kaggle

README.md

@@ -27,3 +27,7 @@ psql -h 127.0.0.1 -d sql -U sql -c "\copy (select * from ligne order by id) to '
 psql -h 127.0.0.1 -d sql -U sql -c "\copy (select id, source, target, cost, reverse_cost, ST_AsText(geom) from route order by id) to './route.csv' with csv header"
 
 ```
+
+### Jeux de données
+
+- https://www.kaggle.com/datasets/alexandrelemercier/food-detailed-nutritional-content

docker-entrypoint-initdb.d/6_produit.sql

@@ -1,44 +0,0 @@
-create table produit (
-  id bigint primary key,
-  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/produit.csv' (FORMAT CSV, header, ENCODING 'UTF8');

pgvector/pgvector.sql

@@ -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;

pgvector/populate.sql

@@ -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;

postgis/postgis.sql

@@ -5,7 +5,8 @@ create table point (
   geom geometry(point, 4326) not null
 );
 
-create index idx_point_geom on point using gist (geom);
+create index idx_point_geom
+  on point using gist (geom);
 
 create table route (
   id serial primary key,
@@ -15,7 +16,8 @@ create table route (
   longueur double precision
 );
 
-create index idx_route_geom on route using gist (geom);
+create index idx_route_geom
+  on route using gist (geom);
 
 create or replace function maj_longueur()
 returns trigger as $$

vector.sql

@@ -1,60 +0,0 @@
-CREATE TABLE produits (
-  id SERIAL PRIMARY KEY,
-  nom TEXT,
-  caracteristiques VECTOR(6)
-);
-
-INSERT INTO produits (nom, caracteristiques) VALUES
-('Tomate',      '[0.6, 0.3, 0.3, 1.0, 0.5, 1.0]'),
-('Concombre',   '[0.2, 0.1, 0.9, 1.0, 0.0, 0.0]'),
-('Courgette',   '[0.3, 0.1, 0.5, 1.0, 0.0, 0.0]'),
-('Carotte',     '[0.5, 0.1, 0.8, 0.5, 0.0, 1.0]'),
-('Poivron',     '[0.4, 0.2, 0.6, 1.0, 0.0, 1.0]'),
-('Aubergine',   '[0.2, 0.1, 0.4, 1.0, 0.0, 0.0]'),
-('Pomme',       '[0.8, 0.3, 0.9, 1.0, 1.0, 1.0]'),
-('Poire',       '[0.7, 0.2, 0.7, 1.0, 1.0, 0.0]'),
-('Fraise',      '[0.9, 0.4, 0.7, 1.0, 1.0, 1.0]'),
-('Cerise',      '[0.8, 0.3, 0.6, 1.0, 1.0, 1.0]'),
-('Citron',      '[0.2, 1.0, 0.6, 1.0, 1.0, 1.0]'),
-('Orange',      '[0.7, 0.6, 0.7, 1.0, 1.0, 1.0]'),
-('Banane',      '[0.9, 0.1, 0.2, 1.0, 1.0, 0.0]'),
-('Raisin',      '[0.8, 0.3, 0.5, 1.0, 1.0, 1.0]'),
-('Pastèque',    '[0.8, 0.2, 0.6, 1.0, 1.0, 1.0]'),
-('Melon',       '[0.9, 0.2, 0.5, 1.0, 1.0, 1.0]'),
-('Betterave',   '[0.5, 0.1, 0.4, 0.0, 0.0, 1.0]'),
-('Radis',       '[0.2, 0.3, 0.9, 0.5, 0.0, 1.0]'),
-('Brocoli',     '[0.1, 0.1, 0.6, 0.0, 0.0, 0.0]'),
-('Chou-fleur',  '[0.1, 0.1, 0.7, 0.0, 0.0, 0.0]');
-
-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;
-
-
-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 'Familia%'
-    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;