-
Notifications
You must be signed in to change notification settings - Fork 0
/
surveillance-report.Rmd
3298 lines (2674 loc) · 141 KB
/
surveillance-report.Rmd
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
---
output:
html_document:
toc: TRUE
toc_depth: 3
toc_float: TRUE
theme: journal
params:
run_checks: FALSE # whether to run and print out basic data checks
show_cleaning: FALSE # whether to print out basic info about data cleaning steps
concord: TRUE #indicate whether to run extra graphics for concord
manchester: TRUE #indicate whether to run extra graphics for manchester
report_date: "AUTO" # if "AUTO", takes Sys.Date()-2; otherwise specify as YYYY-MM-DD
state_conditions: "Limited Open"
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = FALSE, warning = FALSE, message = FALSE, fig.topcaption = TRUE)
knitr::opts_knit$set(eval.after = 'fig.cap')
fig_counter <- 1
tab_counter <- 1
quar_bed_limit <- 180
isol_bed_limit <- 217
library(tidyverse)
library(glue)
library(colorspace)
library(flextable)
library(lubridate)
library(rvest)
library(scales)
library(sf)
library(ggrepel)
library(lwgeom)
library(officer)
library(tibbletime)
pick_color_threshold <- function(value,
thresholds,
colors=c("#8bcca3", "#f0e37f", "#e6b367", "#de6e66")){
return(colors[max(which(value > thresholds))])
}
pick_color_threshold_str <- function(value,
thresholds,
strings=c("Green", "Yellow", "Orange", "Red")){
return(strings[max(which(value > thresholds))])
}
```
```{r data-load, warning = params$run_checks}
routinetesting <- read_csv("raw_data/routinetesting.csv") %>%
mutate(resultsdate = as.Date(resultsdate),
collectdate = as.Date(collectdate),
onsetdate = as.Date(onsetdate))
isolationquarantine <- read_csv("raw_data/isolationquarantine.csv")
individualdemographics <- read_csv("raw_data/individualdemographics.csv")
```
```{r params}
if(params$report_date=="AUTO"){
report_date <- Sys.Date() - 2
}else{
report_date <- as.Date(params$report_date)
}
report_date_str_long <- as.character(format(report_date, format="%B %d, %Y"))
report_date_str_short <- as.character(format(report_date, format="%b %d"))
# Date on which report begins (inclusive)
start_date <- report_date - 6
start_date_str_long <- as.character(format(start_date, format="%B %d, %Y"))
start_date_str_short <- as.character(format(start_date, format="%b %d"))
# Date to which active cases are counted
report_date_minus10 <- report_date - 10
# one week date (exclusive)
report_date_minus7 <- report_date - 7
report_date_minus7_str_short <- as.character(format(report_date_minus7, format="%b %d"))
# two week date
report_date_minus14 <- report_date - 14
# common axis limits
xaxis_reporting <- c(start_date-0.5, report_date+0.5)
xaxis_entire <- c(as.Date("2020-08-10")-0.5, report_date+0.5)
```
```{r demo-checks, eval=params$run_checks}
## print out missingness in demographics
summary(is.na(individualdemographics))
## print out how many repeat IDs there are by campus and user status
individualdemographics %>%
group_by(uid) %>%
summarize(n = n(),
campus = campus[1],
user_status = user_status[1]) %>%
filter(n > 1) %>%
ungroup() %>%
group_by(campus, user_status) %>%
summarize(n = n())
```
```{r demo-duplicates}
## remove duplicates if they still exist
## favor entries that have complete campus, age, user_status where available
## logic: add number of missing values (of campus, age, user_status, )
## arrange data so that NAs are last, then fill in NAs
## keep the row that had the fewest elements filled in
individualdemographics <- individualdemographics %>%
group_by(uid) %>%
mutate(n_missing = sum(is.na(c(user_status, sex, age, campus)), na.rm=TRUE)) %>%
arrange(user_status) %>%
fill(user_status) %>%
arrange(sex) %>%
fill(sex) %>%
arrange(age) %>%
fill(age) %>%
arrange(campus) %>%
fill(campus) %>%
arrange(n_missing) %>%
mutate(n = 1:n()) %>%
ungroup() %>%
filter(n==1)
```
```{r demo-recoding, include=params$show_cleaning}
## numeric categorical for user_status
## 0, student; 1, faculty; 2, staff; 3, employee; 4, unknown
table(individualdemographics$user_status)
individualdemographics <- individualdemographics %>%
mutate(user_status = tolower(user_status)) %>%
mutate(user_status_num = recode(user_status,
student = 0,
faculty = 1,
staff = 2,
employee = 3,
unknown = 4,
.missing = 4,
.default = 4),
user_status_fac = factor(user_status_num,
levels = 0:4,
labels = c("Student", "Faculty", "Staff", "Employee", "Unknown")))
table(individualdemographics$user_status, individualdemographics$user_status_num)
table(individualdemographics$user_status, individualdemographics$user_status_fac)
## numeric age categories
## [15, 20), then 10y bins to 80+
table(individualdemographics$age)
individualdemographics <- individualdemographics %>%
mutate(age_cat = cut(age, breaks=c(15, seq(20, 60, 10), 200), right = FALSE),
age_cat_num = as.numeric(age_cat),
age_cat_num= ifelse(is.na(age_cat_num), 7, age_cat_num),
age_cat = factor(age_cat_num,
levels = 1:7,
labels = c("15-19", "20-29", "30-39", "40-49", "50-59", "60+", "Other/Missing")))
table(individualdemographics$age_cat_num, individualdemographics$age_cat)
table(individualdemographics$age, individualdemographics$age_cat)
## numeric gender categories from `sex`
table(individualdemographics$sex)
individualdemographics <- individualdemographics %>%
mutate(sex = tolower(sex)) %>%
mutate(gender=recode(sex,
"cisgender man"="Assigned Male at Birth",
"cisgender woman"="Assigned Female at Birth",
"male"="Assigned Male at Birth",
"female"="Assigned Female at Birth",
"transgender man"= "Trans Man",
"transgender woman"= "Trans Woman",
"gender non-conforming"= "Genderqueer/Non-binary (GNB)",
"gender queer"="Genderqueer/Non-binary (GNB)",
"non-binary"= "Genderqueer/Non-binary (GNB)",
"my identity is not listed"= "Not listed or prefer not to say",
"prefer not to say"="Not listed or prefer not to say",
.missing = "Not listed or prefer not to say",
.default = "Not listed or prefer not to say"
)) %>%
mutate(gender=factor(gender,levels=c("Assigned Male at Birth",
"Assigned Female at Birth",
"Trans Man",
"Trans Woman",
"Genderqueer/Non-binary (GNB)",
"Not listed or prefer not to say"))) %>%
mutate(gender_num = as.numeric(gender) - 1)
table(individualdemographics$sex, individualdemographics$gender)
table(individualdemographics$gender_num, individualdemographics$gender)
## numeric campus indicator
## 0 "Durham"; 1 "Concord (Law)"; 2 "Manchester"; 3 "Other"
table(individualdemographics$campus)
individualdemographics <- individualdemographics %>%
mutate(campus = tolower(campus)) %>%
mutate(campus_num=recode(campus,
"unh durham" = 0,
"unh law"= 1,
"unh manchester" = 2,
"other" = 3,
)) %>%
mutate(campus_num=ifelse(is.na(campus_num),4,campus_num)) %>%
mutate(campus_fac=factor(campus_num,
levels = 0:4,
labels = c("UNH Durham","UNH Law","UNH Manchester","Other","No Campus Listed")),
campus_num=as.numeric(campus_fac)-1)
table(individualdemographics$campus, individualdemographics$campus_fac)
table(individualdemographics$campus_num, individualdemographics$campus_fac)
## numeric program result
## 0 "Lib Arts"; 1 "Business"; 2 "Agriculture"; 3 "Engineering"; 4 "Health"; 5 "Graduate School";
## 6 "Continuing Ed"; 7 "Manchester"; 8 "Law"; 9 "Applied Sciences"
table(individualdemographics$college)
individualdemographics <- individualdemographics %>%
mutate(college_num = tolower(college),
college_num = str_replace(college_num, ".*liberal arts.*", "0"),
college_num = str_replace(college_num, ".*business.*", "1"),
college_num = str_replace(college_num, ".*life science.*", "2"),
college_num = str_replace(college_num, ".*engineer.*", "3"),
college_num = str_replace(college_num, ".*health.*", "4"),
college_num = str_replace(college_num, ".*graduate.*", "5"),
college_num = str_replace(college_num, ".*continuing.*", "6"),
college_num = str_replace(college_num, ".*manchester.*", "7"),
college_num = str_replace(college_num, ".*law.*", "8"),
college_num = str_replace(college_num, ".*applied.*", "9"),
college_num = str_replace(college_num, ".*designated.*", "10")) %>%
mutate(college_num = as.numeric(college_num)) %>%
mutate(college_fac = factor(college_num,
levels = 0:10,
labels = c("Liberal Arts",
"Business",
"Agriculture/Life Sci",
"Engineering/Phys Sci",
"Health",
"Graduate School",
"Continuing Ed",
"Manchester",
"Law",
"Applied Sciences",
"No college designated")))
table(individualdemographics$college, individualdemographics$college_fac)
table(individualdemographics$college_num, individualdemographics$college_fac)
## dorimtory + on/off campus levels
## On/Off: 1 if no dorm listed
## Dorm: 0 "Hills" 1 "Valley" 2 "Timbers" 3 "Woodside Apts" 4 "Gables Apts"
# note the that no students are listed in the isolation and quarantine dorm:
# https://www.unh.edu/housing/residence-halls
# Adams Tower West and Babcock Hall are being utilized as UNH's isolation and quarantine dorms.
# Adams Tower West has single rooms with ensuite bathrooms.
# Babcock Hall offers single residence hall rooms with community bathrooms.
# Students assigned to the Quarantine or Isolation Halls will be provided meals, snacks and beverages.
table(individualdemographics$dorm)
individualdemographics <- individualdemographics %>%
mutate(off_campus_num=ifelse(is.na(dorm), 1, 0),
off_campus_fac = factor(off_campus_num,
levels = 0:1,
labels = c("On Campus", "Off Campus"))) %>%
mutate(dorm_group=recode(dorm,
"Alexander Hall"= "The Valley",
"Christensen Hall"= "The Timbers",
"Congreve Hall"= "The Hills",
"Devine Hall" = "Upper Quad",
"Eaton House" = "The Minis",
"Engelhardt Hall"="The Valley",
"Fairchild Hall"="The Valley",
"Gables North" = "Gables Apts",
"Gables South" = "Gables Apts",
"Gibbs Hall"= "The Valley",
"Haaland Hall" = "The Timbers",
"Hall House" = "The Minis",
"Handler Hall"= "The Timbers",
"Hetzel Hall" = "The Valley",
"Hitchcock Hall"= "Upper Quad",
"Hubbard Hall" = "The Timbers",
"Hunter Hall" = "The Valley",
"Jessie Doe Hall"="The Hills",
"Lord Hall"="The Hills",
"Marston House" = "The Minis",
"Mclaughlin Hall"="The Hills",
"Mills Hall"="The Valley",
"Peterson Hall"="The Timbers",
"Randall Hall" = "Upper Quad",
"Richardson House" = "The Minis",
"Sawyer Hall"="The Hills",
"Scott Hall"="The Hills",
"Stoke Hall"="The Hills",
"The Gables - A" = "Gables Apts",
"The Gables - B" = "Gables Apts",
"The Gables - C" = "Gables Apts",
"Williamson Hall"="The Timbers",
"Woodside Apts. A" = "Woodside Apts",
"Woodside Apts. B" = "Woodside Apts",
"Woodside Apts. C" = "Woodside Apts",
"Woodside Apts. D" = "Woodside Apts",
"Woodside Apts. E" = "Woodside Apts",
"Woodside Apts. F" = "Woodside Apts",
"Woodside Apts. G" = "Woodside Apts",
"Woodside Apts. H"= "Woodside Apts",
"Woodside Apts. I"= "Woodside Apts",
"Woodside Apts. J"= "Woodside Apts",
"Woodside Apts. K"= "Woodside Apts",
"Woodside Apts. L"= "Woodside Apts",
"Woodside Apts. M"= "Woodside Apts",
"Woodside Apts. N"= "Woodside Apts",
"Woodside Apts. O"= "Woodside Apts",
"Woodside Apts. P"= "Woodside Apts",
"Woodside Apts. Q"= "Woodside Apts",
"Woodside Apts. R"= "Woodside Apts")) %>%
mutate(dorm_group_num = recode(dorm_group,
"The Hills" = 0,
"The Valley" = 1,
"The Timbers" = 2,
"Woodside Apts" = 3,
"Gables Apts" = 4),
dorm_group = as.factor(dorm_group))
table(individualdemographics$dorm, individualdemographics$off_campus_num)
table(individualdemographics$off_campus_fac, individualdemographics$off_campus_num)
table(individualdemographics$dorm, individualdemographics$dorm_group)
table(individualdemographics$dorm_group_num, individualdemographics$dorm_group)
```
```{r demo-testing-merge}
## merge the testing and demographics datasets
demo_testing <- routinetesting %>%
left_join(individualdemographics, by="uid")
```
```{r demo-testing-merge-checks, eval=params$run_checks}
## missingness
summary(is.na(demo_testing))
## are the dimensions of `demo_testing` the same as `routine_testing`
nrow(demo_testing) == nrow(routinetesting)
## how many IDs have no testing information ever, in last 1 week, or in last 2 weeks?
tmp <- demo_testing %>%
mutate(tested_1week = ifelse((resultsdate > report_date_minus7 & resultsdate <= report_date) |
(collectdate > report_date_minus7 & collectdate <= report_date), 1, 0),
tested_2week = ifelse((resultsdate > report_date_minus14 & resultsdate <= report_date) |
(collectdate > report_date_minus14 & collectdate <= report_date), 1, 0))
individualdemographics %>%
group_by(campus, user_status) %>%
summarise(n_never_tested = sum(!(uid %in% tmp$uid), na.rm=TRUE),
n_not_tested_2week = sum(!(uid %in% tmp$uid[tmp$tested_2week==1])),
n_not_tested_1week = sum(!(uid %in% tmp$uid[tmp$tested_1week==1])))
## how complete does the testing data look for report period?
## using collectdate, which appears to be more complete
tmp %>%
filter(tested_1week == 1) %>%
group_by(collectdate) %>%
summarise(n_tests = n())
```
```{r isolation-recoding, include=params$show_cleaning}
## Recoding dates, date-times
isolationquarantine <- isolationquarantine %>%
mutate(quar_entrydttm = as.POSIXct(quar_entrydate),
quar_exitdttm = as.POSIXct(quar_exitdate),
quar_exposuredttm = as.POSIXct(quar_exposuredate),
iso_entrydttm = as.POSIXct(iso_entrydate),
iso_exitdttm = as.POSIXct(iso_exitdate),
quar_entrydate = as.Date(quar_entrydate),
quar_exitdate = as.Date(quar_exitdate),
quar_exposuredate = as.Date(quar_exposuredate),
iso_entrydate = as.Date(iso_entrydate),
iso_exitdate = as.Date(iso_exitdate),
notifydttm = as.POSIXct(notifydate),
notifydate = as.Date(notifydate))
## Recoding location
table(isolationquarantine$location)
table(isolationquarantine$dorm)
isolationquarantine <- isolationquarantine %>%
mutate(quar_isol_bed = ifelse(location=="Campus", 1, 0)) %>%
rename(dorm_isol = dorm)
isolationquarantine <- isolationquarantine %>%
mutate(location_num = recode(location,
"Campus" = 1,
"Home" = 2,
"Off-Campus - A/O" = 3,
"Off-Campus - Durham" = 4,
.default=5)) %>%
mutate(location_old = location,
location = factor(location_num,
levels = 1:5,
labels = c("Campus", "Home", "Off-Campus - A/O", "Off-Campus - Durham", "Other Campus/Unknown")))
```
```{r demo-isolation-merge}
## merge the isolation and demographics datasets
demo_isol <- isolationquarantine %>%
left_join(individualdemographics, by="uid")
```
```{r demo-isolation-checks, eval=params$run_checks}
## how many isolation/quar events don't have demo data?
summary(is.na(demo_isol))
## how many listed more than once?
demo_isol %>%
mutate(quar_ind = ifelse(is.na(quar_entrydate), 0, 1),
isol_ind = ifelse(is.na(iso_entrydate), 0, 1)) %>%
group_by(uid) %>%
summarise(n = n(),
n_quar = sum(quar_ind),
n_isol = sum(isol_ind)) %>%
ungroup() %>%
summarise(n_quar_morethanonce = sum(n_quar>1, na.rm=TRUE),
n_quar_morethantwice = sum(n_quar>2, na.rm = TRUE),
n_isol_morethanonce = sum(n_isol>1, na.rm=TRUE),
n_quar_and_isol = sum(n_isol>0 & n_quar>0, na.rm = TRUE))
## any overlapping quarantine periods?
demo_isol %>%
group_by(uid) %>%
filter(sum(!is.na(quar_entrydate)) > 1) %>%
arrange(uid, quar_entrydate) %>%
mutate(prev_quarexit = lag(quar_exitdate)) %>%
mutate(overlap = ifelse(prev_quarexit > quar_entrydate, 1, 0)) %>%
ungroup() %>%
filter(overlap==1) %>%
group_by(campus, user_status) %>%
summarise(n_overlapping_quar = n())
```
```{r isol-duplicates}
## remove duplicate/overlapping quarantines if they still exist
## favor entries that have complete notification date, location, isolation dorm
## first, find the IDs that have overlapping quarantine periods + the two overlapping entries
## then select the one to remove
demo_isol <- demo_isol %>%
mutate(ind = 1:n())
to_rm <- demo_isol %>%
group_by(uid) %>%
filter(sum(!is.na(quar_entrydate)) > 1) %>%
arrange(uid, quar_entrydate) %>%
mutate(prev_quarexit = lag(quar_exitdate)) %>%
mutate(overlap = ifelse(prev_quarexit > quar_entrydate, 1, 0)) %>%
mutate(overlap = max(overlap, na.rm = TRUE)) %>%
filter(overlap == 1) %>%
mutate(n_missing = sum(is.na(c(as.character(notifydate), location)), na.rm=TRUE)) %>%
arrange(desc(n_missing)) %>%
mutate(n = 1:n()) %>%
ungroup() %>%
filter(n==1)
demo_isol <- demo_isol %>%
filter(!(ind %in% to_rm$ind))
```
```{r isol-reformat, include=params$run_checks}
## create df of only quarantine events
demo_quar <- demo_isol %>%
filter(!is.na(quar_entrydate))
## any weird dates?
reasonable_dates <- as.Date(as.Date("2020-01-01"):as.Date("2022-01-01"), origin="1970-01-01")
demo_quar %>%
filter(!(quar_entrydate %in% reasonable_dates) | !(quar_exitdate %in% reasonable_dates)) %>%
group_by(campus_fac, user_status_fac) %>%
summarise(n_weird_quar_dates=n())
## TO DO: for now, filtering out those weird dates
demo_quar <- demo_quar %>%
filter((quar_entrydate %in% reasonable_dates) & (quar_exitdate %in% reasonable_dates))
## create df of only isolation events
## checks whether dates are reasonable
## filters to only include those reasonable events
demo_isol <- demo_isol %>%
filter(!is.na(iso_entrydate))
demo_isol %>%
filter(!(iso_entrydate %in% reasonable_dates) | !(iso_exitdate %in% reasonable_dates)) %>%
group_by(campus_fac, user_status_fac) %>%
summarise(n_weird_isol_dates=n())
demo_isol <- demo_isol %>%
filter((iso_entrydate %in% reasonable_dates) & (iso_exitdate %in% reasonable_dates))
## create long quarantine dataset (1 row per ID, per day in quarantine)
## TO DO: this imputes any missing exit dates with the entry date + 10
demo_quar_long <- demo_quar %>%
mutate(quar_exitdate = ifelse(is.na(quar_exitdate) & !is.na(quar_entrydate),
quar_entrydate + 10,
quar_exitdate)) %>%
mutate(quar_exitdate = as.Date(quar_exitdate, origin="1970-01-01")) %>%
rowwise() %>%
do(data.frame(date = .$quar_entrydate:.$quar_exitdate,
uid = .$uid,
location = .$location,
dorm_isol = .$dorm_isol,
quar_isol_bed = .$quar_isol_bed,
campus_fac = .$campus_fac,
off_campus_fac = .$off_campus_fac,
user_status_fac = .$user_status_fac))
demo_isol_long <- demo_isol %>%
replace_na(list(iso_exitdate = report_date)) %>%
rowwise() %>%
do(data.frame(date = .$iso_entrydate:.$iso_exitdate,
uid = .$uid,
location = .$location,
dorm_isol = .$dorm_isol,
quar_isol_bed = .$quar_isol_bed,
campus_fac = .$campus_fac,
off_campus_fac = .$off_campus_fac,
user_status_fac = .$user_status_fac))
```
```{r demo-testing-long-cleaning, include=params$show_cleaning}
## Rename variables to be more accurate: collectdate > labeldate, collecttime > labeltime
demo_testing <- demo_testing %>%
rename(labeldate = collectdate,
labeltime = collecttime)
## numeric test result
## 0 "Neg"; 1 "Pos"; 2 "Inconclusive"; 3 "Invalid/Rejected/No Result"
table(tolower(demo_testing$result))
demo_testing <- demo_testing %>%
mutate(result = tolower(result)) %>%
mutate(result_num = recode(result,
"negative" = 0,
"positive" = 1,
"test was positive provided letter to be on campus" = 1,
"inconclusive" = 2,
.default = 3)) %>%
mutate(result_fac = factor(result_num,
levels = 0:3,
labels = c("Negative", "Positive", "Inconclusive", "Invalid/Rejected/No Result")))
table(demo_testing$result, demo_testing$result_num)
table(demo_testing$result_fac, demo_testing$result_num)
## recode dates
## uses resultsdate, unless missing, then uses labeldate
demo_testing <- demo_testing %>%
mutate(testdate = ifelse(is.na(resultsdate), labeldate, resultsdate)) %>%
mutate(testdate = as.Date(testdate, origin="1970-01-01"))
## numeric laboratory indicator
## 0 "Sequoia"; 1 "Convenient MD"; 2 "Health & Wellness"; 3 "Pre-Arrival"; 4 "Quest"; 5 "Temp UNH Lab"
table(tolower(demo_testing$laboratory))
demo_testing <- demo_testing %>%
mutate(laboratory = tolower(laboratory)) %>%
mutate(laboratory_num = recode(laboratory,
"sequoia" = 0,
"cmd" = 1,
"healthwellnesslab" = 2,
"prearrival" = 3,
"quest" = 4,
"unhlab_temp" = 5)) %>%
mutate(laboratory_fac = factor(laboratory_num,
levels = 0:5,
labels = c("Sequoia", "Convenient MD", "Health + Wellness", "Pre-Arrival", "Quest", "UNH Temp.")))
table(demo_testing$laboratory, demo_testing$laboratory_num)
table(demo_testing$laboratory_fac, demo_testing$laboratory_num)
## binary test result indicators in long data - pos, neg, incon, invalid
demo_testing <- demo_testing %>%
mutate(pos = ifelse(result_num == 1, 1, 0),
neg = ifelse(result_num == 0, 1, 0),
incon = ifelse(result_num == 2, 1, 0),
invalid = ifelse(result_num == 3, 1, 0))
## remove duplicate test results (labeldate, resultsdate, result, laboratory)
demo_testing <- demo_testing %>%
distinct_at(vars(uid, testdate, result, laboratory), .keep_all = TRUE)
## make sure those positive once do not have positive counted more than once
## for each positive test result, check if there is another positive test result in the next 10 days
## QUESTION: repeat positives are currently dropped altogether
demo_testing <- demo_testing %>%
mutate(posdate = ifelse(result_num==1, testdate, NA)) %>%
group_by(uid) %>%
arrange(desc(pos), testdate) %>%
fill(posdate) %>%
mutate(posdate_diff = c(-1, diff(posdate))) %>%
mutate(dup_pos = ifelse(result_num==1 & !is.na(posdate) & posdate_diff >= 0 & posdate_diff < 10, 1, 0)) %>%
ungroup() %>%
filter(dup_pos == 0)
## add epiweek
## add indicators for whether testdate is within 7 or 10 days of report date
demo_testing <- demo_testing %>%
mutate(epiweek = epiweek(testdate),
test_10days = ifelse(testdate <= report_date & testdate > report_date_minus10, 1, 0),
test_7days = ifelse(testdate <= report_date & testdate > report_date_minus7, 1, 0))
## create data frame just of positive tests, without duplicates
cases <- demo_testing %>%
filter(result_fac=="Positive")
```
```{r demo-testing-wide, include=params$run_checks}
## KYRA: I don't think we actually need this wide dataset? I think the summarized datasets below are more helpful
## by UID, add a sample number
## then make wide dataset by ID
# demo_testing_wide <- demo_testing %>%
# group_by(uid) %>%
# mutate(sample_id = 1:n()) %>%
# ungroup() %>%
# select(uid, sample_id, testdate, result_fac, laboratory_fac) %>%
# pivot_wider(id_cols = uid, names_from = sample_id, values_from = c(testdate, result_fac, laboratory_fac))
## print out max # of times someone was tested
## active case indicator: who had a positive test in the last 10 days report_date_minus10 - report_date
## 7-day case indicator
## tested in last 10 days indicator
demo_testing_sum <- demo_testing %>%
group_by(uid) %>%
summarize(n_test = n(),
n_test_10day = sum(test_10days, na.rm=TRUE),
n_test_7days = sum(test_7days, na.rm=TRUE),
n_pos = sum(pos, na.rm=TRUE),
n_pos_10day = sum(pos*test_10days, na.rm=TRUE),
n_pos_7day = sum(pos*test_7days, na.rm=TRUE),
case_10day = ifelse(n_pos_10day>0, 1, 0),
case_7day = ifelse(n_pos_7day>0, 1, 0),
tested_10day = ifelse(n_test_10day>0, 1, 0),
tested_7day = ifelse(n_test_7days>0, 1, 0)) %>%
left_join(individualdemographics, by="uid")
## most recent lab result if tested in past week
## pull out most recent test result for anyone tested in last week
## (if there is more than one test on the last test date, use the positive)
## QUESTION: worth having this as an indicator in the long dataset?
demo_testing_recent <- demo_testing %>%
filter(test_7days == 1) %>%
group_by(uid) %>%
arrange(desc(testdate), desc(pos)) %>%
slice(1)
```
```{r totals-by-date}
## data frame: number first positive by campus, role, testdate
ts_cases_role <- cases %>%
group_by(testdate, campus_fac, user_status_fac) %>%
summarize(n = n()) %>%
ungroup()
## data frame: number first positive by campus status, campus, testdate
ts_cases_offcamp <- cases %>%
group_by(testdate, campus_fac, off_campus_fac) %>%
summarize(n = n()) %>%
ungroup()
## data frame: number first positive by campus, testdate
ts_cases_campus <- cases %>%
group_by(testdate, campus_fac) %>%
summarize(n = n())
# data frame: active cases by day, by campus, by off/on campus for students only
rollsum <- rollify(sum, window=7)
ts_active_offcamp <- cases %>%
filter(user_status_fac=="Student") %>%
group_by(testdate, campus_fac, off_campus_fac) %>%
summarize(n = n()) %>%
ungroup() %>%
group_by(campus_fac, off_campus_fac) %>%
complete(testdate = as.Date(as.Date("2020-07-15"):report_date, origin="1970-01-01")) %>%
replace_na(list(n=0)) %>%
arrange(testdate) %>%
mutate(active_cases = rollsum(n)) %>%
ungroup()
# data frame: active cases by day, by campus, by dorm for students only
# note: this is not currently used anywhere, but may be needed for automated text triggers
ts_active_dorm <- cases %>%
filter(user_status_fac=="Student") %>%
group_by(testdate, campus_fac, dorm) %>%
summarize(n = n()) %>%
ungroup() %>%
group_by(campus_fac, dorm) %>%
complete(testdate = as.Date(as.Date("2020-07-15"):report_date, origin="1970-01-01")) %>%
replace_na(list(n=0)) %>%
arrange(testdate) %>%
mutate(active_cases = rollsum(n)) %>%
ungroup()
## data frame: number pos, neg, incon, invalid, pos+neg, by campus, role, testdate
ts_test_res <- demo_testing %>%
mutate(test = 1) %>%
group_by(testdate, campus_fac, user_status_fac) %>%
select(test, pos, neg, incon, invalid) %>%
summarise_all(sum) %>%
mutate(pos_neg = pos + neg,
pct_pos = pos / pos_neg) %>%
ungroup()
## data frame: number total tests, by campus, lab, testdate
ts_test_lab <- demo_testing %>%
group_by(testdate, campus_fac, laboratory_fac) %>%
summarise(n_test = n(),
n_valid = n() - sum(invalid),
n_with_res = sum(neg) + sum(pos)) %>%
ungroup()
## data frame: number pos, neg, pos+neg by week
ts_test_res_wk_all <- ts_test_res %>%
filter(testdate <= report_date) %>%
mutate(weeks_prior = as.numeric(report_date - testdate)%/%7) %>%
group_by(weeks_prior) %>%
summarise(pos = sum(pos),
neg = sum(neg),
pos_neg = pos + neg,
pct_pos = pos / pos_neg) %>%
mutate(start_date = report_date - 7*weeks_prior - 6,
end_date = report_date - 7*weeks_prior,
label = glue("{format(start_date, '%b %d')} - {format(end_date, '%b %d')}"))
## data frame: number pos, neg, pos+neg by week, campus
ts_test_res_wk_camp <- ts_test_res %>%
filter(testdate <= report_date) %>%
mutate(weeks_prior = as.numeric(report_date - testdate)%/%7) %>%
group_by(weeks_prior, campus_fac) %>%
summarise(pos = sum(pos),
neg = sum(neg),
test = sum(test),
pos_neg = pos + neg,
pct_pos = pos / pos_neg) %>%
ungroup() %>%
mutate(start_date = report_date - 7*weeks_prior - 6,
end_date = report_date - 7*weeks_prior,
label = glue("{format(start_date, '%b %d')} - {format(end_date, '%b %d')}"))
## data frame: number pos, neg, pos+neg by week, campus, user_status
ts_test_res_wk_role <- ts_test_res %>%
filter(testdate <= report_date) %>%
mutate(weeks_prior = as.numeric(report_date - testdate)%/%7) %>%
group_by(weeks_prior, campus_fac, user_status_fac) %>%
summarise(pos = sum(pos),
neg = sum(neg),
test = sum(test),
pos_neg = pos + neg,
pct_pos = pos / pos_neg) %>%
ungroup() %>%
mutate(start_date = report_date - 7*weeks_prior - 6,
end_date = report_date - 7*weeks_prior,
label = glue("{format(start_date, '%b %d')} - {format(end_date, '%b %d')}"))
## long versions of quarantine and isolation
## data frame: number in quarantine by campus, role, testdate
ts_quar_role <- demo_quar_long %>%
group_by(date, campus_fac, user_status_fac) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
## data frame: number in quarantine by location, campus, testdate
ts_quar_offcamp <- demo_quar_long %>%
group_by(date, campus_fac, location) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
## data frame: number in quarantine by campus, testdate
ts_quar_campus <- demo_quar_long %>%
group_by(date, campus_fac, off_campus_fac) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
## data frame: number entering quarantine by campus, residence dorm
ts_quar_ent_dorm <- demo_quar %>%
group_by(quar_entrydate, campus_fac, dorm) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(quar_entrydate, origin="1970-01-01"))
## data frame: number in quarantine by campus, residence dorm
ts_quar_dorm <- demo_quar_long %>%
left_join(demo_quar %>% select(uid, dorm), by="uid") %>%
group_by(date, campus_fac, dorm) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
## data frame: number in isolation by campus, role, testdate
ts_isol_role <- demo_isol_long %>%
group_by(date, campus_fac, user_status_fac) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
## data frame: number in isolation by location, campus, testdate
ts_isol_offcamp <- demo_isol_long %>%
group_by(date, campus_fac, location) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
## data frame: number in isolation by campus, testdate
ts_isol_campus <- demo_isol_long %>%
group_by(date, campus_fac, off_campus_fac) %>%
summarize(n = n_distinct(uid),
nbed = sum(quar_isol_bed, na.rm=TRUE)) %>%
ungroup() %>%
mutate(date = as.Date(date, origin="1970-01-01"))
```
```{r map loading}
box = c(xmin = 1177000 , xmax = 1183000 ,ymin=229500,ymax=237000 )
BaseMap <- read_sf("shapefiles/UNH_Basemap.shp")
Buildings <- read_sf("shapefiles/UNH_Buildings.shp")%>%
st_crop(box)
sidewalks <- filter(BaseMap,LAND_USE=="Sidewalk")%>%
st_make_valid()%>%
st_crop(box)
greenspace <- filter(BaseMap,LAND_USE=="Green Space")%>%
st_make_valid()%>%
st_crop(box)
```
```{r isol-quar-projections}
## QUARANTINE PROJECTIONS
# finding the number of individuals who entered quarantined (by on/off campus status)
# in the 7 days prior to report period
# then projecting those entries forward to act as 'new' entries in the 7 days
# after the report period
new_entry_quar <- demo_quar %>%
filter(!is.na(quar_entrydate)) %>%
filter(quar_isol_bed==1) %>%
group_by(quar_entrydate, campus_fac, off_campus_fac) %>%
summarise(n = n()) %>%
ungroup() %>%
filter(quar_entrydate > report_date_minus7 & quar_entrydate <= report_date) %>%
expand_grid(.,
scaling_factor = c(0.5, 1, 4)) %>%
rename(quar_entrydate_actual = quar_entrydate) %>%
# shift everything forward 7 days
mutate(quar_entrydate = quar_entrydate_actual + 7) %>%
# assign quarantine exit date
mutate(quar_exitdate = quar_entrydate + 10)
new_entry_quar_long <- new_entry_quar %>%
# apply scaling factor
mutate(n = n*scaling_factor) %>%
rowwise() %>%
do(data.frame(n = 1:.$n,
quar_entrydate = .$quar_entrydate,
quar_exitdate = .$quar_exitdate,
campus_fac = .$campus_fac,
off_campus_fac = .$off_campus_fac,
scaling_fac = .$scaling_factor)) %>%
do(data.frame(date = .$quar_entrydate:.$quar_exitdate,
campus_fac = .$campus_fac,
off_campus_fac = .$off_campus_fac,
scaling_fac = .$scaling_fac)) %>%
mutate(date = as.Date(date, origin="1970-01-01"))
# actual quarantine use for the next seven days
to_add_quar <- ts_quar_campus %>%
expand_grid(scaling_fac = c(0.5, 1, 4))
# adding in total
to_add_quar <- to_add_quar %>%
group_by(campus_fac, date, scaling_fac) %>%
summarize(nbed=sum(nbed)) %>%
mutate(off_campus_fac = "Total") %>%
bind_rows(to_add_quar) %>%
mutate(scaling_fac = glue::glue("{scaling_fac}"))
# adding in total with 4x scaling factor, without off-campus
to_add_quar <- to_add_quar %>%
filter(off_campus_fac=="Total" & scaling_fac==4) %>%
mutate(scaling_fac = "4 w/o off-campus") %>%
bind_rows(to_add_quar)
# projected quarantine use (adding in projected new entries with actual known use)
ts_quar_proj <- new_entry_quar_long %>%
group_by(date, campus_fac, off_campus_fac, scaling_fac) %>%
summarize(nbed = n()) %>%
ungroup() %>%
mutate(scaling_fac = glue::glue("{scaling_fac}"))
# formatting to add in 'total' + 'total w/o off-campus' categories
ts_quar_proj <- ts_quar_proj %>%
group_by(campus_fac, date, scaling_fac) %>%
summarize(nbed=sum(nbed)) %>%
mutate(off_campus_fac = "Total") %>%
bind_rows(ts_quar_proj)
ts_quar_proj <- ts_quar_proj %>%
filter(off_campus_fac=="On Campus" & scaling_fac==4) %>%
mutate(off_campus_fac="Total") %>%
mutate(scaling_fac = "4 w/o off-campus") %>%
bind_rows(ts_quar_proj)
ts_quar_proj_final <- ts_quar_proj %>%
bind_rows(to_add_quar) %>%
group_by(date, campus_fac, off_campus_fac, scaling_fac) %>%
summarize(nbed=sum(nbed)) %>%
filter(date >= report_date_minus7)
# formatting to add in 'actual' categories
ts_quar_actual <- ts_quar_campus %>%
filter(date >= report_date_minus7 & date <= report_date) %>%
select(-n) %>%
mutate(scaling_fac = "Actual") %>%
distinct()
ts_quar_actual <- ts_quar_actual %>%
group_by(date, campus_fac, scaling_fac) %>%
summarise(nbed = sum(nbed)) %>%
mutate(off_campus_fac="Total") %>%
bind_rows(ts_quar_actual)
ts_quar_proj_final <- ts_quar_actual %>%
bind_rows(ts_quar_proj_final %>% filter(date >= report_date))
## ISOLATION PROJECTIONS
# finding the number of individuals who entered isolation (by on/off campus status)
# in the 7 days prior to report period
# then projecting those entries forward to act as 'new' entries in the 7 days
# after the report period
new_entry_isol <- demo_isol %>%
filter(!is.na(iso_entrydate)) %>%
filter(quar_isol_bed==1) %>%
group_by(iso_entrydate, campus_fac, off_campus_fac) %>%
summarise(n = n()) %>%
ungroup() %>%
filter(iso_entrydate > report_date_minus7 & iso_entrydate <= report_date) %>%
expand_grid(.,
scaling_factor = c(0.5, 1, 4)) %>%
rename(iso_entrydate_actual = iso_entrydate) %>%
# shift everything forward 7 days
mutate(iso_entrydate = iso_entrydate_actual + 7) %>%
# assign quarantine exit date
mutate(iso_exitdate = iso_entrydate + 13)
new_entry_isol_long <- new_entry_isol %>%
# apply scaling factor
mutate(n = n*scaling_factor) %>%