-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathTopic2.R
2586 lines (1708 loc) · 111 KB
/
Topic2.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
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
library(stringr)
# library(doSNOW) # foreach()
library(openxlsx)
library(plyr)
library(RColorBrewer)
library(openxlsx)
source("Starting.R")
############Define a color scheme#####################
IPbesdarkgreen <- rgb(92/255, 102/255, 93/255) #5c665d
IPbeslightgreen <- rgb(181/255, 212/255, 141/255) #b5d48d
colfunc <- colorRampPalette(c(rgb(92/255, 102/255, 93/255), rgb(181/255, 212/255, 141/255)))
brewer.YlGnBu <- colorRampPalette(brewer.pal(9, "YlGnBu"), interpolate = "spline")
brewer.BuPu <- colorRampPalette(brewer.pal(9, "BuPu"), interpolate = "spline")
brewer.Greens <- colorRampPalette(brewer.pal(9, "Greens"), interpolate = "spline")
######### USE this function where stringr::functions() used
escapeForStringR = function(x) {
gsub("([.|()\\^{}+$*?/-]|\\[|\\])", "\\\\\\1", x)
}
###### Topic 2 - Context of application
### 2.1- The application addresses the following spatial scales (multiple possible)
### Their multiple answers are separated by ','
summary(s3_single$"2.1")
# how many are 'multiple scales' ?
levels(s3_single$"2.1")
summary(s3_single$"2.2")
table(s3_single$"2.1")
## Replace the problematic answers
choices_org = c("local \\(incl. village, parish, municipality, town, city\\)",
"district, county",
"administrative region \\(as sub-national\\), \\(incl. province, state\\)",
"cross-national or cross-region Indigenous territories\\/jurisdictions\\/lands",
"cross-national or cross-region protected areas",
"national, federal",
"regional as multi-national",
"continental",
"global"
#"Option 9"
)
choices_alt = c("O1_Local", "O2_District", "O3_Administrative", "O4_CrossNationalIndigenous", "O5_CrossNationalProtected", "O6_National", "07_Regional", "O8_Continental", "O9_Global") # "Other")
choice_org_v = as.character(s3_single$"2.1")
choice_alt_v = choice_org_v
# Replace well-defined options to simple format
for (o_idx in 1:length(choices_org)) {
choice_alt_v = str_replace_all(choice_alt_v, pattern = choices_org[o_idx], replacement = choices_alt[o_idx])
}
# head(table(choice_org_v))
# table(choice_org_v)
# Split choices
row_idx = 1
library(doMC)
# install.packages("doMC")
split_res_l<-list()
for(row_idx in 1:nrow(s3_single)){
split_tmp = str_trim(str_split(choice_alt_v[row_idx], pattern = ",")[[1]])
split_res_l[[row_idx]]<-split_tmp
}
choice_split_v = unlist(split_res_l)
choice_split_v_fac = factor(choice_split_v)
choice_tb_sorted = sort(table(choice_split_v_fac), decreasing = F)
barplot(choice_tb_sorted, log="x", las=1, horiz=T, cex.names = 0.5)
# choice_ordreded = names(choice_tb_sorted)
choice_tb_reduced = (table(choice_split_v_fac))[which (table(choice_split_v_fac)>2)]
barplot(sort(choice_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
barplot(sort(table(choice_split_v_fac), F), log="x", las=1, horiz=T, cex.names = 0.5)
# split list to data frame
split_res_df = plyr::ldply(split_res_l, rbind) # automatically decide how many columns should it have
split_res_df = sapply(split_res_df, FUN = function(x) as.character(x))
# Extract Paper IDs of the choice_malformed
# Be aware of the NA values when counting
other_choice_cnt = apply(split_res_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% choices_alt)))) # how many choices (non-NA) are not in the given well-formed answers
# length(idx1)
table(other_choice_cnt > 0 ) # 189 studies
cnt_otherchoice = length(which(other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[other_choice_cnt > 0 ]
s3_single_with_other_choices_df = s3_single[other_choice_cnt > 0, c("paperID", "2.1")] # "MF1.key" "MF2.key" "MF3.key" "MF4.key" "MFA.key" "MFB.key" )]
#write.xlsx(s3_single_with_other_choices_df, paste0("output/s3_single_with_other_choices_n", cnt_otherchoice, ".xlsx"))
split_cnt_v = sapply(split_res_l, FUN = length)
stopifnot(max(split_cnt_v) == ncol(split_res_df))
# Multi scale studies
table(split_cnt_v)
# split_cnt_v
# 1 2 3 4 5
# 1065 86 10 1 1
#pdf("output/Fig_NumberofScalesPerApp.pdf", width=15, height = 8, pointsize = 12)
barplot(table(split_cnt_v), las= 1, col = IPbeslightgreen, border = IPbeslightgreen, ylim = c(0, 1200), xlab = "# of scales per application", ylab = "# of application")
#dev.off()
pie(table(split_cnt_v), col = brewer.YlGnBu(5), labels = NA)
# Max 5 items
str(split_res_df)
head(split_res_df)
tail(split_res_df)
table(split_cnt_v)
tail(s3_single$"2.1")
table(split_res_df)
s3_single_2.1_comparison_df = cbind(split_res_df, RawData_2.1 = as.character(s3_single$"2.1"))
colnames(s3_single_2.1_comparison_df)[1:5] = paste0("Scale_Split_", 1:5)
#write.xlsx(s3_single_2.1_comparison_df, file = "output/s3_single_2.1_for_comparison.xlsx")
################ Read corrected data (from Raphael)
scale_corrected_df = read.xlsx("Corrected/s3_single_with_other_choices_n189_Raphael_NoComment.xlsx", sheet = 1)
str(scale_corrected_df)
# Identify other answers in the uncorrected data
scale_other_v = choice_alt_v
for (given_idx in 1:length(choices_alt)) {
scale_other_v = str_replace_all(scale_other_v, pattern = choices_alt[given_idx], replacement = "")
}
scale_other_v = str_trim(str_replace_all(scale_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(scale_other_v)
scale_other_wospace_v = str_replace_all(scale_other_v, pattern = "[ ]", replacement = "") # remove whitespace
scale_other_idx_2.1 = str_length(scale_other_wospace_v) >= 1 # does it have still more characters?
scale_other_v[scale_other_idx_2.1]
n_other_2.1 = length(which(scale_other_idx_2.1)); n_other_2.1
# Count given and other answers individually
scale_given_detected = sapply(choices_alt, FUN = function(x) str_detect(choice_alt_v, pattern = x))
scale_given_detected_one_na = ifelse(scale_given_detected, yes = 1, no = NA)
scale_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.1", scale_given_detected_one_na, other=NA)
colnames(scale_given_detected_df) = colnames(scale_corrected_df) # Make sure two datasets are in the same order
# merge two datasets using paperID
scale_given_detected_df[match(scale_corrected_df$paperID, scale_given_detected_df$paperID), ] = scale_corrected_df
scale_tb_final = colSums(scale_given_detected_df[,-c(1:2)], na.rm = T)
scale.names = c("Local (incl. village, parish, municipality, town, city)",
"District, county",
"Administrative region",
"Cross-national or cross-region \nIndigenous territories/jurisdictions/lands",
"Cross-national or cross-region protected areas",
"National, federal",
"Regional as multi-national",
"Continental",
"Global")
pdf("output/Q2.1_Scale_bar_3Dec.pdf", width= 15, height = 8, pointsize = 20)
# png("output/Q2.1_Scale_bar_3Dec.png", width= 25, height = 15, unit = "cm", res = 400)
par(mar=c(5,20,1,1))
barplot(rev(scale_tb_final[-10]), horiz=T, names.arg = rev(scale.names), las = 1, col = gray(0.7), xlim = c(0, 400), main = "Scale of application", xlab = "Number of applications")
dev.off()
MF_cols = paste0("MF", 1:4, ".key")
s3_single_MF = s3_single[,c("paperID", MF_cols)]
scale_by_mf_df = foreach (scale_idx = 1:9, .combine = "rbind") %do% {
print(scale.names[scale_idx])
scale_by_mf = sapply(MF_cols, FUN = function(mf_colname) by(scale_given_detected_df[,scale_idx +2 ], INDICES = s3_single_MF[,mf_colname], FUN = sum, na.rm=T))
return(scale_by_mf["1",])
}
rownames(scale_by_mf_df) =scale.names
colnames(scale_by_mf_df) = paste0("MF", 1:4)
#pdf("output/Fig_2.1_scale_corrected_MF.pdf", width=15, height = 8, pointsize = 12)
par(mar=c(5,20,1,1))
barplot(t(scale_by_mf_df)[,c(9:1)], names.arg = rev(scale.names), col = viridis(4), las=1, horiz=T)
legend("bottomright", #inset=c(1,0),
fill=viridis(4),
legend=paste0("MF", 1:4))
#dev.off()
barplot(scale_by_mf_df, names.arg = paste0("MF", 1:4), col = viridis(9))
# scale_given_cnt= apply(scale_given_detected, MARGIN = 1, FUN = function(x) (which(x)))
# scale_given_tb = table(unlist(scale_given_cnt))
# names(scale_given_tb) = choices_org
#
# scale_all_tb= c(Other = n_other_2.1, sort(scale_given_tb, decreasing = F))
#
# par(mar=c(5,20,1,1))
# barplot(scale_all_tb, las=1, horiz=T, col = IPbeslightgreen, border =IPbeslightgreen, xlim = c(0, max(habitat_all_tb) *1.1))
# #dev.off()
### 2.2 - The application assesses the following habitats (multiple possible)
summary(s3_single$"2.2")
# write.xlsx(table(s3_single$"2.2"), file = "output/summary_s3_single_2.2_raw.xlsx")
# Multiple answers are separated by ','
wetland_org = c("Wetlands \\– peatslands, mires, bogs")
wetland_alt = "Wetlands"
wetland_org_v = as.character(s3_single$"2.2")
wetland_alt_v = wetland_org_v
wetland_alt_v = str_replace_all(wetland_alt_v, pattern = wetland_org, replacement = wetland_alt)
split_res_l_2.2 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(wetland_alt_v[row_idx], pattern = ",")[[1]])
split_res_l_2.2[[row_idx]] = split_tmp
}
habitat_split_v = unlist(split_res_l_2.2)
habitat_split_v_fac = factor(habitat_split_v)
habitat_tb_sorted = sort(table(habitat_split_v_fac), decreasing = F)
barplot(habitat_tb_sorted, log="x", las=1, horiz=T, cex.names = 0.5)
habitat_tb_reduced = (table(habitat_split_v_fac))[which (table(habitat_split_v_fac)>5)]
barplot(sort(habitat_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
# don't use escaping! as we don't use regexp-like functions below
habitat_given_answer = c( "Forests",
"Savannah",
"Deserts",
"Grasslands",
"Shrublands",
"Wetlands", #\\- peatlands, mires, bogs",
"Mountain habitats",
"Urban / Semi-urban",
"Cultivated areas",
"Aquaculture",
"Inland surface water and water bodies / freshwater",
"Coastal areas",
"Deep sea", "unclear", "Irrelevant"
)
# split list to data frame
split_res_2.2_df = plyr::ldply(split_res_l_2.2, rbind) # automatically decide how many columns should it have
split_res_2.2_df = sapply(split_res_2.2_df, FUN = function(x) as.character(x))
names(table(split_res_2.2_df))
# Extract Paper IDs of the choice_malformed
# Be aware of the NA values when counting
habitat_other_choice_cnt = apply(split_res_2.2_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% habitat_given_answer)))) # how many choices (non-NA) are not in the given well-formed answers
table(habitat_other_choice_cnt > 0 ) # 127 studies
cnt_otherchoice_habitat = length(which(habitat_other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[habitat_other_choice_cnt > 0 ]
other_answers_habitat = apply(split_res_2.2_df, MARGIN = 1, FUN = function(x) x[(which(!(x[!is.na(x)] %in% habitat_given_answer)))]) # how many choices (non-NA) are not in the given well-formed answers
other_answers_habitat = unlist(other_answers_habitat)
other_answers_habitat_tb = table(other_answers_habitat)
table(other_answers_habitat_tb)
other_answers_habitat_tb[other_answers_habitat_tb>2]
s3_single_with_other_habitat_df = s3_single[habitat_other_choice_cnt > 0, c("paperID", "2.2")]
head(s3_single_with_other_habitat_df)
# write.xlsx(s3_single_with_other_habitat_df, paste0("output/s3_single_with_other_habitat_n", cnt_otherchoice_habitat, ".xlsx"))
################ Read corrected data (from Sander)
habitat_corrected_df = read.xlsx("Corrected/s3_single_with_other_habitat_n127-corrSJ.xlsx", sheet = 1)
str(habitat_corrected_df)
# Identify other answers in the uncorrected data
habitat_other_v = wetland_alt_v
for (given_idx in 1:length(habitat_given_answer)) {
habitat_other_v = str_replace_all(habitat_other_v, pattern = habitat_given_answer[given_idx], replacement = "")
}
habitat_other_v = str_trim(str_replace_all(habitat_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(habitat_other_v)
habitat_other_wospace_v = str_replace_all(habitat_other_v, pattern = "[ ]", replacement = "") # remove whitespace
habitat_other_idx_2.2 = str_length(habitat_other_wospace_v) >= 1 # does it have still more characters?
wetland_alt_v[habitat_other_idx_2.2]
n_other_2.2 = length(which(habitat_other_idx_2.2)); n_other_2.2
# other_df_6.1= cbind(paperID= s3_single$paperID, OTHER_ANSWER_6_1 = wellbeing_indicator_other_v,ANSWER_RAW=as.character(s3_single$"6.1") )[other_idx_6.1,]
# write.xlsx(other_df_6.1, file = "output/6.1_otheranswers.xlsx")
# Count given and other answers individually
habitat_given_detected = sapply(habitat_given_answer, FUN = function(x) str_detect(wetland_alt_v, pattern = x))
habitat_given_detected_one_na = ifelse(habitat_given_detected, yes = 1, no = NA)
habitat_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.2", habitat_given_detected_one_na, other=NA)
colnames(habitat_given_detected_df) = colnames(habitat_corrected_df) # Make sure two datasets are in the same order
# merge two datasets using paperID
habitat_given_detected_df[match(habitat_corrected_df$paperID, habitat_given_detected_df$paperID), ] = habitat_corrected_df
habitat_tb_final = colSums(habitat_given_detected_df[,-c(1:2)], na.rm = T)
barplot(habitat_tb_final, horiz=T, las=2)
names(habitat_tb_final)
habitat_tb_final[16] <- habitat_tb_final[16] + habitat_tb_final[14] # other + unclear
habitat.name.plot <- c("Forests",
"Savannah",
"Deserts",
"Grasslands",
"Shrublands",
"Wetlands",
"Mountain habitats",
"Urban / Semi-urban",
"Cultivated areas",
"Aquaculture",
"Inland surface water and water bodies / freshwater",
"Coastal areas",
"Deep sea",
"unclear",
"No habitat assessed",
"Other / Unclear")
#
# names(habitat_tb_final)[15] <- "No habitat assessed"
#
# names(habitat_tb_final[16]) <- "Other and unclear"
names(habitat_tb_final) <- habitat.name.plot
habitat_tb_final <- habitat_tb_final[-(14)]
pdf("output/Q2.2_Habitat_bar_3Dec.pdf", width=15, height = 8, pointsize = 20)
png(file="output/Q2.2_Habitat_bar_3Dec.png", width=25, height = 15, units= "cm", res = 400)
par(mar=c(5,20,1,1))
barplot(rev(habitat_tb_final), las=1, horiz=T, col = gray(0.7), xlim = c(0, max(habitat_tb_final) *1.1), xlab = "Number of applications", main = "The application assesses the following habitats ")
dev.off()
#pdf("output/Fig_habitat_corrected_30Oct.pdf", width=15, height = 8, pointsize = 12)
#png("output/Fig_habitat_corrected_30Oct.png", width=800, height = 600, pointsize = 12)
# par(mar=c(5,20,1,1))
# barplot(habitat_all_tb[c(8,1:7,9:15)], las=1, horiz=T, col = IPbeslightgreen, border =IPbeslightgreen, xlim = c(0, max(habitat_all_tb) *1.1))
#dev.off()
### 2.7 - The application collected data with the following temporal frequency: (only one answer)
summary(s3_single$"2.7")
table(s3_single$"2.7")
barplot(table(s3_single$"2.7"))
pdf("output/Q2.7_Temporal Frequency_bar_3Dec.pdf", width=8, height = 8, pointsize = 20)
png("output/Q2.7_Temporal Frequency_bar_3Dec.png", width=15, height = 8, unit = "cm", res = 400)
barplot(table(s3_single$"2.7"), las = 1, col = gray(0.7), ylab = "Number of applications", xlab = "Temporal frequency")
dev.off()
pdf("output/Q2.7_Temporal Frequency_pie_3Dec.pdf", width=8, height = 8, pointsize = 20)
# png("output/Q2.7_Temporal Frequency_pie_3Dec.png", width=10, height = 8, unit = "cm", res = 400)
pie(table(s3_single$"2.7"), init.angle = 90, col = gray.colors(3, start = 0.9, end = 0.3), main = "Temporal frenquency")
dev.off()
### 2.8 - The application assesses values change over time:
summary(s3_single$"2.8")
pdf("output/Q2.8_overTime_pie_3Dec.pdf", width=10, height = 10, pointsize = 20)
# png("output/Q2.8_overTime_pie_3Dec.png", width=14, height = 10, unit= "cm", res = 400)
pie(table(s3_single$"2.8"), labels = c("No", "Yes"), main = "The application assesses values change over time", init.angle = 90, col = gray.colors(2, start = 0.9, end = 0.3))
dev.off()
### 2.9 The application assesses following temporal changes :
summary(s3_single$"2.9")
sort(table(s3_single$"2.9"))
split_res_l_2.9 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(as.character(s3_single$"2.9")[row_idx], pattern = ",")[[1]])
split_res_l_2.9[[row_idx]] = split_tmp
}
time_split_v = unlist(split_res_l_2.9)
time_split_v_fac = factor(time_split_v)
time_tb_sorted = sort(table(time_split_v_fac), decreasing = F)
pdf("output/Q2.9_TemporalChange_bar_3Dec.pdf", width=12, height = 8, pointsize = 20)
png("output/Q2.9_TemporalChange_bar_3Dec.png", width=20, height = 15, unit = "cm", res = 400)
par(mar=c(5,20,5,5))
barplot(sort(time_tb_sorted, F)[-(9)], horiz=T, las=1, xlim = c(0, 100), col = gray(0.7), main = "Temporal Changes", xlab = "Number of applications")
dev.off()
### 2.10 There are multiple classifications of 'what is valued'. We want to know how these fit in the IPBES categories. The application assesses the following 'targets of valuation' regarding Nature Itself (multiple possible)
summary(s3_single$"2.10")
# Multiple answers are separated by ','
split_res_l_2.10 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(as.character(s3_single$"2.10")[row_idx], pattern = ",")[[1]])
split_res_l_2.10[[row_idx]] = split_tmp
}
nature_split_v = unlist(split_res_l_2.10)
nature_split_v_fac = factor(nature_split_v)
nature_tb_sorted = sort(table(nature_split_v_fac), decreasing = F)
nature_tb_reduced = (table(nature_split_v_fac))[which (table(nature_split_v_fac)>1)]
barplot(sort(nature_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
# split list to data frame
split_res_2.10_df = plyr::ldply(split_res_l_2.10, rbind) # automatically decide how many columns should it have
split_res_2.10_df = sapply(split_res_2.10_df, FUN = function(x) as.character(x))
nature_given_answers = c(
"Individual organisms \\(e.g. the sacred village tree\\)",
"Biophysical assemblages",
"Biophysical processes",
"Biodiversity",
"Maintenance of options",
"none"
)
# Extract Paper IDs of the choice_malformed
# Be aware of the NA values when counting
nature_other_choice_cnt = apply(split_res_2.10_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% nature_given_answers)))) # how many choices (non-NA) are not in the given well-formed answers
# length(idx1)
table(nature_other_choice_cnt > 0 ) # 20 studies
cnt_otherchoice_nature = length(which(nature_other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[nature_other_choice_cnt > 0 ]
s3_single_with_other_nature_df = s3_single[nature_other_choice_cnt > 0, c("paperID", "2.10")]
#write.xlsx(s3_single_with_other_nature_df, paste0("output/s3_single_with_other_nature_n", cnt_otherchoice_nature, ".xlsx"))
# Identify other answers in the uncorrected data
NCP_nature_other_v = as.character(s3_single$"2.10")
for (given_idx in 1:length(nature_given_answers)) {
NCP_nature_other_v = str_replace_all(NCP_nature_other_v, pattern = nature_given_answers[given_idx], replacement = "")
}
NCP_nature_other_v = str_trim(str_replace_all(NCP_nature_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(NCP_nature_other_v)
NCP_nature_other_wospace_v = str_replace_all(NCP_nature_other_v, pattern = "[ ]", replacement = "") # remove whitespace
NCP_nature_other_idx_2.10 = str_length(NCP_nature_other_wospace_v) >= 1 # does it have still more characters?
NCP_nature_other_v[NCP_nature_other_idx_2.10]
n_other_2.10 = length(which(NCP_nature_other_idx_2.10)); n_other_2.10
# other_df_6.1= cbind(paperID= s3_single$paperID, OTHER_ANSWER_6_1 = wellbeing_indicator_other_v,ANSWER_RAW=as.character(s3_single$"6.1") )[other_idx_6.1,]
# write.xlsx(other_df_6.1, file = "output/6.1_otheranswers.xlsx")
# Count given and other answers individually
NCP_nature_given_detected = sapply(nature_given_answers, FUN = function(x) str_detect(as.character(s3_single$"2.10"), pattern = x))
NCP_nature_given_detected_one_na = ifelse(NCP_nature_given_detected, yes = 1, no = NA)
NCP_nature_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.10", NCP_nature_given_detected_one_na, other=NA)
NCP_nature_given_detected_df<- NCP_nature_given_detected_df[-c(8:9)]
colnames(NCP_nature_given_detected_df)
NCP_nature_given_detected_df[is.na(NCP_nature_given_detected_df)] = 0
colSums(NCP_nature_given_detected_df[-c(1:2)])
MF_cols = paste0("MF", 1:4, ".key")
s3_single_MF = s3_single[,c("paperID", MF_cols)]
# Sum all the nature given answers
NCP_nature_sum_v =rowSums(NCP_nature_given_detected_df[, 3:7], na.rm=T)
# Tabulate by MF
NCP_nature_by_mf_df = sapply(MF_cols, FUN = function(mf_colname) tapply(NCP_nature_sum_v, INDEX = s3_single_MF[,mf_colname], FUN = sum, na.rm=T))
NCP_nature_by_mf_df = NCP_nature_by_mf_df["1", ]
names(NCP_nature_by_mf_df) = c("MF1", "MF2", "MF3", "MF4")
barplot(NCP_nature_by_mf_df)
pdf("output/Q2.10_Nature_pie_3Dec.pdf", width=15, height = 15, pointsize = 20)
pie(NCP_nature_by_mf_df, col = viridis(4), main = "NCP Nature", init.angle = 90, labels = NA)
dev.off()
# dim(NCP_nature_given_detected_df)
#
# #
# NCP_nature_given_detected_df[match(CorrectedOtherTF_df$paperID, NCP_nature_given_detected_df$s3_single.paperID), 3:8] = CorrectedOtherTF_df[, c(3:8)]
#
# NCP_list[match(NCP_nature_corrected_df$paperID, NCP_nature_full$paperID), ] = NCP_nature_corrected_df
#
# # merge two datasets using paperID
# NCP_nature_full[match(NCP_nature_corrected_df$paperID, NCP_nature_full$paperID), ] = NCP_nature_corrected_df
#
# NCP_nature_full_final = colSums(NCP_nature_full[,-c(1:2)], na.rm = T)
#
# barplot(NCP_nature_full_final, horiz=T, las=2)
#
# #pdf("output/Fig_habitat_corrected_25Oct.pdf", width=15, height = 8, pointsize = 12)
# #png("output/Fig_habitat_corrected_25Oct.png", width=800, height = 600, pointsize = 12)
#
# par(mar=c(5,20,1,1))
# barplot(NCP_nature_full_final, las=1, horiz=T, col = IPbeslightgreen, border =IPbeslightgreen, xlim = c(0, max(NCP_nature_full_final) *1.1))
# #dev.off()
#
### 2.11 There are multiple classifications of 'what is valued'. We want to know how these fit in the IPBES categories. The application assesses the following 'targets of valuation' regarding REgulating Nature Contributions To People (multiple possible)
summary(s3_single$"2.11")
# Multiple answers are separated by ','
flow_org = c("Regulation of freshwater quantity, flow and timing \\(\\!includes water provision\\!\\)", "Formation, protection and decontamination of soils and sediments")
flow_alt = c("Regulation of freshwater quantity", "Soil formation")
flow_org_v = as.character(s3_single$"2.11")
flow_alt_v = flow_org_v
# Replace well-defined options to simple format
for (o_idx in 1:length(flow_org)) {
flow_alt_v = str_replace_all(flow_alt_v, pattern = flow_org[o_idx], replacement = flow_alt[o_idx])
}
split_res_l_2.11 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(flow_alt_v[row_idx], pattern = ",")[[1]])
split_res_l_2.11[[row_idx]] = split_tmp
}
regul_split_v = unlist(split_res_l_2.11)
regul_split_v_fac = factor(regul_split_v)
regul_tb_sorted = sort(table(regul_split_v_fac), decreasing = F)
regul_tb_reduced = (table(regul_split_v_fac))[which (table(regul_split_v_fac)>2)]
barplot(sort(regul_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
split_res_2.11_df = plyr::ldply(split_res_l_2.11, rbind) # automatically decide how many columns should it have
split_res_2.11_df = sapply(split_res_2.11_df, FUN = function(x) as.character(x))
regul_given_answer = c(
"Maintenance of options",
"Habitat creation and maintenance",
"Pollination and dispersal of seeds and other propagules",
"Regulation of air quality",
"Regulation of climate",
"Regulation of ocean acidification",
"Regulation of freshwater quantity", #Regulation of freshwater quantity, flow and timing (!includes water provision!),
"Regulation of freshwater and coastal water quality",
"Soil formation", #Formation, protection and decontamination of soils and sediments
"Regulation of hazards and extreme events",
"None"
)
# Be aware of the NA values when counting
regul_other_choice_cnt = apply(split_res_2.11_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% regul_given_answer)))) # how many choices (non-NA) are not in the given well-formed answers
# length(idx1)
table(regul_other_choice_cnt > 0 ) # 46 studies
cnt_otherchoice_regul = length(which(regul_other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[regul_other_choice_cnt > 0 ]
s3_single_with_other_regul_df = s3_single[regul_other_choice_cnt > 0, c("paperID", "2.11")]
# write.xlsx(s3_single_with_other_regul_df, paste0("output/s3_single_with_other_regul_n", cnt_otherchoice_regul, ".xlsx"))
# Identify other answers in the uncorrected data
NCP_regul_other_v = flow_alt_v
for (given_idx in 1:length(regul_given_answer)) {
NCP_regul_other_v = str_replace_all(NCP_regul_other_v, pattern = regul_given_answer[given_idx], replacement = "")
}
NCP_regul_other_v = str_trim(str_replace_all(NCP_regul_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(NCP_regul_other_v)
NCP_regul_other_wospace_v = str_replace_all(NCP_regul_other_v, pattern = "[ ]", replacement = "") # remove whitespace
NCP_regul_other_idx_2.11 = str_length(NCP_regul_other_wospace_v) >= 1 # does it have still more characters?
NCP_regul_other_v[NCP_regul_other_idx_2.11]
n_other_2.11 = length(which(NCP_regul_other_idx_2.11)); n_other_2.11
# Count given and other answers individually
NCP_regul_given_detected = sapply(regul_given_answer, FUN = function(x) str_detect(flow_alt_v, pattern = x))
NCP_regul_given_detected_one_na = ifelse(NCP_regul_given_detected, yes = 1, no = NA)
NCP_regul_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.11", NCP_regul_given_detected_one_na, other=NA)
NCP_regul_given_detected_df <- NCP_regul_given_detected_df[-c(13:14)]
colnames(NCP_regul_given_detected_df)
NCP_regul_given_detected_df[is.na(NCP_regul_given_detected_df)] = 0
colSums(NCP_regul_given_detected_df[-c(1:2)])
## create a full matrix
# colnames(NCP_nature_corrected_df)
ncol(NCP_regul_given_detected_df)
# nrow(NCP_nature_given_detected_df) ; nrow(NCP_regul_given_detected_df)
# NCP_list <- matrix(NA, ncol = ncol(NCP_nature_corrected_df)-12, nrow = nrow(NCP_regul_given_detected_df))
#
# colnames(NCP_list[c(1:8)]) ) <- colnames(NCP_nature_corrected_df)[c(1:8)]
#
# NCP_nature_full <- cbind(NCP_nature_given_detected_df, NCP_list)
# NCP_nature_full[is.na(NCP_nature_full)] = 0
#
# dim(NCP_nature_full)
# colnames(NCP_nature_full[,c(7:16)])
#
MF_cols = paste0("MF", 1:4, ".key")
s3_single_MF = s3_single[,c("paperID", MF_cols)]
# Sum all the nature given answers
NCP_regul_sum_v =rowSums(NCP_regul_given_detected_df[, 3:12], na.rm=T)
# Tabulate by MF
NCP_regul_by_mf_df = sapply(MF_cols, FUN = function(mf_colname) tapply(NCP_regul_sum_v, INDEX = s3_single_MF[,mf_colname], FUN = sum, na.rm=T))
NCP_regul_by_mf_df = NCP_regul_by_mf_df["1", ]
names(NCP_regul_by_mf_df) = c("MF1", "MF2", "MF3", "MF4")
barplot(NCP_regul_by_mf_df)
pdf("output/Q2.11_Regulating_Pie_3Dec.pdf", width=10, height = 10, pointsize = 20)
pie(NCP_regul_by_mf_df, col = viridis(4), main = "Regulating Nature Contribution to People", init.angle = 90, labels = NA)
dev.off()
# pie(NCP_nature_by_mf_df, col = viridis(4), main = "NCP Nature")
### 2.12 There are multiple classifications of 'what is valued'. We want to know how these fit in the IPBES categories. The application assesses the following 'targets of valuation' regarding Material Nature Contributions To People (multiple possible)
summary(s3_single$"2.12")
medi_org = c("Medicinal, biochemical and genetic resources")
medi_alt = "Medicinal resources"
medi_org_v = as.character(s3_single$"2.12")
medi_alt_v = medi_org_v
medi_alt_v = str_replace_all(medi_alt_v, pattern = medi_org, replacement = medi_alt)
# Multiple answers are separated by ','
split_res_l_2.12 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(medi_alt_v[row_idx], pattern = ",")[[1]])
split_res_l_2.12[[row_idx]] = split_tmp
}
material_split_v = unlist(split_res_l_2.12)
material_split_v_fac = factor(material_split_v)
material_tb_sorted = sort(table(material_split_v_fac), decreasing = F)
material_tb_reduced = (table(material_split_v_fac))[which (table(material_split_v_fac)>1)]
barplot(sort(material_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
split_res_2.12_df = plyr::ldply(split_res_l_2.12, rbind) # automatically decide how many columns should it have
split_res_2.12_df = sapply(split_res_2.12_df, FUN = function(x) as.character(x))
material_given_answer = c(
"Energy",
"Food and feed",
"Materials",
"Medicinal resources",
"None"
)
# Be aware of the NA values when counting
material_other_choice_cnt = apply(split_res_2.12_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% material_given_answer)))) # how many choices (non-NA) are not in the given well-formed answers
# length(idx1)
table(material_other_choice_cnt > 0 ) # 25 studies
cnt_otherchoice_material = length(which(material_other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[material_other_choice_cnt > 0 ]
s3_single_with_other_material_df = s3_single[material_other_choice_cnt > 0, c("paperID", "2.12")]
#write.xlsx(s3_single_with_other_material_df, paste0("output/s3_single_with_other_material_n", cnt_otherchoice_material, ".xlsx"))
NCP_material_other_v = medi_alt_v
for (given_idx in 1:length(material_given_answer)) {
NCP_material_other_v = str_replace_all(NCP_material_other_v, pattern = material_given_answer[given_idx], replacement = "")
}
NCP_material_other_v = str_trim(str_replace_all(NCP_material_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(NCP_material_other_v)
NCP_material_other_wospace_v = str_replace_all(NCP_material_other_v, pattern = "[ ]", replacement = "") # remove whitespace
NCP_material_other_idx_2.12 = str_length(NCP_material_other_wospace_v) >= 1 # does it have still more characters?
NCP_material_other_v[NCP_material_other_idx_2.12]
n_other_2.12 = length(which(NCP_material_other_idx_2.12)); n_other_2.12
# Count given and other answers individually
NCP_material_given_detected = sapply(material_given_answer, FUN = function(x) str_detect(medi_alt_v, pattern = x))
NCP_material_given_detected_one_na = ifelse(NCP_material_given_detected, yes = 1, no = NA)
NCP_material_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.12", NCP_material_given_detected_one_na, other=NA)
NCP_material_given_detected_df <- NCP_material_given_detected_df[-c(7:8)]
colnames(NCP_material_given_detected_df)
NCP_material_given_detected_df[is.na(NCP_material_given_detected_df)] = 0
colSums(NCP_material_given_detected_df[-c(1:2)])
MF_cols = paste0("MF", 1:4, ".key")
s3_single_MF = s3_single[,c("paperID", MF_cols)]
# Sum all the nature given answers
NCP_material_sum_v =rowSums(NCP_material_given_detected_df[, 3:6], na.rm=T)
# Tabulate by MF
NCP_material_by_mf_df = sapply(MF_cols, FUN = function(mf_colname) tapply(NCP_material_sum_v, INDEX = s3_single_MF[,mf_colname], FUN = sum, na.rm=T))
NCP_material_by_mf_df = NCP_material_by_mf_df["1", ]
names(NCP_material_by_mf_df) = c("MF1", "MF2", "MF3", "MF4")
barplot(NCP_material_by_mf_df)
pdf("output/Q2.12_Material_pie_3Dec.pdf", width=10, height = 10, pointsize = 20)
pie(NCP_material_by_mf_df, col = viridis(4), main = "Material Nature Contribution to People", init.angle = 90, labels = NA)
dev.off()
### 2.13 There are multiple classifications of 'what is valued'. We want to know how these fit in the IPBES categories. The application assesses the following 'targets of valuation' regarding non-material Nature Contributions To People (multiple possible)
summary(s3_single$"2.13")
# Multiple answers are separated by ','
split_res_l_2.13 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(s3_single$"2.13"[row_idx], pattern = ",")[[1]])
split_res_l_2.13[[row_idx]] = split_tmp
}
non_material_split_v = unlist(split_res_l_2.13)
non_material_split_v_fac = factor(non_material_split_v)
non_material_tb_sorted = sort(table(non_material_split_v_fac), decreasing = F)
non_material_tb_reduced = (table(non_material_split_v_fac))[which (table(non_material_split_v_fac)>1)]
barplot(sort(non_material_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
split_res_2.13_df = plyr::ldply(split_res_l_2.13, rbind) # automatically decide how many columns should it have
split_res_2.13_df = sapply(split_res_2.13_df, FUN = function(x) as.character(x))
non_material_given_answer = c(
"Learning and inspiration",
"Physical and psychological experiences",
"Supporting identities",
"None"
)
# Be aware of the NA values when counting
non_material_other_choice_cnt = apply(split_res_2.13_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% non_material_given_answer)))) # how many choices (non-NA) are not in the given well-formed answers
# length(idx1)
table(non_material_other_choice_cnt > 0 ) # 22 studies
cnt_otherchoice_non_material = length(which(non_material_other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[non_material_other_choice_cnt > 0 ]
s3_single_with_other_non_material_df = s3_single[non_material_other_choice_cnt > 0, c("paperID", "2.13")]
#write.xlsx(s3_single_with_other_non_material_df, paste0("output/s3_single_with_other_non_material_n", cnt_otherchoice_non_material, ".xlsx"))
NCP_non_material_other_v = as.character(s3_single$"2.13")
for (given_idx in 1:length(non_material_given_answer)) {
NCP_non_material_other_v = str_replace_all(NCP_non_material_other_v, pattern = non_material_given_answer[given_idx], replacement = "")
}
NCP_non_material_other_v = str_trim(str_replace_all(NCP_non_material_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(NCP_non_material_other_v)
NCP_non_material_other_wospace_v = str_replace_all(NCP_non_material_other_v, pattern = "[ ]", replacement = "") # remove whitespace
NCP_non_material_other_idx_2.13 = str_length(NCP_non_material_other_wospace_v) >= 1 # does it have still more characters?
NCP_non_material_other_v[NCP_non_material_other_idx_2.13]
n_other_2.13 = length(which(NCP_non_material_other_idx_2.13)); n_other_2.13
# Count given and other answers individually
NCP_non_material_given_detected = sapply(non_material_given_answer, FUN = function(x) str_detect(as.character(s3_single$"2.13"), pattern = x))
NCP_non_material_given_detected_one_na = ifelse(NCP_non_material_given_detected, yes = 1, no = NA)
NCP_non_material_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.13", NCP_non_material_given_detected_one_na, other=NA)
colnames(NCP_non_material_given_detected_df)
NCP_non_material_given_detected_df <- NCP_non_material_given_detected_df[-c(6:7)]
colnames(NCP_non_material_given_detected_df)
NCP_non_material_given_detected_df[is.na(NCP_non_material_given_detected_df)] = 0
colSums(NCP_non_material_given_detected_df[-c(1:2)])
MF_cols = paste0("MF", 1:4, ".key")
s3_single_MF = s3_single[,c("paperID", MF_cols)]
# Sum all the nature given answers
NCP_non_material_sum_v =rowSums(NCP_non_material_given_detected_df[, 3:5], na.rm=T)
# Tabulate by MF
NCP_non_material_by_mf_df = sapply(MF_cols, FUN = function(mf_colname) tapply(NCP_non_material_sum_v, INDEX = s3_single_MF[,mf_colname], FUN = sum, na.rm=T))
NCP_non_material_by_mf_df = NCP_non_material_by_mf_df["1", ]
names(NCP_non_material_by_mf_df) = c("MF1", "MF2", "MF3", "MF4")
barplot(NCP_non_material_by_mf_df)
# pdf("output/Fig_non_material_MF_12Nov.pdf", width=10, height = 10, pointsize = 12)
pie(NCP_non_material_by_mf_df, col = viridis(4), main = "Non Material Nature Contribution to People", init.angle = 90, labels = NA)
# dev.off()
### 2.14 There are multiple classifications of 'what is valued'. We want to know how these fit in the IPBES categories. The application assesses the following 'targets of valuation' regarding People's quality of life (multiple possible)
summary(s3_single$"2.14")
# Multiple answers are separated by ','
split_res_l_2.14 = vector("list", length = nrow(s3_single))
for (row_idx in 1:nrow(s3_single)) {
split_tmp = str_trim(str_split(s3_single$"2.14"[row_idx], pattern = ",")[[1]])
split_res_l_2.14[[row_idx]] = split_tmp
}
QoL_split_v = unlist(split_res_l_2.14)
QoL_split_v_fac = factor(QoL_split_v)
QoL_tb_sorted = sort(table(QoL_split_v_fac), decreasing = F)
QoL_tb_reduced = (table(QoL_split_v_fac))[which (table(QoL_split_v_fac)>1)]
barplot(sort(QoL_tb_reduced, F), horiz=T, las=1, cex.names=0.5)
split_res_2.14_df = plyr::ldply(split_res_l_2.14, rbind) # automatically decide how many columns should it have
split_res_2.14_df = sapply(split_res_2.14_df, FUN = function(x) as.character(x))
QoL_given_answer = c(
"Living well in harmony with nature",
"Identity and Autonomy",
"Spirituality and Religions",
"Art and Cultural heritage",
"Sustainability and Resilience",
"Diversity and Options",
"Governance and Justice",
"Health and Wellbeing",
"Education and Knowledge",
"Good social relations",
"Security and Livelihoods",
"None"
)
# Be aware of the NA values when counting
QoL_other_choice_cnt = apply(split_res_2.14_df, MARGIN = 1, FUN = function(x) length(which(!(x[!is.na(x)] %in% QoL_given_answer)))) # how many choices (non-NA) are not in the given well-formed answers
# length(idx1)
table(QoL_other_choice_cnt > 0 ) # 29 studies
cnt_otherchoice_QoL = length(which(QoL_other_choice_cnt > 0))
# studies including other choices
s3_single$paperID[QoL_other_choice_cnt > 0 ]
s3_single_with_other_QoL_df = s3_single[QoL_other_choice_cnt > 0, c("paperID", "2.14")]
#write.xlsx(s3_single_with_other_QoL_df, paste0("output/s3_single_with_other_QoL_n", cnt_otherchoice_QoL, ".xlsx"))
NCP_QoL_other_v = as.character(s3_single$"2.14")
for (given_idx in 1:length(QoL_given_answer)) {
NCP_QoL_other_v = str_replace_all(NCP_QoL_other_v, pattern = QoL_given_answer[given_idx], replacement = "")
}
NCP_QoL_other_v = str_trim(str_replace_all(NCP_QoL_other_v, pattern = "[,;]", replacement = "")) # warning: other answers without comma and semicolon
table(NCP_QoL_other_v)
NCP_QoL_other_wospace_v = str_replace_all(NCP_QoL_other_v, pattern = "[ ]", replacement = "") # remove whitespace
NCP_QoL_other_idx_2.14 = str_length(NCP_QoL_other_wospace_v) >= 1 # does it have still more characters?
NCP_QoL_other_v[NCP_QoL_other_idx_2.14]
n_other_2.14 = length(which(NCP_QoL_other_idx_2.14)); n_other_2.14
# Count given and other answers individually
NCP_QoL_given_detected = sapply(QoL_given_answer, FUN = function(x) str_detect(as.character(s3_single$"2.14"), pattern = x))
NCP_QoL_given_detected_one_na = ifelse(NCP_QoL_given_detected, yes = 1, no = NA)
NCP_QoL_given_detected_df = data.frame(s3_single$paperID, s3_single$"2.14", NCP_QoL_given_detected_one_na, other=NA)
colnames(NCP_QoL_given_detected_df)
NCP_QoL_given_detected_df <- NCP_QoL_given_detected_df[-c(14:15)]
colnames(NCP_QoL_given_detected_df)
NCP_QoL_given_detected_df[is.na(NCP_QoL_given_detected_df)] = 0
colSums(NCP_QoL_given_detected_df[-c(1:2)])
MF_cols = paste0("MF", 1:4, ".key")
s3_single_MF = s3_single[,c("paperID", MF_cols)]
# Sum all the nature given answers
NCP_QoL_sum_v =rowSums(NCP_QoL_given_detected_df[, 3:13], na.rm=T)
# Tabulate by MF
NCP_QoL_by_mf_df = sapply(MF_cols, FUN = function(mf_colname) tapply(NCP_QoL_sum_v, INDEX = s3_single_MF[,mf_colname], FUN = sum, na.rm=T))
NCP_QoL_by_mf_df = NCP_QoL_by_mf_df["1", ]