{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# 2A.ml - 2017 - Pr\u00e9paration des donn\u00e9es\n", "\n", "Ce notebook explique comment les donn\u00e9es de la comp\u00e9tation 2017 ont \u00e9t\u00e9 pr\u00e9par\u00e9es. On r\u00e9cup\u00e9re d'abord les donn\u00e9es depuis le site [OpenFoodFacts](https://world.openfoodfacts.org/data)."]}, {"cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [{"data": {"text/html": ["
\n", ""], "text/plain": ["\n", "code\turl\tcreator\tcreated_t\tcreated_datetime\tlast_modified_t\tlast_modified_datetime\tproduct_name\tgeneric_name\tquantity\tpackaging\tpackaging_tags\tbrands\tbrands_tags\tcategories\tcategories_tags\tcategories_fr\torigins\torigins_tags\tmanufacturing_places\tmanufacturing_places_tags\tlabels\tlabels_tags\tlabels_fr\temb_codes\temb_codes_tags\tfirst_packaging_code_geo\tcities\tcities_tags\tpurchase_places\tstores\tcountries\tcountries_tags\tcountries_fr\tingredients_text\tallergens\tallergens_fr\ttraces\ttraces_tags\ttraces_fr\tserving_size\tno_nutriments\tadditives_n\tadditives\tadditives_tags\tadditives_fr\tingredients_from_palm_oil_n\tingredients_from_palm_oil\tingredients_from_palm_oil_tags\tingredients_that_may_be_from_palm_oil_n\tingredients_that_may_be_from_palm_oil\tingredients_that_may_be_from_palm_oil_tags\tnutrition_grade_uk\tnutrition_grade_fr\tpnns_groups_1\tpnns_groups_2\tstates\tstates_tags\tstates_fr\tmain_category\tmain_category_fr\timage_url\timage_small_url\tenergy_100g\tenergy-from-fat_100g\tfat_100g\tsaturated-fat_100g\tbutyric-acid_100g\tcaproic-acid_100g\tcaprylic-acid_100g\tcapric-acid_100g\tlauric-acid_100g\tmyristic-acid_100g\tpalmitic-acid_100g\tstearic-acid_100g\tarachidic-acid_100g\tbehenic-acid_100g\tlignoceric-acid_100g\tcerotic-acid_100g\tmontanic-acid_100g\tmelissic-acid_100g\tmonounsaturated-fat_100g\tpolyunsaturated-fat_100g\tomega-3-fat_100g\talpha-linolenic-acid_100g\teicosapentaenoic-acid_100g\tdocosahexaenoic-acid_100g\tomega-6-fat_100g\tlinoleic-acid_100g\tarachidonic-acid_100g\tgamma-linolenic-acid_100g\tdihomo-gamma-linolenic-acid_100g\tomega-9-fat_100g\toleic-acid_100g\telaidic-acid_100g\tgondoic-acid_100g\tmead-acid_100g\terucic-acid_100g\tnervonic-acid_100g\ttrans-fat_100g\tcholesterol_100g\tcarbohydrates_100g\tsugars_100g\tsucrose_100g\tglucose_100g\tfructose_100g\tlactose_100g\tmaltose_100g\tmaltodextrins_100g\tstarch_100g\tpolyols_100g\tfiber_100g\tproteins_100g\tcasein_100g\tserum-proteins_100g\tnucleotides_100g\tsalt_100g\tsodium_100g\talcohol_100g\tvitamin-a_100g\tbeta-carotene_100g\tvitamin-d_100g\tvitamin-e_100g\tvitamin-k_100g\tvitamin-c_100g\tvitamin-b1_100g\tvitamin-b2_100g\tvitamin-pp_100g\tvitamin-b6_100g\tvitamin-b9_100g\tfolates_100g\tvitamin-b12_100g\tbiotin_100g\tpantothenic-acid_100g\tsilica_100g\tbicarbonate_100g\tpotassium_100g\tchloride_100g\tcalcium_100g\tphosphorus_100g\tiron_100g\tmagnesium_100g\tzinc_100g\tcopper_100g\tmanganese_100g\tfluoride_100g\tselenium_100g\tchromium_100g\tmolybdenum_100g\tiodine_100g\tcaffeine_100g\ttaurine_100g\tph_100g\tfruits-vegetables-nuts_100g\tfruits-vegetables-nuts-estimate_100g\tcollagen-meat-protein-ratio_100g\tcocoa_100g\tchlorophyl_100g\tcarbon-footprint_100g\tnutrition-score-fr_100g\tnutrition-score-uk_100g\tglycemic-index_100g\twater-hardness_100g\n", "0000000003087\thttp://world-fr.openfoodfacts.org/produit/0000000003087/farine-de-ble-noir-ferme-t-y-r-nao\topenfoodfacts-contributors\t1474103866\t2016-09-17T09:17:46Z\t1474103893\t2016-09-17T09:18:13Z\tFarine de bl\u00e9 noir\t\t1kg\t\t\tFerme t'y R'nao\tferme-t-y-r-nao\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\ten:FR\ten:france\tFrance\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\ten:to-be-completed, en:nutrition-facts-to-be-completed, en:ingredients-to-be-completed, en:expiration-date-to-be-completed, en:characteristics-to-be-completed, en:categories-to-be-completed, en:brands-completed, en:packaging-to-be-completed, en:quantity-completed, en:product-name-completed, en:photos-to-be-validated, en:photos-uploaded\ten:to-be-completed,en:nutrition-facts-to-be-completed,en:ingredients-to-be-completed,en:expiration-date-to-be-completed,en:characteristics-to-be-completed,en:categories-to-be-completed,en:brands-completed,en:packaging-to-be-completed,en:quantity-completed,en:product-name-completed,en:photos-to-be-validated,en:photos-uploaded\tA compl\u00e9ter,Informations nutritionnelles \u00e0 compl\u00e9ter,Ingr\u00e9dients \u00e0 compl\u00e9ter,Date limite \u00e0 compl\u00e9ter,Caract\u00e9ristiques \u00e0 compl\u00e9ter,Cat\u00e9gories \u00e0 compl\u00e9ter,Marques compl\u00e9t\u00e9es,Emballage \u00e0 compl\u00e9ter,Quantit\u00e9 compl\u00e9t\u00e9e,Nom du produit complete,Photos \u00e0 valider,Photos envoy\u00e9es\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n", "\n", ""], "text/plain": ["
\n", " |
---|
code | \n", "
url | \n", "
creator | \n", "
created_t | \n", "
created_datetime | \n", "
last_modified_t | \n", "
last_modified_datetime | \n", "
product_name | \n", "
generic_name | \n", "
quantity | \n", "
packaging | \n", "
packaging_tags | \n", "
brands | \n", "
brands_tags | \n", "
categories | \n", "
categories_tags | \n", "
categories_fr | \n", "
origins | \n", "
origins_tags | \n", "
manufacturing_places | \n", "
manufacturing_places_tags | \n", "
labels | \n", "
labels_tags | \n", "
labels_fr | \n", "
emb_codes | \n", "
emb_codes_tags | \n", "
first_packaging_code_geo | \n", "
cities | \n", "
cities_tags | \n", "
purchase_places | \n", "
... | \n", "
pantothenic-acid_100g | \n", "
silica_100g | \n", "
bicarbonate_100g | \n", "
potassium_100g | \n", "
chloride_100g | \n", "
calcium_100g | \n", "
phosphorus_100g | \n", "
iron_100g | \n", "
magnesium_100g | \n", "
zinc_100g | \n", "
copper_100g | \n", "
manganese_100g | \n", "
fluoride_100g | \n", "
selenium_100g | \n", "
chromium_100g | \n", "
molybdenum_100g | \n", "
iodine_100g | \n", "
caffeine_100g | \n", "
taurine_100g | \n", "
ph_100g | \n", "
fruits-vegetables-nuts_100g | \n", "
fruits-vegetables-nuts-estimate_100g | \n", "
collagen-meat-protein-ratio_100g | \n", "
cocoa_100g | \n", "
chlorophyl_100g | \n", "
carbon-footprint_100g | \n", "
nutrition-score-fr_100g | \n", "
nutrition-score-uk_100g | \n", "
glycemic-index_100g | \n", "
water-hardness_100g | \n", "
163 rows \u00d7 0 columns
\n", "\n", " | code | \n", "url | \n", "creator | \n", "created_t | \n", "created_datetime | \n", "last_modified_t | \n", "last_modified_datetime | \n", "product_name | \n", "generic_name | \n", "quantity | \n", "... | \n", "fruits-vegetables-nuts_100g | \n", "fruits-vegetables-nuts-estimate_100g | \n", "collagen-meat-protein-ratio_100g | \n", "cocoa_100g | \n", "chlorophyl_100g | \n", "carbon-footprint_100g | \n", "nutrition-score-fr_100g | \n", "nutrition-score-uk_100g | \n", "glycemic-index_100g | \n", "water-hardness_100g | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "0000000003087 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "openfoodfacts-contributors | \n", "1474103866 | \n", "2016-09-17T09:17:46Z | \n", "1474103893 | \n", "2016-09-17T09:18:13Z | \n", "Farine de bl\u00e9 noir | \n", "NaN | \n", "1kg | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
1 | \n", "0000000004530 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "Banana Chips Sweetened (Whole) | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "14.0 | \n", "14.0 | \n", "NaN | \n", "NaN | \n", "
2 | \n", "0000000004559 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "Peanuts | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "0.0 | \n", "0.0 | \n", "NaN | \n", "NaN | \n", "
3 | \n", "0000000016087 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055731 | \n", "2017-03-09T10:35:31Z | \n", "1489055731 | \n", "2017-03-09T10:35:31Z | \n", "Organic Salted Nut Mix | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "12.0 | \n", "12.0 | \n", "NaN | \n", "NaN | \n", "
4 | \n", "0000000016094 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055653 | \n", "2017-03-09T10:34:13Z | \n", "1489055653 | \n", "2017-03-09T10:34:13Z | \n", "Organic Polenta | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
5 rows \u00d7 163 columns
\n", "\n", " | code | \n", "url | \n", "creator | \n", "created_t | \n", "created_datetime | \n", "last_modified_t | \n", "last_modified_datetime | \n", "product_name | \n", "generic_name | \n", "quantity | \n", "... | \n", "fruits-vegetables-nuts-estimate_100g | \n", "collagen-meat-protein-ratio_100g | \n", "cocoa_100g | \n", "chlorophyl_100g | \n", "carbon-footprint_100g | \n", "nutrition-score-fr_100g | \n", "nutrition-score-uk_100g | \n", "glycemic-index_100g | \n", "water-hardness_100g | \n", "hasE | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "0000000003087 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "openfoodfacts-contributors | \n", "1474103866 | \n", "2016-09-17T09:17:46Z | \n", "1474103893 | \n", "2016-09-17T09:18:13Z | \n", "Farine de bl\u00e9 noir | \n", "NaN | \n", "1kg | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "False | \n", "
1 | \n", "0000000004530 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "Banana Chips Sweetened (Whole) | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "14.0 | \n", "14.0 | \n", "NaN | \n", "NaN | \n", "False | \n", "
2 | \n", "0000000004559 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "Peanuts | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "0.0 | \n", "0.0 | \n", "NaN | \n", "NaN | \n", "False | \n", "
3 | \n", "0000000016087 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055731 | \n", "2017-03-09T10:35:31Z | \n", "1489055731 | \n", "2017-03-09T10:35:31Z | \n", "Organic Salted Nut Mix | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "12.0 | \n", "12.0 | \n", "NaN | \n", "NaN | \n", "False | \n", "
4 | \n", "0000000016094 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055653 | \n", "2017-03-09T10:34:13Z | \n", "1489055653 | \n", "2017-03-09T10:34:13Z | \n", "Organic Polenta | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "False | \n", "
5 rows \u00d7 164 columns
\n", "\n", " | code | \n", "url | \n", "creator | \n", "created_t | \n", "created_datetime | \n", "last_modified_t | \n", "last_modified_datetime | \n", "product_name | \n", "generic_name | \n", "quantity | \n", "... | \n", "collagen-meat-protein-ratio_100g | \n", "cocoa_100g | \n", "chlorophyl_100g | \n", "carbon-footprint_100g | \n", "nutrition-score-fr_100g | \n", "nutrition-score-uk_100g | \n", "glycemic-index_100g | \n", "water-hardness_100g | \n", "hasE | \n", "s100 | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | \n", "0000000004530 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "Banana Chips Sweetened (Whole) | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "14.0 | \n", "14.0 | \n", "NaN | \n", "NaN | \n", "False | \n", "17 | \n", "
2 | \n", "0000000004559 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "1489069957 | \n", "2017-03-09T14:32:37Z | \n", "Peanuts | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "0.0 | \n", "0.0 | \n", "NaN | \n", "NaN | \n", "False | \n", "17 | \n", "
3 | \n", "0000000016087 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055731 | \n", "2017-03-09T10:35:31Z | \n", "1489055731 | \n", "2017-03-09T10:35:31Z | \n", "Organic Salted Nut Mix | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "12.0 | \n", "12.0 | \n", "NaN | \n", "NaN | \n", "False | \n", "13 | \n", "
4 | \n", "0000000016094 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055653 | \n", "2017-03-09T10:34:13Z | \n", "1489055653 | \n", "2017-03-09T10:34:13Z | \n", "Organic Polenta | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "False | \n", "5 | \n", "
5 | \n", "0000000016100 | \n", "http://world-fr.openfoodfacts.org/produit/0000... | \n", "usda-ndb-import | \n", "1489055651 | \n", "2017-03-09T10:34:11Z | \n", "1489055651 | \n", "2017-03-09T10:34:11Z | \n", "Breadshop Honey Gone Nuts Granola | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "True | \n", "9 | \n", "
5 rows \u00d7 165 columns
\n", "\n", " | additives | \n", "hasE | \n", "
---|---|---|
0 | \n", "[ russet-potatoes -> en:russet-potatoes ] [... | \n", "False | \n", "
1 | \n", "[ grade-a-reduced-fat-milk -> en:grade-a-redu... | \n", "True | \n", "
2 | \n", "[ cake -> en:cake ] [ sugar -> en:sugar ] ... | \n", "True | \n", "
3 | \n", "[ whole-grain-yellow-corn -> en:whole-grain-y... | \n", "True | \n", "
4 | \n", "[ fresh-cucumbers -> en:fresh-cucumbers ] [... | \n", "True | \n", "