Created
March 7, 2024 22:26
-
-
Save aborruso/ade0154e3eb61558e1bd2cf8122c2a57 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# ISPIRATO DAL SOMMO SIMON https://til.simonwillison.net/duckdb/remote-parquet | |
# estrai elenco degli URL dei file | |
curl -X GET "https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train" | |
# interroga i file parquet, come se fosse un'unica risorsa, con l'hard coding degli URL | |
duckdb -c "select CODICE_NATURA_INTERVENTO,NATURA_INTERVENTO,count(*) conteggio FROM read_parquet( | |
['https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/0.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/1.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/2.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/3.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/4.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/5.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/6.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/7.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/8.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/9.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/10.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/11.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/12.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/13.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/14.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/15.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/16.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/17.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/18.parquet','https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/19.parquet']) group by ALL order by conteggio DESC" | |
# interroga i file parquet, come se fosse un'unica risorsa, senza scrivere elenco URL | |
# ma facendolo generare, con funzioni lambda | |
duckdb -c " | |
SELECT | |
CODICE_NATURA_INTERVENTO, | |
NATURA_INTERVENTO, | |
COUNT(*) AS conteggio | |
FROM read_parquet( | |
list_transform( | |
generate_series(0, 19), -- Genera una serie di numeri da 0 a 19. | |
n -> 'https://huggingface.co/api/datasets/aborruso/open_cup_complessivo/parquet/default/train/' || | |
n || '.parquet' -- Crea un URL per ciascun file Parquet | |
) | |
) | |
GROUP BY | |
CODICE_NATURA_INTERVENTO, | |
NATURA_INTERVENTO | |
ORDER BY | |
conteggio DESC; -- Ordina i risultati in base al conteggio decrescente. | |
" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment