-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathcalc_numbers_for_results.R
176 lines (156 loc) · 6.99 KB
/
calc_numbers_for_results.R
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
#summarize numbers for results
library(tidyverse)
library(lubridate)
setwd("C:/Users/alice.carter/git/ghg_patterns_nhc/")
dat <- read_csv("data/ghg_flux_complete_drivers_dataframe.csv")%>%
filter(!is.na(datetime),
site != "MC751")
dvs <- read_csv("data/ghg_filled_drivers_dataframe.csv")
# magnitudes ####
dat$site <- factor(dat$site, levels = c("NHC", "PM", "CBP", "WB", "WBP","UNHC"))
dat <- dat %>% mutate(across(ends_with('flux_ugld'), ~.*depth)) %>%
rename_with(ends_with("flux_ugld"),.fn = ~gsub("_ugld", "_mgm2d", .) )
dat %>% dplyr::select(ends_with(c('.obs','ugL', 'mgm2d', 'K600'))) %>%
summarize(across(everything(), .fns = list(mean = ~mean(.x, na.rm = T),
sd = ~sd(.x, na.rm = T),
min = ~min(.x, na.rm = T),
max = ~max(.x, na.rm = T)))) %>%
pivot_longer(cols = everything(), names_to = c('gas', 'stat'),
values_to = 'value',
names_pattern = '(^[A-Z,a-z,0-9,\\.,_]+)_([a-z]+$)') %>%
data.frame()
# anova ####
anova(lm(CO2.ugL ~ site, data = dat ))
anova(lm(CH4.ugL ~ site, data = dat ))
anova(lm(N2O.ugL ~ site, data = dat ))
anova(lm(DO.obs ~ site, data = dat ))
anova(lm(CO2.flux_mgm2d ~ site, data = dat ))
anova(lm(CH4.flux_mgm2d ~ site, data = dat ))
anova(lm(N2O.flux_mgm2d ~ site, data = dat ))
anova(lm(O2.flux_mgm2d ~ site, data = dat ))
# seasonal patterns
unique(dat$group)
dat %>% dplyr::select(c(group, DO.obs)) %>%
filter(group %in% as.Date(c('2019-11-11','2020-01-29', '2020-03-20'))) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CO2.ugL)) %>%
filter(group %in% as.Date(c('2019-11-11','2019-12-03',
'2019-12-12','2020-03-11'))) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CO2.ugL)) %>%
filter(group %in% as.Date(c('2019-12-03',
'2019-12-12'))) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CH4.ugL)) %>%
# filter(group %in% as.Date(c('2019-11-11','2019-12-03',
# '2019-12-12','2020-03-20'))) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CH4.ugL)) %>%
filter(group %in% as.Date(c('2019-12-03',
'2019-12-12','2020-01-05', '2020-01-29'))) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, N2O.ugL)) %>%
# filter(group %in% as.Date(c('2019-11-11','2019-12-03',
# '2019-12-12','2020-03-20'))) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
# fluxes ####
dat %>% dplyr::select(c(group, O2.flux_mgm2d)) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, O2.flux_mgm2d)) %>%
filter(group %in% as.Date(c('2019-11-11',
'2019-11-20'))) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CO2.flux_mgm2d)) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CO2.flux_mgm2d)) %>%
filter(group %in% as.Date(c('2019-11-11',
'2019-11-20',
'2019-11-26'))) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CH4.flux_mgm2d)) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, CH4.flux_mgm2d)) %>%
filter(group %in% as.Date(c('2019-11-11',
'2019-11-20'))) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
dat %>% dplyr::select(c(group, N2O.flux_mgm2d)) %>%
group_by(group) %>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T),
n = ~n()))
# site Characteristics####
dat %>%
select(site, depth) %>%
group_by(site) %>%
summarize(across(everything(), .fns = list(mean, sd)))
ins <- read_csv('data/fraction_of_instream_production_CO2_and_CH4CO2ratios.csv')
ss <- ins %>%
select(site, date, CO2_flux, NEP, instr) %>%
group_by(site) %>%
select( -date)%>%
summarize_all(.funs = list(mean = ~mean(., na.rm = T),
sd = ~sd(., na.rm = T)))
summary(ins)
summary(aov(instr ~CO2_flux, data = ins))
ins %>% select(site, date, CO2_flux, instr, NEP_CO2) %>%
# filter(CO2_flux>0) %>%
mutate(instr = ifelse(instr<0, 0, instr)) %>%
summary()
ins %>% select(site, date, CO2_flux, instr, NEP_CO2) %>%
filter(CO2_flux<0) %>%
mutate(instr = ifelse(instr>0, 0, instr)) %>%
summary()
ins %>% select(site, date, CO2_flux, instr, NEP_CO2) %>%
mutate(instr = case_when(instr < 0 ~ 0,
instr > 1 ~ 1,
TRUE ~ instr)) %>%
group_by(date) %>%
summarize(mean = mean(instr, na.rm = T),
median = median(instr, na.rm = T),
sd = sd(instr, na.rm=T))
ins %>% filter(CO2_flux > 0) %>%
select(site, date, CO2_flux, NEP_CO2) %>%
mutate(NEP_CO2 = case_when(NEP_CO2 <0 ~ 0,TRUE ~ NEP_CO2)) %>%
summarize(CO2 = sum(CO2_flux), NEP = sum(NEP_CO2))
filter(!is.na(datetime),
site != "MC751") %>%
# mutate(date = as.Date(group))%>%
select(datetime, date, site, habitat, distance_upstream_m, watertemp_C,
depth, GPP, ER, discharge, DO.obs, no3n_mgl, ends_with('ugld')) %>%
pivot_longer(ends_with("ugld"), names_to = "gas",
names_pattern ='([0-9A-Z]+).', values_to = "flux_ugld") %>%
left_join(gas, by = c("date",'datetime', "site", "gas")) %>%
mutate(gas = factor(gas, levels = c('CO2','O2', 'CH4', 'N2O')),
flux_mgm2d = flux_ugld * depth)%>%
arrange(date, distance_upstream_m)