Recreation of Cole Nussbaumer Knaflicās Storytelling with Data
Trung Dang
26/08/2021
Recreation of Cole Nussbaumer Knaflicās Storytelling with Data (Wiley, 2015) plots using R an ggplot2.
Original data provided by the bookās author https://www.storytellingwithdata.com/book/downloads
library(ggtext)## Warning: package 'ggtext' was built under R version 4.0.5library(tidyselect)
library(ggplot2)
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --## v tibble 3.0.5 v dplyr 1.0.3
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.0
## v purrr 0.3.4## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(gridExtra)##
## Attaching package: 'gridExtra'## The following object is masked from 'package:dplyr':
##
## combinelibrary(gridtext)## Warning: package 'gridtext' was built under R version 4.0.5Chapter 2: Choosing an effective visual
Simple text
df_box <- tibble(
label = c("<span style='font-size:128pt;color:#31859C'>**20%**</span> <br/>
<span style='font-size:20pt;color:#7F7F7F'>**of children had a**</span><br/>
<span style='font-size:20pt;color:#31859C'>**traditional stay-at-home mom** </span><br/>
<span style='font-size:20pt;color:#7F7F7F'>**in 2012, compared to 41% in 1970**</span>"),
x = 0.01,
y = 0.5,
color = c("white"),
fill = c("white"))
ggplot()+
geom_textbox(data = df_box,
aes(x , y, label = label),
box.color = "white",
fill = "white", lineheight = 2,
width = unit(400, "pt"),
hjust = 0,
box.padding = unit(c(0, 0, 0, 0), "pt")) + # control the width
xlim(0, 1) +
ylim(0, 1) +
theme(axis.ticks.x = element_blank(),
axis.ticks.y = element_blank(),
axis.title = element_blank(),
axis.line = element_blank(),
axis.text.y = element_blank(),
axis.text.x = element_blank(),
axis.title.x = element_blank(),
axis.title.y = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = unit(c(0,0,0,0),"cm"))
Figure 2.3 Stay-at-home moms simple text makeover
ggsave("Figure 2.3 Stay-at-home moms simple text makeover.png", height = 7, width = 11,units = "in",dpi = 300)Scatter Plot
miles <- read_csv("milesdriven.csv")##
## -- Column specification --------------------------------------------------------
## cols(
## `Miles Driven` = col_number(),
## `Cost Per Mile` = col_double()
## )avg_cost <- mean(miles$`Cost Per Mile`)
avg_mile <- mean(miles$`Miles Driven`)
ggplot(data = miles,aes(x = `Miles Driven`, y = `Cost Per Mile`)) +
geom_point(data = filter(miles,`Cost Per Mile` < avg_cost),color = "#BFBEBE",size = 5)+
geom_point(data = filter(miles,`Cost Per Mile` >= avg_cost),color = "#F79747",size = 5) +
geom_hline(yintercept = avg_cost, linetype = "longdash") +
geom_point(x = avg_mile,y = avg_cost, size = 6) +
geom_label(x = avg_mile, y = avg_cost, label = "AVG", hjust = 1.25, label.size = 0) +
scale_x_continuous(expand = c(0, 0),limits = c(0, 4000), n.breaks = 5) +
scale_y_continuous(expand = c(0, 0),limits = c(0, 3),labels = scales::dollar_format(), n.breaks = 7) +
labs(title = "Cost per mile by miles driven",
x = "Miles driven per month",
y = "Cost per mile") +
theme(plot.title = element_markdown(size=16),
plot.title.position = "plot",
# axis.title.y = element_text(hjust = 1, margin = margin(0, 6, 0, 15, "pt")),
# axis.title.x = element_text(hjust = 0, margin = margin(6, 0, 15, 0, "pt")),
axis.title.x= element_text(size = 12, hjust = 0, vjust = -1, color = "#555655"),
axis.title.y = element_text(size = 12, hjust = 1 ,vjust = 1, color = "#555655"),
axis.text.x = element_text(color ="#777B7E", face="bold"),
axis.text.y = element_text(color ="#777B7E", face="bold"),
axis.ticks.x = element_line(color="#a9a9a9"),
axis.ticks.y = element_line(color="#a9a9a9"),
axis.line.x = element_line(color="grey", size = 1),
axis.line.y = element_line(color="grey", size = 1),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = margin(.5,.5,.5,.5,"cm"))
Figure 2.7 Modified Scatterplot
ggsave("Figure 2.7 Modified Scatterplot.png", height = 7, width = 11,units = "in",dpi = 300)Line graph
passport <- read_csv("passport.csv")##
## -- Column specification --------------------------------------------------------
## cols(
## year = col_double(),
## month = col_character(),
## Min = col_double(),
## Avg = col_double(),
## Max = col_double(),
## `Max to graph` = col_double()
## )theme_ch2 <- theme(plot.title = element_markdown(size=16),
plot.title.position = "plot",
plot.subtitle = element_markdown(size =14),
# axis.title.y = element_text(hjust = 1, margin = margin(0, 6, 0, 15, "pt")),
# axis.title.x = element_text(hjust = 0, margin = margin(6, 0, 15, 0, "pt")),
axis.title.x = element_text(size = 12, hjust = 0, vjust = -1, color = "#555655"),
axis.title.y = element_text(size = 12, hjust = 1 ,vjust = 1, color = "#555655"),
axis.text.x = element_text(size = 12,color ="#777B7E", face="bold"),
axis.text.y = element_text(size = 12,color ="#777B7E", face="bold"),
axis.ticks.x = element_line(color="#a9a9a9"),
axis.ticks.y = element_line(color="#a9a9a9"),
axis.line.x = element_line(color="grey", size = 1),
axis.line.y = element_line(color="grey", size = 1),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = margin(.5,.5,.5,.5,"cm"))passport <- passport %>%
mutate(date = ymd(paste(year, month, 1)))passport %>%
filter(date== "2014-09-01")## # A tibble: 1 x 7
## year month Min Avg Max `Max to graph` date
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <date>
## 1 2014 Sep 9 18 27 18 2014-09-01ggplot(data = passport) +
geom_ribbon(aes(x= date, ymin = Min, ymax = Max), fill = "grey70") +
geom_line(aes(x= date, y = Avg), size = 2) +
geom_point(data= filter(passport, date == "2015-09-01"), aes(x= date, y = Avg), size = 5) +
annotate("text", x = as.Date("2015-09-20"), y = 21, label = "21", color = "black", size = 5) +
annotate("text", x = as.Date("2014-09-15"), y = 10, label = "MIN", color = "#76787B", size = 5) +
annotate("text", x = as.Date("2014-09-15"), y = 20, label = "AGV", color = "black", size = 5,fontface =2) +
annotate("text", x = as.Date("2014-09-15"), y = 25, label = "MAX", color = "#76787B",size = 5) +
scale_x_date(expand = c(0, 0),
labels = function(x) if_else(is.na(lag(x)) | !year(lag(x)) == year(x),
paste(month(x, label = TRUE), "\n", year(x)),
paste(month(x, label = TRUE))),
limits = c(ymd("2014-08-16"), ymd("2015-10-01")),
breaks = passport$date) + # n.breaks does not work
scale_y_continuous(expand = c(0, 0),
limit = c(0, 40),
n.breaks = 9) +
labs(title = "Passport control wait time",
subtitle = "Past 13 months",
y = "Wait time (minutes)") +
coord_cartesian(clip = "off") +
theme_ch2 +
theme(axis.title.x = element_blank(),
plot.margin = margin(.5,0.5,0.5,0.5,"cm"))
Figure 2.9 Showing average within a range in a line graph
ggsave("Figure 2.9 Showing average within a range in a line graph.png", height = 7, width = 11,units = "in",dpi = 300)Slopegraphe
feedback <- read_csv("feedback.csv")##
## -- Column specification --------------------------------------------------------
## cols(
## Category = col_character(),
## `2014` = col_double(),
## `2015` = col_double()
## )feedback## # A tibble: 7 x 3
## Category `2014` `2015`
## <chr> <dbl> <dbl>
## 1 Culture 80 96
## 2 Peers 85 91
## 3 Work environment 76 75
## 4 Leadership 59 62
## 5 Rewards & recognition 41 45
## 6 Perf management 33 42
## 7 Career development 49 33df_long <- feedback %>%
pivot_longer(cols = c("2014","2015"),
names_to = "year",
values_to = "percent")
head(df_long,10)## # A tibble: 10 x 3
## Category year percent
## <chr> <chr> <dbl>
## 1 Culture 2014 80
## 2 Culture 2015 96
## 3 Peers 2014 85
## 4 Peers 2015 91
## 5 Work environment 2014 76
## 6 Work environment 2015 75
## 7 Leadership 2014 59
## 8 Leadership 2015 62
## 9 Rewards & recognition 2014 41
## 10 Rewards & recognition 2015 45ggplot(data = df_long)+
#Line
geom_line(aes(x = year, y = percent, group= Category),
size = 1.5, color ="#76787B") +
geom_line(data = filter(df_long, Category == "Career development"),
aes(year, percent,group= Category),
size = 1.5, color = "#FF3403") +
#point
geom_point(aes(x = year, y = percent, group= Category),
size = 3, color ="#76787B") +
geom_point(data = filter(df_long, Category == "Career development"),
aes(year, percent),
size = 3, color = "#FF3403") +
#Percent-labels
geom_text(data= filter(df_long, year== 2014),aes(x= year,y = percent, label=paste(percent,"%",sep = "")),
nudge_x = -.2, color ="#76787B") +
geom_text(data= filter(df_long, year== 2015),aes(x= year,y = percent, label=paste(percent,"%",sep = "")),
nudge_x = .25, color ="#76787B") +
geom_text(data= filter(df_long, year == 2014, Category == "Career development"),
aes(x= year,y = percent, label=paste(percent,"%",sep = "")),
nudge_x = -.2, color ="#FF3403") +
geom_text(data= filter(df_long, year == 2015, Category == "Career development"),
aes(x= year,y = percent, label=paste(percent,"%",sep = "")),
nudge_x = .25, color = "#FF3403") +
# Category-labels
geom_text(data= filter(df_long, year == 2014),
aes(x= year,y = percent, label=paste(Category)),
nudge_x = -.4,hjust = 1, color ="#76787B") +
geom_text(data= filter(df_long, year == 2014, Category == "Career development"),
aes(x= year,y = percent, label=paste(Category)),
nudge_x = -.4,hjust = 1, color = "#FF3403") +
scale_x_discrete(expand = expansion(2,0),
limits = c("2014","2015"),
labels = c(2014,2015)) +
scale_y_continuous(limits = c(20,100)) +
labs(title = "Employee feedback over time",
x = "Survey Year",
subtitle = "Survey Category | Percent Favorable") +
theme(plot.title = element_markdown(size=16),
plot.title.position = "plot",
plot.subtitle = element_markdown(size =14, hjust = 0.15, color = "#76787B"),
# axis.title.y = element_text(hjust = 1, margin = margin(0, 6, 0, 15, "pt")),
# axis.title.x = element_text(hjust = 0, margin = margin(6, 0, 15, 0, "pt")),
axis.title.x = element_text(size = 12, hjust = 0, vjust = -1, color = "#555655"),
axis.title.y = element_blank(),
axis.text.x = element_text(size = 12,color ="#777B7E", face="bold"),
axis.text.y = element_blank(),
axis.ticks.x = element_line(color="#a9a9a9"),
axis.ticks.y = element_blank(),
axis.line.x = element_line(color="grey", size = 1),
# axis.line.y = element_line(color="grey", size = 1),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = margin(.5,.5,.5,.5,"cm"))
Figure 2.11 Modified slopegraph (page 49)
ggsave("Figure 2.11 Modified slopegraph.png", height = 7, width = 11,units = "in",dpi = 300)bars: Stacked horizontal bar chart (FIG2.19)
survey <- read_csv("survey.csv")##
## -- Column specification --------------------------------------------------------
## cols(
## items = col_character(),
## `Strongly Disagree` = col_character(),
## Disagree = col_character(),
## Neutral = col_character(),
## Agree = col_character(),
## `Strongly Agree` = col_character()
## )survey## # A tibble: 5 x 6
## items `Strongly Disagree` Disagree Neutral Agree `Strongly Agree`
## <chr> <chr> <chr> <chr> <chr> <chr>
## 1 Survey item E 5% 5% 30% 27% 33%
## 2 Survey item D 6% 11% 35% 28% 20%
## 3 Survey item C 6% 14% 45% 15% 20%
## 4 Survey item B 8% 32% 20% 23% 17%
## 5 Survey item A 16% 25% 32% 18% 9%Transforming data
df_long <- survey %>%
pivot_longer(cols = c("Strongly Disagree","Disagree","Neutral","Agree","Strongly Agree"),
names_to = "Scale",
values_to = "Percent") %>%
mutate(percent = as.numeric(str_remove(Percent,"%")))
df_long$Scale <- factor(df_long$Scale,levels=c("Strongly Agree","Agree", "Neutral","Disagree","Strongly Disagree"))
head(df_long, 10)## # A tibble: 10 x 4
## items Scale Percent percent
## <chr> <fct> <chr> <dbl>
## 1 Survey item E Strongly Disagree 5% 5
## 2 Survey item E Disagree 5% 5
## 3 Survey item E Neutral 30% 30
## 4 Survey item E Agree 27% 27
## 5 Survey item E Strongly Agree 33% 33
## 6 Survey item D Strongly Disagree 6% 6
## 7 Survey item D Disagree 11% 11
## 8 Survey item D Neutral 35% 35
## 9 Survey item D Agree 28% 28
## 10 Survey item D Strongly Agree 20% 20cols <- c("Strongly Disagree" = '#404040',
"Disagree" = '#404040',
"Neutral"= '#BFBFBF' ,
"Agree"= '#1F497D',
"Strongly Agree"= '#1F497D')
ggplot(data = df_long) +
geom_bar(stat = "identity",
aes(x = items, y = percent, fill = Scale),
width = 0.65,
color = "white")+
scale_y_continuous(name = "Percent of total",
limits = c(0, 100),
breaks = seq(0, 100, by = 20),
labels = function(x) paste0(x,"%"),
position = 'right') +
labs(title= "Survey results",
subtitle = "<span style='color:#404040'>Strongly Disagree</span>|
<span style='color:#404040'>Disagree</span> |
<span style='color:#BFBFBF'>Neutral</span> |
<span style='color:#1F497D'>Agree</span> |
<span style='color:#1F497D'>Strongly Agree</span>") +
scale_fill_manual(values = cols) +
coord_flip() +
theme(plot.title = element_markdown(size=18, hjust =-0.25),
plot.subtitle = element_markdown(size=12,face="bold", color="#777B7E"),
axis.title.y = element_blank(),
axis.ticks.y = element_blank(),
axis.text.y = element_text(color ="#777B7E", face="bold", size = 12),
axis.title.x = element_markdown(hjust = 0,size = 12),
axis.text.x = element_text(color ="#777B7E", face="bold", size = 12),
axis.line.x = element_line(color="grey", size = 1),
axis.ticks.x = element_line(color="#a9a9a9"),
legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank())
Figure 2.19 100% stacked horizontal bar chart (Page 59)
ggsave("Figure 2.19.png", height = 4, width = 7,units = "in",dpi = 300)Chapter three: Clutter is your enemy !
attributes <- c("Colleague recommendation",
"Previous work together",
"Affordability of services",
"National reputation",
"Local knowledge",
"Content expertise",
"Demonstration of results")
percent <- c(4,17,19,21,42,53,72)
feedback <- data.frame(attributes, percent)library(gridExtra)
library(grid)p1 <- ggplot(data = feedback, aes (x = reorder(attributes,percent), y = percent)) +
geom_bar(stat = "identity")+
geom_bar(data = feedback %>%
filter(attributes %in% c("Demonstration of results",
"Previous work together",
"Affordability of services")),
stat = "identity",
fill ="black")+
labs(title = "**Demonstring effectiveness**<span style = 'color:#404040'> is most important consideration<br>
when selecting a provider</span> ",
subtitle= "<span style = 'color:#404040'>In general,</span>
**what attributes are the most important** <br>
<span style = 'color:#404040'>to you in selecting a service provider</span>",
caption = "Data source: xyz; indluces N number of surbey respondents.\nNote that respondents were able to choose up to 3 options.") +
scale_y_continuous(name = "% selecting given attribute",
limits = c(0, 80),
breaks = seq(0, 80, by = 20),
labels = function(x) paste0(x,"%"),
position = 'right') +
coord_flip() +
theme(plot.title = element_markdown(size=18),
plot.title.position = "plot",
plot.subtitle = element_markdown(size=12, face="bold"),
axis.title.y = element_blank(),
axis.ticks.y = element_blank(),
axis.text.y = element_text(color ="#777B7E", face="bold", size = 12),
axis.title.x = element_markdown(hjust = 0,size = 12, ),
axis.text.x = element_text(color ="#777B7E", face="bold", size = 12),
axis.line.x = element_line(color="grey", size = 1),
axis.ticks.x = element_line(color="#a9a9a9"),
legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank())
df <- tibble(
label = c(
"<span style='color:#000000'>Survey shows that **demonstation<br>
of results** is the single most<br>
important dimension when<br>
chosing a service provider</span>",
"<span style='color:#000000'>**Affodability** and **exprerience** <br>
**working together previously**,<br>
which were hypothesis to be<br>
very important in the decision<br>
making process, were both cited<br>
less frequently as important attributes.</span>"),
x = c(0, 0),
y = c(0.6, 0.2),
hjust = c(0, 0),
vjust = c(0.5, 0.5),
color = c("white", "white"), # contour
fill = c("white", "white")
)
p2 <- ggplot(df) +
aes(x, y,
label = label,
color = color,
fill = fill,
hjust = hjust,
vjust = vjust) +
geom_richtext() +
scale_color_identity() +
scale_fill_identity() +
xlim(0, 1) + ylim(0, 1) +
theme(axis.title = element_blank(), # weird, why y here ?
axis.text = element_blank(),
axis.ticks = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank())
grid.arrange(p1, p2,ncol= 2,widths = c(6.5,3))
Figure 3.14 Revamped summary of survey feedback
fig3.14 <- arrangeGrob(p1, p2, ncol= 2, widths = c(6.5,3))
ggsave(file="Figure 3.14 Revamped summary of survey feedback.png", fig3.14, height = 5, width = 10,units = "in",dpi = 300)Chapter four: Focus on your audienceās attention
concern <- c("Engine power is less than expected",
"Tires make excessive noise while driving" ,
"Engine makes abnormal/excessive noise",
"Seat material concerns",
"Excessive wind noise" ,
"Hesitation or delay when shifting",
"Bluetooth system has poor sound quality",
"Steering system/wheel has too much play",
"Bluetooth system is difficult to use",
"Front seat audio/entertainment/navigation controls")
number <- c(12.9,12.3,11.6,11.6,11.0,10.3,10.0,8.8,8.6,8.2)
design <- data.frame(concern, number)p3 <- ggplot(data =design , aes (x = reorder(concern,number), y = number)) +
geom_bar(stat = "identity",
fill = "#7F7F7F")+
geom_bar(data = design %>%
filter(concern %in% c("Tires make excessive noise while driving",
"Engine makes abnormal/excessive noise",
"Excessive wind noise")),
stat = "identity",
fill = "#C0504D")+
geom_bar(data = design %>%
filter(concern %in% c("Engine power is less than expected",
"Seat material concerns",
"Hesitation or delay when shifting",
"Bluetooth system has poor sound quality")),
stat = "identity",
fill ="#E6B9B8")+
geom_text(aes(label =number),colour = "white", vjust = 0.5, hjust = 1.25) +
labs(title = "Of the top design concerns, three are noise-related",
subtitle = "Top 10 design concerns",
y = "concerns per 1000") +
scale_y_continuous(position = 'right') +
#Complaints about engine noise commonly cited after the car had not been driven for a while.
# Excessive wind noise is noted primarily in freeway driving at high speeds
coord_flip() +
theme(plot.title = element_markdown(size=16),
plot.title.position = "plot",
plot.subtitle = element_markdown(size=12, face="bold"),
axis.title.y = element_blank(), # weird, why y here ?
axis.text.y = element_text(size = 12),
axis.ticks.y = element_blank(),
axis.title.x = element_markdown(hjust = 0,size = 12),
axis.text.x = element_blank(),
axis.line.x = element_blank(),
axis.ticks.x = element_blank(),
#plot.margin = unit(c(1,6,1,1),"cm")
plot.margin=unit(c(1,-0.5,1,1), "cm"),
# legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank())
df2 <- tibble(
label = c(
"<span style='color:#000000'>Comments indicate that</span><br>
<span style='color:#C0504D'>**noisy tire issues**</span><span style='color:#000000'> are</span><br>
<span style='color:#000000'>most apparent **in the rain.**</span>",
"<span style='color:#000000'>Complaints about</span><span style='color:#C0504D'> **engine**</span><br>
<span style='color:#C0504D'>**noise**</span><span style='color:#000000'>commonly cited<br>
**after the car had not<br>
been driven for a while**.</span>",
"<span style='color:#000000'>Excessive</span><span style='color:#C0504D'> **wind noise**</span>
<span style='color:#000000'>is</span><br>
<span style='color:#000000'>noted primarily in **freeway**<br>
**driving ar high speeds**.</span>"),
x = c(0, 0, 0),
y = c(0.65, 0.4,0.25),
hjust = c(0, 0,0),
vjust = c(0, 0,0),
color = c("white", "white", "white"), # contour
fill = c("white", "white", "white")
)
p4 <- ggplot(df2) +
aes(x, y,
label = label,
color = color,
fill = fill,
hjust = hjust,
vjust = vjust) +
geom_richtext() +
scale_color_identity() +
scale_fill_identity() +
xlim(0, 1) + ylim(0, 1) +
theme(axis.title = element_blank(), # weird, why y here ?
axis.text = element_blank(),
axis.ticks = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank())
grid.arrange(p3, p4,ncol= 2, widths = c(12,4))
Figure 4.9 Create a visual hierarchy pf information
fig4.9 <- arrangeGrob(p3, p4, ncol= 2, widths = c(12,4))
ggsave(file="Figure 4.9 Create a visual hoerarchy of imformation.png", fig4.9, height = 5, width = 10,units = "in",dpi = 300)ticket_wide <- read_csv("ticket.csv")##
## -- Column specification --------------------------------------------------------
## cols(
## ticket_type = col_character(),
## Jan = col_double(),
## Feb = col_double(),
## Mar = col_double(),
## Apr = col_double(),
## May = col_double(),
## Jun = col_double(),
## Jul = col_double(),
## Aug = col_double(),
## Sep = col_double(),
## Oct = col_double(),
## Nov = col_double(),
## Dec = col_double()
## )ticket <- ticket_wide %>%
pivot_longer(cols = !ticket_type,
names_to = "month",
values_to = "tickets") %>%
mutate(month = factor(month, levels = month.abb))cols <- c("Processed" = "#1F497D",
"Received" = "#7F7F7F")
ggplot(data= ticket) +
geom_line(aes(x= month, y = tickets, group = ticket_type, colour= ticket_type), size = 1.5) +
geom_point(data = ticket %>%
filter(month %in% c("Aug","Sep","Oct","Nov","Dec")),
aes(x= month, y = tickets, color = ticket_type, size = 1.5))+
geom_text(aes(x = month, y = tickets, color = ticket_type, label = tickets), nudge_y = 20, size = 4,
data = ticket %>% filter(month %in% c("Aug","Sep","Oct","Nov","Dec"), ticket_type == "Received")) +
geom_text(aes(x = month, y = tickets, color = ticket_type, label = tickets), nudge_y = -20, size = 4,
data = ticket %>% filter(month %in% c("Aug","Sep","Oct","Nov","Dec"), ticket_type == "Processed")) +
#annotate("text", x = "Dec", y = 177, label = "Received", color = "#1F497D", hjust = 0, size = 4.5) +
# annotate("text", x = "Dec" , y = 140, label = "Processed", color ="#7F7F7F", hjust = 0, size = 4.5, fontface="bold") +
scale_colour_manual(values = cols) +
scale_y_continuous(expand = c(0,0),
limits = c(0,300),
n.breaks = 7) +
labs(title = "Ticket volume over time",
caption = "Data source: XYZ Dashboard, as of 12/31/2014 | A detailed analysis on tickets processed \nper person and time to resolve issues was undertaken to inform this request and can be provided.",
x = "2014",
y = "Number of tickets") +
coord_cartesian(clip = 'off') +
theme(plot.title = element_markdown(size=16),
plot.title.position = "plot",
plot.caption = element_text(hjust = 0),
plot.caption.position = "plot",
axis.text.y = element_text(size = 12),
axis.line.y = element_line(color = "#7F7F7F"),
axis.title.x= element_text(size = 12, hjust = 0, vjust = 0, color = "#6d6d6d"),
axis.text.x = element_text(size = 12),
axis.line.x = element_line(color = "#7F7F7F"),
axis.title.y = element_text(size = 12, hjust = 1 ,vjust = 2, color = "#6d6d6d"),
axis.ticks = element_line(color="#a9a9a9") ,
legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = unit(c(0.5,2.5,0.5,0.5),"cm"))
Figure 4.14 Data labels used sparingly help draw attention
ggsave("Figure 4.14 Data labels used sparingly help draw attention.png", height = 5, width = 8,units = "in",dpi = 300)Chapter five: think like a designer
grob_explanation <- grobTree(richtext_grob(
"<span style='background-color:white'><b>2 employees quit in May.</b> We nearly kept up with<br>
incoming bolume in the following two months, but fell<br>
behind with the increase in Aug and haven't been able<br>
to catch up since.</span>",
x=.375,
y = .90,
hjust=0, gp=gpar(col = "#6d6d6d", fontsize=11),
box_gp = gpar(col = "white", fill = "white"),
padding = margin(0,0,0,0,"in")))
label1 <- grobTree(richtext_grob(
"**Recieved**",
x= 1,
y = .62,
hjust = 0, gp=gpar(col = "#7F7F7F", fontsize = 12),
box_gp = gpar(col = "white", fill = "white"),
padding = margin(0,0,0,0,"in")))
label2 <- grobTree(richtext_grob(
"**Processed**",
x=1,
y = .48,
hjust=0, gp=gpar(col = "#1F497D", fontsize = 12),
box_gp = gpar(col = "white", fill = "white"),
padding = margin(0,0,0,0,"in")))cols <- c("Processed" = "#1F497D",
"Received" = "#7F7F7F")
ggplot(data= ticket) +
geom_line(aes(x= month, y = tickets, group = ticket_type, colour= ticket_type), size = 1.5) +
geom_point(data = ticket %>%
filter(month %in% c("Aug","Sep","Oct","Nov","Dec")),
aes(x= month, y = tickets, color = ticket_type, size = 1.5))+
geom_text(aes(x = month, y = tickets, color = ticket_type, label = tickets), nudge_y = 20, size = 4,
data = ticket %>% filter(month %in% c("Aug","Sep","Oct","Nov","Dec"), ticket_type == "Received")) +
geom_text(aes(x = month, y = tickets, color = ticket_type, label = tickets), nudge_y = -20, size = 4,
data = ticket %>% filter(month %in% c("Aug","Sep","Oct","Nov","Dec"), ticket_type == "Processed")) +
scale_colour_manual(values = cols) +
scale_y_continuous(expand = c(0,0),
limits = c(0,300),
n.breaks = 7) +
labs(title = "Ticket volume over time",
caption = "Data source: XYZ Dashboard, as of 12/31/2014 | A detailed analysis on tickets processed \nper person and time to resolve issues was undertaken to inform this request and can be provided.",
x = "2014",
y = "Number of tickets") +
coord_cartesian(clip = 'off') +
annotation_custom(grob_explanation) +
annotation_custom(label1) +
annotation_custom(label2) +
annotate("segment",
x = 5, xend = 5,
y = 0, yend = 230,
colour = "#7F7F7F") +
theme(plot.title = element_markdown(size=16),
plot.title.position = "plot",
plot.caption = element_text(hjust = 0),
plot.caption.position = "plot",
axis.text.y = element_text(size = 12),
axis.line.y = element_line(color = "#7F7F7F"),
axis.title.x= element_text(size = 12, hjust = 0, vjust = 0, color = "#6d6d6d"),
axis.text.x = element_text(size = 12),
axis.line.x = element_line(color = "#7F7F7F"),
axis.title.y = element_text(size = 12, hjust = 1 ,vjust = 2, color = "#6d6d6d"),
axis.ticks = element_line(color="#a9a9a9") ,
legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = unit(c(0.5,2.5,0.5,0.5),"cm"))
Figure 5.10 Add action title and annotation
ggsave("Figure 5.10 Add action title and annotation.png", height = 5, width = 8,units = "in",dpi = 300)marriage_wide <- read_csv("marriage.csv")##
## -- Column specification --------------------------------------------------------
## cols(
## education = col_character(),
## `2008` = col_double(),
## `2009` = col_double(),
## `2010` = col_double(),
## `2011` = col_double(),
## `2012` = col_double()
## )marriage_wide ## # A tibble: 4 x 6
## education `2008` `2009` `2010` `2011` `2012`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Less than high school 26.8 25 23 23.2 23.4
## 2 High school graduate 35.9 34 31 30.5 30.1
## 3 Some college 42.5 41 37 36.7 36.5
## 4 Bachelor's degree or more 61.5 61 59 55 56.7marriage <- marriage_wide %>%
pivot_longer(cols = !education,
names_to = "year",
values_to = "rate")
marriage$education<- factor(marriage$education,levels=c("Less than high school","High school graduate", "Some college","Bachelor's degree or more"))
marriage$year <- as.numeric(marriage$year)
marriage## # A tibble: 20 x 3
## education year rate
## <fct> <dbl> <dbl>
## 1 Less than high school 2008 26.8
## 2 Less than high school 2009 25
## 3 Less than high school 2010 23
## 4 Less than high school 2011 23.2
## 5 Less than high school 2012 23.4
## 6 High school graduate 2008 35.9
## 7 High school graduate 2009 34
## 8 High school graduate 2010 31
## 9 High school graduate 2011 30.5
## 10 High school graduate 2012 30.1
## 11 Some college 2008 42.5
## 12 Some college 2009 41
## 13 Some college 2010 37
## 14 Some college 2011 36.7
## 15 Some college 2012 36.5
## 16 Bachelor's degree or more 2008 61.5
## 17 Bachelor's degree or more 2009 61
## 18 Bachelor's degree or more 2010 59
## 19 Bachelor's degree or more 2011 55
## 20 Bachelor's degree or more 2012 56.7grob_title <- grobTree(textGrob("New marriage rate by education",
x=-.7, y=1.1, hjust=0,
gp=gpar(fontsize=16)))
grob_subtitle <- grobTree(textGrob("Number of newly married adults per 1000 marriage eligible adults",
x=-.7, y=1.03, hjust=0,
gp=gpar(col = "#76787B", fontsize=14)))
grob_caption <- grobTree(textGrob("Note: Marriage eligible includes the newly married plus those widowed,divorced\nor never married at interview\nSource: US Census\nAdapted from PEW RESEARCH CENTER",
x = -.7, y = -.2,
hjust = 0,
gp=gpar(col = "#76787B", fontsize=11)))
ggplot()+
geom_line(data = marriage,
aes(x = year, y = rate, group = education),
size= 2,
color = "#A6A6A6") +
geom_point(data= marriage %>%
filter(year == 2008 | year == 2012),
aes(x= year, y= rate),
color = "#A6A6A6",
size = 6) +
geom_line(data = marriage %>%
filter(education == "Bachelor's degree or more"),
aes(x = year, y = rate, group = education),
size= 2,
color = "#FF3403") +
geom_point(data= marriage %>%
filter(education == "Bachelor's degree or more" & (year == 2008 | year == 2012)),
aes(x= year, y= rate),
color = "#FF3403",
size = 6) +
scale_y_continuous(limits = c(0,70)) +
geom_text(data = filter(marriage, year== 2008),
aes(x= year,y = rate, label=rate),
nudge_x = -.5,
color ="#76787B",
size = 5) +
geom_text(data= filter(marriage, year== 2012),
aes(x= year,y = rate, label=rate),
nudge_x = .5,
color ="#76787B",
size = 5) +
geom_text(data = filter(marriage, year== 2008,education == "Bachelor's degree or more"),
aes(x= year,y = rate, label=rate),
nudge_x = -.5,
color ="#FF3403",
size = 5) +
geom_text(data= filter(marriage, year== 2012,education == "Bachelor's degree or more"),
aes(x= year,y = rate, label=rate),
nudge_x = .5,
color ="#FF3403",
size = 5) +
geom_text(data= filter(marriage, year == 2008),
aes(x= year,y = rate,label=education),
nudge_x = -1,
hjust = 1,
color ="#76787B",
size = 5) +
geom_text(data= filter(marriage, year == 2008,
education == "Bachelor's degree or more"),
aes(x= year,y = rate,label=education),
nudge_x = -1,
hjust = 1,
color ="#FF3403",
size = 5) +
annotation_custom(grob_title) +
annotation_custom(grob_subtitle) +
annotation_custom(grob_caption)+
coord_cartesian(clip = "off") +
theme(plot.subtitle = element_text(color = "#76787B"),
plot.title = element_text(hjust = -3),
plot.caption = element_text(size = 8, color = "#76787B", hjust = 0, margin = margin(15,0,0,0, "pt")),
axis.title.x = element_blank(),
axis.title.y = element_blank(),
axis.text.x = element_text(size = 12, color ="black"),
axis.text.y = element_blank(),
axis.ticks.x = element_line(color="#a9a9a9"),
axis.ticks.y = element_blank(),
axis.line.x = element_line(color="grey", size = 1),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
plot.margin = unit(c(2,1,3,7.5), "cm")) # margin(t = 2, r = 0, b = 0, l = 0, unit = "pt")
ggsave("Figure 5.4 Eliminate distractions.png", height = 6, width = 7,units = "in",dpi = 300)