-
Notifications
You must be signed in to change notification settings - Fork 23
/
05-addendum.Rmd
178 lines (144 loc) · 5.75 KB
/
05-addendum.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
---
title: "Lab 05: Addendum"
subtitle: "CS631"
author: "Alison Hill"
output:
html_document:
theme: flatly
toc: TRUE
toc_float: TRUE
toc_depth: 2
number_sections: TRUE
---
```{r setup, include = FALSE, cache = FALSE}
knitr::opts_chunk$set(error = TRUE, comment = NA, warning = FALSE, errors = FALSE, message = FALSE, tidy = FALSE, cache = FALSE)
```
# Packages
```{r}
library(tidyverse)
library(babynames)
# load hd data
hot_dogs_aff <- read_csv("http://bit.ly/cs631-hotdog-affiliated",
col_types = cols(
affiliated = col_factor(levels = NULL),
gender = col_factor(levels = NULL)
)) %>%
mutate(post_ifoce = year >= 1997) %>%
filter(year >= 1981 & gender == "male")
```
# Plot 1: Add
What is this code trying to accomplish?
```{r}
temp=hot_dogs_aff
for (i in 1:nrow(hot_dogs_aff)) {
# if the maximum num_eaten is equal to the num_eaten for the year AND it's not the same as the year before
if ((max(temp$num_eaten) == hot_dogs_aff$num_eaten[i]) && (max(temp$num_eaten) != hot_dogs_aff$num_eaten[i+1]) && (i<nrow(hot_dogs_aff))) {
hot_dogs_aff$record[i] = TRUE
temp = temp[-1,] # take the most recent year OUT of the running
} else if (i<nrow(hot_dogs_aff)) {
hot_dogs_aff$record[i] = FALSE
temp = temp[-1,]
}
}
label.df <- data.frame(year = hot_dogs_aff$year[hot_dogs_aff$record],
num_eaten = hot_dogs_aff$num_eaten[hot_dogs_aff$record]) # turn this into a label dataframe
```
# Tidyverse approach
The first thing we notice is that we don't have data about whether each year's winner is a record or not.
```{r}
hot_dogs <- read_csv("http://bit.ly/cs631-hotdog",
col_types = cols(
gender = col_factor(levels = NULL)
))
```
Since our data is nicely tidy, we can use `dplyr` window functions:
- First, we use base R's `cummax` to create a new variable that reflects the maximum HDB eaten cumulatively, that is, compared to all earlier years. For this reason, the `arrange(year)` here is critical.
- Next, we want to know if the `hdb_record` is actually a *new* record or not, compared to all previous years. We can use `case_when` to create a logical variable that is TRUE if the `hdb_record` for a given year is greater than the `hdb_record` from the year before (using `dplyr::lag`). If not, this variable is FALSE.
```{r}
hot_dogs_records <- hot_dogs %>%
filter(year >= 1980 & gender == 'male') %>%
arrange(year) %>%
mutate(hdb_record = cummax(num_eaten),
new_record = case_when(
hdb_record > lag(hdb_record) ~ TRUE,
TRUE ~ FALSE
)) %>%
filter(year >= 1981)
```
We'll also make our x-axis ticks again...
```{r}
years_to_label <- seq(from = 1981, to = 2017, by = 4)
years_to_label
hd_years <- hot_dogs_records %>%
distinct(year) %>%
mutate(year_lab = ifelse(year %in% years_to_label, year, ""))
```
```{r}
hdb_records <- ggplot(hot_dogs_records,
aes(x = year, y = num_eaten)) +
geom_col(aes(fill = new_record)) +
labs(x = "Year", y = "Hot Dogs and Buns Consumed") +
ggtitle("Nathan's Hot Dog Eating Contest Results, 1981-2017") +
scale_fill_manual(values = c('#284a29', '#629d62')) +
scale_y_continuous(expand = c(0, 0),
breaks = seq(0, 70, 10)) +
scale_x_continuous(expand = c(0, 0),
breaks = hd_years$year,
labels = hd_years$year_lab) +
coord_cartesian(xlim = c(1980, 2018), ylim = c(0, 80)) +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5),
axis.text = element_text(size = 12),
panel.background = element_blank(),
axis.line.x = element_line(color = "gray92",
size = 0.5),
axis.ticks = element_line(color = "gray92",
size = 0.5),
text = element_text(family = "Lato"),
legend.position = "bottom",
panel.grid.minor = element_blank())
hdb_records
```
# Plot 2
Goal is to observe popular first letter trends in `babynames`.
First filter/arrange data.
```{r}
# add column of first letters
baby_letters <- babynames %>%
mutate(first_letter = str_sub(name, 1, 1))
# add up proportion for each letter by year + sex
letter_by_year <- baby_letters %>%
count(year, sex, first_letter, wt = prop) %>%
rename(total_prop = nn)
# label most popular for each year + sex
letter_by_year <- letter_by_year %>%
group_by(sex, year) %>%
mutate(top_yearly = case_when(
total_prop == max(total_prop) ~ first_letter)) %>%
ungroup() %>%
mutate(top_latest = case_when(
year == max(year) ~ top_yearly
))
# make a data frame with just latest top letters
top_current <- letter_by_year %>%
filter(!is.na(top_latest)) %>%
rename(color_by = top_latest) %>%
select(sex, first_letter, color_by)
# now merge in
letter_by_year <- letter_by_year %>%
left_join(top_current) %>%
mutate(color_by = replace_na(color_by, "else"))
# set up my colors for males and females
my_colors <- c("#FF1493", "gray80", "#3399ff")
```
Plot it!
```{r}
ggplot(letter_by_year, aes(x = year, y = total_prop, color = color_by, group = first_letter)) +
geom_line() +
scale_color_manual(values = my_colors) +
facet_wrap(~sex)
```
```{r}
ColorM2 <- c(A="Gray80",B="gray80",C="gray80",D="gray80",E="gray80",F="gray80",G="gray80",H="gray80",I="gray80",J="Black",K="gray80",L="gray80",M="gray80",N="gray80",O="gray80",P="gray80",Q="gray80",R="gray80",S="gray80",T="gray80",U="gray80",V="gray80",W="gray80",X="gray80",Y="gray80",Z="gray80")
ColorF2 <- c(A="Black",B="gray80",C="gray80",D="gray80",E="gray80",F="gray80",G="gray80",H="gray80",I="gray80",J="gray80",K="gray80",L="gray80",M="gray80",N="gray80",O="gray80",P="gray80",Q="gray80",R="gray80",S="gray80",T="gray80",U="gray80",V="gray80",W="gray80",X="gray80",Y="gray80",Z="gray80")
```