Exercice

1 Create function

1. BMI
2. Celcius to Farenheit
3. Euclidean Distance

Show/Hide Code

bmi <- function(weight_kg, height_m) {
  bmi_output <- weight_kg/height_m^2
  
  return(bmi_output)
}

bmi(70,1.7)

[1] 24.22145

Show/Hide Code

ctf <- function(celcius){
  celcius * 9/5 + 32
}
  
ctf(30)

[1] 86

Show/Hide Code

euclidean_distance <- function (x1,y1,x2,y2){sqrt((x2-x1)^2 + (y2-y1)^2)
}

euclidean_distance(0,0,1,1)

[1] 1.414214

##Prepare Analysis import library

Show/Hide Code

library("readr")
library("sf")

Warning: package 'sf' was built under R version 4.3.3

Linking to GEOS 3.11.0, GDAL 3.5.3, PROJ 9.1.0; sf_use_s2() is TRUE

Show/Hide Code

library("dplyr")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

Show/Hide Code

library("lubridate")

Attaching package: 'lubridate'

The following objects are masked from 'package:base':

    date, intersect, setdiff, union

Show/Hide Code

library("ggplot2")

Import data and filter

Show/Hide Code

wildschwein <- read_delim("Datasets-20250312/wildschwein_BE_2056.csv")

Rows: 51246 Columns: 6
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr  (2): TierID, TierName
dbl  (3): CollarID, E, N
dttm (1): DatetimeUTC

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Show/Hide Code

#filter data "Rosa" & "Sabi" in the time 01.04.2015 - 15.04.2015

wildschwein <- wildschwein |>
    filter(
      TierName %in% c("Sabi", "Rosa"), 
      DatetimeUTC >= "2015-04-01", 
      DatetimeUTC < "2015-04-15"
      )

2 Create a Join Key

1. round the minutes of DatetimeUTC
2. store the value in a new column

Show/Hide Code

#1. 

wildschwein <- wildschwein |> 
  mutate(rounded_time = round_date(DatetimeUTC, unit = "15 minutes"))

wildschwein

# A tibble: 2,688 × 7
   TierID TierName CollarID DatetimeUTC                E        N
   <chr>  <chr>       <dbl> <dttm>                 <dbl>    <dbl>
 1 002A   Sabi        12275 2015-03-31 22:00:28 2570296. 1205283.
 2 002A   Sabi        12275 2015-03-31 22:15:44 2570259. 1205259.
 3 002A   Sabi        12275 2015-03-31 22:30:44 2570255. 1205259.
 4 002A   Sabi        12275 2015-03-31 22:46:04 2570245. 1205268.
 5 002A   Sabi        12275 2015-03-31 23:00:17 2570364. 1205314.
 6 002A   Sabi        12275 2015-03-31 23:15:12 2570375. 1205320.
 7 002A   Sabi        12275 2015-03-31 23:30:08 2570411. 1205347.
 8 002A   Sabi        12275 2015-03-31 23:45:13 2570429. 1205361.
 9 002A   Sabi        12275 2015-04-01 00:00:11 2570372. 1205313.
10 002A   Sabi        12275 2015-04-01 00:15:22 2570309. 1205262.
# ℹ 2,678 more rows
# ℹ 1 more variable: rounded_time <dttm>

3 Measuring distance at concurrent locations

1. Split the wildschwein object into one data.frame per animal

Show/Hide Code

rosa <- wildschwein |>
    filter(
      TierName == "Rosa")

sabi <- wildschwein  |>
    filter(
      TierName == "Sabi")

2. Join these datasety by the new Datetime

Show/Hide Code

joined <- full_join(rosa,sabi, by = "rounded_time", suffix = c("rosa","sabi"))

3. Calculate Euclidean distances between concurrent observations and store value in a new column

Show/Hide Code

joined <- joined |>
  rowwise() |>
  mutate(distance = euclidean_distance(Erosa,Nrosa,Esabi,Nsabi)) |>
  ungroup()

joined <- joined |>
  mutate(meet = distance <= 100)

4 Visualise Data

Show/Hide Code

#filter the data 

meets_data <- joined |> filter(meet)

# create plot

ggplot() +
  geom_point(data = rosa, aes(x = E, y = N, color = "Rosa"), alpha = 0.6) +
  geom_point(data = sabi, aes(x = E, y = N, color = "Sabi"), alpha = 0.6) +
  geom_point(data = meets_data, aes(x = (Erosa + Esabi) / 2, y = (Nrosa + Nsabi) / 2, color = "Meet"), size = 3) +
  scale_color_manual(values = c("Rosa" = "blue", "Sabi" = "red", "Meet" = "grey"))