-
Notifications
You must be signed in to change notification settings - Fork 2
/
02_data-vis.Rmd
267 lines (196 loc) · 8.27 KB
/
02_data-vis.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
---
title: "Data Visualization"
output: html_notebook
---
This week we'll cover a few packages for visualizing our data:
* [`ggplot2`](https://ggplot2.tidyverse.org/), our main package for static data visualization with the tidyverse
* [`timetk`](https://business-science.github.io/timetk/index.html), a package built by Matt Dancho for working with time series data
* [`plotly`](https://github.com/ropensci/plotly), an interactive visualization builder that also integrates nicely with ggplot.
```{r setup, message = FALSE, warning = FALSE}
library(tidyverse)
library(timetk)
library(plotly)
library(readxl)
library(janitor)
library(lubridate)
knitr::opts_chunk$set(message = FALSE, warning = FALSE, comment = NA)
```
Let's load our HPI dataset, wrangle it, and pivot it into long format.
```{r}
hpi <- read_excel("HPI_PO_monthly_hist.xls", skip = 3)
hpi_wrangled <- hpi %>%
clean_names() %>%
slice(-1) %>% # remove empty row
rename(date = month) %>%
select(date, ends_with("_sa")) %>% # only keep seasonally adj. data
# separate() from tidyr package to split date into separate columns for day/month/year
separate(date, into = c("year", "month", "day"), sep = '-', convert = TRUE, remove = FALSE) %>%
# unite() from tidyr to join columns
unite(yr_mon, year, month, sep = "/", remove = FALSE) %>%
mutate_if(is.numeric, round, digits = 2) %>% # round all numeric columns to 2 digits
# add labels with case_when()
mutate(season = case_when(between(month, 3, 5) ~ "spring",
between(month, 6, 8) ~ "summer",
between(month, 9, 11) ~ "fall",
# between(month, 12, 2) ~ "winter" == won't work because there's no numbers between 12 and 2
TRUE ~ "winter")) %>%
select(date, yr_mon, year, month, day, season, everything()) %>% # reorder columns
# arrange() from dplyr to sort rows
arrange(date)
hpi_tidy <-
hpi_wrangled %>%
select(date, contains("north"), contains("south")) %>%
# pivot_longer makes data long, or tidy
pivot_longer(-date, names_to = "division", values_to = "hpi") %>%
group_by(division)
hpi_tidy
```
# `ggplot2`
And now let's create a basic `ggplot`.
```{r}
ggplot(hpi_tidy, aes(x = date, y = hpi, color = division)) +
geom_line()
```
The `ggplot2` package uses some unique syntax (the "grammar of graphics") that allows us to create highly customizable static graphics. This grammar can be a bit hard to grasp, so don't worry if it takes a while to "click".
I think about ggplot like this:
* We always start by calling `ggplot()` to create our plot object. This is (usually!) where we will specify our data and *aesthetic mappings*, or how our variables should map onto features of the plot like axes, colored groupings, etc.
* Then we add *geoms* to our plot. This is the step that will actually display our data on the graph. We will always have at least one of these, and sometimes multiple.
* Finally, we can change the appearance of our plot by adding things like *themes* and changing titles and captions.
Let's dissect the code above to understand each step.
Wait, why a `+` instead of `%>%`? You can think of ggplots in layers. At each step, we're adding a new layer, like we're painting on a canvas. This is different than the pipe, which is for passing an object along to a new function.
## Faceting
Another thing we can "add" to our ggplots is a faceting layer. Facets divide a plot into subplots based on one of our variables. For example:
```{r}
ggplot(hpi_tidy, aes(x = date, y = hpi, color = division)) +
geom_line() +
facet_wrap(~division)
```
## Scatterplot
There are many kinds of geoms we can add. For example, a scatterplot uses `geom_point()`.
```{r}
hpi_pct <-
hpi_tidy %>%
mutate(pct_change = (hpi / lag(hpi)) - 1,
pct_change_12_mons = (hpi / lag(hpi, 12)) - 1) %>%
na.omit()
hpi_pct %>%
ggplot(aes(x = pct_change_12_mons, y = pct_change, color = division)) +
geom_point() + #alpha = .5
facet_wrap(~division, ncol = 4) +
labs(x = "% change (1 yr.)", y = "% change (1 mo.)") +
theme(legend.position = "none",
axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5),
plot.title = element_text(hjust = 0.5))
```
## Scatterplot with trend line
We can also add multiple geoms to a `ggplot` object, e.g. adding a trend line to our scatterplots:
```{r}
hpi_pct %>%
ggplot(aes(x = pct_change_12_mons, y = pct_change, color = division)) +
geom_point() + #alpha = .5
geom_smooth(method = "lm", se = TRUE, color = "purple") +
facet_wrap(~division, ncol = 4) +
labs(x = "% change (1 mo.)", y = "% change (1 yr.)") +
theme(legend.position = "none",
axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5),
plot.title = element_text(hjust = 0.5))
```
## Histogram
There are lots of ways to customize the look and feel of your plots:
```{r}
hpi_pct %>%
ggplot(aes(x = pct_change)) +
geom_histogram(fill = "darkblue", color = "darkred", bins = 50) +
facet_wrap(~division) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5)) +
theme_minimal()
```
## Density
```{r}
hpi_pct %>%
ggplot(aes(x = pct_change)) +
geom_density(fill = "darkblue", color = "darkred", bins = 50) +
facet_wrap(~division) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5)) +
theme_minimal()
```
## Histogram and Density
```{r}
hpi_pct %>%
ggplot(aes(x = pct_change)) +
geom_histogram(fill = "darkblue", color = "darkred", bins = 20) +
geom_density(color = "red") +
facet_wrap(~division) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
```
## Shading for recession
We can even combine datasets on the same plot. Let's create a geom to shade the background of a plot during recession periods.
```{r}
# First, create our recessions tibble with tribble()
recessions <-
tribble(
~Peak, ~Trough,
"1948-11-01", "1949-10-01",
"1953-07-01", "1954-05-01",
"1957-08-01", "1958-04-01",
"1960-04-01", "1961-02-01",
"1969-12-01", "1970-11-01",
"1973-11-01", "1975-03-01",
"1980-01-01", "1980-07-01",
"1981-07-01", "1982-11-01",
"1990-07-01", "1991-03-01",
"2001-03-01", "2001-11-01",
"2007-12-01", "2009-06-01",
"2020-02-01", "2020-05-01"
) %>%
mutate(Peak = ymd(Peak),
Trough = ymd(Trough))
recession_shade <-
geom_rect(data = recessions,
inherit.aes = F,
aes(xmin = Peak,
xmax = Trough,
ymin = -Inf,
ymax = +Inf),
fill = 'pink',
alpha = 0.5)
hpi_pct %>%
ggplot(aes(x = ymd(date), y = pct_change, color = division)) +
recession_shade +
geom_line() +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90, hjust = 1),
plot.title = element_text(hjust = 0.5),
plot.subtitle = element_text(hjust = 0.5),
plot.caption = element_text(hjust=0)) +
ylab("") +
xlab("Percent change, monthly") +
ggtitle("Housing Price Appreciation",
subtitle = "by US Census Division") +
labs(caption = "data source: FHFA") +
scale_x_date(limits = c(as.Date(min(hpi_pct$date)), as.Date(max(hpi_pct$date))))
```
# `timetk` for time series data
The [`timetk`](https://business-science.github.io/timetk/index.html) package includes a bunch of functions that make working with time series data super easy. This includes functions for easily creating great looking plots of time series data:
```{r}
hpi_pct %>%
ungroup() %>%
plot_time_series(date, pct_change, .color_var = division, .smooth = FALSE, .interactive = FALSE)
```
## Anomaly diagnostics with `timetk`
`timetk` also includes functions for automatic anomaly detection:
```{r}
hpi_pct %>%
filter(division == "south_atlantic_sa") %>%
ungroup() %>%
plot_anomaly_diagnostics(date, pct_change, .alpha = .05)
```
# Plotly and `ggplotly()`
`timetk`'s interactive plots rely on [plotly](https://plotly.com/r/), a library for building interactive JavaScript visualizations. Plotly is supported in several different languages (including R) and has its own syntax.
Importantly, the `plotly` R package includes a function called `ggplotly()` that (you guessed it!) turns ggplots into plotly charts.
```{r}
hpi_plot <- ggplot(hpi_tidy, aes(x = date, y = hpi, color = division)) +
geom_line()
hpi_plot %>%
ggplotly()
```