Address potential data mistakes flagged by ANU students (#790)

Fixes issue #775 

* I collapsed some duplicate context property names
* Removed a special character from traits.yml but @ehwenk not sure if this is allowed with the new APD workflow
* ABRS_1981 measurements will apparently be removed anyway with @ehwenk's work cleaning duplicates
* Fixed issues and documented in another column here:

https://github.com/traitecoevo/austraits.build/files/13519251/AusTraits.potential.errors.-.Sheet1.csv

config/traits.yml

@@ -4362,7 +4362,7 @@ traits:
         (at dispersal, mature); 'air dried' (at local ambient conditions); 'seed bank
         air dried' (to 15% relative humidity); and 'oven dried' (>100 deg C for a
         set number of hours; e.g. seed bank standard is 103 deg C for 17 hours). It
-        is expected that some observations in AusTraits mapped onto ‘seed_dry_mass'
+        is expected that some observations in AusTraits mapped onto 'seed_dry_mass'
         will actually include both the seed and some dispersal tissue, if the two
         cannot easily be separated; these should be mapped to 'diaspore_dry_mass'.
       type: numeric
@@ -6741,7 +6741,7 @@ traits:
         their host plant. The trait `root_structures` includes specialised root structures
       type: categorical
       allowed_values_levels:
-        saprophyte: Plant that acquires nutrients from decaying biomass.        
+        saprophyte: Plant that acquires nutrients from decaying biomass.
         carnivorous: Plant that acquires some or most of its nutrients from animals or protozoa.
         nutrient_mining: Plant that uses a specialised root structure, such as cluster roots, to mine nutrients inaccessible to other plant taxa.
       entity_URI: https://w3id.org/APD/traits/trait_0030017

data/ABRS_1981/data.csv

@@ -13086,7 +13086,7 @@ Aloe parvibracteata,leaf length maximum,cm,40
 Aloe saponaria,leaf length maximum,cm,16
 Aloe vera,leaf length maximum,cm,60
 Alpinia arctiflora,leaf length maximum,cm,50
-Alpinia arundelliana,leaf length maximum,cm,25
+Alpinia arundelliana,leaf length maximum,mm,25
 Alpinia coerulea,leaf length maximum,cm,40
 Alpinia hylandii,leaf length maximum,cm,16
 Alpinia modesta,leaf length maximum,cm,30
@@ -13603,7 +13603,7 @@ Choretrum glomeratum var. glomeratum,leaf length maximum,,
 Choretrum lateriflorum,leaf length maximum,mm,2
 Choretrum pauciflorum,leaf length maximum,mm,1
 Choretrum pritzelii,leaf length maximum,mm,1.5
-Choretrum spicatum,leaf length maximum,cm,2.5
+Choretrum spicatum,leaf length maximum,mm,2.5
 Cinnamomum baileyanum,leaf length maximum,cm,13
 Cinnamomum laubatii,leaf length maximum,cm,14.5
 Cinnamomum oliveri,leaf length maximum,cm,17
@@ -13794,7 +13794,7 @@ Coopernookia chisholmii,leaf length maximum,cm,9
 Coopernookia georgei,leaf length maximum,cm,5
 Coopernookia polygalacea,leaf length maximum,cm,30
 Coopernookia scabridiuscula,leaf length maximum,cm,8
-Coopernookia strophiolata,leaf length maximum,cm,35
+Coopernookia strophiolata,leaf length maximum,mm,35
 Cordyline cannifolia,leaf length maximum,cm,50
 Cordyline congesta,leaf length maximum,cm,40
 Cordyline fruticosa,leaf length maximum,cm,80
@@ -14573,14 +14573,14 @@ Gonocarpus humilis,leaf length maximum,mm,18
 Gonocarpus implexus,leaf length maximum,mm,11
 Gonocarpus intricatus,leaf length maximum,cm,1.3
 Gonocarpus leptothecus,leaf length maximum,mm,30
-Gonocarpus longifolius,leaf length maximum,cm,25
+Gonocarpus longifolius,leaf length maximum,mm,25
 Gonocarpus mezianus,leaf length maximum,mm,17
 Gonocarpus micranthus,leaf length maximum,mm,13
 Gonocarpus micranthus subsp. micranthus,leaf length maximum,mm,7
 Gonocarpus micranthus subsp. ramosissimus,leaf length maximum,mm,13
 Gonocarpus montanus,leaf length maximum,mm,6
 Gonocarpus nodulosus,leaf length maximum,mm,6
-Gonocarpus oreophilus,leaf length maximum,cm,35
+Gonocarpus oreophilus,leaf length maximum,mm,35
 Gonocarpus paniculatus,leaf length maximum,cm,5
 Gonocarpus pithyoides,leaf length maximum,mm,15
 Gonocarpus pusillus,leaf length maximum,mm,8
@@ -17130,7 +17130,7 @@ Viscum whitei,leaf length maximum,cm,5.5
 Viscum whitei subsp. flexicaule,leaf length maximum,cm,5
 Viscum whitei subsp. whitei,leaf length maximum,cm,4
 Watsonia versfeldii var. alba,leaf length maximum,cm,120
-Wikstroemia indica,leaf length maximum,cm,80
+Wikstroemia indica,leaf length maximum,mm,80
 Wilkiea angustifolia,leaf length maximum,cm,21
 Wilkiea austroqueenslandica,leaf length maximum,cm,21
 Wilkiea cordata,leaf length maximum,cm,26
@@ -17389,7 +17389,7 @@ Aloe parvibracteata,leaf length minimum,cm,30
 Aloe saponaria,leaf length minimum,cm,12
 Aloe vera,leaf length minimum,cm,40
 Alpinia arctiflora,leaf length minimum,,
-Alpinia arundelliana,leaf length minimum,cm,12
+Alpinia arundelliana,leaf length minimum,mm,12
 Alpinia coerulea,leaf length minimum,,
 Alpinia hylandii,leaf length minimum,cm,10
 Alpinia modesta,leaf length minimum,cm,10
@@ -17906,7 +17906,7 @@ Choretrum glomeratum var. glomeratum,leaf length minimum,,
 Choretrum lateriflorum,leaf length minimum,mm,1
 Choretrum pauciflorum,leaf length minimum,mm,0.5
 Choretrum pritzelii,leaf length minimum,,
-Choretrum spicatum,leaf length minimum,mm,15
+Choretrum spicatum,leaf length minimum,mm,1.5
 Cinnamomum baileyanum,leaf length minimum,cm,5
 Cinnamomum laubatii,leaf length minimum,cm,8
 Cinnamomum oliveri,leaf length minimum,cm,8.5
@@ -18097,7 +18097,7 @@ Coopernookia chisholmii,leaf length minimum,cm,4
 Coopernookia georgei,leaf length minimum,cm,2
 Coopernookia polygalacea,leaf length minimum,cm,12
 Coopernookia scabridiuscula,leaf length minimum,cm,4
-Coopernookia strophiolata,leaf length minimum,cm,10
+Coopernookia strophiolata,leaf length minimum,mm,10
 Cordyline cannifolia,leaf length minimum,cm,20
 Cordyline congesta,leaf length minimum,cm,30
 Cordyline fruticosa,leaf length minimum,cm,25
@@ -18876,14 +18876,14 @@ Gonocarpus humilis,leaf length minimum,mm,11
 Gonocarpus implexus,leaf length minimum,mm,6
 Gonocarpus intricatus,leaf length minimum,cm,1
 Gonocarpus leptothecus,leaf length minimum,mm,25
-Gonocarpus longifolius,leaf length minimum,cm,15
+Gonocarpus longifolius,leaf length minimum,mm,15
 Gonocarpus mezianus,leaf length minimum,mm,7
 Gonocarpus micranthus,leaf length minimum,mm,3
 Gonocarpus micranthus subsp. micranthus,leaf length minimum,mm,3
 Gonocarpus micranthus subsp. ramosissimus,leaf length minimum,mm,10
 Gonocarpus montanus,leaf length minimum,mm,3.5
 Gonocarpus nodulosus,leaf length minimum,mm,3
-Gonocarpus oreophilus,leaf length minimum,cm,10
+Gonocarpus oreophilus,leaf length minimum,mm,10
 Gonocarpus paniculatus,leaf length minimum,cm,2
 Gonocarpus pithyoides,leaf length minimum,mm,10
 Gonocarpus pusillus,leaf length minimum,mm,7

data/ABRS_1981/metadata.yml

@@ -17,7 +17,7 @@ contributors:
   dataset_curators: Rachael Gallagher
 dataset:
   data_is_long_format: yes
-  custom_R_code:        '
+  custom_R_code: '
     data$i <- seq_len(nrow(data));
 
     data_numeric <- data %>%
@@ -82,12 +82,14 @@ dataset:
             value = ifelse(species_name %in% c("Piper hederaceum var. hederaceum") & trait == "lifeform","climber_vine_woody",value),
             value = ifelse(species_name %in% c("Stephania japonica var. discolor") &  trait == "lifeform","vine",value),
             value = ifelse(species_name %in% c("Caesalpinia subtropica") & trait == "lifeform","climber_woody",value),
-            trait = ifelse(value %in% c("HE", "A", "E"), "plant_growth_substrate", trait)
+            trait = ifelse(value %in% c("HE", "A", "E"), "plant_growth_substrate", trait),
+            value = ifelse(stringr::str_detect(species_name, "^Xanthorrhoea") &
+            stringr::str_detect(trait, "^leaf length"), NA, value)
       ) %>%
       group_by(species_name, trait) %>%
         distinct(value, .keep_all = TRUE) %>%
       ungroup()
-  '
+    '
   collection_date: unknown/2015
   taxon_name: species_name
   trait_name: trait
@@ -98,7 +100,10 @@ dataset:
   sampling_strategy: herbarium specimens
   original_file: STU
   notes: Request ackowledgment "Data was sourced from the Flora of Australia with
-    permission from the Australian Biological Resources Study"
+    permission from the Australian Biological Resources Study"; Choretrum spicatum
+    leaf_length in data.csv corrected to 15 to 1.5, leaf_length units corrected for
+    Alpinia arundelliana, Choretrum spicatum, Coopernookia strophiolata, Gonocarpus
+    longifolius, Gonocarpus oreophilus, Wikstroemia indica, due to likely typos.
 locations: .na
 contexts: .na
 traits:

data/ABRS_2023/data.csv

@@ -152130,7 +152130,8 @@ Flora_of_Australia,Thysanotus rectantherus,seed_breadth,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus sabulosus,seed_breadth,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus scaber,seed_breadth,seeds,1.5,,mm,maximum
 Flora_of_Australia,Thysanotus sparteus,seed_breadth,seeds,1,,mm,maximum
-Flora_of_Australia,Thysanotus tenellus,seed_breadth,seeds,0.5,,mm,maximum
+Flora_of_Australia,Thysanotus tenellus,seed_breadth,seeds,1.5,,mm,maximum
+Flora_of_Australia,Thysanotus tenellus,seed_length,seeds,1.5,,mm,maximum
 Flora_of_Australia,Thysanotus tenuis,seed_breadth,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus thyrsoideus,seed_breadth,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus triandrus,seed_breadth,seeds,1,,mm,maximum
@@ -169008,7 +169009,7 @@ Flora_of_Australia,Thysanotus sabulosus,seed_width,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus scaber,seed_width,seeds,1.5,,mm,maximum
 Flora_of_Australia,Thysanotus sparteus,seed_width,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus speckii,seed_width,seeds,1.5,,mm,maximum
-Flora_of_Australia,Thysanotus tenellus,seed_width,seeds,0.5,,mm,maximum
+Flora_of_Australia,Thysanotus tenellus,seed_width,seeds,1.5,,mm,maximum
 Flora_of_Australia,Thysanotus tenuis,seed_width,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus thyrsoideus,seed_width,seeds,1,,mm,maximum
 Flora_of_Australia,Thysanotus triandrus,seed_width,seeds,1,,mm,maximum

data/ABRS_2023/metadata.yml

@@ -136,7 +136,7 @@ contexts:
     description: Trait value inferred from the value of a different trait.
   - value: inferred_from_taxonomy
     description: Trait value inferred from a higher level taxon description.
-- context_property: entity_measured
+- context_property: entity measured
   category: method_context
   var_in: entity_measured
 - context_property: replicate observations

data/Briggs_2010/metadata.yml

@@ -26,7 +26,13 @@ contributors:
   dataset_curators: Rachael Gallagher
 dataset:
   data_is_long_format: no
-  custom_R_code:        data %>% mutate(site_name = "Terrick Terrick National Park")
+  custom_R_code:   '
+    data %>%
+      mutate(
+        site_name = "Terrick Terrick National Park",
+        `Seed mass (mg)` = `Seed mass (mg)`/50
+      )
+    '
   collection_date: 2007/2007
   taxon_name: Scientific Name
   location_name: site_name
@@ -41,7 +47,8 @@ dataset:
     database.xls" extracted. Original copy of the excel file located in Google Drive
     in the folder "Morgan_2011_1 Morgan_2011_2 Morgan_2014 Angevin_2010 Briggs_2010
     Cross_2011 Lunt_2012 Roberts_2006 Scott_2010"
-  notes: none
+  notes: Divided all seed mass measurements by 50 (the number of replicates) as otherwise
+    the measurements are outliers (seem to be off by 50 times).
 locations:
   Terrick Terrick National Park:
     latitude (deg): -36.1738

data/Kew_2019_1/metadata.yml

@@ -16,7 +16,7 @@ contributors:
   dataset_curators: Elizabeth Wenk
 dataset:
   data_is_long_format: no
-  custom_R_code:        '
+  custom_R_code: '
     data %>%
       mutate(
         ref_year = stringr::str_extract(refshort, "(?<!\\d)\\d{4}(?!\\d)"),
@@ -46,21 +46,32 @@ dataset:
             "REFERENCE: ", original_dataset_id
         ),
         measurement_remarks = stringr::str_replace(
-            measurement_remarks, 
+            measurement_remarks,
             "MATERIAL: NA; ", ""),
         measurement_remarks = stringr::str_replace(
-            measurement_remarks, 
-            "NOTES: NA; ", "")
-      ) %>% 
-      filter(!original_dataset_id %in% c("Jurado_1991", "Moles_2000", "Milberg_1998")) %>% 
-      arrange(taxa, materialweigheddesc, thousandseedweight, original_dataset_id) %>% 
+            measurement_remarks,
+            "NOTES: NA; ", ""),
+        seed_mass_method = case_when(
+          stringr::str_detect(seedweightnotes, "wet mass") ~ "Weight refers to wet mass of mature seed.",
+          stringr::str_detect(seedweightnotes, "air-dry|air dry|Air-dry") ~ "Weight refers to the air-dried mass of mature seed.",
+          stringr::str_detect(seedweightnotes, "oven dry|dried at|dried to|dried in|dried for") ~ "Weight refers to the oven-dried mass of mature seed.",
+          stringr::str_detect(seedweightnotes, "fresh|Fresh") ~ "Weight refers to fresh mass of mature seed.",
+          stringr::str_detect(seedweightnotes, "mean weight of 20 dry seeds|Dired seed") ~ "Weight refers to dry mass of mature seed.",
+          stringr::str_detect(seedweightnotes, "dry weight") & stringr::str_detect(seedweightnotes, "SE=") ~ "Weight refers to dry mass of mature seed.",
+          seedweightnotes %in% c("Dry weight", "Dry weight.", "dry", "Weight refers to seed dry mass", "Seed dry-weight.") ~ "Weight refers to dry mass of mature seed.",
+          TRUE ~ "Weight probably refers to dry mass (see measurement remarks)."),
+        thousandseedweight = ifelse(taxa == "Angophora bakeri", thousandseedweight/1000, thousandseedweight)
+
+      ) %>%
+      filter(!original_dataset_id %in% c("Jurado_1991", "Moles_2000", "Milberg_1998")) %>%
+      arrange(taxa, materialweigheddesc, thousandseedweight, original_dataset_id) %>%
       group_by(taxa, materialweigheddesc, thousandseedweight, seedweightnotes, weightprecision) %>%
       mutate(merged_ref = ifelse(length(unique(original_dataset_id)) == 1, original_dataset_id, paste0(original_dataset_id, collapse = "; "))) %>%
-      ungroup() %>% 
+      ungroup() %>%
       group_by(taxa, merged_ref) %>%
-      mutate(across(c(thousandseedweight, materialweigheddesc), replace_duplicates_with_NA)) %>% 
+      mutate(across(c(thousandseedweight, materialweigheddesc), replace_duplicates_with_NA)) %>%
       ungroup()
-  '
+    '
   collection_date: unknown/2019
   taxon_name: taxa
   source_id: original_dataset_id
@@ -72,9 +83,32 @@ dataset:
   original_file: in raw data folder
   measurement_remarks: merged_ref
   notes: Data provided for inclusion in AusTraits and subsequent reuse under a Creative
-    Commons license. Data not to be used for Commercial Purposes.
+    Commons license. Data not to be used for Commercial Purposes. Seed weight for Angophora
+    bakeri divided by 1000 in custom_R_code due to extreme outlier.
 locations: .na
-contexts: .na
+contexts:
+- context_property: seed mass method
+  category: method_context
+  var_in: seed_mass_method
+  values:
+  - find: Weight probably refers to dry mass (see measurement remarks).
+    value: dry mass (assumed)
+    description: Weight probably refers to dry mass (see measurement remarks).
+  - find: Weight refers to the air-dried mass of mature seed.
+    value: air-dried mass
+    description: Weight refers to the air-dried mass of mature seed.
+  - find: Weight refers to the oven-dried mass of mature seed.
+    value: oven-dried mass
+    description: Weight refers to the oven-dried mass of mature seed.
+  - find: Weight refers to dry mass of mature seed.
+    value: dry mass
+    description: Weight refers to dry mass of mature seed.
+  - find: Weight refers to fresh mass of mature seed.
+    value: fresh mass
+    description: Weight refers to fresh mass of mature seed.
+  - find: Weight refers to wet mass of mature seed.
+    value: wet mass
+    description: Weight refers to wet mass of mature seed.
 traits:
 - var_in: thousandseedweight
   unit_in: mg

data/Kooyman_2011/metadata.yml

@@ -21,7 +21,7 @@ contributors:
   dataset_curators: Rachael Gallagher
 dataset:
   data_is_long_format: no
-  custom_R_code:          '
+  custom_R_code: '
     data %>%
       group_by(`Species_reconciled with updates and additions`) %>%
         mutate(across(c(`seed length maximum (mm)`,`seed length minimum (mm)`,
@@ -38,7 +38,11 @@ dataset:
         `leaf width minimum (mm)` = ifelse(is.na(leaf_width_min_duplicate),`leaf width minimum (mm)`,NA),
         `leaf width maximum (mm)` = ifelse(is.na(leaf_width_max_duplicate),`leaf width maximum (mm)`,NA),
         `leaf length minimum (mm)` = ifelse(is.na(leaf_length_min_duplicate),`leaf length minimum (mm)`,NA),
-        `leaf length maximum (mm)` = ifelse(is.na(leaf_length_max_duplicate),`leaf length maximum (mm)`,NA)
+        `leaf length maximum (mm)` = ifelse(is.na(leaf_length_max_duplicate),`leaf length maximum (mm)`,NA),
+        `seed length minimum (mm)` = ifelse(`Species_reconciled with updates and additions` == "Rhizophora mucronata", NA, `seed length minimum (mm)`),
+        `seed length maximum (mm)` = ifelse(`Species_reconciled with updates and additions` == "Rhizophora mucronata", NA, `seed length maximum (mm)`),
+        `seed width minimum (mm)` = ifelse(`Species_reconciled with updates and additions` == "Rhizophora mucronata", NA, `seed width minimum (mm)`),
+        `seed width maximum (mm)` = ifelse(`Species_reconciled with updates and additions` == "Rhizophora mucronata", NA, `seed width maximum (mm)`)
       ) %>%
       select(-`seed size categorical: <10mm`,-`seed size categorical: >10mm`,
       `wood density genus`, `wood density family`, -seed_width_min_duplicate, - seed_width_max_duplicate,
@@ -126,7 +130,8 @@ dataset:
     of the five areas; Cape York (CY) andWet Tropics (WT) in Qld, and Nightcap-Border
     Ranges (NB), Dorrigo (DO) and Washpool (WA) in NSW.
   original_file: Aust_RF_Traits_Kooyman_original.xls
-  notes: none
+  notes: Excluded seed widths and lengths for Rhizophora mucronata as seed length
+    seems to be for hypocotyl according to Flora of Australia.
 locations: .na
 contexts: .na
 traits:

data/Laxton_2005/metadata.yml

@@ -22,10 +22,10 @@ contributors:
   dataset_curators: Rachael Gallagher
 dataset:
   data_is_long_format: no
-  custom_R_code:        '
+  custom_R_code: '
     data %>%
       mutate(SITE_ID = ifelse(is.na(SITE_ID),"unknown", SITE_ID))
-  '
+    '
   collection_date: 2002/2004
   taxon_name: species_name
   location_name: SITE_ID

data/Leishman_2007/metadata.yml

@@ -24,14 +24,14 @@ contributors:
 dataset:
   data_is_long_format: no
   custom_R_code:          '
-    data %>% 
+    data %>%
       mutate(
         across(c(`gs (molm-2s-1)`), ~na_if(.x, 0)),
         entity_to_use = ifelse(is.na(Replicate),"population","individual"),
         value_type_to_use = ifelse(is.na(Replicate),"mean","raw"),
         replicates_to_use = ifelse(is.na(Replicate),"3","1")
       )
-  '
+    '
   collection_date: unknown/2007
   taxon_name: Species
   location_name: site

data/McGlone_2015/metadata.yml

@@ -22,22 +22,24 @@ contributors:
   dataset_curators: Elizabeth Wenk
 dataset:
   data_is_long_format: no
-  custom_R_code:        '
-    data %>% 
+  custom_R_code: '
+    data %>%
       mutate(
         woodiness = "woody",
         plant_growth_form = habit,
-        parasitic = ifelse(habit %in% c("parasite", "mistletoe"), "parasitic", NA),        
+        parasitic = ifelse(habit %in% c("parasite", "mistletoe"), "parasitic", NA),
         plant_growth_substrate = ifelse(habit %in% c("mistletoe"), "epiphyte", NA),
-        leaf_type = NA
-      ) %>% 
+        leaf_type = NA,
+        `ht (m)` = ifelse(`species name` == "Acacia mitchellii" & `ht (m)` == 30, NA, `ht (m)`),
+        `ht (m)` = ifelse(`species name` == "Gyrostemon australasicus" & `ht (m)` == 10, NA, `ht (m)`)
+      ) %>%
       distinct(`species name`, `ht (m)`, `ll (mm)`, `lw (mm)`, `leaf form`, `habit`, .keep_all = TRUE) %>%
       move_values_to_new_trait(
         "leaf form", "leaf_type",
         "scale", "scale", ""
       ) %>%
       mutate(across(c(`leaf form`), ~na_if(.x,"")))
-  '
+    '
   collection_date: 2014/2014
   taxon_name: species name
   location_name: sites
@@ -56,7 +58,8 @@ dataset:
     Walsh, N.G. & Entwistle, T.J. 1997. Flora of Victoria Volume 4. Chatswood. Enkata
     Press.
   original_file: Woody plants in Tasmania and Victoria.xls
-  notes: none
+  notes: plant_height values for Acacia mitchellii and Gyrostemon australasicus have
+    been removed as outliers, using `custom_R_code`
 locations:
   state not specified:
     latitude (deg): .na.real