-
Notifications
You must be signed in to change notification settings - Fork 0
/
TidyTuesday2.Rmd
321 lines (259 loc) · 14.5 KB
/
TidyTuesday2.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
---
title: "Tidy Tuesday"
author: "Simon Leech"
date: "`r format(Sys.time(), '%B %d, %Y')`"
output:
html_document:
keep_md: true # so can display on GitHub
toc: true # table of content true
toc_float : true
toc_depth: 3 # upto three depths of headings (specified by #, ## and ###)
number_sections: true ## if you want number sections at each table header
theme: united # many options for theme, this one is my favorite.
highlight: tango # specifies the syntax highlighting style
---
# Tidy Tuesday
* This RMarkdown file will contain examples of data cleaning and data wrangling using [Tidy Tuesday Datasets](https://github.com/rfordatascience/tidytuesday) and Instructions.
* The file will be formatted into headers, with the Dates of the Tidy Tuesday and html links to the code stores.
* The file may not follow Tidyverse nomenclature, and may use other methods- but this is simply for personal development!
```{r Libraries, message=FALSE, warning=FALSE}
library(tidyverse)
library(dplyr)
library(ggplot2)
library(data.table)
library(readr)
library(scales)
library(ggrepel)
```
# 16/02/2021- [Dubois Challenge](https://github.com/rfordatascience/tidytuesday/tree/master/data/2021/2021-02-16)
## Challenge 01- Comparative Increase of White and Black Population in Georgia
### Initial read in and understanding
```{r 01 Import and initial understanding}
# Get the Data
georgia_pop <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/georgia_pop.csv')
head(georgia_pop) # check first 5 columns
colnames(data)
colnames(georgia_pop)[2] <- "Black" #rename offensive Colored to Black
```
### Plot
```{r 01 plot}
# Pivot data so Black and White in a column together
georgia_pop_gather <- gather(georgia_pop, Black, White, -Year)
colnames(georgia_pop_gather) <- c("Year", "Race", "Percent")
ggplot(data=georgia_pop_gather, aes(x=Year, y=Percent)) +
# Set linetype to differ by Race
geom_line(aes(linetype=Race)) +
# Flip the coordinates to plot year on y
coord_flip() +
# set scale to 100
scale_y_continuous(breaks = seq(0, 100, by=5), limits=c(0,100)) +
# Set scale to sit right at end of plot box
scale_y_reverse(expand=c(0,0)) +
# Set scale to 1890
scale_x_continuous(breaks = seq(1790, 1890, by=10), limits=c(1790,1890)) +
# Set title and labels
ggtitle("COMPARATIVE INCREASE OF WHITE AND BLACK \n POPULATION OF GEORGIA") +
xlab(NULL) + ylab("PERCENTS") +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5), # center the title
plot.background = element_rect(fill = '#EAD4BC', colour = '#ECDED1'), # change the plot background colour to beige
panel.background = element_rect(fill = '#EAD4BC', colour = '#ECDED1')) + # change the whole background colour to beige
theme(panel.grid.major = element_line("#C93211"), # change plot lines to orange
panel.grid.minor = element_line("#C93211"), # change plot lines to organge
panel.border = element_rect(color = "#2B2B2B", fill = NA)) + # set border around the plot
theme(legend.position="bottom", # move legend to the bottom
legend.title = element_blank()) + # remove legend title
theme(plot.margin = unit(c(0.1,5,0.1,5),"cm")) # set plot margins to ensure fit
```
Comparison to what we were trying to achieve!
## Challenge 02- Conjugal Condition
### Initial read in and understanding
```{r 02 Import and initial understanding}
# Get the Data
conjugal <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/conjugal.csv')
head(conjugal) # check first 5 columns
colnames(conjugal)
```
### Plot
```{r 02 plot}
# Pivot data so Black and White in a column together
conjugal_gather <- gather(conjugal, Single, Married,-Population, -Age)
conjugal_gather
colnames(conjugal_gather) <- c("Population", "Age", "Condition", "Percent")
conjugal_gather$Condition <- toupper(conjugal_gather$Condition)
conjugal_gather$Population <- toupper(conjugal_gather$Population)
conjugal_gather$Population[conjugal_gather$Population=="NEGROES"] <- "BLACK/\nAFRICAN-\nAMERICAN"
conjugal_gather$Age <- toupper(conjugal_gather$Age)
pal <- c("#4C6655", "#F2B937", "#D34150") # set colours
# To do this just remove, position=dodge from the geom_bar argument
ggplot(data =conjugal_gather,
# Set x to Percentage, y to Population and fill using Condition of Relationship
aes(x = Percent, y = Population, fill = Condition, color=Condition)) +
# Use filled bars, with a border of grey around them
geom_bar(position="fill", stat = 'identity', width = 0.55, color = "grey50", size = 0.2) +
# Set title, x label and y label
ggtitle("CONJUGAL CONDITION") + ylab(NULL) + xlab(NULL)+
# facet the graph on the age, using just one column, switch=both moves facet to other axis
facet_wrap(vars(Age), ncol=1, switch="both") +
# Set the percentages to show in the centre of each condition box, at size of 2
geom_text(aes(y = Population, x = Percent, label = paste0(Percent, "%")), size = 2, color="black",position = position_fill(vjust = 0.5)) +
# Set the colours to the pal to enable similarity to original
scale_fill_manual(values = pal) +
# Set theme to minimal
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5), # center the title
plot.background = element_rect(fill = '#EAD4BC', colour = NA), # change the plot background colour to beige
panel.background = element_rect(fill = '#EAD4BC', colour = NA)) + # change the whole background colour to beige
theme(panel.grid.major = element_line(NA), # change plot lines to orange
panel.grid.minor = element_line(NA), # change plot lines to organge
panel.border = element_rect(color = NA, fill = NA)) + # set border around the plot
theme(legend.position="top", # move legend to the bottom
legend.title = element_blank()) + # remove legend title
theme(plot.margin = unit(c(0.1,5,0.1,5),"cm")) + # set plot margins to ensure fit
theme(axis.text.x=element_blank()) + # turn off the x axis
theme(strip.placement="outside") # reposition facets to outside of population labels
```
Comparison to what we were trying to achieve!
## Challenge 03- Occupations of Black/ African-American and Whites in Georgia
### Initial read in and understanding
```{r 03 Import and initial understanding}
# Get the Data
occupation <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/occupation.csv')
head(occupation) # check first 5 columns
colnames(occupation)
```
### Plot
* Cannot work out how to do the Pie Chart in the same way as original, but never done pie charts in ggplot anyway- so gave them a go!
```{r 03 plot}
occupation$Group <- toupper(occupation$Group)
occupation$Occupation <- toupper(occupation$Occupation)
occupation$Group[occupation$Group=="NEGROES"] <- "BLACK/\nAFRICAN-\nAMERICAN"
pal <- c("#b8243c", "#f2c50a", "#5a6796", "#d5c8b7", "#ab927a") # set colours
ggplot(data =occupation,
# Set x to Percentage, y to Population and fill using Condition of Relationship
aes(x ="", y = Percentage, fill = Occupation, group=Group)) +
# Use filled bars, with a border of grey around them
geom_bar(stat = 'identity', width = 1) +
coord_polar("y", start=0) +
# Set title, x label and y label
ggtitle("OCCUPATION OF BLACK/AFRICAN-AMERICAN AND WHITES IN GEORGIA") + ylab(NULL) + xlab(NULL) +
# Set the percentages to show in the centre of each occupation pie section, at size of 2
geom_text(aes(label = paste0(Percentage, "%")), size = 2, color="black",position = position_stack(vjust = 0.5)) + facet_wrap(~Group) +
# Set the colours to the pal to enable similarity to original
scale_fill_manual(values = pal) +
# Set theme to minimal
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5), # center the title
plot.background = element_rect(fill = '#EAD4BC', colour = NA), # change the plot background colour to beige
panel.background = element_rect(fill = '#EAD4BC', colour = NA)) + # change the whole background colour to beige
theme(panel.grid.major = element_line(NA), # change plot lines to NA
panel.grid.minor = element_line(NA), # change plot lines to NA
panel.border = element_rect(color = NA, fill = NA)) + # set border around the plot
theme(legend.position="bottom", # move legend to the bottom
legend.title = element_blank(), # remove legend title
legend.text = element_text(size=5.5)) +
theme(plot.margin = unit(c(0.1,5,0.1,5),"cm")) + # set plot margins to ensure fit
guides(fill=guide_legend(nrow=2, byrow=TRUE)) + # legend in two rows
theme(axis.text.x=element_blank()) + # turn off the x axis
theme(strip.placement="outside") # reposition facets to outside of population labels
```
Comparison to what we were trying to achieve!
## Challenge 04- Proportion of Freeman and Slaves Among American Black Population
### Initial read in and understanding
```{r 04 Import and initial understanding}
# Get the Data
freed <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/freed_slaves.csv')
head(freed) # check first 5 columns
colnames(freed)
```
### Plot
```{r 04 plot, fig.height=10, fig.width=7}
# sort data not adding to 100 always
freed$sum <- freed$Slave + freed$Free
# 1800 adds to 99%?
freed$Slave[2] <- freed$Slave[2] + 0.5
freed$Free[2] <- freed$Free[2] + 0.5
freed <- subset(freed, select=c(Year, Slave, Free))
ggplot(data=freed,
# Set Y to Slave, x to Year)
aes(x=Year, y=Slave)) +
# Use geom_area for this
geom_area() +
# set x and y limits
scale_y_continuous(limits=c(0,100), expand=c(0,0)) +
scale_x_continuous(limits=c(NA,NA), n.breaks=9, expand=c(0,0), position="top")+
coord_cartesian(clip="off") +
labs(
title = "PROPORTION OF FREEMEN AND SLAVES\n AMONG AMERICAN BLACK POPULATION.",
subtitle = "\nDONE BY ATLANTA UNIVERSITY.\n"
) +
# Adding annotation to the plot
geom_text(aes(Year, Slave, label= paste0(100-Slave, "%")), vjust=-1, size=4, fontface="bold") +
# add labels
annotate("text", x=1830, y=95, label= "FREE", size=8, color="black", fontface="bold") +
annotate("text", x=1830, y=60, label="SLAVES", size=8, color="#e0d5c8", fontface="bold") +
# Set the colours to the pal to enable similarity to original
scale_fill_manual(values = c("Dark Green", "Black")) +
# Set theme to minimal
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5), # center the title
plot.subtitle = element_text(hjust=0.5), #center the subtitle
plot.background = element_rect(fill = '#EAD4BC', colour = NA), # change the plot background colour to beige
panel.background = element_rect(fill = '#3c7753')) + # change the whole background colour to beige
theme(panel.grid.major.x = element_line("black"), # change plot lines to NA
panel.grid.major.y = element_line(NA),
panel.grid.minor = element_line(NA)) +
theme(legend.position="none", # remove legend
legend.title = element_blank(), # remove legend title
legend.text = element_text(size=5.5)) +
theme(plot.margin = unit(c(0.5,0.5,0.5,0.5),"cm"), # set plot margins to ensure fit
axis.text.y = element_blank(), axis.title.y = element_blank(), axis.title.x= element_blank(), axis.text.x.top=element_text(vjust=1, size=14, face="bold")) # turn off axis y and axis y and x labels
```
Comparison to what we were trying to achieve!
## Challenge 05- Income and Expenditure of 150 Black Families in Atlanta, GA, USA
### Initial read in and understanding
```{r 05 Import and initial understanding}
# Get the Data
income <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-16/income.csv')
head(income) # check first 5 columns
colnames(income)
```
### Plot
```{r 05 plot, fig.height=10, fig.width=7}
income_gather <- gather(income, key="Class_Spending", value="Percent", -Class, -"Actual Average")
income_gather$Class <- fct_relevel(income_gather$Class, "Over $1000", "$750-1000", "$500-750", "$400-500", "$300-400", "$200-300", "$100-200")
income_gather$Class_Spending <- fct_relevel(income_gather$Class_Spending, "Other", "Tax", "Clothes", "Food", "Rent")
# Create cumulative value for each Class to enable lines between
income_gather <- income_gather %>% group_by(Class) %>% mutate(Cumulative_Income=cumsum(Percent)) %>% ungroup()
ggplot(data =income_gather,
# Set x to Percentage, y to Class and fill using Class_Spending
aes(x = Percent, y = Class, fill = Class_Spending, color=Class_Spending)) +
# Use filled bars, with a border of grey around them
geom_bar(position="fill", stat = 'identity', color="grey") +
# Labels
labs(title="INCOME AND EXPENDITURE \nOF 150 BLACKFAMILIES IN ATLANTA, GA., U.S.A.", x="", y="") +
# Set axis to 100%
scale_fill_manual(values=c("grey", "lightblue", "pink", "purple", "black")) +
scale_x_continuous(labels=scales::percent_format(scale=100)) +
geom_text_repel(aes((Percent/100), Class, label= paste0((Percent), "%")), position="stack", size=4, fontface="bold", color="white", vjust=0.5, hjust=0, box.padding=unit(0.3, "lines")) +
# Set theme to minimal
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5), # center the title
plot.subtitle = element_text(hjust=0.5), #center the subtitle
plot.background = element_rect(fill = '#EAD4BC', colour = NA), # change the plot background colour to beige
panel.background = element_rect(fill = '#EAD4BC')) + # change the whole background colour to beige
#theme(panel.grid.major.x = element_line("black"), # change plot lines to NA
# panel.grid.major.y = element_line(NA),
# panel.grid.minor = element_line(NA)) +
#theme(legend.position="none", # remove legend
# legend.title = element_blank(), # remove legend title
# legend.text = element_text(size=5.5)) +
theme(plot.margin = unit(c(0.5,0.5,0.5,0.5),"cm"), # set plot margins to ensure fit
axis.text.x=element_blank(), axis.title.x= element_blank(), axis.text.x.top=element_text(vjust=1, size=14, face="bold")) # turn off axis y and axis y and x labels
```
Comparison to what we were trying to achieve!
