-
Notifications
You must be signed in to change notification settings - Fork 0
/
final_qc.R
424 lines (308 loc) · 17 KB
/
final_qc.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
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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
## Checking the results
# Loading packages
library(dplyr)
## Loading data
stand_fct <- readRDS(here::here("data", "FAO-fish-standardised_v1.0.0.RDS"))
harmo_fct <- readRDS(here::here("data", "FAO-fish-harmonised_v1.0.0.RDS"))
# Checking Beta-Carotene sources
grep("CARTBEQmcg_std imputed", harmo_fct$comments, value = TRUE)
length(harmo_fct$fdc_id[(grep("Impausible value of CARTBEQmcg_std", harmo_fct$comments))])/nrow(harmo_fct)*100
length(harmo_fct$fdc_id[(grep("CARTBEQmcg_std calculated", harmo_fct$comments))])
# Checking SOP outside the range
#No. of values
# Checkig for NA
sum(is.na(harmo_fct$SOP_std))
#Checking values outside of range
#acepatable (95-105) & prefered (97-103) (FAO)
upper <- 103
lower <- 97
sum(harmo_fct$SOP_std<lower | harmo_fct$SOP_std > upper)
hist(as.numeric(harmo_fct$SOP_std), main = "Sum of Proximate")
abline(v = lower, col = 2, lwd=3, lty =2)
abline(v = upper, col = 2, lwd=3, lty =2)
# Original 122 columns
fao_fish <- read.csv(here::here("data", "FISHERIES-GlobalNCT_ForSharing_Feb2022.csv"))
#fao_fish <- readxl::read_excel(here::here("data", "FAO_fish.xlsx"))
source(here::here("Summary_Table_Production.R"))
dim(fao_fish)
names(fao_fish)
names(fao_fish[, c(1:122)])
fao_fish[c(1:2), c(1:122)]
fao_fish[2, c(13:30)]
which(is.na(fao_fish[1, c(1:122)]))
which(fao_fish[1, c(1:122)] == "")
fao_fish[1, c(1:30)]
n <- which(fao_fish[1, c(1:122)] == "")
which(fao_fish[2, c(1:122)] == "Quality rating for food match")
fao_fish[1, n]
fao_fish[1, c(1:122)[!c(1:122) %in% n]]
names(fao_fish)[1:6] <- fao_fish[2, c(1:6)]
names(fao_fish)[(7:122)[!c(7:122) %in% n]] <- fao_fish[1, c(7:122)[!c(7:122) %in% n]]
names(fao_fish)
fao_fish <- fao_fish %>% select(1, Source, fcd_id_old, fdc_id, `Food description`, `Scientific name`,
36, `3-alpha code`) %>%
filter(fdc_id != "")
names(fao_fish) <- gsub(" ", ".", fao_fish[2,])
# Checking duplicates - in original file
which(fao_fish[2, c(1:122)] == "fdc_id")
fao_fish[3:nrow(fao_fish), c(1, 33)] %>%
group_by(`ï..GLOBAL.TABLE.OF.NUTRIENT.VALUES`) %>% count(X.30) %>%
filter(n>1) %>%
arrange(desc(n))
fao_fish <- readxl::read_excel(here::here("data", "FAO_fish.xlsx"))
fao_fish$`FIBTG(g) (standardized)`
unique(fao_fish$Source)
unique(subset(fao_fish, Source == "IN17", select =c(`FIBTG(g) (standardized)`)))
fao_fish$ICS_FAOSTAT <- ifelse(is.na(fao_fish$`ICS FAOSTAT SUA Current Code`),
fao_fish$`ICS FAOSTAT SUA Future Code`,
fao_fish$`ICS FAOSTAT SUA Current Code` )
fao_fish$fdc_id <- ifelse(!is.na(fao_fish$fcd_id_old),
fao_fish$fcd_id_old,
fao_fish$fdc_id )
# Getting only mean values
which(is.na(fao_fish$`ICS FAOSTAT SUA title`))
mean_loc <- which(is.na(fao_fish$`Food description`))
fao_cat <- fao_fish[mean_loc,]
## Getting summary rows (FISHERIES in R)
summary.df <- subset(recalculated_results_table,
str_detect(ICS.FAOSTAT.SUA.Current.Code, "SUMMARY ROW"))
subset(summary.df, !is.na(comment),
select = c(ICS.FAOSTAT.SUA.Current.Code, CHOAVLDFg_std, comment))
# MEAN CHOALVDF (standardise) ----
#Checking non-calculated values
subset(summary.df, is.na(CHOAVLDFg_std),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, CHOAVLDFg_std, ALCg))
#Checking negative values
subset(summary.df, CHOAVLDFg_std <0,
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, CHOAVLDFg_std))
subset(fao_cat, `CHOAVLDF(g)_standardized` < 0,
select = c( `CHOAVLDF(g)_standardized`))
hist(fao_cat$`CHOAVLDF(g)_standardized`,
xlab = "Carbohydrates by difference",
main = "Fisheries Global NCT (Feb, 2022)")
hist(summary.df$CHOAVLDFg_std,
xlab = "Carbohydrates by difference",
main = "Fisheries Global NCT (Oct, 2022)")
mean_proxi$ICS_FAOSTAT <- as.factor(mean_proxi$ICS_FAOSTAT)
fao_cat$ICS_FAOSTAT <- as.factor(fao_cat$ICS_FAOSTAT)
left_join(mean_proxi, fao_cat %>% select(ICS_FAOSTAT,
`CHOAVLDF(g)_standardized`,
`ICS FAOSTAT SUA title`) ) %>% arrange(ICS_FAOSTAT)
left_join(mean_proxi, fao_cat %>% select(ICS_FAOSTAT,
`CHOAVLDF(g)_standardized`,
`ICS FAOSTAT SUA title`) ) %>%
mutate(`CHOAVLDF(g)_standardized` = ifelse(`CHOAVLDF(g)_standardized` <0,
0, `CHOAVLDF(g)_standardized`),
CHOAVLDFg_std = ifelse(CHOAVLDFg_std <0,
0, CHOAVLDFg_std ),
CHO_diff = CHOAVLDFg_std-`CHOAVLDF(g)_standardized`) %>%
arrange(desc(CHO_diff))
subset(fao_fish, ICS_FAOSTAT == "1533") %>% count(Source)
#MEAN ASH
hist(fao_cat$`ASH(g)`,
xlab = "ASH(g)",
main = "Fisheries Global NCT (FAO)")
fao_cat$`ICS FAOSTAT SUA title`[fao_cat$`ASH(g)` > 3]
#MEAN FIBGT
fao_cat$`FIBTG(g) (standardized)` <- as.numeric(fao_cat$`FIBTG(g) (standardized)`)
hist(as.numeric(fao_cat$`FIBTG(g) (standardized)`),
xlab = "Fibre (g/100g)",
main = "Fisheries Global NCT (FAO)")
fao_cat$`ICS FAOSTAT SUA title`[as.numeric(fao_cat$`FIBTG(g) (standardized)`) > 0]
subset(fao_cat, as.numeric(`FIBTG(g) (standardized)`) > 0,
select = c(`ICS FAOSTAT SUA title`,
round(`FIBTG(g) (standardized)`, 2)))
#MEAN ALC
hist(as.numeric(fao_cat$`ALC(g)`),
xlab = "Alcohol (g/100g)",
main = "Fisheries Global NCT (FAO)")
fao_cat$`ICS FAOSTAT SUA title`[as.numeric(fao_cat$`ALC(g)`) == 0]
# MEAN SOP (own calculations) ----
#Checking non-calculated values
subset(summary.df, is.na(SOP_std),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, SOP_std))
#Checking values outside of range (95-105) & (98-102)
subset(summary.df, SOP_std <98 | SOP_std >102,
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, SOP_std))
hist(as.numeric(summary.df$SOP_std), main = "Sum of Proximate")
abline(v = 95, col = 2, lwd=3, lty =2)
abline(v = 105, col = 2, lwd=3, lty =2)
#Checking EP
hist(as.numeric(fao_cat$`Edible factor in FCT`),
xlab = "Alcohol (g/100g)",
main = "Fisheries Global NCT (FAO)")
fao_cat$`Edible factor in FCT`
fao_cat$`Edible coefficient to be used`
subset(fao_fish, ICS_FAOSTAT == "1545", select = c(fdc_id, Source, `WATER(g)`)) %>%
left_join(subset(fao_fish_fct, ICS.FAOSTAT.SUA.Current.Code == "1545",
select = c(fdc_id, WATERg, source_fct))) %>%
mutate(water_diff =WATERg- `WATER(g)`) %>% filter(water_diff>0)
#MEAN THIA
#Differences - 1573 (bc we added values i.e., raw as per agreed w/ F.G)
#1541 - we couldn't find but no NO21 values, and seemed the same (n=154)
hist(as.numeric(fao_cat$`THIA(mg)_standardized`),
xlab = "Thiamine (mg/100g)",
main = "Fisheries Global NCT (FAO)")
match("THIA(mg)_standardized", names(fao_cat))
fao_cat$`ICS FAOSTAT SUA Current Code` <- as.character(fao_cat$`ICS FAOSTAT SUA Current Code`)
subset(results_table, str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"),
select = c(ICS.FAOSTAT.SUA.Current.Code,
ics_faostat_sua_english_description, THIAmg_std)) %>%
mutate(ICS.FAOSTAT.SUA.Current.Code = str_extract(ICS.FAOSTAT.SUA.Current.Code,
"[:digit:]{4,6}")) %>%
left_join(., fao_cat[c(1:95), c(1,76)], by =
c("ICS.FAOSTAT.SUA.Current.Code" = "ICS FAOSTAT SUA Current Code")) %>%
mutate(THIAmg_diff = as.numeric(THIAmg_std) - as.numeric(`THIA(mg)_standardized`)) %>%
mutate_at(c(3:5), as.numeric) %>% mutate_if(is.numeric, round,
digits = 2) %>%
filter(THIAmg_diff >0) %>% arrange(desc(THIAmg_diff))
fao_fish_fct$ICS.FAOSTAT.SUA.Current.Code[fao_fish_fct$fdc_id == "10366"]
fao_fish_fct$THIAmg[fao_fish_fct$fdc_id == "04.100"]
results_table$THIAmg_std[results_table$ICS.FAOSTAT.SUA.Current.Code == "1541"]
results_table$THIAHCLmg[results_table$ICS.FAOSTAT.SUA.Current.Code == "1590"]
#MEAN RETOL ----
#Need to keep checking, odd calculations and imputations...
#Histogram of retinol values from Fisheries version Feb., 2022.
hist(as.numeric(fao_cat$`RETOL(µg)`),
xlab = "Retinol (mcg/100g)",
main = "Fisheries Global NCT (FAO), Feb., 2022 \r\n (Only mean values of 95 categories)")
#Histogram of retinol values from Fisheries version Oct., 2022.
hist(as.numeric(recalculated_results_table$RETOLmcg),
xlab = "Retinol (mcg/100g)",
main = "Fisheries Global NCT (FAO), Oct., 2022")
#Max value of retinol in Feb., fisheries dataset
max(as.numeric(fao_fish$`RETOL(µg)`), na.rm = T)
#Checking high values
subset(recalculated_results_table, as.numeric(RETOLmcg) >33000)
#Checking that no mean values in our dataset are below 0
subset(recalculated_results_table, as.numeric(RETOLmcg) <0 &
!str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"))
#Identifying the retinol column in Feb., 2022 dataset
n <- match("RETOL(µg)", names(fao_cat))
#Aligning data class for joining datasets
fao_cat$`ICS FAOSTAT SUA Current Code` <- as.character(fao_cat$`ICS FAOSTAT SUA Current Code`)
#Identifying max. difference between retinol values by category
retol_max <- subset(recalculated_results_table, str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, RETOLmcg)) %>%
mutate(ICS.FAOSTAT.SUA.Current.Code = str_extract(ICS.FAOSTAT.SUA.Current.Code,
"[:digit:]{4,6}")) %>%
left_join(., fao_cat[c(1:95), c(1,n)], by =
c("ICS.FAOSTAT.SUA.Current.Code" = "ICS FAOSTAT SUA Current Code")) %>%
mutate(diff = as.numeric(RETOLmcg) - as.numeric(`RETOL(µg)`)) %>%
mutate_at(c(3:5), as.numeric) %>% mutate_if(is.numeric, round,
digits = 2) %>%
filter(diff >0) %>% pull(diff) %>% max(.)
#Identifying max. negative difference between retinol values by category
retol_min <- subset(recalculated_results_table, str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, RETOLmcg)) %>%
mutate(ICS.FAOSTAT.SUA.Current.Code = str_extract(ICS.FAOSTAT.SUA.Current.Code,
"[:digit:]{4,6}")) %>%
left_join(., fao_cat[c(1:95), c(1,n)], by =
c("ICS.FAOSTAT.SUA.Current.Code" = "ICS FAOSTAT SUA Current Code")) %>%
mutate(diff = as.numeric(RETOLmcg) - as.numeric(`RETOL(µg)`)) %>%
mutate_at(c(3:5), as.numeric) %>% mutate_if(is.numeric, round,
digits = 2) %>%
filter(diff <0) %>% pull(diff) %>% min(.)
#Checking categories w/ higher RETOL (negative) and lower RETOL (positive) values
#in the Feb/, 2022 vs Oct., 2022 dataset.
subset(recalculated_results_table, str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, RETOLmcg)) %>%
mutate(ICS.FAOSTAT.SUA.Current.Code = str_extract(ICS.FAOSTAT.SUA.Current.Code,
"[:digit:]{4,6}")) %>%
left_join(., fao_cat[c(1:95), c(1,n)], by =
c("ICS.FAOSTAT.SUA.Current.Code" = "ICS FAOSTAT SUA Current Code")) %>%
mutate(diff = as.numeric(RETOLmcg) - as.numeric(`RETOL(µg)`)) %>%
mutate_at(c(3:5), as.numeric) %>% mutate_if(is.numeric, round,
digits = 2) %>%
filter(diff <0) %>% arrange(desc(diff))
#Checking actual fisheries entries to identify differences in unique entries
subset(recalculated_results_table, ICS.FAOSTAT.SUA.Current.Code == "1510") %>%
count(source_fct)
#Evaluating influence of NO21 values into mean category values
subset(recalculated_results_table, ICS.FAOSTAT.SUA.Current.Code == "1519" &
source_fct == "NO21") %>%
pull(RETOLmcg) %>% mean(.)
#Evaluting values (important for imputed values) differences between datasets
recalculated_results_table$RETOLmcg[recalculated_results_table$ICS.FAOSTAT.SUA.Current.Code == "1510"]
fao_fish_fct$RETOLmcg[fao_fish_fct$ICS.FAOSTAT.SUA.Current.Code == "1510"]
fao_fish$`RETOL(µg)`[fao_fish$`ICS FAOSTAT SUA Current Code` == "1541"]
#Evaluting influence of the values (important for imputed values) to the mean
mean(recalculated_results_table$RETOLmcg[recalculated_results_table$ICS.FAOSTAT.SUA.Current.Code == "1541"])
mean(as.numeric(fao_fish_fct$RETOLmcg[fao_fish_fct$ICS.FAOSTAT.SUA.Current.Code == "1541"]
))
mean(as.numeric(fao_fish$`RETOL(µg)`[fao_fish$`ICS FAOSTAT SUA Current Code` == "1541"][c(1:154)]), na.rm = T)
fao_fish_fct$VITA_RAEmcg[fao_fish_fct$fdc_id == "35014"]
results_table$THIAmg_std[results_table$ICS.FAOSTAT.SUA.Current.Code == "1541"]
results_table$fdc_id[results_table$ICS.FAOSTAT.SUA.Current.Code == "1519"]
results_table$source_fct[results_table$ICS.FAOSTAT.SUA.Current.Code == "1505"]
fao_fish_fct$food_desc[fao_fish_fct$fdc_id == "04.286"]
fao_fish_fct$RETOLmcg[str_detect(fao_fish_fct$food_desc, "Saithe")]
fao_fish_fct$fdc_id[str_detect(fao_fish_fct$food_desc, "Saithe")]
# MEAN CARTBEQ (standardise) ----
hist(as.numeric(fao_cat$`CARTBEQ(mcg) (standardized)`),
xlab = "Beta-Carotene eq. (mcg/100g)",
main = "Fisheries Global NCT (FAO), Feb., 2022 \r\n (Only mean values of 95 categories)")
#Checking that no mean values in our dataset are below 0
subset(recalculated_results_table, as.numeric(CARTBEQmcg_std) <0 &
!str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"))
#Identifying the beta-carotene eq. column in Feb., 2022 dataset
n <- match("CARTBEQ(mcg) (standardized)", names(fao_cat))
fao_cat$`ICS FAOSTAT SUA Current Code` <- as.character(fao_cat$`ICS FAOSTAT SUA Current Code`)
subset(recalculated_results_table, str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, CARTBEQmcg_std, CARTBEQmcg,
RETOLmcg, VITA_RAEmcg)) %>%
mutate(ICS.FAOSTAT.SUA.Current.Code = str_extract(ICS.FAOSTAT.SUA.Current.Code,
"[:digit:]{4,6}")) %>%
mutate(CARTBEQ_fromVITA_RAE = ifelse(!is.na(VITA_RAEmcg) & !is.na(RETOLmcg), (VITA_RAEmcg - RETOLmcg)*12, NA)) %>%
left_join(., fao_cat[c(1:95), c(1,n)], by =
c("ICS.FAOSTAT.SUA.Current.Code" = "ICS FAOSTAT SUA Current Code")) %>%
mutate(CARTBEQ_diff = as.numeric(CARTBEQmcg_std) - as.numeric(`CARTBEQ(mcg) (standardized)`)) %>%
mutate_at(c(3:5), as.numeric) %>% mutate_if(is.numeric, round,
digits = 2) %>%
filter(CARTBEQ_diff <0) %>% arrange(desc(CARTBEQ_diff))
#Checking actual fisheries entries to identify differences in unique entries
subset(recalculated_results_table, ICS.FAOSTAT.SUA.Current.Code == "1549") %>%
count(source_fct)
#fao_fish_fct$ICS.FAOSTAT.SUA.Current.Code[fao_fish_fct$fdc_id == "1549"]
fao_fish_fct$CARTBEQmcg[fao_fish_fct$ICS.FAOSTAT.SUA.Current.Code == "15360"]
recalculated_results_table$CARTBEQmcg_std[recalculated_results_table$ICS.FAOSTAT.SUA.Current.Code == "15360"]
fao_fish$`CARTBEQ(mcg) (standardized)`[fao_fish$`ICS FAOSTAT SUA Current Code` == "15360"]
# MEAN VITA_RAE (standardise) ----
subset(recalculated_results_table, fdc_id == "09_0007") %>% distinct()
subset(recalculated_results_table, fdc_id == "09_0007",
select = c(RETOLmcg, CARTBEQmcg, CARTBEQmcg_std))
#Identifying the beta-carotene eq. column in Feb., 2022 dataset
n <- match("VITA_RAE(µg) (standardized)", names(fao_cat))
fao_cat$`ICS FAOSTAT SUA Current Code` <- as.character(fao_cat$`ICS FAOSTAT SUA Current Code`)
#Checking categories w/ higher RETOL (negative) and lower RETOL (positive) values
#in the Feb/, 2022 vs Oct., 2022 dataset.
subset(recalculated_results_table, str_detect(ICS.FAOSTAT.SUA.Current.Code,
"SUMMARY ROW"),
select = c(ICS.FAOSTAT.SUA.Current.Code,
`ICS FAOSTAT SUA title`, VITA_RAEmcg_std)) %>%
mutate(ICS.FAOSTAT.SUA.Current.Code = str_extract(ICS.FAOSTAT.SUA.Current.Code,
"[:digit:]{4,6}")) %>%
left_join(., fao_cat[c(1:95), c(1,n)], by =
c("ICS.FAOSTAT.SUA.Current.Code" = "ICS FAOSTAT SUA Current Code")) %>%
mutate(diff = as.numeric(VITA_RAEmcg_std) - as.numeric(`VITA_RAE(µg) (standardized)`)) %>%
mutate_at(c(3:5), as.numeric) %>% mutate_if(is.numeric, round,
digits = 2) %>%
filter(diff <0) %>% arrange(desc(diff))
#VITA
subset(results_table, food_desc == "Algae, green laver, dried",
select = c(RETOLmcg,CARTBEQmcg, CARTBEQmcg_std, VITA_RAEmcg_std))