Work on the following parts:

a.

me <- c("Ryan", "Safner")

b.

me

## [1] "Ryan"   "Safner"

c.

class(me)

## [1] "character"

Use R’s help functions to determine what the paste() function does. Then paste together your first name and last name.

?paste() # or help(paste)
 # paste is a function that combines (concatenates) multiple string objects into a single object
paste("Ryan", "Safner")

## [1] "Ryan Safner"

# note you can choose how to separate string objects with the "sep" argument
# for example
paste("Ryan", "Safner", sep="") # no separation

## [1] "RyanSafner"

paste("Ryan", "Safner", sep=" ") # separate with a space " " (the default)

## [1] "Ryan Safner"

paste("Ryan", "Safner", sep="_") # separate with underscore

## [1] "Ryan_Safner"

Create a vector called my_vector with all the even integers from 2 to 10.

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

# verify it worked
my_vector

## [1]  2  4  6  8 10

# alternatively, you can use the sequence function, seq()
# see the Class page for more about this function
my_vector <- seq(from = 2, # starting integer
                 to = 10, # ending integer
                 by = 2) # by 2's

# you can shorten it by not including the names of the arguments:
my_vector <- seq(2,10,2)

# verify it worked
my_vector

## [1]  2  4  6  8 10

Find the mean of my_vector with mean().

mean(my_vector)

## [1] 6

Take all the integers from 18 to 763,¹ then get the mean.

# create a sequence of integers by 1 with starting_number:ending_number
# see Class 3 page for more

# you can do this all at once without making an object
mean(18:763)

## [1] 390.5

# alternatively you can save this as a vector and run the mean on it
vec1 <- 18:763

mean(vec1)

## [1] 390.5

Install ggplot2.

install.packages("ggplot2") # note the s and the quotes

Load ggplot2 with the library() command.

library("ggplot2") # quotes not necessary, but can be used

Get the structure of the diamonds data frame. What are the different variables and what kind of data does each contain?

str(diamonds)

## Classes 'tbl_df', 'tbl' and 'data.frame':    53940 obs. of  10 variables:
##  $ carat  : num  0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
##  $ cut    : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
##  $ color  : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
##  $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
##  $ depth  : num  61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
##  $ table  : num  55 61 65 58 58 57 57 55 61 61 ...
##  $ price  : int  326 326 327 334 335 336 336 337 337 338 ...
##  $ x      : num  3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
##  $ y      : num  3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
##  $ z      : num  2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...

# We have
# - carat: a number
# - cut: an ordered factor
# - color: an ordered factor
# - clarity: an ordered factor
# - depth: a number
# - table: a number
# - price: an integer
# - x: a number
# - y: a number
# - z: a number

Get summary statistics separately for carat, depth, table, and price.

summary(diamonds$carat)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.2000  0.4000  0.7000  0.7979  1.0400  5.0100

summary(diamonds$depth)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   43.00   61.00   61.80   61.75   62.50   79.00

summary(diamonds$table)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   43.00   56.00   57.00   57.46   59.00   95.00

summary(diamonds$price)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##     326     950    2401    3933    5324   18823

color, cut, and clarity are categorical variables (factors). Use the table() command to generate frequency tables for each.

table(diamonds$color)

## 
##     D     E     F     G     H     I     J 
##  6775  9797  9542 11292  8304  5422  2808

table(diamonds$cut)

## 
##      Fair      Good Very Good   Premium     Ideal 
##      1610      4906     12082     13791     21551

table(diamonds$clarity)

## 
##    I1   SI2   SI1   VS2   VS1  VVS2  VVS1    IF 
##   741  9194 13065 12258  8171  5066  3655  1790

Now rerun the summary() command on the entire data frame.

summary(diamonds)

##      carat               cut        color        clarity     
##  Min.   :0.2000   Fair     : 1610   D: 6775   SI1    :13065  
##  1st Qu.:0.4000   Good     : 4906   E: 9797   VS2    :12258  
##  Median :0.7000   Very Good:12082   F: 9542   SI2    : 9194  
##  Mean   :0.7979   Premium  :13791   G:11292   VS1    : 8171  
##  3rd Qu.:1.0400   Ideal    :21551   H: 8304   VVS2   : 5066  
##  Max.   :5.0100                     I: 5422   VVS1   : 3655  
##                                     J: 2808   (Other): 2531  
##      depth           table           price             x         
##  Min.   :43.00   Min.   :43.00   Min.   :  326   Min.   : 0.000  
##  1st Qu.:61.00   1st Qu.:56.00   1st Qu.:  950   1st Qu.: 4.710  
##  Median :61.80   Median :57.00   Median : 2401   Median : 5.700  
##  Mean   :61.75   Mean   :57.46   Mean   : 3933   Mean   : 5.731  
##  3rd Qu.:62.50   3rd Qu.:59.00   3rd Qu.: 5324   3rd Qu.: 6.540  
##  Max.   :79.00   Max.   :95.00   Max.   :18823   Max.   :10.740  
##                                                                  
##        y                z         
##  Min.   : 0.000   Min.   : 0.000  
##  1st Qu.: 4.720   1st Qu.: 2.910  
##  Median : 5.710   Median : 3.530  
##  Mean   : 5.735   Mean   : 3.539  
##  3rd Qu.: 6.540   3rd Qu.: 4.040  
##  Max.   :58.900   Max.   :31.800  
## 

Now look only at (subset) the first 4 diamonds in the dataset.

# remember, dataframes are indexed by: df[row#s, column#s]
diamonds[1:4,] # select first through fourth rows, all columns

# alternatively
diamonds[c(1,2,3,4),] # using a vector-approach

Now look only at (subset) the third and seventh diamond in the dataset.

diamonds[c(3,7),] # select 3rd and 7th row, all columns

Now look only at (subset) the second column of the dataset.

diamonds[,2] # select all rows, 2nd column

Do this again, but look using the $ to pull up the second column by name.

# second column is called "cut"
diamonds$cut # dont' run this, it'll print 53,000 rows!

Now look only at diamonds that have a carat greater than or equal to 1.

# use the [square brackets] to subset, 
# first argument (rows) are chosen by conditional: 
# - choose diamonds based on their carat, and only carats >= 1
diamonds[diamonds$carat >= 1,] # select rows on condition, and all columns

Now look only at diamonds that have a VVS1 clarity.

# we are testing for equality, so we need two ==
# we are selecting based on clarity, a character/factor, so we need quotes
diamonds[diamonds$clarity=="VVS1",] # select rows on condition, and all columns

Now look only at dimaonds that have a color of E, F, I, and J.

# same idea as last problem, except now we want one of any of these 4 colors

# first (tedious) way, a series of checking equality and using "OR"s (|) 
diamonds[diamonds$color=="E" | diamonds$color=="F" | diamonds$color=="I" | diamonds$color=="J",] # select rows on condition, and all columns

# second (better) way, using group membership operator (%in%) and list the elements as a vector
diamonds[diamonds$color %in% c("E","F","I","J"),] # select rows on condition, and all columns 

Now look only at diamonds that have a carat greater than or equal to 1 and a VVS1 clarity.

# testing for two conditions (AND)
diamonds[diamonds$carat>=1 & diamonds$clarity=="VVS1",] # select rows on condition, and all columns 

Get the average price of diamonds in question 18.²

# use command from last question as the argument to the mean function, 
## but be sure that you look at the price, specifically

mean(diamonds$price[diamonds$carat>=1 & diamonds$color=="D" & diamonds$clarity=="VVS1"])

## [1] 13935.48

What is the highest price for a diamond with a 1.0 carat, D color, and VVS1 clarity?

max(diamonds$price[diamonds$carat>=1 & diamonds$color=="D" & diamonds$clarity=="VVS1"])

## [1] 17932