ean13

data/marque.csv

@@ -0,0 +1,4 @@
+id,marque
+1,Gerblé
+2,Nestlé
+3,La Laitière

data/marques.csv

@@ -1,2 +0,0 @@
-id,marque
-1,Gerblé

data/produits/confiture.csv

@@ -1,14 +1,14 @@
-id,nom,marque,categorie,energie,proteines,glucide,sucre,graisse,graisse_saturee,sel,fibres,nutriscore,additifs,additifs_list,potassium,calcium,magnesium,sodium,chlorure,sulfate,nitrate,hydrogenocarbonate,silice,fluor,residu,ph,vitamin_a,vitamin_c
+id,ean13,nom,marque,categorie,energie,proteines,glucides,sucres,graisses,graisses_saturees,sel,fibres,nutriscore,additifs,additifs_list,potassium,calcium,magnesium,sodium,chlorure,sulfate,nitrate,hydrogenocarbonate,silice,fluor,residu,ph,vitamin_a,vitamin_c
-1401675,Confiture rhubarbe rouge,Biocoop,Jams,234,0.6,57,56,0.5,0.1,0.07,,10,1,"{""E440 - Pectins""}",,,,,,,,,,,,,,
+1401675,,Confiture rhubarbe rouge,Biocoop,Jams,234,0.6,57,56,0.5,0.1,0.07,,10,1,"{""E440 - Pectins""}",,,,,,,,,,,,,,
-1634268,Confiture d’abricot,Biocoop,Jams,232,0.5,64,61,0.5,0.1,0.04,0,11,0,,,,,,,,,,,,,,,
+1634268,,Confiture d’abricot,Biocoop,Jams,232,0.5,64,61,0.5,0.1,0.04,0,11,0,,,,,,,,,,,,,,,
-1634304,Confiture rhubarbe,Biocoop,Jams,231,0.4,56,55.5,0.1,0.1,0.01,2,9,0,,,,,,,,,,,,,,,
+1634304,,Confiture rhubarbe,Biocoop,Jams,231,0.4,56,55.5,0.1,0.1,0.01,2,9,0,,,,,,,,,,,,,,,
-1634305,Confiture de fraise,Biocoop,Jams,237,0.5,57.6,57.1,0.2,0.1,0.01,1.2,10,0,,,,,,,,,,,,,,,
+1634305,,Confiture de fraise,Biocoop,Jams,237,0.5,57.6,57.1,0.2,0.1,0.01,1.2,10,0,,,,,,,,,,,,,,,
-1634306,Confiture de fruits rouges,Biocoop,Jams,243,0.6,57.9,56.7,0.2,0.1,0.01,2.9,9,0,,,,,,,,,,,,,,,
+1634306,,Confiture de fruits rouges,Biocoop,Jams,243,0.6,57.9,56.7,0.2,0.1,0.01,2.9,9,0,,,,,,,,,,,,,,,
-1634490,Confiture de framboise,Biocoop,Jams,242,0.5,63,55,0.5,0.1,0.03,,12,0,,,,,,,,,,,,,,,
+1634490,,Confiture de framboise,Biocoop,Jams,242,0.5,63,55,0.5,0.1,0.03,,12,0,,,,,,,,,,,,,,,
-1674818,"Confiture orange, citron et pamplemousse",Elibio,Jams,198,0.5,48,48,40.5,0.1,0.05,1.3,10,2,"{""E300 - Ascorbic acid"",""E440 - Pectins""}",,,,,,,,,,,,,,
+1674818,,"Confiture orange, citron et pamplemousse",Elibio,Jams,198,0.5,48,48,40.5,0.1,0.05,1.3,10,2,"{""E300 - Ascorbic acid"",""E440 - Pectins""}",,,,,,,,,,,,,,
-1674819,Préparation de fraises,Elibio,Jams,178,0.5,45,44,0.5,0.1,0.05,1.3,9,1,"{""E440 - Pectins""}",,,,,,,,,,,,,,
+1674819,,Préparation de fraises,Elibio,Jams,178,0.5,45,44,0.5,0.1,0.05,1.3,9,1,"{""E440 - Pectins""}",,,,,,,,,,,,,,
-1227545,Confiture de framboise,Gerblé,Jams,82,0.6,15,2.4,0,0,0.04,15,-5,7,"{""E1400 - Dextrin"",""E202 - Potassium sorbate"",""E330 - Citric acid"",""E333 - Calcium citrates"",""E440 - Pectins"",""E955 - Sucralose"",""E965 - Maltitol""}",,,,,,,,,,,,,,
+1227545,,Confiture de framboise,Gerblé,Jams,82,0.6,15,2.4,0,0,0.04,15,-5,7,"{""E1400 - Dextrin"",""E202 - Potassium sorbate"",""E330 - Citric acid"",""E333 - Calcium citrates"",""E440 - Pectins"",""E955 - Sucralose"",""E965 - Maltitol""}",,,,,,,,,,,,,,
-1228640,Confiture de fraise,Gerblé,Jams,76,0.5,13,3.2,0,0,0.03,14,-6,7,"{""E1400 - Dextrin"",""E202 - Potassium sorbate"",""E330 - Citric acid"",""E333 - Calcium citrates"",""E440 - Pectins"",""E955 - Sucralose"",""E965 - Maltitol""}",,,,,,,,,,,,,,
+1228640,,Confiture de fraise,Gerblé,Jams,76,0.5,13,3.2,0,0,0.03,14,-6,7,"{""E1400 - Dextrin"",""E202 - Potassium sorbate"",""E330 - Citric acid"",""E333 - Calcium citrates"",""E440 - Pectins"",""E955 - Sucralose"",""E965 - Maltitol""}",,,,,,,,,,,,,,
-1393224,La tomate cerise de marianne,Gerblé,Jams,77,0,15,4,0,0,0.03,12,-6,8,"{""E1400 - Dextrin"",""E202 - Potassium sorbate"",""E300 - Ascorbic acid"",""E330 - Citric acid"",""E333 - Calcium citrates"",""E440 - Pectins"",""E955 - Sucralose"",""E965 - Maltitol""}",,,,,,,,,,,,,,
+1393224,,La tomate cerise de marianne,Gerblé,Jams,77,0,15,4,0,0,0.03,12,-6,8,"{""E1400 - Dextrin"",""E202 - Potassium sorbate"",""E300 - Ascorbic acid"",""E330 - Citric acid"",""E333 - Calcium citrates"",""E440 - Pectins"",""E955 - Sucralose"",""E965 - Maltitol""}",,,,,,,,,,,,,,
-3106829,Confiture d’abricot,Gerblé,Jams,77,0,15,4,0,0,15,12,4,,,,,,,,,,,,,,,,
+3106829,,Confiture d’abricot,Gerblé,Jams,77,0,15,4,0,0,15,12,4,,,,,,,,,,,,,,,,
-1775102,Confiture de framboise,Mövenpick,Jams,189,0.7,46.2,45.9,0.2,0,0.03,,11,2,"{""E330 - Citric acid"",""E440a - Pectin""}",,,,,,,,,,,,,,
+1775102,,Confiture de framboise,Mövenpick,Jams,189,0.7,46.2,45.9,0.2,0,0.03,,11,2,"{""E330 - Citric acid"",""E440a - Pectin""}",,,,,,,,,,,,,,

docker-entrypoint-initdb.d/1_initdb.sql

@@ -2,7 +2,6 @@ create extension if not exists ltree;
 create extension if not exists pgtap;
 create extension if not exists postgis;
 create extension if not exists pgrouting;
-create extension if not exists vector;
 create extension if not exists pgcrypto;
 
 create table adherent (
@@ -46,6 +45,11 @@ create table ligne (
   quantite decimal
 );
 
+create table marque (
+  id int primary key,
+  marque text not null
+);
+
 create table fournisseur (
   id int primary key,
   fournisseur text not null

docker-entrypoint-initdb.d/2_seed.sql

@@ -3,9 +3,14 @@ truncate table famille;
 truncate table article;
 truncate table ticket;
 truncate table ligne;
+truncate table marque;
+truncate table fournisseur;
 
 \COPY adherent FROM '/tmp/adherent.csv' (FORMAT CSV, header, ENCODING 'UTF8');
 \COPY famille FROM '/tmp/famille.csv' (FORMAT CSV, header, ENCODING 'UTF8');
 \COPY article FROM '/tmp/article.csv' (FORMAT CSV, header, ENCODING 'UTF8');
 \COPY ticket FROM '/tmp/ticket.csv' (FORMAT CSV, header, ENCODING 'UTF8');
 \COPY ligne FROM '/tmp/ligne.csv' (FORMAT CSV, header, ENCODING 'UTF8');
+
+\COPY marque FROM '/tmp/marque.csv' (FORMAT CSV, header, ENCODING 'UTF8');
+\COPY fournisseur FROM '/tmp/marque.csv' (FORMAT CSV, header, ENCODING 'UTF8');

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

@@ -0,0 +1 @@
+\dx

pgvector/classification.md

@@ -0,0 +1,55 @@
+Parfait 👍 Alors, puisque vous avez vos vecteurs nutritionnels dans une colonne nutrition vector (normalisés avec un Z-score), vous pouvez utiliser l’extension pgvector pour faire une classification KNN directement dans PostgreSQL.
+
+Voici un exemple de requête complète en k-nearest neighbors (kNN) :
+
+-- Supposons que vous avez :
+-- table produit(id serial, nom text, famille text, nutrition vector)
+
+-- Exemple : on veut classifier un produit inconnu
+
+```sql
+WITH nouveau AS (
+  SELECT
+    ARRAY[
+      80,   -- énergie (kcal/100g)
+      3.5,  -- protéines
+      12,   -- glucides
+      11,   -- sucres
+      2.0,  -- graisses
+      0.8,  -- graisses_saturées
+      0.1,  -- sel
+      1.2,  -- fibres
+      5,    -- nutriscore numérique
+      0     -- nombre d'additifs
+    ]::vector AS nutrition
+)
+SELECT p.famille,
+       COUNT(*) AS voisins,
+       ROUND(AVG(p.nutrition <-> n.nutrition)::numeric, 3) AS distance_moyenne
+FROM produit p
+JOIN nouveau n ON true
+ORDER BY p.nutrition <-> n.nutrition   -- tri par distance euclidienne
+LIMIT 5;  -- on récupère les 5 plus proches voisins
+```
+
+```sql
+Étape suivante : classification majoritaire
+
+Pour prédire la famille (yaourt ou confiture), on peut compter la famille majoritaire parmi les k plus proches voisins :
+
+WITH nouveau AS (
+  SELECT ARRAY[80, 3.5, 12, 11, 2.0, 0.8, 0.1, 1.2, 5, 0]::vector AS nutrition
+),
+voisins AS (
+  SELECT p.famille
+  FROM produit p
+  JOIN nouveau n ON true
+  ORDER BY p.nutrition <-> n.nutrition
+  LIMIT 5  -- k=5
+)
+SELECT famille, COUNT(*) AS occurrences
+FROM voisins
+GROUP BY famille
+ORDER BY occurrences DESC
+LIMIT 1;  -- famille prédite
+```

pgvector/pgvector.sql

@@ -1,6 +1,11 @@
+-- 1. Ajouter les extensions
+create extension if not exists vector;
+create extension if not exists isn;
+
+-- 2. Créer la table des produits
 create table produit (
   id bigint primary key,
-  ean13 EAN13 null
+  ean13 EAN13 null,
   nom text not null,
   marque text null,
   categorie text null,
@@ -31,6 +36,7 @@ create table produit (
   vitamin_c float null
 );
 
+-- 3. ajouter les commentaires
 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';
@@ -39,15 +45,51 @@ 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.silice IS '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
+-- 5. ajouter une colonne vecteur
+alter table produit
 add column nutrition vector(10);
 
-update produits
+-- 6. Création de l’index ivfflat
-set nutrition = ARRAY[energie, proteines, glucides, sucres, graisses, graisses_saturees, sel, fibres, nutriscore, additifs]::vector;
+create index produit_nutrition_hnsw
+  on produit
+  using hnsw (nutrition vector_l2_ops)
+  with (m = 16, ef_construction = 200);
+
+-- 7. calculer la moyenne et l'écart-type pour chaque colonne, puis construire le vecteur :
+WITH stats AS (
+  SELECT
+    AVG(energie) AS mu_energie,       STDDEV_SAMP(energie)    AS sigma_energie,
+    AVG(proteines) AS mu_proteines,   STDDEV_SAMP(proteines)  AS sigma_proteines,
+    AVG(glucides) AS mu_glucides,     STDDEV_SAMP(glucides)   AS sigma_glucides,
+    AVG(sucres) AS mu_sucres,         STDDEV_SAMP(sucres)     AS sigma_sucres,
+    AVG(graisses) AS mu_graisses,     STDDEV_SAMP(graisses)   AS sigma_graisses,
+    AVG(graisses_saturees) AS mu_graisses_saturees, STDDEV_SAMP(graisses_saturees) AS sigma_graisses_saturees,
+    AVG(sel) AS mu_sel,               STDDEV_SAMP(sel)        AS sigma_sel,
+    AVG(fibres) AS mu_fibres,         STDDEV_SAMP(fibres)     AS sigma_fibres,
+    AVG(nutriscore) AS mu_nutriscore, STDDEV_SAMP(nutriscore) AS sigma_nutriscore,
+    AVG(additifs) AS mu_additifs,     STDDEV_SAMP(additifs)   AS sigma_additifs
+  FROM produit
+)
+UPDATE produit
+SET nutrition = (
+  SELECT ARRAY[
+    ((COALESCE(energie, mu_energie) - mu_energie) / NULLIF(sigma_energie,0)),
+    ((COALESCE(proteines, mu_proteines) - mu_proteines) / NULLIF(sigma_proteines,0)),
+    ((COALESCE(glucides, mu_glucides) - mu_glucides) / NULLIF(sigma_glucides,0)),
+    ((COALESCE(sucres, mu_sucres) - mu_sucres) / NULLIF(sigma_sucres,0)),
+    ((COALESCE(graisses, mu_graisses) - mu_graisses) / NULLIF(sigma_graisses,0)),
+    ((COALESCE(graisses_saturees, mu_graisses_saturees) - mu_graisses_saturees) / NULLIF(sigma_graisses_saturees,0)),
+    ((COALESCE(sel, mu_sel) - mu_sel) / NULLIF(sigma_sel,0)),
+    ((COALESCE(fibres, mu_fibres) - mu_fibres) / NULLIF(sigma_fibres,0)),
+    ((COALESCE(nutriscore, mu_nutriscore) - mu_nutriscore) / NULLIF(sigma_nutriscore,0)),
+    ((COALESCE(additifs, mu_additifs) - mu_additifs) / NULLIF(sigma_additifs,0))
+  ]::vector
+  FROM stats
+);