Packages
library(pracma)
library(tidyverse)
library(readxl)
library(glmnet)
library(knitr)
library(kableExtra)
library(plotly)
library(paletteer)Import data
FN1.tbl <- read_excel("data/CropType2018_PixelCounting.xlsx",
sheet = "Feuil1", range = "E2:F8", col_names = FALSE,
col_types = c("text", "numeric"),
.name_repair = ~ c('crop', 'value')) %>%
mutate(crop = recode(crop,
'Mill' = 'Millet',
'Groundnut' = 'Groundnuts',
'Coton' = 'Cotton'))
FN2.tbl <- read_excel("data/CropType2018_ConfusionMatrix.xlsx",
sheet = "Matrice_Regroupement 1",
range = "B2:I9",
.name_repair = ~ if_else(.x == '', 'crop', .x)) %>%
mutate(crop = recode(crop,
'Mill' = 'Millet',
'Groundnut' = 'Groundnuts',
'Coton' = 'Cotton')) %>%
rename(Cotton = Coton, Groundnuts = Groundnut)Sample confusion matrix
FN2.tbl %>% kbl(caption = "Sample confusion matrix") %>%
kable_styling(bootstrap_options =
c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(1, bold = TRUE)| crop | Maize | Other crops | Groundnuts | Cotton | Rice | Sorghum | Millet |
|---|---|---|---|---|---|---|---|
| Maize | 9713 | 954 | 29 | 2094 | 144 | 20 | 602 |
| Other crops | 2125 | 2448 | 95 | 2598 | 35 | 78 | 297 |
| Groundnuts | 441 | 85 | 419 | 464 | 19 | 37 | 41 |
| Cotton | 2370 | 541 | 114 | 12770 | 88 | 121 | 255 |
| Rice | 514 | 21 | 2 | 327 | 887 | 23 | 0 |
| Sorghum | 531 | 133 | 32 | 584 | 12 | 888 | 335 |
| Millet | 668 | 27 | 4 | 426 | 14 | 83 | 3510 |
Image classification vector
FN1.tbl %>% kbl(caption = "R vector") %>%
kable_styling(bootstrap_options =
c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(1, bold = TRUE)| crop | value |
|---|---|
| Maize | 99454021 |
| Other crops | 5373340 |
| Groundnuts | 651230 |
| Cotton | 102803268 |
| Rice | 9654264 |
| Sorghum | 10911297 |
| Millet | 68759277 |
R vector and sample confusion matrix
R_vector <- FN1.tbl %>%
rename(R = value) %>%
mutate(crop = if_else(crop %in% c('Other crops', 'Groundnuts', 'Rice', 'Sorghum'), 'Other crops', crop)) %>%
group_by(crop) %>%
summarise(R = sum(R), .groups = "drop") %>%
filter(crop != 'Other crops') %>%
column_to_rownames(var = "crop") %>%
as.matrix()
a_matrix <- FN2.tbl %>%
mutate(crop = if_else(crop %in% c('Other crops', 'Groundnuts', 'Rice', 'Sorghum'), 'Other crops', crop)) %>%
group_by(crop) %>%
summarise_all(sum) %>%
mutate(`Other crops` = `Other crops` + Groundnuts + Rice + Sorghum) %>%
select(crop, Cotton, Maize, Millet) %>%
filter(crop != 'Other crops') %>%
column_to_rownames(var = "crop") %>%
as.matrix() R_vector %>%
as.data.frame() %>%
rownames_to_column(var = "crop") %>%
mutate(R = format(R, nsmall = 0, big.mark = ",", digits = 10)) %>%
kable(caption = "R vector", align = "lr") %>%
kable_styling(bootstrap_options =
c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12)| crop | R |
|---|---|
| Cotton | 102,803,268 |
| Maize | 99,454,021 |
| Millet | 68,759,277 |
a_matrix %>%
as.data.frame() %>%
rownames_to_column(var = "crop") %>%
kable(caption = "'a' matrix") %>%
kable_styling(bootstrap_options =
c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(1, bold = TRUE)| crop | Cotton | Maize | Millet |
|---|---|---|---|
| Cotton | 12770 | 2370 | 255 |
| Maize | 2094 | 9713 | 602 |
| Millet | 426 | 668 | 3510 |
Function to generate artifitial population
gen_U_star <- function(a_matrix, size){
sample_pi <-
expand_grid(
c = colnames(a_matrix),
g = rownames(a_matrix)) %>%
mutate(n = c(a_matrix),
pi = n/sum(n),
Code = paste0(c, ' - ', g))
U_star <- sample_pi %>%
sample_n(size = size, replace = TRUE, weight = pi) %>%
select(c, g, pi)
return(U_star)
}Get a artifitial population and associate R vector
# Population Size
Size = 1000000
U_0 <- gen_U_star(a_matrix, size = Size)
R_U_0 <- U_0 %>%
count(c) %>%
arrange(match(c, colnames(a_matrix))) %>%
column_to_rownames(var = 'c') %>%
as.matrix() U_0 %>% head()## # A tibble: 6 × 3
## c g pi
## <chr> <chr> <dbl>
## 1 Cotton Cotton 0.394
## 2 Cotton Cotton 0.394
## 3 Cotton Cotton 0.394
## 4 Millet Millet 0.108
## 5 Cotton Cotton 0.394
## 6 Cotton Cotton 0.394
Get a artifitial population for bootstrap sampling
U_star <- gen_U_star(a_matrix, size = Size)Function to get a sample from artifitial population
get_a_sample <- function(U_star, N_0, order = NULL){
a_sample <- U_star %>%
sample_n(N_0) %>%
count(c, g) %>%
pivot_wider(names_from = 'c', values_from = n, values_fill = 0) %>%
column_to_rownames(var = 'g') %>%
as.matrix()
if (is.null(order)) return(a_sample)
else return(a_sample[order, order])
}Function to get estimates from sample confution matrix from artifitial population
get_estimates <- function(a_matrix, R_U_0){
e_g_dado_c <- a_matrix %*% solve(diag(colSums(a_matrix)))
e_c_dado_g <- t(a_matrix) %*% solve(diag(rowSums(a_matrix)))
inverse_e_c_dado_g <- solve(e_c_dado_g)
rownames(inverse_e_c_dado_g) <- rownames(e_c_dado_g)
direct <- (e_g_dado_c %*% R_U_0) %>%
as_tibble(rownames = 'crop') %>%
mutate(estimator = 'direct')
inverse <- (inverse_e_c_dado_g %*% R_U_0) %>%
as_tibble(rownames = 'crop') %>%
mutate(estimator = 'inverse')
return(bind_rows(direct, inverse))
}Function to get bootstrap replicas
get_bootstrap <- function(B, U_star, N_0, R_U_0, order = NULL) {
1:B %>%
map(~ get_a_sample(U_star, N_0, order)) %>%
map_dfr(~ get_estimates(.x, R_U_0)) %>%
mutate(replica = ceiling(row_number()/6))
}Generate 1000 bootstrap replicas
set.seed(11235)
N_0 <- sum(a_matrix)
result <- get_bootstrap(1000, U_star, N_0, R_U_0, order = colnames(a_matrix))Plot result
result %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75) +
facet_wrap(~ crop, scales = 'free') +
theme(legend.position="bottom") + labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`)Bootstrap summary
result %>% group_by(crop, estimator) %>%
summarise(Mean = mean(n),
Variance = var(n),
`Standard Deviation` = sd(n),
CV = `Standard Deviation`/Mean,
.groups = 'drop') %>%
rename(Crop = crop, Estimator = estimator) %>%
mutate(Mean = format(round(Mean), nsmall = 0, big.mark = ","),
Variance = format(round(Variance), nsmall = 0, big.mark = ","),
`Standard Deviation` = format(round(`Standard Deviation`), nsmall = 0, big.mark = ","),
CV = format(round(CV, 4), nsmall = 2, big.mark = ",")) %>%
kable(caption = "Direct and Inverse Estimators Bootstrap Results (1000 rounds)", align = "lcrrrr") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(1, bold = TRUE) | Crop | Estimator | Mean | Variance | Standard Deviation | CV |
|---|---|---|---|---|---|
| Cotton | direct | 475,115 | 3,943,709 | 1,986 | 0.0042 |
| Cotton | inverse | 476,093 | 9,296,184 | 3,049 | 0.0064 |
| Maize | direct | 382,685 | 4,306,957 | 2,075 | 0.0054 |
| Maize | inverse | 381,801 | 11,091,144 | 3,330 | 0.0087 |
| Millet | direct | 142,200 | 1,506,982 | 1,228 | 0.0086 |
| Millet | inverse | 142,106 | 2,841,263 | 1,686 | 0.0119 |
Other plots
result %>% filter(crop == 'Maize') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Maize")result %>% filter(crop == 'Millet') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Millet")result %>% filter(crop == 'Cotton') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Cotton")result %>% filter(crop == 'Cotton') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density), color = estimator),
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
scale_color_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Cotton")result %>% filter(crop == 'Maize') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density), color = estimator),
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
scale_color_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Maize")result %>% filter(crop == 'Millet') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density), color = estimator),
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
scale_color_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Millet")result %>%
ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density), color = estimator),
alpha = .5,
bins = 30,
position = 'identity') +
geom_density(aes(x = n/1000, color = estimator), size = .75, position = 'identity') +
facet_wrap(~ crop, scales = 'free') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
scale_color_paletteer_d(`"ggthemes::wsj_red_green"`)Jacques’ Matrix
jacques_tibble <- read_excel("data/Simdata.xlsx",
sheet = "Sheet1",
range = "B3:G8",
.name_repair = ~ if_else(.x == '', 'crop', .x))
jacques_matrix <- jacques_tibble %>%
column_to_rownames(var = "crop") %>%
as.matrix() jacques_matrix %>%
as.data.frame() %>%
rownames_to_column(var = "crop") %>%
kable(caption = "Jacques' matrix") %>%
kable_styling(bootstrap_options =
c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(1, bold = TRUE)| crop | Wheat | Rapeseed | Corn | Sugarbeet | Others |
|---|---|---|---|---|---|
| Wheat | 0.200 | 0.020 | 0.005 | 0.005 | 0.020 |
| Rapeseed | 0.010 | 0.030 | 0.000 | 0.000 | 0.010 |
| Corn | 0.001 | 0.010 | 0.080 | 0.005 | 0.004 |
| Sugarbeet | 0.005 | 0.015 | 0.040 | 0.120 | 0.020 |
| Others | 0.100 | 0.020 | 0.010 | 0.030 | 0.240 |
\(T\) and \(V\) vectors
R_vector <- jacques_matrix %>%
{ matrix(colSums(.), ncol = 1, dimnames = list(colnames(.), 'value')) * Size } %>%
t()
T_vector <- jacques_matrix %>%
{ matrix(rowSums(.), ncol = 1, dimnames = list(colnames(.), 'value')) * Size }
Reference <-
bind_rows(
T_vector %>% as_tibble(rownames = "crop") %>% mutate(References = "T"),
R_vector %>% t() %>% as_tibble(rownames = "crop") %>% mutate(References = "R")
) %>%
mutate(crop = factor(crop, levels = colnames(jacques_matrix), ordered = TRUE))jacques_tibble %>%
mutate_if(is.numeric, function(x) 1000*x) %>%
bind_rows(as_tibble(R_vector/1000) %>% mutate(crop = 'R')) %>%
bind_cols(as_tibble(T_vector/1000) %>% rename(T = value) %>%
bind_rows(tibble(T = 1000))) %>%
kable(caption = "Jacques' confusion sample matrix") %>%
kable_styling(bootstrap_options =
c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(c(1,7), bold = TRUE) %>%
row_spec(6, bold = TRUE)| crop | Wheat | Rapeseed | Corn | Sugarbeet | Others | T |
|---|---|---|---|---|---|---|
| Wheat | 200 | 20 | 5 | 5 | 20 | 250 |
| Rapeseed | 10 | 30 | 0 | 0 | 10 | 50 |
| Corn | 1 | 10 | 80 | 5 | 4 | 100 |
| Sugarbeet | 5 | 15 | 40 | 120 | 20 | 200 |
| Others | 100 | 20 | 10 | 30 | 240 | 400 |
| R | 316 | 95 | 135 | 160 | 294 | 1000 |
Get a artifitial population and associate R vector
# Population Size
Size = 1000000
U_0 <- gen_U_star(jacques_matrix, size = Size)
R_U_0 <- U_0 %>%
count(c) %>%
arrange(match(c, colnames(jacques_matrix))) %>%
column_to_rownames(var = 'c') %>%
as.matrix() U_0 %>% head()## # A tibble: 6 × 3
## c g pi
## <chr> <chr> <dbl>
## 1 Rapeseed Sugarbeet 0.015
## 2 Wheat Wheat 0.2
## 3 Corn Corn 0.08
## 4 Others Others 0.24
## 5 Corn Sugarbeet 0.04
## 6 Wheat Others 0.1
Get a artifitial population for bootstrap sampling
U_star <- gen_U_star(jacques_matrix, size = Size)Generate 1000 bootstrap replicas
set.seed(112358)
N_0 <- 1000
result <- get_bootstrap(1000, U_star, N_0, R_U_0, order = colnames(jacques_matrix))Plot result
Palette <- palettes_d_names %>%
filter(length == 3) %>%
mutate(code = paste0(package, "::", palette)) %>%
pull(code) %>%
.[7] #3 5
result %>%
mutate(crop = factor(crop, levels = colnames(jacques_matrix), ordered = TRUE)) %>%
ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
facet_wrap(~ crop, scales = 'free', ncol = 2) +
theme(legend.position="bottom") + labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
geom_vline(aes(xintercept = value/1000, color = References), size = 1, data = Reference) +
scale_color_paletteer_d(Palette)Bootstrap summary
table <- result %>% group_by(crop, estimator) %>%
summarise(Mean = mean(n),
Variance = var(n),
`Standard Deviation` = sd(n),
CV = `Standard Deviation`/Mean,
.groups = 'drop') %>%
mutate(crop = factor(crop, levels = colnames(jacques_matrix), ordered = TRUE)) %>%
left_join(Reference %>% pivot_wider(names_from = References), by = "crop") %>%
mutate(`T Bias` = `T` - Mean,
`R Bias` = `R` - Mean) %>%
rename(Crop = crop, Estimator = estimator) %>%
mutate(Mean = format(round(Mean), nsmall = 0, big.mark = ","),
Variance = format(round(Variance), nsmall = 0, big.mark = ","),
`Standard Deviation` = format(round(`Standard Deviation`), nsmall = 0, big.mark = ","),
CV = format(round(CV, 4), nsmall = 2, big.mark = ","),
`T` = format(round(`T`), nsmall = 0, big.mark = ","),
`T Bias` = format(round(`T Bias`), nsmall = 0, big.mark = ","),
`R` = format(round(`R`), nsmall = 0, big.mark = ","),
`R Bias` = format(round(`R Bias`), nsmall = 0, big.mark = ","))
table %>%
kable(caption = "Direct and Inverse Estimators Bootstrap Results (1000 rounds)", align = "lcrrrr") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, font_size = 12) %>%
column_spec(1, bold = TRUE) %>%
column_spec(9, color = if_else(str_detect(table$`T Bias`, "-"), 'red', 'black')) %>%
column_spec(10, color = if_else(str_detect(table$`R Bias`, "-"), 'red', 'black')) | Crop | Estimator | Mean | Variance | Standard Deviation | CV | T | R | T Bias | R Bias |
|---|---|---|---|---|---|---|---|---|---|
| Corn | direct | 99,732 | 53,116,043 | 7,288 | 0.0731 | 100,000 | 135,000 | 268 | 35,268 |
| Corn | inverse | 99,058 | 159,367,831 | 12,624 | 0.1274 | 100,000 | 135,000 | 942 | 35,942 |
| Others | direct | 399,778 | 167,847,636 | 12,956 | 0.0324 | 400,000 | 294,000 | 222 | -105,778 |
| Others | inverse | 396,422 | 602,911,322 | 24,554 | 0.0619 | 400,000 | 294,000 | 3,578 | -102,422 |
| Rapeseed | direct | 50,288 | 40,733,170 | 6,382 | 0.1269 | 50,000 | 95,000 | -288 | 44,712 |
| Rapeseed | inverse | 52,218 | 262,466,182 | 16,201 | 0.3103 | 50,000 | 95,000 | -2,218 | 42,782 |
| Sugarbeet | direct | 200,513 | 104,372,156 | 10,216 | 0.0510 | 200,000 | 160,000 | -513 | -40,513 |
| Sugarbeet | inverse | 201,257 | 303,354,316 | 17,417 | 0.0865 | 200,000 | 160,000 | -1,257 | -41,257 |
| Wheat | direct | 249,689 | 120,334,207 | 10,970 | 0.0439 | 250,000 | 316,000 | 311 | 66,311 |
| Wheat | inverse | 251,045 | 436,308,560 | 20,888 | 0.0832 | 250,000 | 316,000 | -1,045 | 64,955 |
Other plots
result %>% filter(crop == 'Wheat') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Wheat") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Wheat')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Rapeseed') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Rapeseed") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Rapeseed')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Corn') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Corn") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Corn')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Sugarbeet') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Sugarbeet") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Sugarbeet')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Others') %>% ggplot() +
geom_density(aes(x = n/1000, fill = estimator), alpha = .75, position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Others") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Others')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Wheat') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density)), color = 'gray',
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Reference') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Wheat") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Wheat')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Rapeseed') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density)), color = 'gray',
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Reference') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Rapeseed") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Rapeseed')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Corn') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density)), color = 'gray',
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Reference') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Corn") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Corn')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Sugarbeet') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density)), color = 'gray',
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Reference') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Sugarbeet") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Sugarbeet')) +
scale_color_paletteer_d(Palette)result %>% filter(crop == 'Others') %>% ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density)), color = 'gray',
alpha = .75,
bins = 30,
position = 'identity') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Reference') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
ggtitle("Crop: Others") +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference %>% filter(crop == 'Others')) +
scale_color_paletteer_d(Palette)result %>%
ggplot() +
geom_histogram(aes(x = n/1000, fill = estimator, y=stat(density)),
alpha = .5,
bins = 30,
position = 'identity') +
geom_density(aes(x = n/1000), size = .75, position = 'identity') +
facet_wrap(~ crop, scales = 'free') +
theme(legend.position="bottom") +
labs(x = 'Estimates', y = 'Density', fill = 'Estimator', color = 'Estimator') +
scale_fill_paletteer_d(`"ggthemes::wsj_red_green"`) +
geom_vline(aes(xintercept = value/1000, color = References),
size = 1, data = Reference) +
scale_color_paletteer_d(Palette)