-
Notifications
You must be signed in to change notification settings - Fork 0
/
Lab4.qmd
213 lines (165 loc) · 4.54 KB
/
Lab4.qmd
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
---
title: "Lab 4"
author: "Lianyan Wang"
format:
html:
embed-resources: true
---
```{r}
#1 Read in the data
if (!file.exists("met_all.gz"))
download.file(
url = "https://raw.githubusercontent.com/USCbiostats/data-science-data/master/02_met/met_all.gz",
destfile = "met_all.gz",
method = "libcurl",
timeout = 60
)
met <- data.table::fread("met_all.gz")
#2 Prepare Data
met <- met[met$temp > -17][elev == 9999.0, elev := NA]
summary(met$temp)
library(data.table)
met[,ymd := as.Date(paste(year, month, day, sep = '-'))]
met[, table(week(ymd))]
met_new<- met[week(ymd) == 31]
met_new
met_avg <- met[,.(
temp = mean(temp,na.rm=TRUE),
rh = mean(rh,na.rm=TRUE),
wind.sp = mean(wind.sp,na.rm=TRUE),
vis.dist = mean(vis.dist,na.rm=TRUE),
dew.point = mean(dew.point,na.rm=TRUE),
lat = mean(lat),
lon = mean(lon),
elev = mean(elev,na.rm=TRUE)
), by=c("USAFID", "day")]
library(dplyr)
met_avg <- met_avg %>%
mutate(region = case_when(
lon < -98 & lat > 39.71 ~ "NW",
lon < -98 & lat <= 39.71 ~ "SW",
lon >= -98 & lat > 39.71 ~ "NE",
lon >= -98 & lat <= 39.71 ~ "SE",
TRUE ~ NA_character_
))
met_avg <- met_avg %>%
mutate(elev = as.numeric(elev))
met_avg[, elev := cut(
x = elev,
breaks = c(0, 1000, 2000, 3000, Inf),
labels = c("low", "medium", "high", "very high"),
right = FALSE
)]
library(ggplot2)
met_avg <- met_avg %>%
mutate(region = ifelse(lon < -98.00 & lat > 39.71, "NW",
ifelse(lon < -98.00 & lat <= 39.71, "SW",
ifelse(lon >= -98.00 & lat > 39.71, "NE", "SE"))))
#3 Wind speed and dew point
met_avg <- met_avg %>%
filter(!is.na(region))
ggplot(data = met_avg) +
geom_violin(mapping = aes(x = 1, y = wind.sp, color = region)) +
facet_wrap(~ region, nrow = 1)
#4 Examine the association between dew point and wind speed by region
ggplot(data = met_avg, aes(x = dew.point, y = wind.sp, color = region)) +
geom_jitter(width = 0.2, height = 0.2, na.rn = TRUE) +
stat_smooth(method = "lm", se = FALSE, formula = y ~ x, aes(group = region)) +
scale_color_brewer(palette = "Set1") +
labs(
x = "Dew Point",
y = "Wind Speed",
title = "Association of Dew pt and Wind sp "
)+
theme_classic()
#5 Create barplots of the weather stations by elevation category colored by region
ggplot(data = met_avg, aes(x = elev, fill = region)) +
geom_bar(position = "dodge", na.rm = TRUE) +
scale_fill_brewer(palette = "Set1") +
labs(
x = "Elev",
y = "Weather Stations",
title = "Weather stations by elev"
)+
theme_classic()
#6 Examine mean dew point and wind speed by region with standard deviation error bars
met_avg <- na.omit(met_avg)
ggplot(met_avg, aes(x = region)) +
stat_summary(
aes(y = dew.point),
fun.data = mean_sdl,
geom = "errorbar",
position = position_dodge(width = 0.8),
na.rm = TRUE,
width = 0.2,
color = "blue"
) +
stat_summary(
aes(y = wind.sp),
fun.data = mean_sdl,
geom = "errorbar",
position = position_dodge(width = 0.8),
na.rm = TRUE,
width = 0.2,
color = "red"
) +
labs(
x = "Region",
y = "Values",
title = "Mean and Standard Deviation (SD) Error Bars for Dew Point and Wind Speed by Region"
) +
theme_minimal()
#7 Make a map showing the spatial trend in relative humidity in the US
met_avg <- met_avg[!is.na(met_avg$rh),]
library(colorspace)
library(scales)
breaks <- c(0, 20, 40, 60, 80, 100)
labels <- c("0%", "20%", "40%", "60%", "80%", "100%")
color_palette <- colorRampPalette(c("lightblue", "darkblue"))(length(breaks) - 1)
library(leaflet)
map <- leaflet() %>%
addTiles() %>%
addHeatmap(
data = met_avg,
lat = ~lat,
lng = ~lon,
radius = 10,
blur = 15,
colors = color_palette,
options = heatmapOptions(
minOpacity = 0.2,
maxZoom = 10
)
) %>%
addMarkers(
data = met_avg[order(-met_avg$rh)[1:10], ],
label = ~paste("Place:", place_name, "<br> RH:", rh, "%"),
icon = ~awesomeIcons(
icon = "star",
markerColor = "red",
iconColor = "white",
library = "fa"
)
) %>%
addLegend(
title = "Relative Humidity",
colors = color_palette,
values = breaks,
opacity = 0.7,
position = "bottomright",
labels = labels
)
map
#8 Use a ggplot extension
install.packages("gganimate")
ggplot(met_avg, aes(x = elev, y = wind.sp)) +
geom_boxplot() +
transition_states(
elev,
transition_length = 2,
state_length = 1
) +
enter_fade() +
exit_shrink() +
ease_aes('sine-in-out')
```