-
Notifications
You must be signed in to change notification settings - Fork 0
/
ScripT#7_OVERSEE_v7.R
529 lines (416 loc) · 17.2 KB
/
ScripT#7_OVERSEE_v7.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
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
##### 04/06/2018: R Script to homogenize the taxonomic nomenclature (species names) across all v6 zooplankton datasets
### Aims to
# - load the classification keys (excel sheets of corrected species names) and the v6 datasets
# - use them to correct the species names in the v6 datasets
# - check resulting labels/ species names
# - fill in the potential gaps at the higher taxonomic levels (order? family ?)
module load R/3.4.3/ # To load latest R version on kryo
### Latest update: 05/06/2018
library("dplyr")
library("tidyr")
library("stringr")
library("reshape2")
### ----------------------------------------------------------------------------------------------------------------------------
##### 1) v6-v5.1v3.1 ----------------------------------------------------------------------------------------------------------
### First, load the classif file containing the corrected species labels
setwd("/UP_home/fabioben/Desktop/OVERSEE/data")
names_main <- read.csv("species_v6-v5.1v3.2.csv", h = TRUE, sep = ";")
dim(names_main)
str(names_main)
head(names_main)
# Plus the v6-v5.1v3.1 species
names <- read.csv("species_v6-v5.1v3.1.csv", h = TRUE, sep = ";")
dim(names)
str(names)
head(names)
# rbind both
names <- rbind(names_main, names)
rm(names_main)
# unique(names$correct_name)
### Second, load the observation data
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.1v3.1/")
# dir()
# Identify the group files to clean, apply correction and save in v7 directory per file
files <- dir()[c(1:3,5,7:19,21:22)]
# files
### For each file:
# - remove the obs that correspond to species names that are labelled as "to remove"
# - correct the labels that are labelled as 'to correct
# - save in v7 dir, check results
# f <- files[3]
for(f in files) {
# Useless message
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.1v3.1/")
message(paste(f, sep = ""))
# Load the data
data <- get(load(f))
# Add underscore to species names if you have not done so already
data$species <- str_replace_all(as.character(data$species), " ", "_")
# unique(data$species)
# class(data$species)
# Remove the species that are marked as 'remove'
toremove <- as.character(unique(names[which(names$action == "remove"),"species"]))
# class(toremove)
data2 <- data[!(data$species %in% toremove),]
# dim(data) ; dim(data2)
# And correct species labels when necessary
tocorrect <- unique(names[which(names$action == "correct"),"correct_name"])
### BEWARE: 'tocorrect' contains correct labels but only for the species to be corrected,
### the current wrong species names will be in the 'wrongnames' string
### For each label to be corrected, find the wrong labels in 'data2' and replace them
data3 <- as.matrix(data2) # needed to replace factor levels...
for(sp in tocorrect) {
# Useless message, again
message(paste(sp, sep = ""))
# Find the wrong names that correspond to 'sp', the real name
wrongnames <- names[names$correct_name == sp,"species"]
# Correct
data3[which(data3[,"species"] %in% wrongnames),"species"] <- as.character(sp)
} # eo for loop
# Check data3 if necessary
data3 <- as.data.frame(data3)
# dim(data3)
# str(data3)
# head(data3)
# unique(data3$species)
### Save in proper v7 dir
message(paste("------------------------------------------------------------------------------------------", sep = ""))
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.1v3.1/")
save(data3, file = str_replace(f, "15_05_18", "05_06_18") )
} # eo for loop
### Check v7 results
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.1v3.1/")
files <- dir()
res <- lapply(files, function(f) {
dd <- get(load(f))
return(dd)
}
) # eo lapply
table <- do.call(rbind, res)
dim(table) # 1'532'615
str(table)
length(unique(table$species)) # 1973 species
rm(res,data3,data2,data,tocorrect,toremove,wrongnames) ; gc()
### Check if they match with the correct_names from names
unique(table$species)
dplyr::setdiff(unique(table$species), names$correct_name)
table[table$species == "Caesaromysis_hispida",]
names[names$correct_name == "Caesaromysis_hispida",]
# OK
unique(table[table$class == "Scyphozoa","species"])
# OK only the 3 holoplanktonic species :)
unique(table[table$class == "Hexanauplia","species"])
# count species and order per n
data.frame(table[table$class == "Hexanauplia",] %>% count(species))
# OK gut !!
rm(table)
gc()
### You can keep these v7 datasets, just copy/paste the two PANGAEA datasets
##### 2) v6-v5.1v3.2 ----------------------------------------------------------------------------------------------------------
### First, load the classif file containing the corrected species labels
setwd("/UP_home/fabioben/Desktop/OVERSEE/data")
names <- read.csv("species_v6-v5.1v3.2.csv", h = TRUE, sep = ";")
dim(names)
str(names)
head(names)
### Second, load the observation data
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.1v3.2/")
# dir()
# Identify the group files to clean, apply correction and save in v7 directory per file
files <- dir()[c(1:3,5,7:19,21:22)]
# files
### For each file:
# - remove the obs that correspond to species names that are labelled as "to remove"
# - correct the labels that are labelled as 'to correct
# - save in v7 dir, check results
# f <- files[2]
for(f in files) {
# Useless message
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.1v3.2/")
message(paste(f, sep = ""))
# Load the data
data <- get(load(f))
# Add underscore to species names if you have not done so already
data$species <- str_replace_all(as.character(data$species), " ", "_")
# Remove the species that are marked as 'remove'
toremove <- as.character(unique(names[which(names$action == "remove"),"species"]))
# class(toremove)
data2 <- data[!(data$species %in% toremove),]
# dim(data) ; dim(data2)
# And correct species labels when necessary
tocorrect <- unique(names[which(names$action == "correct"),"correct_name"])
### BEWARE: 'tocorrect' contains correct labels but only for the species to be corrected,
### the current wrong species names will be in the 'wrongnames' string
### For each label to be corrected, find the wrong labels in 'data2' and replace them
data3 <- as.matrix(data2) # needed to replace factor levels...
for(sp in tocorrect) {
# Useless message, again
message(paste(sp, sep = ""))
# Find the wrong names that correspond to 'sp', the real name
wrongnames <- names[names$correct_name == sp,"species"]
# Correct
data3[which(data3[,"species"] %in% wrongnames),"species"] <- as.character(sp)
} # eo for loop
# Check data3 if necessary
data3 <- as.data.frame(data3)
# dim(data3)
# str(data3)
# head(data3)
# unique(data3$species)
### Save in proper v7 dir
message(paste("------------------------------------------------------------------------------------------", sep = ""))
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.1v3.2/")
save(data3, file = str_replace(f, "15_05_18", "05_06_18") )
} # eo for loop
### Check v7 results
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.1v3.2/")
files <- dir()
res <- lapply(files, function(f) {
dd <- get(load(f))
return(dd)
}
) # eo lapply
table <- do.call(rbind, res)
dim(table) # 2'393'495
str(table)
length(unique(table$species)) # 2211 species
# Clean
rm(res, data3, data2, data, tocorrect, toremove, wrongnames) ; gc()
### Check if they match with the correct_names from names
unique(table$species)
dplyr::setdiff(unique(table$species), names$correct_name)
table[table$species == "Caesaromysis_hispida",]
names[names$correct_name == "Caesaromysis_hispida",]
# OK
unique(table[table$class == "Scyphozoa","species"])
# OK only the 3 holoplanktonic species :)
unique(table[table$class == "Hexanauplia","species"])
# count species and order per n
data.frame(table[table$class == "Hexanauplia",] %>% count(species))
# OK gut !!
rm(table)
gc()
##### 3) v6-v5.2v3.1 ----------------------------------------------------------------------------------------------------------
### First, load the classif file containing the corrected species labels
setwd("/UP_home/fabioben/Desktop/OVERSEE/data")
names_main <- read.csv("species_v6-v5.1v3.2.csv", h = TRUE, sep = ";")
dim(names_main)
str(names_main)
head(names_main)
# Plus the v6-v5.1v3.1 species
names <- read.csv("species_v6-v5.2v3.1.csv", h = TRUE, sep = ";")
dim(names)
str(names)
head(names)
# rbind both
names <- rbind(names_main, names)
rm(names_main)
### Second, load the observation data
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.2v3.1/")
# dir()
# Identify the group files to clean, apply correction and save in v7 directory per file
files <- dir()[c(1:3,5,7:19,21:22)]
# files
### For each file:
# - remove the obs that correspond to species names that are labelled as "to remove"
# - correct the labels that are labelled as 'to correct
# - save in v7 dir, check results
# f <- files[2]
for(f in files) {
# Load the data
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.2v3.1/")
data <- get(load(f))
# Add underscore to species names if you have not done so already
data$species <- str_replace_all(as.character(data$species), " ", "_")
# Remove the species that are marked as 'remove'
toremove <- as.character(unique(names[which(names$action == "remove"),"species"]))
# class(toremove)
data2 <- data[!(data$species %in% toremove),]
# dim(data) ; dim(data2)
# And correct species labels when necessary
tocorrect <- unique(names[which(names$action == "correct"),"correct_name"])
### BEWARE: 'tocorrect' contains correct labels but only for the species to be corrected,
### the current wrong species names will be in the 'wrongnames' string
### For each label to be corrected, find the wrong labels in 'data2' and replace them
data3 <- as.matrix(data2) # needed to replace factor levels...
for(sp in tocorrect) {
# Useless message, again
message(paste(sp, sep = ""))
# Find the wrong names that correspond to 'sp', the real name
wrongnames <- names[names$correct_name == sp,"species"]
# Correct
data3[which(data3[,"species"] %in% wrongnames),"species"] <- as.character(sp)
} # eo for loop
# Check data3 if necessary
data3 <- as.data.frame(data3)
# dim(data3)
# str(data3)
# head(data3)
# unique(data3$species)
### Save in proper v7 dir
message(paste("------------------------------------------------------------------------------------------", sep = ""))
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.1/")
save(data3, file = str_replace(f, "15_05_18", "05_06_18") )
} # eo for loop
### Check v7 results
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.1/")
files <- dir()
res <- lapply(files, function(f) {
dd <- get(load(f))
return(dd)
}
) # eo lapply
table <- do.call(rbind, res)
dim(table) # 1'072'102
str(table)
length(unique(table$species)) # 1313 species
rm(res, data3, data2, data, tocorrect, toremove, wrongnames) ; gc()
### Check if they match with the correct_names from names
unique(table$species)
dplyr::setdiff(unique(table$species), names$correct_name)
table[table$species == "Caesaromysis_hispida",]
names[names$correct_name == "Caesaromysis_hispida",]
# OK
unique(table[table$class == "Scyphozoa","species"])
# OK only the 3 holoplanktonic species :)
unique(table[table$class == "Hexanauplia","species"])
# count species and order per n
data.frame(table[table$class == "Hexanauplia",] %>% count(species))
# OK gut !!
rm(table)
gc()
##### 4) v6-v5.2v3.2 ----------------------------------------------------------------------------------------------------------
### First, load the classif file containing the corrected species labels
setwd("/UP_home/fabioben/Desktop/OVERSEE/data")
names_main <- read.csv("species_v6-v5.1v3.2.csv", h = TRUE, sep = ";")
dim(names_main)
str(names_main)
head(names_main)
# Plus the v6-v5.1v3.1 species
names <- read.csv("species_v6-v5.2v3.2.csv", h = TRUE, sep = ";")
dim(names)
str(names)
head(names)
# rbind both
names <- rbind(names_main, names)
rm(names_main)
### Second, load the observation data
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.2v3.2/")
# dir()
# Identify the group files to clean, apply correction and save in v7 directory per file
files <- dir()[c(1:3,5,7:19,21:22)]
# files
### For each file:
# - remove the obs that correspond to species names that are labelled as "to remove"
# - correct the labels that are labelled as 'to correct
# - save in v7 dir, check results
# f <- files[2]
for(f in files) {
# Useless message
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.2v3.2/")
message(paste(f, sep = ""))
# Load the data
data <- get(load(f))
# Add underscore to species names if you have not done so already
data$species <- str_replace_all(as.character(data$species), " ", "_")
# Remove the species that are marked as 'remove'
toremove <- as.character(unique(names[which(names$action == "remove"),"species"]))
# class(toremove)
data2 <- data[!(data$species %in% toremove),]
# dim(data) ; dim(data2)
# And correct species labels when necessary
tocorrect <- unique(names[which(names$action == "correct"),"correct_name"])
### BEWARE: 'tocorrect' contains correct labels but only for the species to be corrected,
### the current wrong species names will be in the 'wrongnames' string
### For each label to be corrected, find the wrong labels in 'data2' and replace them
data3 <- as.matrix(data2) # needed to replace factor levels...
for(sp in tocorrect) {
# Useless message, again
message(paste(sp, sep = ""))
# Find the wrong names that correspond to 'sp', the real name
wrongnames <- names[names$correct_name == sp,"species"]
# Correct
data3[which(data3[,"species"] %in% wrongnames),"species"] <- as.character(sp)
} # eo for loop
# Check data3 if necessary
data3 <- as.data.frame(data3)
# dim(data3)
# str(data3)
# head(data3)
# unique(data3$species)
### Save in proper v7 dir
message(paste("------------------------------------------------------------------------------------------", sep = ""))
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.2/")
save(data3, file = str_replace(f, "15_05_18", "05_06_18") )
} # eo for loop
### Check v7 results
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.2/")
files <- dir()
res <- lapply(files, function(f) {
dd <- get(load(f))
return(dd)
}
) # eo lapply
table <- do.call(rbind, res)
dim(table) # 1'864'450 obs
str(table)
length(unique(table$species)) # 1663 species
rm(res, data3, data2, data, tocorrect, toremove, wrongnames) ; gc()
### Check if they match with the correct_names from names
unique(table$species)
dplyr::setdiff(unique(table$species), names$correct_name)
table[table$species == "Heteromysis_panamaensis",]
names[names$correct_name == "Heteromysis_panamaensis",]
# OK
unique(table[table$class == "Scyphozoa","species"])
# OK only the 3 holoplanktonic species :)
unique(table[table$class == "Hexanauplia","species"])
# count species and order per n
data.frame(table[table$class == "Hexanauplia",] %>% count(species))
# OK gut !!
rm(table)
gc()
##### ----------------------------------------------------------------------------------------------------------
### For each v7 dataset, report n obs and n species onto the workflow excel sheet
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.2/")
files <- dir()
for(f in files) {
message(paste(f, sep = ""))
d <- get(load(f))
message(paste("n obs = ", nrow(d), sep = ""))
message(paste("n species = ", length(unique(d$species)), sep = ""))
message(paste("", sep = ""))
message(paste("", sep = ""))
rm(d)
gc()
} # eo for loop
##### ----------------------------------------------------------------------------------------------------------
### Finally, just c/p the 2 PANGAEA datasets in the v7 directories
# Load
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.2v3.2/")
d1 <- get(load("Copepoda_PANGAEA_04_06_18.Rdata"))
d2 <- get(load("Thecosomata_MAREDAT_31_05_18.Rdata"))
# Save in the v7 dir
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.2/")
save(d1, file = "Copepoda_PANGAEA_05_06_18.Rdata")
save(d2, file = "Thecosomata_MAREDAT_05_06_18.Rdata")
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v7-5.2v3.2/")
d1 <- get(load("Copepoda_PANGAEA_05_06_18.Rdata"))
nrow(d1)
unique(d1$species)
d2 <- get(load("Thecosomata_MAREDAT_05_06_18.Rdata"))
nrow(d2)
unique(d2$species)
### And gather all datasets to report total nb of occurrences and species number
setwd("/UP_home/fabioben/Desktop/OVERSEE/data/biology/occurence_data_groups/v6-v5.2v3.2/")
dir()
res <- lapply(dir(), function(f) {
dd <- get(load(f))
return( dd[,c("x","y","species")] )
}
) # eo lapply
table <- do.call(rbind, res)
dim(table)
str(table)
head(table)
length(unique(table$species))