Lesson 5
Sammy Amos
2024-09-11
5.1 Video
Libraries used
library(ggplot2)Visualizing data
ceo <- readr::read_csv("ceo_salaries.csv")
attach(ceo)Histograms
hist(ceo$SALARY,main="Histogram of CEO salaries",xlab="Salary bins in $USD")
hist(ceo$AGE)
Determining number of bins and breaks
Specify number of breaks
R takes the specific number as a suggestion
Makes sure that the x axis is in logical intervals
hist(x=cars$speed, breaks=10) # notice that there are 11 bars
Can specify the range, following example shows 4 through 25 possible breaks specified
hist(x=cars$speed, breaks=4:25, main="Car Speed", xlab="Speed (mph)")
By vector
seq() used in the same way in vector form
hist(cars$speed, breaks=seq(4,25, by=1),main="Car Speed", xlab="Speed (mph)")
Labeling bars
hist(x=cars$speed, breaks=10, labels=TRUE, main="Car Speed", xlab="Speed (mph)") 
Density plot
density(x=cars$speed) ##
## Call:
## density.default(x = cars$speed)
##
## Data: cars$speed (50 obs.); Bandwidth 'bw' = 2.15
##
## x y
## Min. :-2.450 Min. :7.999e-05
## 1st Qu.: 6.025 1st Qu.:5.918e-03
## Median :14.500 Median :2.570e-02
## Mean :14.500 Mean :2.944e-02
## 3rd Qu.:22.975 3rd Qu.:5.442e-02
## Max. :31.450 Max. :6.575e-02cardensity <- density(cars$speed)
plot(cardensity, xlab="Speed (mph)")
Add a curve
hist(x=cars$speed, prob=TRUE, main="Car speed", col="purple", border="white", xlab="Speed (mph)")
lines(density(cars$speed), lwd=3, col="black")
Box (and whisker) plot
Measures Same as scatter plot, but as boxplot()
- Range
- Median
- Interquartile range As well as spread and skewness
horizontal= takes TRUE or
FALSE
boxplot(ceo$SALARY, main="Boxplot showing the median and range of CEO salaries", frame.plot=FALSE) # remove box around graph
Scatter plots
main="" chart title
type= type of chart
pscatter plots (default)
- do not need to explicitly include it as a parameter)
llines,
bboth lines and points,
hhistogram/high-density
sstair steps,
nno plotting.
xlab=Label for x-axis
ylab=Label for y-axis
plot(AGE, SALARY, main="Does salary increase with age?", xlab="Age",ylab="Salary in thousands of $USD",frame.plot=FALSE)
ggplot
Density
ggplot(ceo, aes(x=SALARY)) + geom_density(fill="#4cbe3a")## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_density()`).
Histogram
ggplot(ceo, aes(x=SALARY))+geom_histogram(binwidth=100, fill = "#4cbea3")## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_bin()`).
Scatter plot
Note: geom_point() will require x AND
y in the aes()
ggplot(ceo, aes(x=SALARY,AGE))+geom_point(color="blue")## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_point()`).
Bar graph
ggplot(ceo, aes(AGE)) + geom_bar(fill="blue")
Data formatting
Changing column names
head(ceo,5)## # A tibble: 5 × 2
## AGE SALARY
## <dbl> <dbl>
## 1 53 145
## 2 43 621
## 3 33 262
## 4 45 208
## 5 46 362names(ceo) <- c(tolower("AGE"), tolower("SALARY"))
head(ceo,5)## # A tibble: 5 × 2
## age salary
## <dbl> <dbl>
## 1 53 145
## 2 43 621
## 3 33 262
## 4 45 208
## 5 46 362Reorder columns
head(ceo,5)## # A tibble: 5 × 2
## age salary
## <dbl> <dbl>
## 1 53 145
## 2 43 621
## 3 33 262
## 4 45 208
## 5 46 362ceo <- ceo[c("salary","age")]Notice that the access brackets are used instead. It makes sense to use them since we’re telling the system to create a table with those columns
head(ceo,5)## # A tibble: 5 × 2
## salary age
## <dbl> <dbl>
## 1 145 53
## 2 621 43
## 3 262 33
## 4 208 45
## 5 362 46Tables
table() makes a frequency table
table(AGE)## AGE
## 32 33 36 37 38 40 41 43 44 45 46 47 48 49 50 51 52 53 55 56 57 58 59 60 61 62
## 1 1 1 1 1 1 1 2 2 4 2 3 4 1 6 2 1 3 3 4 2 2 1 1 3 2
## 63 69 70 74
## 1 2 1 1Showing two plots at one time (scatter + box)
chartcolor <- "blue"
hist_salary <- ggplot(ceo, aes(salary)) +
geom_histogram(binwidth = 100, fill=chartcolor) +
labs(title = "Histogram of CEO salaries",
caption = "Kristen Sosulski | Source: Statcrunch (2019)",
x = "Salary in thousands of $USD", y = "Frequency")
hist_age <- ggplot(ceo, aes(age)) +
geom_histogram(binwidth = 100, fill=chartcolor) +
labs(title ="Histogram of CEO ages",
caption = "Kristen Sosulski | Source: Statcrunch (2019)",
x = "Age (in years)", y = "Frequency")Introducing cowplot!
cowplot::plot_grid(hist_age, hist_salary, labels = "AUTO")## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_bin()`).
Another example
library(car) # DO NOT CONFUSE WITH DATASET CAR## Loading required package: carDatascatterplot(x=cars$speed, y=cars$dist, xlab="Speed (mph)", ylab="Stopping distance(ft)", main="Cars: Speed and stopping distance", smooth=FALSE)
Formatting numbers
hist_salary <- hist_salary + scale_x_continuous(labels=scales::comma) #adds comma to thousands
cowplot::plot_grid(hist_age, hist_salary, labels = "AUTO")## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_bin()`).
But there are some values still cut off. Solution: make the graph wider
hist_salary <- hist_salary + scale_x_continuous(labels=scales::comma,
limits=c(min(ceo$salary), 1500))## Scale for x is already present.
## Adding another scale for x, which will replace the existing scale.5.2 Follow along
Ordering factors
Preparing data:
undergrad <- readr::read_csv("undergrad.csv")
undergrad <- data.frame(undergrad)
#renaming columns in the undergrad data frame
names(undergrad) <- c("timestamp","excel","access", "statistics", "programming", "iscourse", "cscourse", "topics", "istopics", "onlinecourse", "concentration")
attach(undergrad)hist(access) ## Error in hist.default(access): 'x' must be numeric#reassign access as a factor variable
access <-as.factor(access)
# cast access as a numeric for plotting.
figure06<- hist(as.numeric(access), main = "Responses to the level of importance of learning Microsoft Access", xlab = "Bins by reponse category", col="#4cbea3", labels=TRUE, border="#FFFFFF")
Calling the figure06 will output the details of the
graph
figure06## $breaks
## [1] 1 2 3 4 5 6
##
## $counts
## [1] 10 9 10 2 8
##
## $density
## [1] 0.25641026 0.23076923 0.25641026 0.05128205 0.20512821
##
## $mids
## [1] 1.5 2.5 3.5 4.5 5.5
##
## $xname
## [1] "as.numeric(access)"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"access_ordered <- ordered(x=access, levels=c("Strongly disagree","Disagree","Somewhat disagree","Neither agree or disagree","Somewhat agree","Agree","Strongly Agree"))
attributes(access_ordered)## $levels
## [1] "Strongly disagree" "Disagree"
## [3] "Somewhat disagree" "Neither agree or disagree"
## [5] "Somewhat agree" "Agree"
## [7] "Strongly Agree"
##
## $class
## [1] "ordered" "factor"table(access_ordered)## access_ordered
## Strongly disagree Disagree Somewhat disagree
## 0 5 2
## Neither agree or disagree Somewhat agree Agree
## 9 10 5
## Strongly Agree
## 8figure07 <- hist(as.numeric(access_ordered),breaks=7, main = "Responses to the level of importance of learning Microsoft Access", xlab = "Bins by reponse category", col="#4cbea3", labels=TRUE, border="#FFFFFF")
figure07## $breaks
## [1] 2 3 4 5 6 7
##
## $counts
## [1] 7 9 10 5 8
##
## $density
## [1] 0.1794872 0.2307692 0.2564103 0.1282051 0.2051282
##
## $mids
## [1] 2.5 3.5 4.5 5.5 6.5
##
## $xname
## [1] "as.numeric(access_ordered)"
##
## $equidist
## [1] TRUE
##
## attr(,"class")
## [1] "histogram"par(mfrow = c(1, 2))
hist(as.numeric(access), main = "Figure 6", xlab = "Bins by reponse category", col="#4cbea3", labels=TRUE, border="#FFFFFF")
hist(as.numeric(access_ordered),breaks=7, main = "Figure 7", xlab = "Bins by reponse category", col="#4cbea3", labels=TRUE, border="#FFFFFF")
detach(undergrad)Data visualization
Data visualization ggplot2 cheat sheet
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ dplyr::recode() masks car::recode()
## ✖ purrr::some() masks car::some()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(dplyr)
penguins <- palmerpenguins::penguins
penguins## # A tibble: 344 × 8
## species island bill_length_mm bill_depth_mm flipper_length_mm body_mass_g
## <fct> <fct> <dbl> <dbl> <int> <int>
## 1 Adelie Torgersen 39.1 18.7 181 3750
## 2 Adelie Torgersen 39.5 17.4 186 3800
## 3 Adelie Torgersen 40.3 18 195 3250
## 4 Adelie Torgersen NA NA NA NA
## 5 Adelie Torgersen 36.7 19.3 193 3450
## 6 Adelie Torgersen 39.3 20.6 190 3650
## 7 Adelie Torgersen 38.9 17.8 181 3625
## 8 Adelie Torgersen 39.2 19.6 195 4675
## 9 Adelie Torgersen 34.1 18.1 193 3475
## 10 Adelie Torgersen 42 20.2 190 4250
## # ℹ 334 more rows
## # ℹ 2 more variables: sex <fct>, year <int>#View(penguins)
dplyr::glimpse(penguins)## Rows: 344
## Columns: 8
## $ species <fct> Adelie, Adelie, Adelie, Adelie, Adelie, Adelie, Adel…
## $ island <fct> Torgersen, Torgersen, Torgersen, Torgersen, Torgerse…
## $ bill_length_mm <dbl> 39.1, 39.5, 40.3, NA, 36.7, 39.3, 38.9, 39.2, 34.1, …
## $ bill_depth_mm <dbl> 18.7, 17.4, 18.0, NA, 19.3, 20.6, 17.8, 19.6, 18.1, …
## $ flipper_length_mm <int> 181, 186, 195, NA, 193, 190, 181, 195, 193, 190, 186…
## $ body_mass_g <int> 3750, 3800, 3250, NA, 3450, 3650, 3625, 4675, 3475, …
## $ sex <fct> male, female, female, NA, female, male, female, male…
## $ year <int> 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007…Creating a ggplot
1) Create ggplot object
library(ggplot2)
ggplot(data = penguins)
2) Mapping visual properties (aesthetics)
ggplot(
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g)
)
3) Add the points/graphs
geom_bar() bar charts
geom_line() line chart
geom_boxplot() boxplot
geom_point() scatterplot
ggplot(
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g)
) +
geom_point() # the graph## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Notice the warning. “there are two penguins in our dataset with missing body mass and/or flipper length values and ggplot2 has no way of representing them on the plot without both of these values” but R calls it out so that we know that there were some taken out
Aesthetics and Layers
aes()
ggplot(
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g, color = species)
) +
geom_point() # the graph## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Scaling
When a categorical variable is mapped to an aesthetic, ggplot2 will
automatically assign a unique value of the aesthetic (here a unique
color) to each unique level of the variable (each of the three
species)
Translated: Color coding happens on its own!
Adding another layer:
- smooth curve
geom_smooth - line of best fit based on linear model
method="lm"
ggplot(
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g, color = species)
) +
geom_point() + # the graph
geom_smooth(method = "lm") # the other layer## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Local vs global mapping
ggplot( # global level
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g)
) + # everything after this is local
geom_point(mapping = aes(color = species)) +
geom_smooth(method = "lm")## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Take into consideration color blindness, so also use shapes
ggplot(
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g)
) +
geom_point(mapping = aes(color = species, shape = species)) + # here
geom_smooth(method = "lm")## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Labels
library(ggthemes)
ggplot(
data = penguins,
mapping = aes(x = flipper_length_mm, y = body_mass_g)
) +
geom_point(aes(color = species, shape = species)) +
geom_smooth(method = "lm") +
labs(
title = "Body mass and flipper length",
subtitle = "Dimensions for Adelie, Chinstrap, and Gentoo Penguins",
x = "Flipper length (mm)", y = "Body mass (g)",
color = "Species", shape = "Species"
) +
ggthemes::scale_color_colorblind()## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Conciseness
ggplot(penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point()## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).and
penguins |>
ggplot(aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point()## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).Visualizing distributions
Categorical variable
can only take one of a small set of values
Example: bar chart
ggplot(penguins, aes(x = species)) +
geom_bar()
In bar plots of categorical variables with non-ordered levels, like the penguin species above, it’s often preferable to reorder the bars based on their frequencies. Doing so requires transforming the variable to a factor (how R handles categorical data) and then reordering the levels of that factor.
ggplot(penguins, aes(x = fct_infreq(species))) +
geom_bar()
Numerical variable
can take on a wide range of numerical values, and it is sensible to
add, subtract, or take averages with those values. Numerical variables
can be continuous or discrete
Example: histogram
ggplot(penguins, aes(x = body_mass_g)) +
geom_histogram(binwidth = 200)## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_bin()`).
Additional bins
ggplot(penguins, aes(x = body_mass_g)) +
geom_histogram(binwidth = 20)## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_bin()`).
ggplot(penguins, aes(x = body_mass_g)) +
geom_histogram(binwidth = 2000)## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_bin()`).
Density plots
ggplot(penguins, aes(x = body_mass_g)) +
geom_density()## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_density()`).
Visualizing relationships
Numerical and categorical
Box plots
- A box that indicates the range of the middle half of the data, a distance known as the interquartile range (IQR), stretching from the 25th percentile of the distribution to the 75th percentile. In the middle of the box is a line that displays the median, i.e. 50th percentile, of the distribution. These three lines give you a sense of the spread of the distribution and whether or not the distribution is symmetric about the median or skewed to one side. Visual points that display observations that fall more than 1.5 times the IQR from either edge of the box. These outlying points are unusual so are plotted individually. A line (or whisker) that extends from each end of the box and goes to the farthest non-outlier point in the distribution.
Explanation of box plot
Example: distribution of body mass
ggplot(penguins, aes(x = species, y = body_mass_g)) +
geom_boxplot()## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
Example: same but with density plot
ggplot(penguins, aes(x = body_mass_g, color = species)) +
geom_density(linewidth = 0.75)## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_density()`).
Prettified
ggplot(penguins, aes(x = body_mass_g, color = species, fill = species)) +
geom_density(alpha = 0.5)## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_density()`).
Two categorical
ggplot(penguins, aes(x = island, fill = species)) +
geom_bar()
in a different way position="fill"
more useful for comparing species distributions across islands since
it’s not affected by the unequal numbers of penguins across the
islands
ggplot(penguins, aes(x = island, fill = species)) +
geom_bar(position = "fill")
Two numerical
scatterplot is probably the most commonly used plot for visualizing the relationship between two numerical variables
ggplot(penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point()## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Three or more variables
Example: the colors of points represent species and the shapes of points represent islands
ggplot(penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point(aes(color = species, shape = island))## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Facets
subplots that each display one subset of the data.
ggplot(penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point(aes(color = species, shape = species)) +
facet_wrap(~island)## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Saving plots
Example: ggsave(filename = "penguin-plot.png")