Universite/sql
2
0
Fork 0
Code Pull Requests Actions Releases Wiki Activity

kaggle

Browse Source
This commit is contained in:
Université
2025-09-14 17:46:21 +02:00
parent eeac8e72da
commit 8eaa75ba5f
7 changed files with 86 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pgvector/openfoodfacts.http Normal file
View File

@@ -0,0 +1,2 @@
https://world.openfoodfacts.net/api/v2/product/3175680011480.json
Authorization: Basic off:off

53
pgvector/pgvector.sql Normal file
View File

@@ -0,0 +1,53 @@
create table produit (
id bigint primary key,
ean13 EAN13 null
nom text not null,
marque text null,
categorie text null,
energie int not null,
proteines float4 null,
glucides float4 null,
sucres float4 null,
graisses float4 null,
graisses_saturees float4 null,
sel float4 null,
fibres float4 null,
nutriscore int null,
additifs int null,
additifs_list text[] null,
potassium float null,
calcium float null,
magnesium float null,
sodium float null,
chlorure float null,
sulfate float null,
nitrate float null,
hydrogenocarbonate float null,
silice float null,
fluor float null,
residu float null,
ph float null,
vitamin_a float null,
vitamin_c float null
);
comment on column produit.potassium IS 'K⁺ en mg/L';
comment on column produit.calcium IS 'Ca²⁺ en mg/L';
comment on column produit.magnesium IS 'Mg²⁺ en mg/L';
comment on column produit.sodium IS 'Na⁺ en mg/L';
comment on column produit.chlorure IS 'Cl⁻ en mg/L';
comment on column produit.sulfate IS 'SO₄²⁻ en mg/L';
comment on column produit.nitrate IS 'NO₃⁻ en mg/L';
comment on column produit.hydrogenocarbonate IS 'HCO₃⁻ en mg/L';
comment on column produit.silice IS s'SiO₂ en mg/L';
comment on column produit.fluor IS 'F en mg/L';
\COPY produit FROM '/tmp/produits/cereales_petitdejeuner.csv' (FORMAT CSV, header, ENCODING 'UTF8');
\COPY produit FROM '/tmp/produits/confiture.csv' (FORMAT CSV, header, ENCODING 'UTF8');
\COPY produit FROM '/tmp/produit.csv' (FORMAT CSV, header, ENCODING 'UTF8');
alter table produits
add column nutrition vector(10);
update produits
set nutrition = ARRAY[energie, proteines, glucides, sucres, graisses, graisses_saturees, sel, fibres, nutriscore, additifs]::vector;

25
pgvector/populate.sql Normal file
View File

@@ -0,0 +1,25 @@
with selection as (
select op.id, product_name, brands, "energy-kcal_100g", fat_100g, "saturated-fat_100g",
"carbohydrates_100g", "sugars_100g", "proteins_100g", "salt_100g", "fiber_100g",
"nutriscore_score", "additives_n", string_to_array(additives_en, ','),
"potassium_100g", "calcium_100g", "vitamin-a_100g", "vitamin-c_100g",
main_category_en
from openfoodfacts_cleaned op
left join produit p on p.id = op.id
where brands like 'Nestlé%'
and p.id is null
and "energy-kcal_100g" is not null
and proteins_100g is not null
and fat_100g is not null
and "saturated-fat_100g" is not null
and carbohydrates_100g is not null
and sugars_100g is not null
and salt_100g is not null
and nutriscore_score is not null
)
insert into produit (id, nom, marque,
energie, graisse, graisse_saturee,
glucide, sucre, proteines, sel,
fibres, nutriscore, additifs, additifs_list,
potassium, calcium, vitamin_a, vitamin_c, categorie)
select * from selection;