply(temp, below_zero)
122 | 
123 | # Apply below_zero over temp using lapply(): freezing_l
124 | freezing_l <- lapply(temp, below_zero)
125 | 
126 | # Compare freezing_s to freezing_l using identical()
127 | identical(freezing_s, freezing_l)
128 | 
129 | ###sapply With Functions That Return NULL
130 | # temp is already available in the workspace
131 | 
132 | # Write a function that 'cat()s' out the average temperatures: print_info
133 | print_info <- function(x) {
134 |   cat("The average temperature is", mean(x), "\n")
135 | }
136 | 
137 | # Apply print_info() over temp using lapply()
138 | sapply(temp, print_info)
139 | 
140 | # Apply print_info() over temp using sapply()
141 | lapply(temp, print_info)
142 | 
143 | ###Reverse Engineering sapply
144 | sapply(list(runif (10), runif (10)), 
145 |        function(x) c(min = min(x), mean = mean(x), max = max(x)))
146 | 
147 | ###Use vapply
148 | # temp is already available in the workspace
149 | 
150 | # Code the basics() function
151 | basics <- function(x) {
152 |   c(min = min(x), mean = mean(x), max = max(x))
153 | }
154 | 
155 | # Apply basics() over temp using vapply()
156 | vapply(temp, basics, numeric(3))
157 | 
158 | ###Use vapply (2)
159 | # temp is already available in the workspace
160 | 
161 | # Definition of the basics() function
162 | basics <- function(x) {
163 |   c(min = min(x), mean = mean(x), median = median(x), max = max(x))
164 | }
165 | 
166 | # Fix the error:
167 | vapply(temp, basics, numeric(4))
168 | 
169 | ###From sapply To vapply
170 | # temp is already defined in the workspace
171 | 
172 | # Convert to vapply() expression
173 | vapply(temp, max, numeric(1))
174 | 
175 | # Convert to vapply() expression
176 | vapply(temp, function(x, y) { mean(x) > y }, logical(1), y = 5)
177 | 
178 | # Definition of get_info (don't change)
179 | get_info <- function(x, y) { 
180 |   if (mean(x) > y) {
181 |     return("Not too cold!")
182 |   } else {
183 |     return("Pretty cold!")
184 |   }
185 | }
186 | 
187 | # Convert to vapply() expression
188 | vapply(temp, get_info, character(1), y = 5)
189 | 
190 | 


--------------------------------------------------------------------------------
/Chapter 5 Utilities.R:
--------------------------------------------------------------------------------
  1 | ###Chapter 5 Utilities
  2 | 
  3 | ###Mathematical Utilities
  4 | # The errors vector has already been defined for you
  5 | errors <- c(1.9,-2.6,4.0,-9.5,-3.4,7.3)
  6 | 
  7 | # Sum of absolute rounded values of errors
  8 | sum(round(abs(errors)))
  9 | 
 10 | ###Find The Error
 11 | # Don't edit these two lines
 12 | vec1 <- c(1.5,2.5,8.4,3.7,6.3)
 13 | vec2 <- rev(vec1)
 14 | 
 15 | # Fix the error
 16 | mean(c(abs(vec1), abs(vec2)))
 17 | 
 18 | ###Data Utilities
 19 | # The linkedin and facebook vectors have already been created for you
 20 | linkedin <- list(16, 9, 13, 5, 2, 17, 14)
 21 | facebook <- list(17, 7, 5, 16, 8, 13, 14)
 22 | 
 23 | # Convert linkedin and facebook to a vector: li_vec and fb_vec
 24 | li_vec <- unlist(linkedin)
 25 | fb_vec <- unlist(facebook)
 26 | 
 27 | # Append fb_vec to li_vec: social_vec
 28 | social_vec <- append(li_vec, fb_vec)
 29 | 
 30 | # Sort social_vec
 31 | sort(social_vec, decreasing = TRUE)
 32 | 
 33 | ###Find The Error (2)
 34 | # Fix me
 35 | round(sum(unlist(list(1.1,3,5))))
 36 | 
 37 | # Fix me
 38 | rep(seq(1, 7, by = 2), times = 7)
 39 | 
 40 | ###Beat Gauss Using R
 41 | # Create first sequence: seq1
 42 | seq1 <- seq(1, 500, by = 3)
 43 | 
 44 | # Create second sequence: seq2
 45 | seq2 <- seq(1200, 900, by = -7)
 46 | 
 47 | # Calculate total sum of the sequences
 48 | sum(seq1) + sum(seq2)
 49 | 
 50 | ###grepl & grep
 51 | # The emails vector has already been defined for you
 52 | emails <- c("john.doe@ivyleague.edu", "education@world.gov", "dalai.lama@peace.org", 
 53 |             "invalid.edu", "quant@bigdatacollege.edu", "cookie.monster@sesame.tv")
 54 | 
 55 | # Use grepl() to match for "edu"
 56 | grepl("edu", emails)
 57 | 
 58 | # Use grep() to match for "edu", save result to hits
 59 | hits <- grep("edu", emails)
 60 | 
 61 | # Subset emails using hits
 62 | emails[hits]
 63 | 
 64 | ###grepl & grep (2)
 65 | # The emails vector has already been defined for you
 66 | emails <- c("john.doe@ivyleague.edu", "education@world.gov", "dalai.lama@peace.org", 
 67 |             "invalid.edu", "quant@bigdatacollege.edu", "cookie.monster@sesame.tv")
 68 | 
 69 | # Use grepl() to match for .edu addresses more robustly
 70 | grepl("@.*\\.edu$", emails)
 71 | 
 72 | # Use grep() to match for .edu addresses more robustly, save result to hits
 73 | hits <- grep("@.*\\.edu$", emails)
 74 | 
 75 | # Subset emails using hits
 76 | emails[hits]
 77 | 
 78 | ###sub & gsub
 79 | # The emails vector has already been defined for you
 80 | emails <- c("john.doe@ivyleague.edu", "education@world.gov", "global@peace.org",
 81 |             "invalid.edu", "quant@bigdatacollege.edu", "cookie.monster@sesame.tv")
 82 | 
 83 | # Use sub() to convert the email domains to datacamp.edu
 84 | sub("@.*\\.edu$", "@datacamp.edu", emails)
 85 | 
 86 | ###sub & gsub (2)
 87 | awards <- c("Won 1 Oscar.",
 88 |             "Won 1 Oscar. Another 9 wins & 24 nominations.",
 89 |             "1 win and 2 nominations.",
 90 |             "2 wins & 3 nominations.",
 91 |             "Nominated for 2 Golden Globes. 1 more win & 2 nominations.",
 92 |             "4 wins & 1 nomination.")
 93 | 
 94 | sub(".*\\s([0-9]+)\\snomination.*$", "\\1", awards)
 95 | 
 96 | ###Right Here, Right Now
 97 | # Get the current date: today
 98 | today <- Sys.Date()
 99 | 
100 | # See what today looks like under the hood
101 | unclass(today)
102 | 
103 | # Get the current time: now
104 | now <- Sys.time()
105 | 
106 | # See what now looks like under the hood
107 | unclass(now)
108 | 
109 | ###Create And Format Dates
110 | # Definition of character strings representing dates
111 | str1 <- "May 23, '96"
112 | str2 <- "2012-03-15"
113 | str3 <- "30/January/2006"
114 | 
115 | # Convert the strings to dates: date1, date2, date3
116 | date1 <- as.Date(str1, format = "%b %d, '%y")
117 | date2 <- as.Date(str2)
118 | date3 <- as.Date(str3, format = "%d/%B/%Y")
119 | 
120 | # Convert dates to formatted strings
121 | format(date1, "%A")
122 | format(date2, "%d")
123 | format(date3, "%b %Y")
124 | 
125 | ###Create And Format Times
126 | # Definition of character strings representing times
127 | str1 <- "May 23, '96 hours:23 minutes:01 seconds:45"
128 | str2 <- "2012-3-12 14:23:08"
129 | 
130 | # Convert the strings to POSIXct objects: time1, time2
131 | time1 <- as.POSIXct(str1, format = "%B %d, '%y hours:%H minutes:%M seconds:%S")
132 | time2 <- as.POSIXct(str2)
133 | 
134 | # Convert times to formatted strings
135 | format(time1, "%M")
136 | format(time2, "%I:%M %p")
137 | 
138 | ###Calculations With Dates
139 | # day1, day2, day3, day4 and day5 are available in Data Camp's workspace
140 | 
141 | # Difference between last and first pizza day
142 | day5 - day1
143 | 
144 | # Create vector pizza
145 | pizza <- c(day1, day2, day3, day4, day5)
146 | 
147 | # Create differences between consecutive pizza days: day_diff
148 | day_diff <- diff(pizza)
149 | 
150 | # Average period between two consecutive pizza days
151 | mean(day_diff)
152 | 
153 | ###Calculations With Times
154 | # login and logout are already defined in the workspace
155 | # Calculate the difference between login and logout: time_online
156 | time_online <- logout - login
157 | 
158 | # Inspect the variable time_online
159 | time_online
160 | 
161 | # Calculate the total time online
162 | sum(time_online)
163 | 
164 | # Calculate the average time online
165 | mean(time_online)
166 | 
167 | ###Time Is Of The Essence
168 | # Convert astro to vector of Date objects: astro_dates
169 | # Source: www.timeanddate.com 
170 | astro_dates <- as.Date(astro, format = "%d-%b-%Y")
171 | 
172 | # Convert meteo to vector of Date objects: meteo_dates
173 | meteo_dates <- as.Date(meteo, format = "%B %d, %y")
174 | 
175 | # Calculate the maximum absolute difference between astro_dates and meteo_dates
176 | max(abs(meteo_dates - astro_dates))
177 | 
178 | 


--------------------------------------------------------------------------------