library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(lubridate)
Attaching package: 'lubridate'The following objects are masked from 'package:base':
date, intersect, setdiff, unionlibrary(readr)
library(tidyr)
library(plotrix)Warning: package 'plotrix' was built under R version 4.4.3sensor <- read_csv("Z:/Isaac/Visual Features/1-5/BioCV_Cohorts_6-7.csv",col_types = cols(
Id_Bio_Cohort = col_factor(),
Bio_ID = col_factor(),
Cohort = col_factor(),
Date = col_date(format = "%m/%d/%Y"),
Loading_date = col_date(format = "%m/%d/%Y"),
Loading_parity= col_integer(),
Sow_ID = col_factor(),
Time = col_character(),
Weaning_date = col_date(format = "%m/%d/%Y"),
c = col_double(),
sensor_ts = col_datetime(),
x = col_double(),
y = col_double(),
z = col_double(),
format = col_character(),
Entry_Far_Room= col_date(),
FD_Gestal = col_date(),
FDM1 = col_date(),
FD_Porcitec = col_date(),
Wean_Porcitec = col_date(),
FARRFAIL = col_integer(),
LACTFAIL = col_integer()
)
)
prod_rec <- read.csv("Z:/Isaac/Visual Features/1-5/Production_cohorts_6_7.csv")str(sensor)spc_tbl_ [2,793,343 × 22] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
$ Id_Bio_Cohort : Factor w/ 191 levels "34009_6_1024",..: 1 1 1 1 1 1 1 1 1 1 ...
$ Bio_ID : Factor w/ 111 levels "1024","1006",..: 1 1 1 1 1 1 1 1 1 1 ...
$ Cohort : Factor w/ 2 levels "6","7": 1 1 1 1 1 1 1 1 1 1 ...
$ Date : Date[1:2793343], format: "2025-03-30" "2025-03-30" ...
$ Loading_date : Date[1:2793343], format: "2025-03-30" "2025-03-30" ...
$ Loading_parity: int [1:2793343] NA NA NA NA NA NA NA NA NA NA ...
$ Sow_ID : Factor w/ 191 levels "34009","28352",..: 1 1 1 1 1 1 1 1 1 1 ...
$ Time : chr [1:2793343] "00:00:00" "00:01:00" "00:02:00" "00:03:00" ...
$ Weaning_date : Date[1:2793343], format: "2025-04-25" "2025-04-25" ...
$ c : num [1:2793343] 30.3 30.3 30.3 30.3 30.4 ...
$ sensor_ts : POSIXct[1:2793343], format: "2025-03-30 00:00:00" "2025-03-30 00:01:00" ...
$ x : num [1:2793343] 0.34 0.338 0.338 0.332 0.332 ...
$ y : num [1:2793343] -0.328 -0.336 -0.336 -0.363 -0.363 ...
$ z : num [1:2793343] 0.877 0.875 0.875 0.879 0.879 ...
$ format : chr [1:2793343] "%Y/%m/%d %H:%M" "%Y/%m/%d %H:%M" "%Y/%m/%d %H:%M" "%Y/%m/%d %H:%M" ...
$ Entry_Far_Room: Date[1:2793343], format: "2025-03-30" "2025-03-30" ...
$ FD_Gestal : Date[1:2793343], format: "2025-04-02" "2025-04-02" ...
$ FDM1 : Date[1:2793343], format: "2025-04-01" "2025-04-01" ...
$ FD_Porcitec : Date[1:2793343], format: "2025-04-02" "2025-04-02" ...
$ Wean_Porcitec : Date[1:2793343], format: "2025-04-21" "2025-04-21" ...
$ FARRFAIL : int [1:2793343] 0 0 0 0 0 0 0 0 0 0 ...
$ LACTFAIL : int [1:2793343] 0 0 0 0 0 0 0 0 0 0 ...
- attr(*, "spec")=
.. cols(
.. Id_Bio_Cohort = col_factor(levels = NULL, ordered = FALSE, include_na = FALSE),
.. Bio_ID = col_factor(levels = NULL, ordered = FALSE, include_na = FALSE),
.. Cohort = col_factor(levels = NULL, ordered = FALSE, include_na = FALSE),
.. Date = col_date(format = "%m/%d/%Y"),
.. Loading_date = col_date(format = "%m/%d/%Y"),
.. Loading_parity = col_integer(),
.. Sow_ID = col_factor(levels = NULL, ordered = FALSE, include_na = FALSE),
.. Time = col_character(),
.. Weaning_date = col_date(format = "%m/%d/%Y"),
.. c = col_double(),
.. sensor_ts = col_datetime(format = ""),
.. x = col_double(),
.. y = col_double(),
.. z = col_double(),
.. format = col_character(),
.. Entry_Far_Room = col_date(format = ""),
.. FD_Gestal = col_date(format = ""),
.. FDM1 = col_date(format = ""),
.. FD_Porcitec = col_date(format = ""),
.. Wean_Porcitec = col_date(format = ""),
.. FARRFAIL = col_integer(),
.. LACTFAIL = col_integer()
.. )
- attr(*, "problems")=<externalptr> str(prod_rec)'data.frame': 200 obs. of 105 variables:
$ Id_Bio_Cohort : chr "29963_6_1072" "24555_6_15" "29823_6_20" "28475_6_33" ...
$ ID : int 29963 24555 29823 28475 28368 33390 34023 28225 33954 25503 ...
$ Cohort : int 6 6 6 6 6 6 6 6 6 6 ...
$ Bio_ID : int 1072 15 20 33 42 44 1001 1007 1013 1026 ...
$ source_file_x : chr "24_28_00_00_02_98" "24_28_00_00_02_12" "24_28_00_00_05_91" "24_28_00_00_03_81" ...
$ Entry_Far_Room: chr "3/30/25" "3/29/25" "3/29/25" "3/29/25" ...
$ FD_Gestal : chr "4/4/25" "4/2/25" "4/1/25" "4/2/25" ...
$ FDM1 : chr "4/3/25" "4/1/25" "3/31/25" "4/1/25" ...
$ FD_Porcitec : chr "11/11/24" "11/5/24" "4/1/25" "11/7/24" ...
$ Wean_Porcitec : chr "4/27/25" "4/29/25" "4/21/25" "4/27/25" ...
$ PARITY : int 0 5 1 1 2 2 3 1 2 4 ...
$ TOTALBORN : int 14 12 20 18 14 14 21 18 22 22 ...
$ LIVEBORN : int 14 12 19 17 12 12 16 17 18 17 ...
$ STILLBORN : int 0 0 1 1 2 2 1 0 0 2 ...
$ MUMMIES : int 0 0 0 0 0 0 4 1 4 3 ...
$ NURSEOFF : int 0 0 0 0 0 0 0 0 16 0 ...
$ NURSEON : int 0 0 0 0 0 0 0 0 0 0 ...
$ FOSTEROFF : int 0 0 5 1 0 0 1 1 3 3 ...
$ FOSTERON : int 0 4 0 0 3 3 0 0 0 0 ...
$ WEAN1NUM : int 14 12 14 13 13 14 13 13 0 12 ...
$ WEANFSTSERV : int 3 4 6 4 6 4 6 4 NA 4 ...
$ REMOVEDATE : chr "" "" "" "" ...
$ REMOVEREASON : chr "" "" "" "" ...
$ CAL_LACT_DAY : int 23 27 20 25 19 24 19 22 13 26 ...
$ FARRFAIL : int 0 0 0 0 0 0 0 0 0 0 ...
$ LACTFAIL : int 0 0 0 0 0 0 0 0 1 0 ...
$ Lact_day_N3 : int -3 -3 NA -3 -3 -3 -3 -3 -3 -3 ...
$ Water_L_N3 : num 6.9 0 NA 8.9 8.73 ...
$ Consumed_N3 : num 5.66 4.35 NA 4.4 4.41 4.32 4.64 4.23 4.3 4.37 ...
$ Lact_day_N2 : int -2 -2 -2 -2 -2 -2 -2 -2 -2 -2 ...
$ Water_L_N2 : num 13.27 0 19.69 10.01 7.29 ...
$ Consumed_N2 : num 5.87 4.43 5.81 4.38 4.43 4.29 4.3 4.09 4.29 4.37 ...
$ Lact_day_N1 : int -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
$ Water_L_N1 : num 10 0 18.8 17.7 12.3 ...
$ Consumed_N1 : num 5.42 4.63 5.93 4.52 4.4 3.13 4.44 1.93 4.53 4.38 ...
$ Lact_day_0 : int 0 0 0 0 0 0 0 0 0 0 ...
$ Water_L_0 : num 10.13 0 22.47 11.77 8.24 ...
$ Consumed_0 : num 6.96 4.72 6.53 5.23 5 4.49 3.83 1.37 4.84 6.62 ...
$ Lact_day_1 : int 1 1 1 1 1 1 1 1 1 1 ...
$ Water_L_1 : num 12.9 0 25 13.7 14.1 ...
$ Consumed_1 : num 10.99 11.68 10.82 7.78 9.64 ...
$ Lact_day_2 : int 2 2 2 2 2 2 2 2 2 2 ...
$ Water_L_2 : num 13.6 0 32.5 17.4 11.7 ...
$ Consumed_2 : num 11.7 15.3 13.7 12.8 10.9 ...
$ Lact_day_3 : int 3 3 3 3 3 3 3 3 3 3 ...
$ Water_L_3 : num 16.9 0 41.3 23 21.4 ...
$ Consumed_3 : num 17.1 17.7 18.2 17.2 14.8 ...
$ Lact_day_4 : int 4 4 4 4 4 4 4 4 4 4 ...
$ Water_L_4 : num 19.5 0 42.1 26.2 18.2 ...
$ Consumed_4 : num 17.3 16.7 19.4 19.9 12.9 ...
$ Lact_day_5 : int 5 5 5 5 5 5 5 5 5 5 ...
$ Water_L_5 : num 21.6 0 42.8 22.2 24.1 ...
$ Consumed_5 : num 16.9 17.9 15 14.7 13.6 ...
$ Lact_day_6 : int 6 6 6 6 6 6 6 6 6 6 ...
$ Water_L_6 : num 21.3 0 39.2 28.5 18.7 ...
$ Consumed_6 : num 20.1 19.9 14.9 18.4 13.8 ...
$ Lact_day_7 : int 7 7 7 7 7 7 7 7 7 7 ...
$ Water_L_7 : num 25.8 0 45.7 36.4 24.9 ...
$ Consumed_7 : num 20.6 20.9 23.9 22.5 17.2 ...
$ Lact_day_8 : int 8 8 8 8 8 8 8 8 8 8 ...
$ Water_L_8 : num 26.7 0 49 41 22.6 ...
$ Consumed_8 : num 23.9 23.7 22.6 25.9 19.9 ...
$ Lact_day_9 : int 9 9 9 9 9 9 9 9 9 9 ...
$ Water_L_9 : num 27.2 0 43.5 41.7 22.8 ...
$ Consumed_9 : num 19.7 23.1 21.3 24.7 15.2 ...
$ Lact_day_10 : int 10 10 10 10 10 10 10 10 10 10 ...
$ Water_L_10 : num 23.8 0 41.8 53.9 30.4 ...
$ Consumed_10 : num 21.4 25.2 25.2 25.6 18.6 ...
$ Lact_day_11 : int 11 11 11 11 11 11 11 11 11 11 ...
$ Water_L_11 : num 28.4 0 49.6 58.1 27.5 ...
$ Consumed_11 : num 21.4 19.7 21.4 22.5 15.2 ...
$ Lact_day_12 : int 12 12 12 12 12 12 12 12 12 12 ...
$ Water_L_12 : num 31 0 50.3 49.9 28.5 ...
$ Consumed_12 : num 24.4 23.5 15.8 21.1 14.3 ...
$ Lact_day_13 : int 13 13 13 13 13 13 13 13 13 13 ...
$ Water_L_13 : num 23.4 0 42.5 48.9 26.6 ...
$ Consumed_13 : num 19.7 25.4 18.9 23.4 18.6 ...
$ Lact_day_14 : int 14 14 14 14 14 14 14 14 14 14 ...
$ Water_L_14 : num 41.1 0 41.4 49.9 27.1 ...
$ Consumed_14 : num 24.3 18.8 25 26 17.8 ...
$ Lact_day_15 : int 15 15 15 15 15 15 15 15 15 15 ...
$ Water_L_15 : num 25.5 0 47.4 44.3 26.9 ...
$ Consumed_15 : num 28.8 19.5 18.9 21.3 18 ...
$ Lact_day_16 : int 16 16 16 16 16 16 16 16 16 16 ...
$ Water_L_16 : num 28.6 0 40.7 54.2 19.2 ...
$ Consumed_16 : num 22.1 23.4 20.2 18.9 13.1 ...
$ Lact_day_17 : int NA 17 17 17 17 17 17 17 17 17 ...
$ Water_L_17 : num NA 0 86.3 35.7 25.7 ...
$ Consumed_17 : num NA 26.5 23 24.3 14.4 ...
$ Lact_day_18 : int NA 18 18 18 18 NA 18 NA 18 18 ...
$ Water_L_18 : num NA 0 56.5 44.2 28.2 ...
$ Consumed_18 : num NA 22.5 23.1 25.6 19.3 ...
$ Lact_day_19 : int NA NA 19 NA NA NA NA NA NA NA ...
$ Water_L_19 : num NA NA 54.4 NA NA ...
$ Consumed_19 : num NA NA 21.2 NA NA ...
$ Lact_day_20 : int NA NA NA NA NA NA NA NA NA NA ...
$ Water_L_20 : num NA NA NA NA NA NA NA NA NA NA ...
$ Consumed_20 : num NA NA NA NA NA NA NA NA NA NA ...
$ Lact_day_21 : int NA NA NA NA NA NA NA NA NA NA ...
[list output truncated]length(unique(sensor$Sow_ID))[1] 191focused <- sensor %>%
select(Sow_ID,Cohort,sensor_ts,FD_Gestal,c,x,y,z)
colnames(focused)[1] "Sow_ID" "Cohort" "sensor_ts" "FD_Gestal" "c" "x"
[7] "y" "z" focused10 <- focused %>%
mutate(
window10 = floor_date(sensor_ts, unit = "10 minutes")
)library(dplyr)
df_window_summary <- focused10 %>%
group_by(Sow_ID, window10) %>%
summarise(
mean_x = mean(x, na.rm = TRUE),
var_x = var(x, na.rm = TRUE),
mean_y = mean(y, na.rm = TRUE),
var_y = var(y, na.rm = TRUE),
mean_z = mean(z, na.rm = TRUE),
var_z = var(z, na.rm = TRUE),
mean_c = mean(c, na.rm = TRUE),
var_c = var(c, na.rm = TRUE),
n_obs = n(), # optional but VERY useful
FD_Gestal = first(FD_Gestal),
.groups = "drop"
)nested_sensor <- df_window_summary %>%
group_by(Sow_ID) %>%
nest()library(dplyr)
sow_time_summary <- df_window_summary %>%
group_by(Sow_ID) %>%
summarise(
first_obs = min(window10, na.rm = TRUE),
last_obs = max(window10, na.rm = TRUE),
n_windows = n(),
FD_Gestal = first(FD_Gestal),
hr_before = as.numeric(
difftime(first(FD_Gestal), first_obs, units = "hours")
),
duration_hours = as.numeric(difftime(last_obs, first_obs, units = "hours")),
.groups = "drop"
)
sow_time_summary# A tibble: 191 × 7
Sow_ID first_obs last_obs n_windows FD_Gestal hr_before
<fct> <dttm> <dttm> <int> <date> <dbl>
1 34009 2025-03-30 00:00:00 2025-03-31 07:40:00 147 2025-04-02 72
2 28352 2025-04-02 07:00:00 2025-04-24 10:00:00 2552 2025-04-03 17
3 30071 2025-04-27 09:10:00 2025-04-27 09:40:00 4 2025-04-29 38.8
4 28918 2025-04-23 09:50:00 2025-05-04 12:40:00 1458 2025-04-27 86.2
5 33981 2025-03-30 12:20:00 2025-04-20 09:30:00 2487 2025-04-02 59.7
6 26441 2025-04-23 09:50:00 2025-05-01 18:50:00 879 2025-04-27 86.2
7 28380 2025-03-30 12:20:00 2025-04-07 11:30:00 975 2025-04-01 35.7
8 31719 2025-04-23 09:50:00 2025-05-04 12:40:00 1455 2025-04-27 86.2
9 34585 2025-03-30 00:00:00 2025-04-20 10:50:00 2890 2025-04-04 120
10 29914 2025-04-23 09:50:00 2025-05-04 12:40:00 1459 2025-04-25 38.2
# ℹ 181 more rows
# ℹ 1 more variable: duration_hours <dbl>my32sows <- c('34113','31336','31460','28927','34023','28829','31043','29934','25618','28442','24555','30312','28475','28507','29818','28806','31024','30212','34041','31719','33390','31520','34096','29933','29284','26413','30094','29989','28110','31229','33981','31482')
mysowlengthsum <- sow_time_summary %>% filter(as.character(Sow_ID) %in% my32sows)save(sow_time_summary,my32sows,nested_sensor,file="Z:/Isaac/Visual Features/1-5/Sensors/3_2.RData")sowsum <- sow_time_summary %>%
summarise(
n_sows = length(unique(Sow_ID)),
mean_hr_before = mean(hr_before,na.rm=TRUE),
se_hr_before = std.error(hr_before,na.rm=TRUE),
min_hr_before = min(hr_before,na.rm=TRUE),
max_hr_before = max(hr_before,na.rm=TRUE),
n_less_than_50 = sum(hr_before < 50,na.rm=TRUE),
n_greater_than_50 = sum(hr_before > 50, na.rm = TRUE),
n_greater_than_100 = sum(hr_before > 100, na.rm=TRUE)
)
sowsumlong <- sowsum %>%
pivot_longer(
cols=everything(),
names_to = "statistic",
values_to = "value"
)
sowsumlong# A tibble: 8 × 2
statistic value
<chr> <dbl>
1 n_sows 191
2 mean_hr_before 67.9
3 se_hr_before 2.05
4 min_hr_before 11.7
5 max_hr_before 144
6 n_less_than_50 44
7 n_greater_than_50 143
8 n_greater_than_100 17 mysowsum <- sow_time_summary %>%
filter(as.character(Sow_ID)%in% my32sows) %>%
summarise(
n_sows = length(unique(Sow_ID)),
mean_hr_before = mean(hr_before,na.rm=TRUE),
se_hr_before = std.error(hr_before,na.rm=TRUE),
min_hr_before = min(hr_before,na.rm=TRUE),
max_hr_before = max(hr_before,na.rm=TRUE),
n_less_than_50 = sum(hr_before < 50,na.rm=TRUE),
n_greater_than_50 = sum(hr_before > 50, na.rm = TRUE),
n_greater_than_100 = sum(hr_before > 100, na.rm=TRUE)
)
mysowsumlong <- mysowsum %>%
pivot_longer(
cols=everything(),
names_to = "statistic",
values_to = "value"
)
mysowsumlong# A tibble: 8 × 2
statistic value
<chr> <dbl>
1 n_sows 31
2 mean_hr_before 76.8
3 se_hr_before 4.20
4 min_hr_before 35.7
5 max_hr_before 130.
6 n_less_than_50 3
7 n_greater_than_50 28
8 n_greater_than_100 5