-
Notifications
You must be signed in to change notification settings - Fork 0
/
daily.Rmd
161 lines (127 loc) · 6.03 KB
/
daily.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
---
output:
html_document:
code_folding: hide
---
```{r hydro, include=F}
knitr::opts_chunk$set(echo = T, message = F, warning = F, fig.path = 'figures/')
library(dataRetrieval)
library(rnoaa)
library(purrr)
library(tidyverse)
library(lubridate)
# These steps outline the process to generate a daily hydrologic input estimate for OTB, utilizing the methodologies develop in TBEP Tech Pub #03-16. Right now the process can only be done a year at a time, due to the NOAA/USGS web api limitations (as far as I can tell). Multiple years could probably be achieved using a function loop or other script.
# key for noaa data
mykey <- Sys.getenv("NOAA_KEY")
start <- "2020-01-01"
end <- "2020-12-31"
# get rainfall data at station
tia_rainfall <- ncdc(datasetid = "GHCND", stationid = "GHCND:USW00012842",
datatypeid = "PRCP", startdate = start, enddate = end,
limit = 500, add_units = TRUE, token = mykey)
# convert rain data to inches
tia_rain <- tia_rainfall$data %>%
mutate(daily_in = (value/254),
Date = as.Date(date))
# get hydrological data
bkr<- readNWISdv("02307359", "00060", start, end) %>%
renameNWISColumns() %>%
mutate(bkr_flow = (Flow*3.05119225))
otb_hydr <- left_join(tia_rain, bkr, by=c("Date")) %>%
select(Date, daily_in, bkr_flow) %>%
mutate(hyd_est = (154.22+(8.12*bkr_flow)+(6.73*daily_in))/365) %>%
drop_na(hyd_est)
```
```{r data_mash, include=F}
library(tbeptools)
library(patchwork)
library(ggbeeswarm)
library(xlsx)
library(runner)
library(ggpubr)
library(car)
library(multcompView)
library(lsmeans)
#Very draft data mash up and analyses.
pth <- 'D:/data/EPCHC_WQ/epchc.xlsx'
chldat <- read_importwq(pth, download_latest = F)
otb_hydr <- read.xlsx("OTB_Hydro_1985-2020.xlsx", sheetName = "data")
daily_chla <- chldat %>%
select(bay_segment, date = SampleTime, chla) %>%
dplyr::filter(bay_segment == !!bay_segment) %>%
mutate(date = as.Date(date)) %>%
group_by(bay_segment, date) %>%
summarise(chla = mean(chla, na.rm = T), .groups = 'drop') %>%
na.omit
daily_data <- left_join(otb_hydr, daily_chla, by='date')
daily_data2 <- daily_data %>%
mutate(mo = month(date),
year = year(date),
Period = ifelse(date<'2008-05-01','Pre-Pyro (<2008)','Post-Pyro (>2008)'),
Season = ifelse(mo >= 5 & mo <=9,'Summer (May-Sep)','All other months'),
running7 = sum_run(x = hyd_est, k = 7, idx = as.Date(date)),
running14 = sum_run(x = hyd_est, k = 14, idx = as.Date(date)),
running28 = sum_run(x = hyd_est, k = 28, idx = as.Date(date)),
running35 = sum_run(x = hyd_est, k = 35, idx = as.Date(date)),
running42 = sum_run(x = hyd_est, k = 42, idx = as.Date(date)),
running56 = sum_run(x = hyd_est, k = 56, idx = as.Date(date)),
running70 = sum_run(x = hyd_est, k = 70, idx = as.Date(date)),
running84 = sum_run(x = hyd_est, k = 84, idx = as.Date(date)),) %>%
filter(date>'1985-04-01') %>%
drop_na(chla)
plot(daily_data$hyd_est, daily_data$chla)
plot(daily_data2$running35, daily_data2$chla)
cor(daily_data2$running35, daily_data2$chla)
ggboxplot(daily_data2, x = "Period", y = "chla", color = "Season", ylab = "Mean Chlorophyl-a (ug/L)")
ggboxplot(daily_data2, x = "Period", y = "running35", color = "Season", ylab = "Cumulative 35-Day Hydro Input (million m3)")
ggline(daily_data2, x = "Period", y = "chla", color = "Season",
add = c("mean_se", "jitter"), ylab = "Mean Chlorophyl-a (ug/L)")
options(contrasts = c("contr.sum", "contr.poly"))
res.aov2 <- lm(chla ~ Period + Season + Period:Season, data = daily_data2)
Anova(res.aov2, type="III")
marginal = lsmeans(res.aov2, ~Period:Season)
CLD(marginal, alpha=0.05, Letters=letters, adjust="tukey")
ggline(daily_data2, x = "Period", y = "running35", color = "Season",
add = c("mean_se", "jitter"), ylab = "Cumulative 35-Day Hydro Input (million m3)")
options(contrasts = c("contr.sum", "contr.poly"))
res.aov3 <- lm(running35 ~ Period + Season + Period:Season, data = daily_data2)
Anova(res.aov3, type="III")
marginal2 = lsmeans(res.aov3, ~Period:Season)
CLD(marginal2, alpha=0.05, Letters=letters, adjust="tukey")
ggscatter(daily_data2, x = "running35", y = "chla", color = "Period", ylab = "Mean Chlorophyl-a (ug/L)", xlab = "Cumulative 35-Day Hydro Input (million m3)", add = "reg.line")+
stat_regline_equation(aes(label = paste(..eq.label.., ..rr.label.., sep = "~~~~"), color = Period)
)
# axis label
axlab <- expression("Mean Chlorophyll-a ("~ mu * "g\u00B7L"^-1 *")")
p3 <- ggplot(daily_data, aes(x=date, y=hyd_est)) +
geom_point(alpha=0) +
geom_hline(aes(yintercept = 0)) +
geom_linerange(aes(x=date, ymax=hyd_est, ymin=0)) +
scale_x_date(date_breaks = '12 month', date_labels = '%b-%Y',
limits = as.Date(c("1985-01-01", "2020-11-30")), expand = c(0,0)) +
scale_y_continuous(limits = c(0, 25), expand = c(0,0)) +
theme(
axis.title.x = element_blank(),
panel.background = element_rect(fill = '#ECECEC'),
panel.grid.minor=element_blank(),
panel.grid.major=element_blank(),
legend.position = 'top',
legend.background = element_rect(fill=NA),
legend.key = element_rect(fill = '#ECECEC'),
legend.title = element_blank(),
axis.text.x = element_text(angle = 45, size = 8, hjust = 1)
) +
labs(
y = "Hydrologic Load\n(mill m3)"
)
p4 <- p3+geom_line(data=daily_data[!is.na(daily_data$chla), ], aes(x=date, y=chla), size=1, color="green") +
scale_y_continuous(limits = c(0, 25),
sec.axis = sec_axis(~ . *2, name = axlab), expand = c(0,0))
p3
p4
#write.xlsx(otb_hydr,"2020.xlsx", sheetName = "data")
#file.names = list.files(pattern="xlsx$")
#df.list = lapply(file.names, read.xlsx, sheetIndex=1, header=TRUE)
#df = do.call(rbind, df.list)
#write.xlsx(df, "OTB_Hydro_1985-2020.xlsx", sheetName="data", row.names=FALSE)
```