Project

General

Profile

« Previous | Next » 

Revision 4950

Added by Aaron Marcuse-Kubitza about 12 years ago

inputs/REMIB/Specimen/map.csv: Remapped accession_number to catalogNumber because it is not globally unique, only (usually) unique within the institution providing the data ("acronym"). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution.

View differences:

inputs/REMIB/Specimen/map.csv
1 1 
REMIB,VegCore,Filter,Comments
2 2 
acronym,institutionCode,,
3 
accession_number,occurrenceID,,
3 
accession_number,catalogNumber,,"Not globally unique, only (usually) unique within the institution providing the data (""acronym""). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution. [1]
4 

  		




  
  5
  
    
[1] Using the following query:


  		




  
  6
  
    
-----


  		




  
  7
  
    
SELECT acronym, accession_number, count(*)


  		




  
  8
  
    
FROM ""REMIB"".""Specimen""


  		




  
  9
  
    
GROUP BY acronym, accession_number


  		




  
  10
  
    
HAVING count(*) > 1


  		




  
  11
  
    
-----"


  		




  4
  12
  
    
family,family,,


  		




  5
  13
  
    
genus,genus,,


  		




  6
  14
  
    
specificEpithet,specificEpithet,,


  		












  

    
      inputs/REMIB/Specimen/VegBIEN.csv
    
  





  1
  1
  
    
REMIB,VegBIEN:/_simplifyPath:[next=parent_id]/path,Comments


  		




  2
  
  
    
accession_number,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_alt/1",


  		




  
  2
  
    
accession_number,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_alt/2/_if[@name=""if catalogNumber""]/cond/_exists","Not globally unique, only (usually) unique within the institution providing the data (""acronym""). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution. [1]


  		




  
  3
  
    

  		




  
  4
  
    
[1] Using the following query:


  		




  
  5
  
    
-----


  		




  
  6
  
    
SELECT acronym, accession_number, count(*)


  		




  
  7
  
    
FROM ""REMIB"".""Specimen""


  		




  
  8
  
    
GROUP BY acronym, accession_number


  		




  
  9
  
    
HAVING count(*) > 1


  		




  
  10
  
    
-----"


  		




  3
  11
  
    
acronym,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_alt/2/_if[@name=""if catalogNumber""]/then/_join/1",


  		




  
  12
  
    
accession_number,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_alt/2/_if[@name=""if catalogNumber""]/then/_join/3/_if[@name=""if indirect voucher""]/else","Not globally unique, only (usually) unique within the institution providing the data (""acronym""). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution. [1]


  		




  
  13
  
    

  		




  
  14
  
    
[1] Using the following query:


  		




  
  15
  
    
-----


  		




  
  16
  
    
SELECT acronym, accession_number, count(*)


  		




  
  17
  
    
FROM ""REMIB"".""Specimen""


  		




  
  18
  
    
GROUP BY acronym, accession_number


  		




  
  19
  
    
HAVING count(*) > 1


  		




  
  20
  
    
-----"


  		




  4
  21
  
    
lat_deg,"/location/locationcoords/latitude_deg/_nullIf:[null=0,type=float]/value",


  		




  5
  22
  
    
long_deg,"/location/locationcoords/longitude_deg/_nullIf:[null=0,type=float]/value",


  		




  6
  23
  
    
coll_day,"/location/locationevent/taxonoccurrence/aggregateoccurrence/collectiondate/_alt/2/_date/day/_nullIf:[null=0,type=float]/value",


  		




  7
  24
  
    
coll_month,"/location/locationevent/taxonoccurrence/aggregateoccurrence/collectiondate/_alt/2/_date/month/_nullIf:[null=0,type=float]/value",


  		




  8
  25
  
    
coll_year,"/location/locationevent/taxonoccurrence/aggregateoccurrence/collectiondate/_alt/2/_date/year/_nullIf:[null=0,type=float]/value",


  		




  
  26
  
    
accession_number,"/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/catalognumber_dwc/_if[@name=""if indirect voucher""]/else","Not globally unique, only (usually) unique within the institution providing the data (""acronym""). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution. [1]


  		




  
  27
  
    

  		




  
  28
  
    
[1] Using the following query:


  		




  
  29
  
    
-----


  		




  
  30
  
    
SELECT acronym, accession_number, count(*)


  		




  
  31
  
    
FROM ""REMIB"".""Specimen""


  		




  
  32
  
    
GROUP BY acronym, accession_number


  		




  
  33
  
    
HAVING count(*) > 1


  		




  
  34
  
    
-----"


  		




  9
  35
  
    
acronym,/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/institution_id/party/organizationname,


  		




  10
  
  
    
accession_number,/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/sourceaccessioncode,


  		




  11
  
  
    
accession_number,/location/locationevent/taxonoccurrence/sourceaccessioncode/_first/3,


  		




  12
  36
  
    
family,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonpath/family,


  		




  13
  37
  
    
genus,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonpath/genus,


  		




  14
  38
  
    
specificEpithet,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonpath/species,


  		




  15
  39
  
    
collector,/location/locationevent/taxonoccurrence/verbatimcollectorname,


  		




  
  40
  
    
accession_number,"/location/locationevent/taxonoccurrence/voucher/*_id/specimenreplicate/catalognumber_dwc/_if[@name=""if indirect voucher""]/then","Not globally unique, only (usually) unique within the institution providing the data (""acronym""). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution. [1]


  		




  
  41
  
    

  		




  
  42
  
    
[1] Using the following query:


  		




  
  43
  
    
-----


  		




  
  44
  
    
SELECT acronym, accession_number, count(*)


  		




  
  45
  
    
FROM ""REMIB"".""Specimen""


  		




  
  46
  
    
GROUP BY acronym, accession_number


  		




  
  47
  
    
HAVING count(*) > 1


  		




  
  48
  
    
-----"


  		




  16
  49
  
    
locality,/location/locationnarrative/_merge/1,


  		




  17
  50
  
    
habitat,"/location/locationnarrative/_merge/3/_label[label=""habitat""]/value","Brad: Free-text description of vegetation community where collected, frequently redundane wrt 'Vegetation'. Bob, Nick: keep as user defined or create special element?"


  		




  18
  51
  
    
country,/location/locationplace/*_id/placepath/country,


  		












  

    
      inputs/REMIB/Specimen/test.xml.ref
    
  





  4
  4
  
    
        <next>parent_id</next>


  		




  5
  5
  
    
        <path>


  		




  6
  6
  
    
            <location>


  		




  7
  
  
    
                <authorlocationcode>$accession_number</authorlocationcode>


  		




  
  7
  
    
                <authorlocationcode>


  		




  
  8
  
    
                    <_join>


  		




  
  9
  
    
                        <1>$acronym</1>


  		




  
  10
  
    
                        <3>$accession_number</3>


  		




  
  11
  
    
                    </_join>


  		




  
  12
  
    
                </authorlocationcode>


  		




  8
  13
  
    
                <locationcoords>


  		




  9
  14
  
    
                    <latitude_deg>


  		




  10
  15
  
    
                        <_nullIf>


  		




  ......




  51
  56
  
    
                            </collectiondate>


  		




  52
  57
  
    
                            <plantobservation>


  		




  53
  58
  
    
                                <specimenreplicate>


  		




  
  59
  
    
                                    <catalognumber_dwc>$accession_number</catalognumber_dwc>


  		




  54
  60
  
    
                                    <institution_id><party><organizationname>$acronym</organizationname></party></institution_id>


  		




  55
  
  
    
                                    <sourceaccessioncode>$accession_number</sourceaccessioncode>


  		




  56
  61
  
    
                                </specimenreplicate>


  		




  57
  62
  
    
                            </plantobservation>


  		




  58
  63
  
    
                        </aggregateoccurrence>


  		




  59
  
  
    
                        <sourceaccessioncode>$accession_number</sourceaccessioncode>


  		




  60
  64
  
    
                        <taxondetermination>


  		




  61
  65
  
    
                            <taxonpath_id>


  		




  62
  66
  
    
                                <taxonpath>


  		












  

    
      inputs/REMIB/Specimen/new_terms.csv
    
  





  1
  1
  
    
acronym,institutionCode,,


  		




  2
  
  
    
accession_number,occurrenceID,,


  		




  
  2
  
    
accession_number,catalogNumber,,"Not globally unique, only (usually) unique within the institution providing the data (""acronym""). Note that there are nevertheless 11,869 rows where an accession_number appears multiple times within the same institution. [1]


  		




  
  3
  
    

  		




  
  4
  
    
[1] Using the following query:


  		




  
  5
  
    
-----


  		




  
  6
  
    
SELECT acronym, accession_number, count(*)


  		




  
  7
  
    
FROM ""REMIB"".""Specimen""


  		




  
  8
  
    
GROUP BY acronym, accession_number


  		




  
  9
  
    
HAVING count(*) > 1


  		




  
  10
  
    
-----"


  		




  3
  11
  
    
long_deg,decimalLongitude,,


  		




  4
  12
  
    
lat_deg,decimalLatitude,,


  		




  5
  13
  
    
coll_day,dayCollected,,


  		












Also available in:  Unified diff