Revision 9856
Added by Aaron Marcuse-Kubitza over 11 years ago
| inputs/GBIF/raw_occurrence_record_plants/postprocess.sql | ||
|---|---|---|
| 20 | 20 |
, 'UBC' |
| 21 | 21 |
, 'WIN' |
| 22 | 22 |
) |
| 23 |
/* there are 4.5 million duplicates [1] |
|
| 24 |
|
|
| 25 |
[1] 59,998,354 rows before [2] - 55,417,646 rows after [3] = 4,580,708 |
|
| 26 |
|
|
| 27 |
[2] 59998354 |
|
| 28 |
SELECT "raw_occurrence_record-row_num" |
|
| 29 |
FROM "GBIF".raw_occurrence_record_plants |
|
| 30 |
ORDER BY "raw_occurrence_record-row_num" DESC |
|
| 31 |
LIMIT 1 |
|
| 32 |
Total query runtime: 19436 ms. |
|
| 33 |
|
|
| 34 |
[3] 55417646 |
|
| 35 |
SELECT COUNT(*) FROM "GBIF".raw_occurrence_record_plants |
|
| 36 |
Total query runtime: 23 ms. |
|
| 37 |
*/ |
|
| 23 | 38 |
/* list obtained using the following on r9459: |
| 24 | 39 |
SELECT DISTINCT dataprovider |
| 25 | 40 |
FROM sourcelist |
Also available in: Unified diff
inputs/GBIF/raw_occurrence_record_plants/postprocess.sql: Remove institutions that we have direct data for: documented that there are 4.5 million duplicates (59,998,354 rows before - 55,417,646 rows after = 4,580,708)