Chapter 3

This code is from chapter 3 of your textbook.

https://www.wiley.com/en-us/Data+Science+and+Big+Data+Analytics%3A+Discovering%2C+Analyzing%2C+Visualizing+and+Presenting+Data-p-9781118876138

##########################################
# section 3.1 Introduction to R
##########################################
# examine the imported dataset
head(yearly_sales)

summary(yearly_sales)

    cust_id        sales_total      num_of_orders       gender         
 Min.   :100001   Min.   :  30.02   Min.   : 1.000   Length:10000      
 1st Qu.:102501   1st Qu.:  80.29   1st Qu.: 2.000   Class :character  
 Median :105001   Median : 151.65   Median : 2.000   Mode  :character  
 Mean   :105001   Mean   : 249.46   Mean   : 2.428                     
 3rd Qu.:107500   3rd Qu.: 295.50   3rd Qu.: 3.000                     
 Max.   :110000   Max.   :7606.09   Max.   :22.000                     

# plot num_of_orders vs. sales
plot(yearly_sales$num_of_orders,yearly_sales$sales_total,
     main="Number of Orders vs. Sales")

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

##########################################
# section 3.1.2 Data Import and Export
##########################################
# add a column for the average sales per order
sales$per_order <- sales$sales_total/sales$num_of_orders
# export data as tab delimited without the row names
write.table(sales,"sales_modified.txt", sep="\t", row.names=FALSE)

##########################################
# section 3.1.3 Attribute and Data Types
##########################################
# Numeric, Character, and Logical Data Types
i <- 1                      # create a numeric variable
sport <- "football"         # create a character variable
flag <- TRUE                # create a logical variable
class(i)                    # returns "numeric"

[1] "numeric"

typeof(i)                   # returns "double"

[1] "double"

class(sport)                # returns "character"

[1] "character"

typeof(sport)               # returns "character"

[1] "character"

class(flag)                 # returns "logical"

[1] "logical"

typeof(flag)                # returns "logical"

[1] "logical"

is.integer(i)               # returns FALSE

[1] FALSE

j <- as.integer(i)          # coerces contents of i into an integer
is.integer(j)               # returns TRUE

[1] TRUE

length(i)                   # returns 1

[1] 1

length(flag)                # returns 1

[1] 1

length(sport)               # returns 1 (not 8 for "football")

[1] 1

# Vectors
is.vector(i)                # returns TRUE

[1] TRUE

is.vector(flag)             # returns TRUE

[1] TRUE

is.vector(sport)            # returns TRUE

[1] TRUE

u <- c("red", "yellow", "blue") # create a vector "red" "yellow" "blue"
u                               # returns "red" "yellow" "blue"

[1] "red"    "yellow" "blue"  

u[1]                            # returns "red" (1st element in u)

[1] "red"

v <- 1:5                        # create a vector 1 2 3 4 5
v                               # returns 1 2 3 4 5

[1] 1 2 3 4 5

sum(v)                          # returns 15

[1] 15

w <- v * 2                      # create a vector 2 4 6 8 10
w                               # returns 2 4 6 8 10

[1]  2  4  6  8 10

w[3]                            # returns 6 (the 3rd element of w)

[1] 6

z <- v + w                      # sums two vectors element by element
z                               # returns 3 6 9 12 15

[1]  3  6  9 12 15

z > 8                           # returns FALSE FALSE TRUE TRUE TRUE

[1] FALSE FALSE  TRUE  TRUE  TRUE

z[z > 8]                        # returns 9 12 15

[1]  9 12 15

z[z > 8 | z < 5]                # returns 3 9 12 15 ("|" denotes "or")

[1]  3  9 12 15

a <- vector(length=3)           # create a logical vector of length 3
a                               # returns FALSE FALSE FALSE

[1] FALSE FALSE FALSE

b <- vector(mode="numeric", 3)  # create a numeric vector of length 3
typeof(b)                       # returns "double"

[1] "double"

b[2] <- 3.1                     # assign 3.1 to the 2nd element
b                               # returns 0.0 3.1 0.0

[1] 0.0 3.1 0.0

c <- vector(mode="integer", 0)  # create an integer vector of length 0
c                               # returns integer(0)

integer(0)

length(c)                       # returns 0

[1] 0

length(b)                       # returns 3

[1] 3

length(sales$num_of_orders)       # returns 10000 (number of customers)

[1] 10000

is.vector(sales$cust_id)          # returns TRUE

[1] TRUE

is.vector(sales$sales_total)      # returns TRUE

[1] TRUE

is.vector(sales$num_of_orders)    # returns TRUE

[1] TRUE

is.vector(sales$gender)           # returns FALSE

[1] TRUE

is.factor(sales$gender)           # returns TRUE

[1] FALSE

str(sales) # display structure of the data frame object

Classes ‘tbl_df’, ‘tbl’ and 'data.frame':   10000 obs. of  5 variables:
 $ cust_id      : int  100001 100002 100003 100004 100005 100006 100007 100008 100009 100010 ...
 $ sales_total  : num  800.6 217.5 74.6 498.6 723.1 ...
 $ num_of_orders: int  3 3 2 3 4 2 2 2 2 2 ...
 $ gender       : chr  "F" "F" "M" "M" ...
 $ per_order    : num  266.9 72.5 37.3 166.2 180.8 ...
 - attr(*, "spec")=List of 2
  ..$ cols   :List of 4
  .. ..$ cust_id      : list()
  .. .. ..- attr(*, "class")= chr  "collector_integer" "collector"
  .. ..$ sales_total  : list()
  .. .. ..- attr(*, "class")= chr  "collector_double" "collector"
  .. ..$ num_of_orders: list()
  .. .. ..- attr(*, "class")= chr  "collector_integer" "collector"
  .. ..$ gender       : list()
  .. .. ..- attr(*, "class")= chr  "collector_character" "collector"
  ..$ default: list()
  .. ..- attr(*, "class")= chr  "collector_guess" "collector"
  ..- attr(*, "class")= chr "col_spec"

# Note: We used Tidyverse to do data manipulation
# However, using the $ notation to access columns is useful
# extract the fourth column of the sales data frame
sales[,4]

# extract the gender column of the sales data frame
sales$gender

   [1] "F" "F" "M" "M" "F" "F" "M" "M" "F" "M" "F" "F" "M" "M" "M" "M" "M" "M" "M" "F" "M" "M" "F" "F" "F" "F"
  [27] "F" "M" "M" "F" "F" "F" "M" "M" "M" "M" "M" "F" "F" "M" "F" "M" "M" "M" "M" "F" "F" "M" "F" "M" "M" "F"
  [53] "F" "F" "M" "M" "M" "M" "M" "F" "M" "M" "M" "M" "M" "M" "M" "F" "F" "M" "F" "F" "M" "F" "M" "M" "F" "F"
  [79] "F" "F" "F" "F" "M" "F" "F" "M" "M" "F" "M" "M" "M" "F" "F" "F" "M" "F" "F" "M" "F" "F" "M" "F" "M" "M"
 [105] "M" "F" "F" "M" "M" "F" "M" "F" "M" "M" "M" "F" "F" "M" "F" "M" "M" "F" "M" "F" "F" "M" "M" "M" "F" "M"
 [131] "M" "F" "M" "F" "M" "M" "M" "F" "M" "M" "F" "M" "M" "F" "F" "M" "F" "M" "M" "F" "F" "F" "M" "M" "M" "M"
 [157] "F" "M" "M" "M" "M" "M" "F" "F" "F" "M" "M" "M" "M" "M" "F" "F" "F" "F" "F" "F" "M" "M" "F" "F" "M" "M"
 [183] "F" "M" "M" "M" "M" "F" "F" "F" "F" "F" "M" "F" "M" "F" "M" "M" "F" "F" "F" "F" "M" "M" "F" "M" "M" "M"
 [209] "M" "F" "F" "M" "F" "F" "M" "F" "F" "M" "M" "M" "M" "F" "M" "F" "M" "M" "M" "M" "M" "M" "M" "M" "F" "M"
 [235] "F" "M" "F" "M" "M" "F" "M" "F" "M" "M" "M" "M" "M" "F" "F" "F" "F" "M" "F" "M" "M" "F" "M" "F" "F" "F"
 [261] "F" "M" "M" "F" "F" "M" "M" "M" "F" "M" "M" "F" "M" "F" "F" "F" "F" "M" "M" "M" "M" "M" "M" "F" "M" "F"
 [287] "M" "F" "F" "F" "F" "F" "F" "F" "F" "F" "F" "F" "M" "M" "M" "M" "M" "M" "M" "M" "F" "F" "M" "M" "F" "M"
 [313] "F" "F" "M" "F" "M" "M" "M" "M" "F" "F" "M" "M" "M" "F" "M" "M" "M" "F" "M" "F" "M" "M" "F" "F" "F" "M"
 [339] "F" "F" "F" "M" "F" "F" "F" "M" "F" "F" "M" "F" "F" "M" "M" "M" "F" "F" "F" "F" "M" "F" "M" "F" "M" "F"
 [365] "M" "F" "M" "M" "F" "M" "M" "F" "M" "F" "M" "F" "M" "F" "F" "M" "M" "M" "F" "F" "M" "F" "M" "M" "F" "F"
 [391] "M" "F" "F" "F" "F" "F" "M" "F" "M" "M" "F" "F" "F" "M" "F" "M" "F" "F" "M" "M" "F" "F" "F" "M" "F" "M"
 [417] "F" "M" "M" "M" "M" "M" "M" "F" "M" "F" "F" "M" "M" "M" "M" "F" "M" "F" "F" "M" "F" "M" "F" "F" "F" "F"
 [443] "M" "F" "F" "F" "M" "M" "M" "M" "F" "M" "F" "F" "F" "F" "F" "M" "F" "M" "M" "F" "F" "F" "F" "M" "M" "M"
 [469] "M" "F" "F" "M" "M" "M" "F" "F" "M" "M" "M" "F" "M" "F" "F" "M" "M" "M" "M" "F" "F" "M" "M" "F" "M" "M"
 [495] "M" "M" "M" "F" "F" "M" "F" "F" "F" "F" "F" "M" "M" "F" "F" "F" "F" "F" "M" "F" "M" "F" "M" "M" "M" "M"
 [521] "F" "M" "M" "M" "M" "F" "M" "M" "M" "M" "M" "M" "F" "F" "M" "F" "M" "M" "F" "F" "M" "F" "F" "F" "F" "F"
 [547] "M" "F" "M" "F" "M" "F" "F" "F" "F" "F" "M" "F" "F" "M" "M" "M" "M" "F" "M" "F" "M" "M" "F" "M" "F" "F"
 [573] "M" "F" "F" "F" "M" "F" "F" "F" "M" "M" "F" "F" "M" "M" "F" "M" "M" "F" "M" "F" "M" "F" "M" "F" "F" "F"
 [599] "M" "F" "F" "M" "F" "M" "M" "M" "M" "F" "F" "M" "F" "F" "M" "M" "M" "M" "M" "M" "F" "M" "M" "M" "M" "M"
 [625] "M" "F" "F" "M" "F" "F" "M" "M" "F" "M" "F" "M" "M" "M" "M" "M" "F" "M" "F" "F" "F" "F" "F" "F" "M" "M"
 [651] "M" "F" "F" "F" "F" "F" "F" "M" "M" "F" "M" "M" "F" "F" "F" "M" "M" "F" "M" "M" "F" "M" "M" "M" "F" "F"
 [677] "F" "F" "F" "M" "M" "M" "M" "F" "F" "M" "M" "M" "M" "F" "M" "M" "F" "M" "F" "M" "M" "F" "M" "M" "M" "F"
 [703] "F" "M" "M" "F" "M" "F" "M" "F" "M" "M" "F" "F" "M" "M" "M" "F" "M" "M" "M" "F" "M" "M" "M" "M" "M" "M"
 [729] "M" "F" "F" "M" "F" "M" "M" "F" "F" "F" "M" "M" "M" "M" "M" "F" "M" "F" "F" "F" "F" "F" "M" "M" "M" "M"
 [755] "F" "F" "M" "F" "F" "F" "F" "M" "F" "F" "M" "M" "F" "F" "M" "F" "M" "F" "M" "M" "M" "F" "M" "M" "M" "F"
 [781] "M" "F" "F" "F" "F" "M" "M" "M" "M" "M" "M" "M" "F" "F" "F" "F" "F" "M" "M" "F" "M" "F" "F" "M" "M" "M"
 [807] "M" "F" "M" "F" "M" "F" "F" "F" "M" "M" "F" "F" "M" "F" "F" "F" "M" "M" "M" "M" "F" "F" "M" "F" "M" "F"
 [833] "F" "F" "F" "M" "M" "M" "M" "M" "F" "F" "F" "F" "M" "M" "M" "F" "M" "F" "F" "F" "M" "F" "M" "M" "F" "M"
 [859] "F" "F" "M" "F" "M" "M" "F" "M" "F" "M" "F" "M" "M" "F" "M" "F" "F" "M" "F" "F" "F" "F" "M" "M" "F" "M"
 [885] "F" "F" "M" "F" "M" "M" "F" "F" "M" "F" "F" "F" "M" "M" "F" "F" "M" "M" "F" "M" "M" "F" "F" "M" "M" "F"
 [911] "F" "M" "F" "F" "M" "F" "M" "M" "F" "M" "F" "M" "F" "F" "M" "F" "F" "M" "M" "M" "M" "M" "F" "F" "F" "M"
 [937] "F" "F" "M" "F" "M" "F" "M" "F" "M" "F" "M" "M" "F" "M" "M" "F" "F" "M" "F" "F" "F" "F" "M" "F" "M" "M"
 [963] "M" "F" "F" "M" "F" "F" "F" "M" "F" "F" "M" "M" "F" "F" "F" "F" "M" "F" "F" "F" "M" "M" "F" "M" "M" "M"
 [989] "F" "M" "F" "M" "M" "M" "F" "M" "M" "M" "F" "M"
 [ reached getOption("max.print") -- omitted 9000 entries ]

# retrieve the first two rows of the data frame
sales[1:2,]

# retrieve the first, third, and fourth columns
sales[,c(1,3,4)]

# retrieve both the cust_id and the sales_total columns
sales[,c("cust_id", "sales_total")]

# retrieve all the records whose gender is female
sales[sales$gender=="F",]

class(sales)

[1] "tbl_df"     "tbl"        "data.frame"

typeof(sales)

[1] "list"

# Factors
class(sales$gender)       # returns "factor"

[1] "character"

is.ordered(sales$gender)  # returns FALSE

[1] FALSE

head(sales$gender)        # display first six values and the levels

[1] "F" "F" "M" "M" "F" "F"

# build an empty character vector of the same length as sales
sales_group <- vector(mode="character",
                      length=length(sales$sales_total))
# group the customers according to the sales amount
sales_group[sales$sales_total<100] <- "small"
sales_group[sales$sales_total>=100 & sales$sales_total<500] <- "medium"
sales_group[sales$sales_total>=500] <- "big"
# create and add the ordered factor to the sales data frame
spender <- factor(sales_group,levels=c("small", "medium", "big"),
                  ordered = TRUE)
sales <- cbind(sales,spender)
str(sales$spender)

 Ord.factor w/ 3 levels "small"<"medium"<..: 3 2 1 2 3 1 1 1 2 1 ...

head(sales$spender)

[1] big    medium small  medium big    small 
Levels: small < medium < big

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.