A_02_Preprocess_data.R

A - 02: Preprocess data

Code

tictoc::tic()

Source 00_Configuration.R

Code

source(here::here("Code/00_Configuration.R"))
x <- lapply(package_list, require, character = TRUE)
sf_use_s2(TRUE)
rm(x)

Load data produced from script: A_01_Get_data

Code

grids <-
  readRDS(vars$grid)

data_sf <-
  readRDS(vars$data_sf)

Add filtering columns

1. Spatial filter

get list of cells and sampling repeats get list of species and filters (or whether to include them)

1.1. Cell-indicator for repeated sampling

Code

cells <-
  data_sf %>%
  st_drop_geometry() %>%
  group_by(datasetID, scalingID, siteID, samplingPeriodID) %>%
  mutate(cell_sampled = if_else(is.na(verbatimIdentification), 0, 1)) %>%
  ungroup() %>%
  distinct(datasetID, scalingID, siteID, samplingPeriodID, cell_sampled, croppedArea, time_span) %>%
  group_by(datasetID, scalingID, siteID, croppedArea) %>%
  dplyr::summarise(
    cell_sampling_repeats = n_distinct(samplingPeriodID, na.rm = TRUE),
    .groups = "keep") %>%
  mutate(cells_keep =
           case_when(
             cell_sampling_repeats == 2 & !is.na(croppedArea) ~ 1,
             cell_sampling_repeats %in% c(0,1) | is.na(croppedArea) ~ 0,
            .default = NA)) %>%
  unique()

Checks:

Code

glimpse(cells)

Rows: 17,286
Columns: 6
Groups: datasetID, scalingID, siteID, croppedArea [17,286]
$ datasetID             <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, …
$ scalingID             <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
$ siteID                <int> 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, …
$ croppedArea           <dbl> 21.076318, 41.363317, 8.586563, 1.390874, 16.092…
$ cell_sampling_repeats <int> 0, 2, 0, 0, 0, 0, 2, 2, 0, 2, 2, 0, 0, 2, 2, 2, …
$ cells_keep            <dbl> 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, …

Code

colSums(is.na(cells)) # 14 cells without area

            datasetID             scalingID                siteID 
                    0                     0                     0 
          croppedArea cell_sampling_repeats            cells_keep 
                   14                     0                     0 

2. Species filter

Code

species_df <-
  data_sf %>%
  st_drop_geometry() %>%
  filter(scalingID == 1) %>%
  distinct(datasetID, verbatimIdentification, scientificName, samplingPeriodID, time_span) %>%
  filter(!is.na(verbatimIdentification))

Checks:

Code

glimpse(species_df)

Rows: 2,272
Columns: 5
$ datasetID              <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,…
$ verbatimIdentification <chr> "Carpodacus erythrinus", "Garrulus glandarius",…
$ scientificName         <chr> "Carpodacus erythrinus", "Garrulus glandarius",…
$ samplingPeriodID       <dbl> 2, 2, 1, 2, 1, 2, 2, 2, 2, 2, 2, 1, 1, 1, 2, 2,…
$ time_span              <int> 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 4, 4, 2, 2,…

Code

colSums(is.na(species_df))

             datasetID verbatimIdentification         scientificName 
                     0                      0                      0 
      samplingPeriodID              time_span 
                     0                      0 

2.1 Under-sampled species from Japan

Code

jp_sp_remove <-
  read.csv(here("Data/input/META_removed_sp_Japan_expert_knowledge.csv"),
           header = FALSE,
           strip.white = TRUE) %>%
  pull(V1)

jp_sp_remove

 [1] "Haliaeetus albicilla " "Spilornis cheela "     "Circus spilonotus "   
 [4] "Accipiter gularis "    "Accipiter nisus "      "Accipiter gentilis "  
 [7] "Butastur indicus "     "Buteo buteo "          "Nisaetus nipalensis " 
[10] "Otus lempiji "         "Otus sunia "           "Otus elegans "        
[13] "Strix uralensis "      "Ninox scutulata "      "Asio otus "           
[16] "Dendrocopos leucotos " "Dendrocopos major "    "Dryocopus martius "   
[19] "Picus awokera "        "Picus canus "          "Falco tinnunculus "   
[22] "Falco subbuteo "       "Falco peregrinus "     "Zoothera sibirica "   
[25] "Zoothera dauma "       "Caprimulgus indicus " 

Code

species_df2 <- species_df %>%
  mutate(
    sp_remove_expert =
      case_when(
        verbatimIdentification %in% jp_sp_remove & datasetID == 13 ~ 1,
        TRUE ~ 0))

head(species_df2)

  datasetID verbatimIdentification        scientificName samplingPeriodID
1         5  Carpodacus erythrinus Carpodacus erythrinus                2
2         5    Garrulus glandarius   Garrulus glandarius                2
3         5   Emberiza schoeniclus  Emberiza schoeniclus                1
4         5        Parus cristatus Lophophanes cristatus                2
5         5    Streptopelia turtur   Streptopelia turtur                1
6         5          Ciconia nigra         Ciconia nigra                2
  time_span sp_remove_expert
1         2                0
2         2                0
3         4                0
4         2                0
5         4                0
6         2                0

2.2. Native vs. Introduced

Read grid shapefiles at largest resolution(1-cell-aggregations)

Code

sf_use_s2(FALSE) # fixes error with crossing geometries in EBBA

countries <-
  grids %>%
  group_by(datasetID) %>%
  filter(scalingID == max(scalingID)) %>%
  select(datasetID, geometry) %>%
  summarize(
    geometry = st_union(geometry),
    .groups = "keep"
  ) %>%
  st_make_valid()

head(countries)

Simple feature collection with 4 features and 1 field
Geometry type: GEOMETRY
Dimension:     XY
Bounding box:  xmin: -79.79188 ymin: 24 xmax: 146 ymax: 81.95675
Geodetic CRS:  WGS 84
# A tibble: 4 × 2
# Groups:   datasetID [4]
  datasetID                                                             geometry
      <int>                                                       <GEOMETRY [°]>
1         5 POLYGON ((18.16496 49.19965, 18.16496 49.09965, 18.16497 48.99964, …
2         6 MULTIPOLYGON (((-71.95444 41.28819, -71.95234 41.33317, -71.89268 4…
3        13 MULTIPOLYGON (((123.25 24.33333, 123 24.33333, 122.75 24.33333, 122…
4        26 MULTIPOLYGON (((-18.45763 28.00178, -17.99985 27.99255, -17.54207 2…

Load range maps for introduced species

Code

BirdLife_introduced <-
  st_read(here("Data/input/shp_introduced/")) %>%
  st_transform(crs = st_crs(countries))

Reading layer `BirdLife_introduced' from data source 
  `C:\Users\wolke\OneDrive - CZU v Praze\Frieda_PhD_files\02_StaticPatterns\Git\Data\input\shp_introduced' 
  using driver `ESRI Shapefile'
Simple feature collection with 90 features and 4 fields
Geometry type: MULTIPOLYGON
Dimension:     XY
Bounding box:  xmin: -180 ymin: -55.97681 xmax: 180 ymax: 66.6413
Geodetic CRS:  WGS 84

check if they are identical now:

Code

st_crs(countries) == st_crs(BirdLife_introduced)

[1] TRUE

Spatial join: Countries and introduced ranges

Code

introduced_sp <-
  st_join(countries, BirdLife_introduced,
          join = st_intersects) %>%
  rename("scientificName" = "sci_name") %>%
  mutate(introduced = 1) %>%
  st_drop_geometry() %>%
  select(datasetID, scientificName, introduced) %>%
  arrange(datasetID)

create new filtering column for introduced species in sp data

Code

species_df3 <-
  species_df2 %>%
  left_join(introduced_sp) %>%
  mutate(introduced = case_when(is.na(introduced) ~ 0,
                                .default = introduced))
head(species_df3)

  datasetID verbatimIdentification        scientificName samplingPeriodID
1         5  Carpodacus erythrinus Carpodacus erythrinus                2
2         5    Garrulus glandarius   Garrulus glandarius                2
3         5   Emberiza schoeniclus  Emberiza schoeniclus                1
4         5        Parus cristatus Lophophanes cristatus                2
5         5    Streptopelia turtur   Streptopelia turtur                1
6         5          Ciconia nigra         Ciconia nigra                2
  time_span sp_remove_expert introduced
1         2                0          0
2         2                0          0
3         4                0          0
4         2                0          0
5         4                0          0
6         2                0          0

2.3. Species lost or gained

excluding species that are introduced or under-sampled

Code

common_sp <-
  data_sf %>%
  st_drop_geometry() %>%
  filter(scalingID == 1) %>%
  left_join(species_df3) %>%
  left_join(cells %>% filter(scalingID == 1)) %>%
  na.omit() %>%
  filter(cells_keep == 1 & introduced == 0 & sp_remove_expert == 0) %>%
  group_by(datasetID, verbatimIdentification) %>%
  dplyr::summarise(sp_sampling_repeats = n_distinct(samplingPeriodID),
                   .groups = "drop")

checks species with sp_sampling_repeats != 2 will be removed from the data

Code

common_sp %>%
  group_by(datasetID, sp_sampling_repeats) %>%
  dplyr::summarise(n_sp = n_distinct(verbatimIdentification),
                   .groups = "keep")

# A tibble: 8 × 3
# Groups:   datasetID, sp_sampling_repeats [8]
  datasetID sp_sampling_repeats  n_sp
      <int>               <int> <int>
1         5                   1    18
2         5                   2   201
3         6                   1    16
4         6                   2   233
5        13                   1    33
6        13                   2   208
7        26                   1     9
8        26                   2   412

add filtering column for species that are kept for analysis

Code

species_df4 <-
  species_df3 %>%
  left_join(common_sp) %>%
  mutate(
    species_keep =
      case_when(
        sp_remove_expert == 0 & sp_sampling_repeats == 2 & introduced == 0 ~ 1,
        TRUE ~ 0))
head(species_df4)

  datasetID verbatimIdentification        scientificName samplingPeriodID
1         5  Carpodacus erythrinus Carpodacus erythrinus                2
2         5    Garrulus glandarius   Garrulus glandarius                2
3         5   Emberiza schoeniclus  Emberiza schoeniclus                1
4         5        Parus cristatus Lophophanes cristatus                2
5         5    Streptopelia turtur   Streptopelia turtur                1
6         5          Ciconia nigra         Ciconia nigra                2
  time_span sp_remove_expert introduced sp_sampling_repeats species_keep
1         2                0          0                   2            1
2         2                0          0                   2            1
3         4                0          0                   2            1
4         2                0          0                   2            1
5         4                0          0                   2            1
6         2                0          0                   2            1

Apply data filters

Code

data_sf2 <-
  data_sf %>%
  left_join(cells) %>%
  left_join(species_df4)

head(data_sf2)

Simple feature collection with 6 features and 32 fields
Geometry type: MULTIPOLYGON
Dimension:     XY
Bounding box:  xmin: 14.16488 ymin: 50.99961 xmax: 14.49822 ymax: 51.09962
Geodetic CRS:  WGS 84
  datasetID scalingID siteID footprintSRS verbatimFootprintSRS     area
1         5         1      1    epsg:4326            epsg:5514 130.0203
2         5         1      2    epsg:4326            epsg:5514 130.0204
3         5         1      2    epsg:4326            epsg:5514 130.0204
4         5         1      2    epsg:4326            epsg:5514 130.0204
5         5         1      2    epsg:4326            epsg:5514 130.0204
6         5         1      2    epsg:4326            epsg:5514 130.0204
  croppedArea areaUnit croppedAreaPercent centroidDecimalLongitude
1    21.07632      km2          0.1621002                 14.24822
2    41.36332      km2          0.3181295                 14.41488
3    41.36332      km2          0.3181295                 14.41488
4    41.36332      km2          0.3181295                 14.41488
5    41.36332      km2          0.3181295                 14.41488
6    41.36332      km2          0.3181295                 14.41488
  centroidDecimalLatitude croppedDecimalLongitude croppedDecimalLatitude
1                51.04961                14.30475               51.02347
2                51.04962                14.40960               51.01669
3                51.04962                14.40960               51.01669
4                51.04962                14.40960               51.01669
5                51.04962                14.40960               51.01669
6                51.04962                14.40960               51.01669
  northSouthLength eastWestLength maxLength croppedNorthSouthLength
1         11.12540       11.69999  16.13557                6.239639
2         11.12541       11.70000  16.13557                5.178504
3         11.12541       11.70000  16.13557                5.178504
4         11.12541       11.70000  16.13557                5.178504
5         11.12541       11.70000  16.13557                5.178504
6         11.12541       11.70000  16.13557                5.178504
  croppedEastWestLength croppedMaxLength lengthUnit startYear endYear
1              4.989069         7.069381         km        NA      NA
2             11.699831        12.789048         km      2001    2003
3             11.699831        12.789048         km      2001    2003
4             11.699831        12.789048         km      1985    1989
5             11.699831        12.789048         km      2001    2003
6             11.699831        12.789048         km      1985    1989
  verbatimIdentification        scientificName samplingPeriodID time_span
1                   <NA>                  <NA>               NA        NA
2  Carpodacus erythrinus Carpodacus erythrinus                2         2
3    Garrulus glandarius   Garrulus glandarius                2         2
4   Emberiza schoeniclus  Emberiza schoeniclus                1         4
5        Parus cristatus Lophophanes cristatus                2         2
6    Streptopelia turtur   Streptopelia turtur                1         4
  cell_sampling_repeats cells_keep sp_remove_expert introduced
1                     0          0               NA         NA
2                     2          1                0          0
3                     2          1                0          0
4                     2          1                0          0
5                     2          1                0          0
6                     2          1                0          0
  sp_sampling_repeats species_keep                       geometry
1                  NA           NA MULTIPOLYGON (((14.16488 51...
2                   2            1 MULTIPOLYGON (((14.33155 51...
3                   2            1 MULTIPOLYGON (((14.33155 51...
4                   2            1 MULTIPOLYGON (((14.33155 51...
5                   2            1 MULTIPOLYGON (((14.33155 51...
6                   2            1 MULTIPOLYGON (((14.33155 51...

keep only species and cells sampled twice

Code

data_filt <-
  data_sf2 %>%
  st_drop_geometry() %>%
  filter(!is.na(verbatimIdentification) & species_keep == 1 & cells_keep == 1)

Checks:

Code

data_filt %>%
  group_by(datasetID, samplingPeriodID) %>%
  skimr::skim()

Data summary

Name	Piped data
Number of rows	2508543
Number of columns	32
_______________________
Column type frequency:
character	6
numeric	24
________________________
Group variables	datasetID, samplingPeriodID

Variable type: character

skim_variable	datasetID	samplingPeriodID	n_missing	complete_rate	min	max	empty	n_unique	whitespace
footprintSRS	5	1	0	1	9	9	0	1	0
footprintSRS	5	2	0	1	9	9	0	1	0
footprintSRS	6	1	0	1	9	9	0	1	0
footprintSRS	6	2	0	1	9	9	0	1	0
footprintSRS	13	1	0	1	9	9	0	1	0
footprintSRS	13	2	0	1	9	9	0	1	0
footprintSRS	26	1	0	1	9	9	0	1	0
footprintSRS	26	2	0	1	9	9	0	1	0
verbatimFootprintSRS	5	1	0	1	9	9	0	1	0
verbatimFootprintSRS	5	2	0	1	9	9	0	1	0
verbatimFootprintSRS	6	1	0	1	10	10	0	1	0
verbatimFootprintSRS	6	2	0	1	10	10	0	1	0
verbatimFootprintSRS	13	1	0	1	9	9	0	1	0
verbatimFootprintSRS	13	2	0	1	9	9	0	1	0
verbatimFootprintSRS	26	1	0	1	9	9	0	1	0
verbatimFootprintSRS	26	2	0	1	9	9	0	1	0
areaUnit	5	1	0	1	3	3	0	1	0
areaUnit	5	2	0	1	3	3	0	1	0
areaUnit	6	1	0	1	3	3	0	1	0
areaUnit	6	2	0	1	3	3	0	1	0
areaUnit	13	1	0	1	3	3	0	1	0
areaUnit	13	2	0	1	3	3	0	1	0
areaUnit	26	1	0	1	3	3	0	1	0
areaUnit	26	2	0	1	3	3	0	1	0
lengthUnit	5	1	0	1	2	2	0	1	0
lengthUnit	5	2	0	1	2	2	0	1	0
lengthUnit	6	1	0	1	2	2	0	1	0
lengthUnit	6	2	0	1	2	2	0	1	0
lengthUnit	13	1	0	1	2	2	0	1	0
lengthUnit	13	2	0	1	2	2	0	1	0
lengthUnit	26	1	0	1	2	2	0	1	0
lengthUnit	26	2	0	1	2	2	0	1	0
verbatimIdentification	5	1	0	1	9	29	0	201	0
verbatimIdentification	5	2	0	1	9	29	0	201	0
verbatimIdentification	6	1	0	1	9	32	0	233	0
verbatimIdentification	6	2	0	1	9	32	0	233	0
verbatimIdentification	13	1	0	1	9	29	0	208	0
verbatimIdentification	13	2	0	1	9	29	0	208	0
verbatimIdentification	26	1	0	1	9	29	0	412	0
verbatimIdentification	26	2	0	1	9	29	0	412	0
scientificName	5	1	0	1	9	29	0	198	0
scientificName	5	2	0	1	9	29	0	198	0
scientificName	6	1	0	1	9	39	0	233	0
scientificName	6	2	0	1	9	39	0	233	0
scientificName	13	1	0	1	9	29	0	208	0
scientificName	13	2	0	1	9	29	0	208	0
scientificName	26	1	0	1	9	29	0	412	0
scientificName	26	2	0	1	9	29	0	412	0

Variable type: numeric

skim_variable	datasetID	samplingPeriodID	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
scalingID	5	1	0	1	2.07	3.92	1.00	1.00	1.00	2.00	64.00	▇▁▁▁▁
scalingID	5	2	0	1	2.05	3.85	1.00	1.00	1.00	2.00	64.00	▇▁▁▁▁
scalingID	6	1	0	1	2.13	4.91	1.00	1.00	1.00	2.00	128.00	▇▁▁▁▁
scalingID	6	2	0	1	2.09	4.76	1.00	1.00	1.00	2.00	128.00	▇▁▁▁▁
scalingID	13	1	0	1	3.46	9.17	1.00	1.00	1.00	2.00	128.00	▇▁▁▁▁
scalingID	13	2	0	1	3.39	8.80	1.00	1.00	1.00	2.00	128.00	▇▁▁▁▁
scalingID	26	1	0	1	2.23	5.50	1.00	1.00	1.00	2.00	128.00	▇▁▁▁▁
scalingID	26	2	0	1	2.18	5.31	1.00	1.00	1.00	2.00	128.00	▇▁▁▁▁
siteID	5	1	0	1	250.54	204.87	1.00	65.00	183.00	425.00	673.00	▇▅▃▃▃
siteID	5	2	0	1	252.28	206.62	1.00	64.00	183.00	431.00	673.00	▇▃▃▃▃
siteID	6	1	0	1	2150.86	1484.84	1.00	872.00	1921.00	3225.00	5335.00	▇▇▆▃▃
siteID	6	2	0	1	2128.88	1473.71	1.00	859.00	1905.00	3175.00	5335.00	▇▇▆▃▃
siteID	13	1	0	1	492.31	423.73	1.00	122.00	365.00	814.00	1464.00	▇▃▂▂▂
siteID	13	2	0	1	490.33	425.59	1.00	118.00	350.00	828.00	1464.00	▇▃▂▂▂
siteID	26	1	0	1	1553.41	945.02	1.00	787.00	1476.00	2187.00	5225.00	▇▇▆▁▁
siteID	26	2	0	1	1574.18	957.70	1.00	788.00	1499.00	2226.00	5225.00	▇▇▆▁▁
area	5	1	0	1	1031.30	5730.33	130.02	133.05	134.95	531.66	90569.14	▇▁▁▁▁
area	5	2	0	1	1008.82	5625.60	130.02	133.05	134.95	531.66	90569.14	▇▁▁▁▁
area	6	1	0	1	291.59	3264.13	24.93	25.01	25.02	100.05	133087.29	▇▁▁▁▁
area	6	2	0	1	282.42	3188.68	24.93	25.01	25.02	100.05	133087.29	▇▁▁▁▁
area	13	1	0	1	6547.79	33516.77	362.47	412.92	432.25	1691.29	538550.03	▇▁▁▁▁
area	13	2	0	1	6231.39	31892.21	362.47	412.92	433.84	1691.29	538550.03	▇▁▁▁▁
area	26	1	0	1	41113.52	455431.19	1550.65	2501.63	2501.97	10005.38	13223660.56	▇▁▁▁▁
area	26	2	0	1	38512.74	437568.42	1550.65	2501.63	2501.97	10005.38	13223660.56	▇▁▁▁▁
croppedArea	5	1	0	1	911.91	5035.89	7.57	132.53	134.43	527.25	78873.98	▇▁▁▁▁
croppedArea	5	2	0	1	892.01	4944.05	7.57	132.52	134.43	525.09	78873.98	▇▁▁▁▁
croppedArea	6	1	0	1	278.72	3120.13	0.01	25.01	25.02	100.05	127077.41	▇▁▁▁▁
croppedArea	6	2	0	1	270.15	3048.35	0.01	25.01	25.02	100.04	127077.41	▇▁▁▁▁
croppedArea	13	1	0	1	4758.46	23545.63	0.15	373.15	420.71	1619.60	371982.46	▇▁▁▁▁
croppedArea	13	2	0	1	4515.97	22411.90	0.15	371.75	419.86	1606.52	371982.46	▇▁▁▁▁
croppedArea	26	1	0	1	34547.11	387572.23	0.15	2494.24	2501.93	8928.22	11171485.87	▇▁▁▁▁
croppedArea	26	2	0	1	32345.75	372332.04	0.15	2493.95	2501.70	8667.47	11171485.87	▇▁▁▁▁
croppedAreaPercent	5	1	0	1	0.91	0.19	0.06	0.97	1.00	1.00	1.00	▁▁▁▁▇
croppedAreaPercent	5	2	0	1	0.91	0.19	0.06	0.97	1.00	1.00	1.00	▁▁▁▁▇
croppedAreaPercent	6	1	0	1	0.96	0.16	0.00	1.00	1.00	1.00	1.00	▁▁▁▁▇
croppedAreaPercent	6	2	0	1	0.96	0.15	0.00	1.00	1.00	1.00	1.00	▁▁▁▁▇
croppedAreaPercent	13	1	0	1	0.77	0.29	0.00	0.60	0.94	1.00	1.00	▁▁▁▂▇
croppedAreaPercent	13	2	0	1	0.76	0.30	0.00	0.58	0.92	1.00	1.00	▁▁▁▂▇
croppedAreaPercent	26	1	0	1	0.84	0.28	0.00	0.77	1.00	1.00	1.00	▁▁▁▁▇
croppedAreaPercent	26	2	0	1	0.84	0.28	0.00	0.78	1.00	1.00	1.00	▁▁▁▁▇
centroidDecimalLongitude	5	1	0	1	15.39	1.60	12.08	14.08	15.25	16.66	18.80	▃▇▇▆▃
centroidDecimalLongitude	5	2	0	1	15.39	1.59	12.08	14.16	15.25	16.58	18.80	▃▇▇▆▃
centroidDecimalLongitude	6	1	0	1	-75.49	1.71	-79.76	-76.63	-75.12	-74.12	-71.87	▂▃▆▇▁
centroidDecimalLongitude	6	2	0	1	-75.55	1.72	-79.76	-76.69	-75.21	-74.15	-71.87	▂▃▆▇▁
centroidDecimalLongitude	13	1	0	1	137.81	4.35	123.00	134.45	138.88	141.12	145.88	▁▂▃▇▅
centroidDecimalLongitude	13	2	0	1	137.73	4.44	123.00	134.19	138.88	140.88	145.88	▁▃▃▇▃
centroidDecimalLongitude	26	1	0	1	14.01	12.02	-31.26	5.42	15.35	23.60	41.92	▁▂▅▇▂
centroidDecimalLongitude	26	2	0	1	14.27	12.17	-31.26	5.43	15.57	24.00	41.92	▁▂▅▇▂
centroidDecimalLatitude	5	1	0	1	49.73	0.56	48.60	49.25	49.75	50.15	51.05	▅▇▇▆▂
centroidDecimalLatitude	5	2	0	1	49.73	0.57	48.60	49.25	49.75	50.20	51.05	▅▇▇▆▂
centroidDecimalLatitude	6	1	0	1	42.88	0.99	40.49	42.22	42.80	43.51	45.03	▂▅▇▅▃
centroidDecimalLatitude	6	2	0	1	42.89	0.97	40.49	42.24	42.81	43.51	45.03	▂▅▇▅▃
centroidDecimalLatitude	13	1	0	1	37.44	4.07	24.25	34.67	36.42	40.90	45.47	▁▁▇▃▃
centroidDecimalLatitude	13	2	0	1	37.35	4.12	24.25	34.58	36.50	40.75	45.47	▁▁▇▃▅
centroidDecimalLatitude	26	1	0	1	51.06	8.27	28.47	44.77	50.09	56.60	80.61	▁▇▇▃▁
centroidDecimalLatitude	26	2	0	1	50.90	8.22	28.47	44.67	49.87	56.35	80.61	▁▇▇▃▁
croppedDecimalLongitude	5	1	0	1	15.39	1.59	12.14	14.10	15.25	16.66	18.75	▃▇▇▆▃
croppedDecimalLongitude	5	2	0	1	15.39	1.58	12.14	14.16	15.25	16.58	18.75	▃▇▇▆▃
croppedDecimalLongitude	6	1	0	1	-75.49	1.71	-79.74	-76.63	-75.12	-74.12	-71.88	▂▃▅▇▁
croppedDecimalLongitude	6	2	0	1	-75.55	1.72	-79.74	-76.69	-75.21	-74.15	-71.88	▂▃▆▇▁
croppedDecimalLongitude	13	1	0	1	137.82	4.33	122.99	134.38	138.88	141.02	145.84	▁▂▃▇▅
croppedDecimalLongitude	13	2	0	1	137.74	4.42	122.99	134.23	138.88	140.88	145.84	▁▃▃▇▃
croppedDecimalLongitude	26	1	0	1	14.02	12.01	-31.19	5.59	15.36	23.64	41.96	▁▂▅▇▂
croppedDecimalLongitude	26	2	0	1	14.29	12.16	-31.19	5.61	15.55	24.00	41.96	▁▂▅▇▂
croppedDecimalLatitude	5	1	0	1	49.73	0.56	48.64	49.25	49.75	50.15	51.02	▅▇▇▅▂
croppedDecimalLatitude	5	2	0	1	49.73	0.56	48.64	49.25	49.75	50.19	51.02	▅▇▇▅▂
croppedDecimalLatitude	6	1	0	1	42.88	0.99	40.51	42.23	42.80	43.51	45.01	▂▅▇▅▃
croppedDecimalLatitude	6	2	0	1	42.89	0.97	40.51	42.24	42.81	43.51	45.01	▂▅▇▅▃
croppedDecimalLatitude	13	1	0	1	37.45	4.06	24.30	34.66	36.42	40.81	45.40	▁▁▇▃▃
croppedDecimalLatitude	13	2	0	1	37.35	4.12	24.30	34.58	36.42	40.75	45.40	▁▁▇▃▅
croppedDecimalLatitude	26	1	0	1	51.06	8.25	28.34	44.89	50.07	56.60	80.27	▁▇▇▃▁
croppedDecimalLatitude	26	2	0	1	50.90	8.20	28.34	44.70	49.87	56.32	80.27	▁▇▇▃▁
northSouthLength	5	1	0	1	20.36	26.05	11.12	11.12	11.12	22.25	289.19	▇▁▁▁▁
northSouthLength	5	2	0	1	20.20	25.69	11.12	11.12	11.12	22.25	289.19	▇▁▁▁▁
northSouthLength	6	1	0	1	9.78	17.62	5.00	5.05	5.12	10.11	509.30	▇▁▁▁▁
northSouthLength	6	2	0	1	9.67	17.28	5.00	5.05	5.12	10.11	509.30	▇▁▁▁▁
northSouthLength	13	1	0	1	60.10	164.39	18.46	18.49	18.52	37.03	2403.75	▇▁▁▁▁
northSouthLength	13	2	0	1	58.67	157.37	18.46	18.49	18.52	37.03	2403.75	▇▁▁▁▁
northSouthLength	26	1	0	1	109.52	259.90	50.16	50.74	51.43	101.61	6056.01	▇▁▁▁▁
northSouthLength	26	2	0	1	106.63	250.62	50.16	50.73	51.40	101.51	6056.01	▇▁▁▁▁
eastWestLength	5	1	0	1	22.79	35.43	11.70	11.97	12.15	24.05	517.14	▇▁▁▁▁
eastWestLength	5	2	0	1	22.61	34.89	11.70	11.97	12.15	24.05	517.14	▇▁▁▁▁
eastWestLength	6	1	0	1	10.03	20.55	5.01	5.05	5.12	10.12	654.17	▇▁▁▁▁
eastWestLength	6	2	0	1	9.90	20.15	5.01	5.05	5.12	10.12	654.17	▇▁▁▁▁
eastWestLength	13	1	0	1	65.95	167.92	19.60	22.30	23.28	46.10	2363.01	▇▁▁▁▁
eastWestLength	13	2	0	1	64.83	161.53	19.60	22.25	23.36	46.19	2363.01	▇▁▁▁▁
eastWestLength	26	1	0	1	114.60	337.24	32.26	50.84	51.63	102.42	9604.23	▇▁▁▁▁
eastWestLength	26	2	0	1	111.60	324.81	32.26	50.82	51.59	102.30	9604.23	▇▁▁▁▁
maxLength	5	1	0	1	30.11	39.79	16.14	16.33	16.46	32.72	512.06	▇▁▁▁▁
maxLength	5	2	0	1	29.88	39.24	16.14	16.33	16.46	32.72	512.06	▇▁▁▁▁
maxLength	6	1	0	1	13.77	24.32	7.06	7.07	7.07	14.15	659.64	▇▁▁▁▁
maxLength	6	2	0	1	13.60	23.88	7.06	7.07	7.07	14.15	659.64	▇▁▁▁▁
maxLength	13	1	0	1	87.35	216.25	26.94	28.99	29.81	59.10	3041.50	▇▁▁▁▁
maxLength	13	2	0	1	85.70	207.63	26.94	28.99	29.88	59.24	3041.50	▇▁▁▁▁
maxLength	26	1	0	1	149.97	313.08	59.51	70.73	70.74	141.46	7056.48	▇▁▁▁▁
maxLength	26	2	0	1	146.30	302.10	59.51	70.73	70.74	141.46	7056.48	▇▁▁▁▁
croppedNorthSouthLength	5	1	0	1	19.66	25.10	3.15	11.12	11.12	22.24	278.50	▇▁▁▁▁
croppedNorthSouthLength	5	2	0	1	19.50	24.76	3.15	11.12	11.12	22.24	278.50	▇▁▁▁▁
croppedNorthSouthLength	6	1	0	1	9.63	17.40	0.18	5.05	5.10	10.10	502.08	▇▁▁▁▁
croppedNorthSouthLength	6	2	0	1	9.52	17.07	0.18	5.05	5.10	10.09	502.08	▇▁▁▁▁
croppedNorthSouthLength	13	1	0	1	58.62	163.09	0.72	18.49	18.52	37.03	2383.21	▇▁▁▁▁
croppedNorthSouthLength	13	2	0	1	57.20	156.14	0.72	18.49	18.52	37.02	2383.21	▇▁▁▁▁
croppedNorthSouthLength	26	1	0	1	106.44	258.76	0.59	50.51	51.29	101.06	6034.16	▇▁▁▁▁
croppedNorthSouthLength	26	2	0	1	103.55	249.53	0.59	50.50	51.27	100.54	6034.16	▇▁▁▁▁
croppedEastWestLength	5	1	0	1	22.30	34.55	4.62	11.97	12.12	23.95	499.54	▇▁▁▁▁
croppedEastWestLength	5	2	0	1	22.12	34.03	4.62	11.97	12.12	23.95	499.54	▇▁▁▁▁
croppedEastWestLength	6	1	0	1	9.92	20.45	0.06	5.05	5.11	10.11	650.95	▇▁▁▁▁
croppedEastWestLength	6	2	0	1	9.78	20.05	0.06	5.05	5.11	10.10	650.95	▇▁▁▁▁
croppedEastWestLength	13	1	0	1	63.50	166.17	0.40	21.81	23.14	45.83	2343.58	▇▁▁▁▁
croppedEastWestLength	13	2	0	1	62.36	159.79	0.40	21.76	23.14	45.83	2343.58	▇▁▁▁▁
croppedEastWestLength	26	1	0	1	110.17	333.37	0.70	50.65	51.51	101.93	9544.56	▇▁▁▁▁
croppedEastWestLength	26	2	0	1	107.22	321.03	0.70	50.64	51.48	101.79	9544.56	▇▁▁▁▁
croppedMaxLength	5	1	0	1	29.17	38.38	5.54	16.33	16.44	32.58	492.74	▇▁▁▁▁
croppedMaxLength	5	2	0	1	28.94	37.84	5.54	16.32	16.44	32.58	492.74	▇▁▁▁▁
croppedMaxLength	6	1	0	1	13.61	24.16	0.32	7.07	7.07	14.15	655.19	▇▁▁▁▁
croppedMaxLength	6	2	0	1	13.44	23.72	0.32	7.07	7.07	14.15	655.19	▇▁▁▁▁
croppedMaxLength	13	1	0	1	83.93	213.23	1.47	28.39	29.64	58.67	2999.27	▇▁▁▁▁
croppedMaxLength	13	2	0	1	82.28	204.70	1.47	28.43	29.67	58.67	2999.27	▇▁▁▁▁
croppedMaxLength	26	1	0	1	144.00	309.76	0.80	70.73	70.74	141.46	7027.49	▇▁▁▁▁
croppedMaxLength	26	2	0	1	140.42	298.86	0.80	70.73	70.74	141.46	7027.49	▇▁▁▁▁
startYear	5	1	0	1	1985.00	0.00	1985.00	1985.00	1985.00	1985.00	1985.00	▁▁▇▁▁
startYear	5	2	0	1	2001.00	0.00	2001.00	2001.00	2001.00	2001.00	2001.00	▁▁▇▁▁
startYear	6	1	0	1	1980.00	0.00	1980.00	1980.00	1980.00	1980.00	1980.00	▁▁▇▁▁
startYear	6	2	0	1	2000.00	0.00	2000.00	2000.00	2000.00	2000.00	2000.00	▁▁▇▁▁
startYear	13	1	0	1	1974.00	0.00	1974.00	1974.00	1974.00	1974.00	1974.00	▁▁▇▁▁
startYear	13	2	0	1	1997.00	0.00	1997.00	1997.00	1997.00	1997.00	1997.00	▁▁▇▁▁
startYear	26	1	0	1	1972.00	0.00	1972.00	1972.00	1972.00	1972.00	1972.00	▁▁▇▁▁
startYear	26	2	0	1	2013.00	0.00	2013.00	2013.00	2013.00	2013.00	2013.00	▁▁▇▁▁
endYear	5	1	0	1	1989.00	0.00	1989.00	1989.00	1989.00	1989.00	1989.00	▁▁▇▁▁
endYear	5	2	0	1	2003.00	0.00	2003.00	2003.00	2003.00	2003.00	2003.00	▁▁▇▁▁
endYear	6	1	0	1	1985.00	0.00	1985.00	1985.00	1985.00	1985.00	1985.00	▁▁▇▁▁
endYear	6	2	0	1	2005.00	0.00	2005.00	2005.00	2005.00	2005.00	2005.00	▁▁▇▁▁
endYear	13	1	0	1	1978.00	0.00	1978.00	1978.00	1978.00	1978.00	1978.00	▁▁▇▁▁
endYear	13	2	0	1	2002.00	0.00	2002.00	2002.00	2002.00	2002.00	2002.00	▁▁▇▁▁
endYear	26	1	0	1	1995.00	0.00	1995.00	1995.00	1995.00	1995.00	1995.00	▁▁▇▁▁
endYear	26	2	0	1	2017.00	0.00	2017.00	2017.00	2017.00	2017.00	2017.00	▁▁▇▁▁
time_span	5	1	0	1	4.00	0.00	4.00	4.00	4.00	4.00	4.00	▁▁▇▁▁
time_span	5	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
time_span	6	1	0	1	5.00	0.00	5.00	5.00	5.00	5.00	5.00	▁▁▇▁▁
time_span	6	2	0	1	5.00	0.00	5.00	5.00	5.00	5.00	5.00	▁▁▇▁▁
time_span	13	1	0	1	4.00	0.00	4.00	4.00	4.00	4.00	4.00	▁▁▇▁▁
time_span	13	2	0	1	5.00	0.00	5.00	5.00	5.00	5.00	5.00	▁▁▇▁▁
time_span	26	1	0	1	23.00	0.00	23.00	23.00	23.00	23.00	23.00	▁▁▇▁▁
time_span	26	2	0	1	4.00	0.00	4.00	4.00	4.00	4.00	4.00	▁▁▇▁▁
cell_sampling_repeats	5	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	5	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	6	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	6	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	13	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	13	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	26	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cell_sampling_repeats	26	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
cells_keep	5	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	5	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	6	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	6	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	13	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	13	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	26	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
cells_keep	26	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
sp_remove_expert	5	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	5	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	6	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	6	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	13	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	13	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	26	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_remove_expert	26	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	5	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	5	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	6	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	6	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	13	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	13	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	26	1	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
introduced	26	2	0	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	▁▁▇▁▁
sp_sampling_repeats	5	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	5	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	6	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	6	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	13	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	13	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	26	1	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
sp_sampling_repeats	26	2	0	1	2.00	0.00	2.00	2.00	2.00	2.00	2.00	▁▁▇▁▁
species_keep	5	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	5	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	6	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	6	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	13	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	13	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	26	1	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁
species_keep	26	2	0	1	1.00	0.00	1.00	1.00	1.00	1.00	1.00	▁▁▇▁▁

Save data to .rds

Code

saveRDS(data_sf2, here::here("Data", "output", "1_data_sf.rds"))
saveRDS(data_filt, here::here("Data", "output", "1_data_filtered.rds"))

Code

tictoc::toc()

161.14 sec elapsed