Browse Source

Finale

master
Ange-Charbelle DURAND 1 year ago
parent
commit
95ae3f2d52
  1. BIN
      Basedonnées_Net/.DS_Store
  2. 82448
      Basedonnées_Net/Entreprisedeplusde50salriés-Net.csv
  3. BIN
      Basedonnées_Net/InstallationPolluantes-Nettoyé/.DS_Store
  4. BIN
      Basedonnées_Net/InstallationPolluantes-Nettoyé/Architectures_Prel_ProdDangereux.docx
  5. 527
      Basedonnées_Net/InstallationPolluantes-Nettoyé/PrelevementPropre.csv
  6. 64101
      Basedonnées_Net/InstallationPolluantes-Nettoyé/ProdProp_Dechets_Dangereux.csv
  7. 13193
      Basedonnées_Net/InstallationPolluantes-Nettoyé/Prod_dechets_nondangereux.csv
  8. 49005
      Basedonnées_Net/InstallationPolluantes-Nettoyé/Trait_dechets_non_dangereux.csv
  9. 7192
      Basedonnées_Net/InstallationPolluantes-Nettoyé/emissions-nettoye.csv
  10. 4212
      Basedonnées_Net/InstallationPolluantes-Nettoyé/rejets.csv
  11. 82908
      Basedonnées_Net/InstallationPolluantes-Nettoyé/trait_dechets_dangereux.csv
  12. 832576
      Basedonnées_Net/SirenAdminNetFinal1.csv
  13. 58607
      Basedonnées_Net/egalite-nettoye.csv
  14. 10016
      Basedonnées_Net/etablissements.csv
  15. 733
      Basedonnées_Net/naf2008_5_niveaux.csv
  16. 22
      Basedonnées_Net/naf2008_liste_n1.csv
  17. BIN
      Basedonnées_initiale/.DS_Store
  18. 82448
      Basedonnées_initiale/Entreprisedeplusde50salrié.csv
  19. BIN
      Basedonnées_initiale/InstallationPolluantes/.DS_Store
  20. BIN
      Basedonnées_initiale/InstallationPolluantes/Architectures_Prel_ProdDangereux.docx
  21. 2405
      Basedonnées_initiale/InstallationPolluantes/Prelevements.csv
  22. 77863
      Basedonnées_initiale/InstallationPolluantes/Prod_dechets_dangereux.csv
  23. 13193
      Basedonnées_initiale/InstallationPolluantes/Prod_dechets_non_dangereux.csv
  24. 83613
      Basedonnées_initiale/InstallationPolluantes/Trait_dechets_dangereux.csv
  25. 49813
      Basedonnées_initiale/InstallationPolluantes/Trait_dechets_non_dangereux.csv
  26. 7192
      Basedonnées_initiale/InstallationPolluantes/emissions.csv
  27. 10016
      Basedonnées_initiale/InstallationPolluantes/etablissements.csv
  28. 4212
      Basedonnées_initiale/InstallationPolluantes/rejets.csv
  29. BIN
      Basedonnées_initiale/SirenAdminNet2.xlsx
  30. 90148
      Basedonnées_initiale/index-egalite-fh.csv
  31. BIN
      Basedonnées_initiale/sirenentr.xlsx
  32. 1095682
      Basedonnées_initiale/te_siren_admin.csv
  33. BIN
      CodePython_Nettoyage/.DS_Store
  34. 1584
      CodePython_Nettoyage/.ipynb_checkpoints/NetSirenplus-checkpoint.ipynb
  35. 955
      CodePython_Nettoyage/.ipynb_checkpoints/Netadmin_siren-checkpoint.ipynb
  36. 979
      CodePython_Nettoyage/.ipynb_checkpoints/Netadmin_sirenfinal-checkpoint.ipynb
  37. 1740
      CodePython_Nettoyage/NetProddechets.ipynb
  38. 1584
      CodePython_Nettoyage/NetSirenplus.ipynb
  39. 955
      CodePython_Nettoyage/Netadmin_siren.ipynb
  40. 979
      CodePython_Nettoyage/Netadmin_sirenfinal.ipynb
  41. 85
      CodeSQL.sql

BIN
Basedonnées_Net/.DS_Store

82448
Basedonnées_Net/Entreprisedeplusde50salriés-Net.csv
File diff suppressed because it is too large
View File

BIN
Basedonnées_Net/InstallationPolluantes-Nettoyé/.DS_Store

BIN
Basedonnées_Net/InstallationPolluantes-Nettoyé/Architectures_Prel_ProdDangereux.docx

527
Basedonnées_Net/InstallationPolluantes-Nettoyé/PrelevementPropre.csv

@ -0,0 +1,527 @@
Siren;Nom_Etablissement;Annee;Prelevements_Eaux_Souterraines;Prelevements_Eaux_Surface;Prelevements_Reseau_Distribution;Prelevements_Mer
6513201;EDF TAC MONTEREAU;2020;0;0;2048;0
7000727;RENAULT DOUAI SNC;2020;0;362694;50201;0
6400445;SMURFIT KAPPA PAPETERIE ALFA D'AVIGNON;2020;0;1025958;0;0
6700614;LEUCO PRODUCTION SAS;2020;55257;0;2716;0
7001036;Centre Hospitalier Universitaire;2020;0;0;338534;0
6300713;CARRIERES TAVANO SA;2020;0;510250;91;0
57100394;GROUPE BIGARD;2020;0;0;312972;0
6104785;BECTON DICKINSON;2020;748826;0;118423;0
5900890;SOCIETE FROMAGERE DE LONS LE SAUNIER;2020;0;0;112724;0
6103703;FRESENIUS MEDICAL CARE SMAD;2020;0;0;402919;0
6400118;LECASUD;2020;27628;0;313;0
7000956;ARCELORMITTAL FRANCE;2020;0;13216009;843968;43920000
10400164;KERRY RAVIFRUIT;2020;111140;0;17245;0
6102715;GERFLOR PROVENCE SNC;2020;144877;0;47572;0
10000496;BALSAN SA;2020;44603;0;885;0
6601574;GIE CHIMIE SALINDRES;2020;0;438109;0;0
5101078;COLGATE PALMOLIVE;2020;495699;0;15552;0
5401104;EUROSERUM;2020;669836;295875;0;0
10000651;CHALUMEAU LAQ'ALU SA - ANOLAQ;2020;11505;0;509;0
5900162;PAPETERIE ZUBER RIEDER;2020;678686;0;872;0
55600800;CADF SA;2020;237859;0;23231;0
5800299;TOTAL FLUIDES;2020;0;326394;3050;0
57908818;SAS SOFIVO;2020;0;0;287299;0
6102660;LABORATOIRE OXENA;2020;15000;0;110;0
6200868;LES SABLIERES DE LAIMONT;2020;0;119000;0;0
5703254;SOCIETE DES CARRIERES DE L'EST;2020;2100;0;0;0
6102033;UGITECH;2020;58529;0;2549;0
5401480;CARRIERES DE MONT ST VINCENT;2020;0;0;800;0
5800635;ARLANXEO ELASTOMERES FRANCE SAS;2020;212613;0;650217;0
6103725;POLYTECHNYL PI Belle-Etoile;2020;11072513;2768612;22240;0
5702721;SAICA PAPER EL;2020;1970353;0;2772;0
6402259;SERAMM Usine des boues;2020;0;77882;55950;0
5200378;VALBOM;2020;0;0;151930;0
7000830;Peugeot Citroën Mécanique du Nord Ouest SNC;2020;0;0;78749;0
6103493;VERALLIA FRANCE (ST GOBAIN EMBALLAGE);2020;44643;22245;7085;0
7000508;COMILOG ex Dunkerque Electrométallurgie;2020;25085;0;46988;0
53000374;DUC (SA);2020;0;0;122539;0
5801765;FROMAGERIE BOURSIN;2020;70358;0;1076;0
6401203;PROVENCE GRANULATS;2020;34950;0;0;0
5206306;BOUYER LEROUX;2020;5686;4091;4930;0
6100715;GRANULATS DE LA DROME;2020;13230;0;0;0
55800261;SARL IMPERY VOLAILLES;2020;0;0;3101;0
6506164;NCS PYROTECHNIE;2020;63744;0;1954;0
6806581;KNAUF INSULATION LANNEMEZAN SAS;2020;0;182698;9906;0
5802143;EDF;2020;0;0;476658;594712832
5302882;SIRAC;2020;73492;0;4848;0
5200361;SIAP-SARP INDUSTRIES AQUITAINE PYRENEES;2020;0;0;57328;0
10000241;HYDRO ALUMINIUM EXTRUSION SERVICES;2020;24416;0;450;0
55301450;HOLVIA PORC;2020;0;0;106456;0
5701463;REMIVAL;2020;44813;0;16135;0
5501795;UFM - UNION FERMIERE MORBIHANNAISE SAS;2020;78;0;405141;0
5901398;EUROCAST;2020;0;0;20533;0
6804068;SOCIETE DES EAUX MINERALES DE LUCHON SAS;2020;223059;0;924;0
6702299;TRANSPORTS KLEIN;2020;0;0;55048;0
7201328;RHODIA OPERATIONS;2020;209188;0;13054;0
7402278;EDF TAC ARRIGHI;2020;0;0;6086;0
52903791;SARL COADOUR;2020;26700;0;0;0
5701143;ARCELORMITTAL FRANCE;2020;0;214930;0;0
7000581;ASTRAZENECA DUNKERQUE PRODUCTION;2020;0;0;54717;0
6107516;VALRHONA;2020;236372;0;11493;0
56800039;SARVAL EST;2020;61640;0;7126;0
5202240;UPSA SAS;2020;0;0;57993;0
52903463;MERALLIANCE ARMORIC;2020;0;0;115428;0
6000456;VEOLIA PROPRETE (centre de tri);2020;0;0;367;0
6102364;OI FRANCE SAS;2020;0;14407;6320;0
6900013;EDF SEI;2020;0;0;221136;0
7001335;O-I FRANCE SAS usine de WINGLES;2020;93009;0;2926;0
6103721;Polytechnyl;2020;1314556;0;0;0
56100400;SOCIETE NOUVELLE DE VOLAILLE - S.N.V.;2020;47178;0;22238;0
6700471;BOREALIS PEC RHIN;2020;3151147;94921488;24096;0
6700681;GALVAnisation HILD (ex ALBERT HILD;2020;0;0;786;0
7000829;FRANCAISE DE MECANIQUE;2020;0;198658;5296;0
7001176;LESAFFRE (Société Industrielle);2020;2001505;3269825;12569;0
6501905;LINDE France s.a.;2020;0;73450;1267;0
5301495;SOCIETE BEURRIERE D'ISIGNY;2020;0;0;117927;0
5205784;GETRAG FORD Transmissions GmbH;2020;0;19217;6621;0
7201789;QUADRIPACK;2020;4947;0;28262;0
6000314;SMURFIT KAPPA Papier Recyclé France;2020;0;1753249;5459;0
6205873;Etablissements GEYER Frères;2020;0;0;55740;0
6200920;SUEZ RV MEUSE (ex-MEUSE ENERGIE);2020;35510;0;18;0
6400243;SAPA PROFILES PUGET SA;2020;0;68589;2351;0
6700187;GRAVIERES D'ALSACE LORRAINE;2020;828400;0;0;0
6700386;SITDCE - CENTRE DE VALORISATION ENERGETIQUE;2020;26512;0;328;0
6517193;SEMAVERT - Mont M√¢le;2020;7123;0;2427;0
7201539;SOCIETE FROMAGERIES LESCURE;2020;0;0;189906;0
5100499;WEST PHARMACEUTICAL SERVICES;2020;0;0;172536;0
5425537;DUC;2020;312347;0;1065;0
6201969;SCHOTT VTF;2020;27842;0;4361;0
6502558;SOPRONEM;2020;161034;0;18439;0
5102505;ROYE sucrerie et conditionnement;2020;238750;0;5333;0
55301494;SCEA FERRE PASCAL;2020;7688;0;0;0
5200249;FORESA FRANCE SAS;2020;99370;0;95857;0
6300981;Fromageries Bel Production France;2020;0;0;501337;0
50100813;BOEHRINGER INGELHEIM SANTE ANIMALE;2020;25216;0;3931;0
6700526;ARLANXEO Emulsion Rubber France SAS;2020;1232364;0;9315;0
6107527;VENCOREX FRANCE;2020;21127284;24491918;171718;0
6102859;SIRA;2020;55406;0;5939;0
6309633;LUISSIER BORDEAU CHESNEL YVRE L'EVEQUE;2020;0;0;116160;0
28100042;PONT SUR SAMBRE POWER;2020;1417107;0;423;0
7000575;DICKSON CONSTANT;2020;0;0;81587;0
5701322;BONGRAIN GERARD (usine);2020;129661;182445;7496;0
6600432;SANOFI-CHIMIE;2020;612928;0;12101;0
5100190;DSP France SAS (ex DOW FRANCE);2020;522751;1012860;21317;0
52903410;EARL PHILIPPE HASCOET;2020;9900;0;0;0
57903131;SAS LOEUL ET PIRIOT;2020;0;0;72520;0
6802175;PRAXAIR PHP SAS;2020;0;90227;0;0
6300918;YARA FRANCE;2020;0;0;1075928;0
58100446;SCEA MAUREL;2020;11600;0;1065;0
6702151;SOJINAL;2020;151132;0;416553;0
22200077;SABLIM Coulée Rivière Blanche Sud;2020;105438;0;1429;0
5703492;COGESAL MIKO;2020;0;0;277290;0
6700423;MARS Chocolat Steinbourg;2020;0;0;78298;0
5502667;QUARTZ ET MINERAUX;2020;0;230;0;0
7000523;EXIDE TECHNOLOGIES SAS;2020;64396;0;10856;0
53502544;ARMOR PROTEINES;2020;0;0;376640;0
6601116;SANOFI Aventis R&D;2020;0;0;72389;0
6400909;EURENCO S.A;2020;12094;0;0;0
5100949;LEBRONZE ALLOYS (ex BRONZE INDUSTRIEL);2020;273049;0;4060;0
6401040;IMERYS Aluminates SA;2020;0;108242;7343;0
5601324;LES FROMAGERIES OCCITANES;2020;0;0;101074;0
56300719;SOCIETE NOUVELLE LAITERIE DE LA MONTAGNE;2020;0;0;123000;0
6502131;A2C Granulat;2020;338631;0;0;0
5800392;DANONE;2020;0;0;624812;0
5801422;CERDATO;2020;15791;0;14502;0
5801578;NIPRO PHARMAPACKAGING FRANCE;2020;37021;0;302;0
6503268;RENAULT FLINS;2020;3;493846;34557;0
10001696;THALES LAS France SAS;2020;70852;0;0;0
7001078;SPAC;2020;0;0;59775;0
5900821;FROMAGERIES BEL PRODUCTION FRANCE (FBPF);2020;0;0;90484;0
7402350;CPCU ST-OUEN III;2020;0;1805070;44595;0
6801192;SITE DE VIC ADOUR;2020;0;94060;0;0
56100545;TRAITEUR DE LA TOUQUES;2020;0;0;61352;0
10000577;INTERNATIONAL COOKWARE;2020;68848;0;33984;0
7001124;COCA-COLA PRODUCTION SAS;2020;0;0;668975;0
5102153;SAINT LOUIS SUCRE;2020;112227;8248;13972;0
7001055;SEVELNORD;2020;191654;0;18484;0
5202602;SIAP LACQ;2020;0;1900;5010;0
9069916;EDF - CNPE du Tricastin;2020;0;4781789184;0;0
7000489;NORPAPER AVOT-VALLEE SAS;2020;1059138;0;5486;0
10001569;Laboratoires SERVIER Industrie;2020;0;0;88993;0
7002377;THYSSEN KRUPP ELECTRICAL STEEL UGO;2020;50036;177971;0;0
7202778;ROUSSELOT ANGOULEME SAS;2020;0;1210883;65908;0
6103844;RENAULT TRUCKS SAS;2020;210473;0;60021;0
57908869;SCEA AVICOLE SEGOVOL;2020;7230;0;0;0
6102436;IMERYS ALUMINATES Usine de LE TEIL;2020;0;10083;0;0
22100032;SRMG (SUCRERIE MARIE-GALANTE);2020;97640;78343;2800;0
54900588;CHARAL SAS;2020;23727;0;157001;0
7001555;CRUSTA C (SA);2020;0;0;86244;0
6411944;INEOS TECHNOLOGIES FRANCE SAS (ITF);2020;0;84497;1434;0
54000823;SASSO - SALLES LAURENT;2020;10313;0;12367;0
7405671;CHIMICMETAL;2020;0;0;371;0
6100021;SARL DANNENMULLER TLTP;2020;15406;0;0;0
7100099;Sucrerie de Bois Rouge;2020;0;835379;3292;0
10000802;ANTARTIC;2020;691006;0;0;0
56401304;LINDT ET SPRUNGLI SAS;2020;0;969383;75188;0
7208527;PINTAUD Sarl;2020;41397;0;0;0
5209347;SOBEGI SAS;2020;0;7805929;57298;0
5702865;OLFA SAS (ex SAHFFF);2020;0;62450;1930;0
6802437;ABATTOIR DE CAPDENAC SARL;2020;0;0;56950;0
6506489;RENAULT;2020;0;4145;1546;0
10000663;PAPETERIES PALM;2020;41159;1471438;40246;0
5800552;GLAXOSMITHKLINE;2020;0;0;56854;0
6104438;FERROPEM;2020;0;1276000;1200;0
5500596;STOCKBREST (STB1);2020;0;0;647;0
6801182;ABCVL S.A.S.;2020;25614;0;0;0
6200837;BONDUELLE FRAIS FRANCE;2020;211963;0;0;0
6104660;BAIKOWSKI;2020;0;0;62223;0
7002443;YKK FRANCE;2020;11275;0;838;0
5102355;STELIA AEROSPACE;2020;15830;0;5506;0
5301505;ACOME;2020;30971;0;9274;0
5800378;SEDIBEX;2020;0;0;685658;0
10300101;GELPAM;2020;150019;0;0;0
52903637;SCO (MONIQUE RANOU);2020;24630;0;188717;0
6700723;ALOXAN;2020;18448;0;2490;0
10004219;PROCTER ET GAMBLE BLOIS;2020;0;0;242996;0
5701344;ENTREMONT SODIAAL;2020;0;0;204986;0
6400589;AIRBUS HELICOPTERS;2020;0;129503;0;0
5701446;GOYARD JEAN DISTILLERIE;2020;124177;0;552;0
6103973;TOTAL RAFFINAGE France;2020;1906883;4561557;99608;0
5703071;ARS;2020;50027;0;6073;0
53800472;DANONE PRODUITS FRAIS;2020;724208;0;0;0
6802382;GIT SAS;2020;29280;0;2818;0
6800635;DRAGAGES DE VALENTINE;2020;0;36539;0;0
5900534;NESTLE FRANCE;2020;0;0;40018;0
6700428;CENPA SAS;2020;0;568967;52428;0
5502142;MICHELIN Vannes;2020;0;0;160677;0
5600518;GRANULATS BOURGOGNE AUVERGNE;2020;0;17310;0;0
5201068;CHU Hôpitaux de Bordeaux;2020;0;0;169473;0
7000483;ARKEMA FRANCE;2020;0;2599817;6348;0
5803187;TEREOS STARCH & SWEETENERS LBN;2020;0;19774704;1490756;0
5306883;SOCIETE DES MAITRES LAITIERS DU COTENTIN;2020;0;0;119120;0
5101491;Centre de Recherche Isolation de Rantigny;2020;0;18500;0;0
7001304;WIZPAPER SAS;2020;1667588;2000;5049;0
6103685;ARKEMA FRANCE;2020;9573000;18781500;198482;0
5701236;LAFIS BOLOGNE;2020;0;51183;45843;0
10000313;PAULSTRA;2020;48931;0;5596;0
6702247;DAIICHI SANKYO ALTKIRCH SARL;2020;0;0;94437;0
54400333;VIOL - CASTEL VIANDES;2020;116051;0;13765;0
5702799;GRANULATS VICAT SAS;2020;9234;0;0;0
6200339;GLANZSTOFF LONGLAVILLE;2020;0;0;125440;0
52500675;FROMAGERIE MULIN SAS;2020;0;0;101985;0
5901928;GE THERMAL MANUFACTURING(exALSTOM POWER);2020;30000;0;6200;0
5600074;Goodyear Montluçon;2020;0;459268;5549;0
5104757;CHU AMIENS PICARDIE;2020;0;0;185023;0
5106026;SUEZ Eau Industrielle (ex ONDEO IS);2020;0;748738;11014;0
5401274;CHEMETALL SA;2020;48001;0;17247;0
10000149;CHARTRES METROPOLE TRAITEMENT VALORISATI;2020;19152;0;316;0
5803207;SEA-TANK ROUEN;2020;23408;0;1027;0
5100912;AGCO;2020;12635;0;10162;0
6504504;Arquus Marolles;2020;0;0;4917;0
7000473;BRIDGESTONE/FIRESTONE FRANCE SA;2020;120000;0;7005;0
7100060;COMPAGNIE LAITIERE DES MASCAREIGNES;2020;306139;0;67635;0
5901400;VON ROLL ISOLA FRANCE;2020;8922;0;797;0
6102585;SAICA PAPER EL (EX EMIN LEYDIER );2020;3238889;0;2558;0
9069941;EDF - CNPE de GOLFECH;2020;0;190647008;0;0
6601905;ROYAL CANIN;2020;1186;0;62936;0
5207266;Centre de Stockage de Lussagnet;2020;1355;10456;2350;0
6104466;TRIMET;2020;2443298;5924350;0;0
5800398;CRISTAL UNION;2020;19266;0;2610;0
6700412;TREDI Hombourg;2020;4343;0;10087;0
5800437;ORFEVRERIE CHRISTOFLE;2020;31282;0;852;0
5701783;MALTEUROP FRANCE;2020;0;0;607087;0
6201051;MANOIR BOUZONVILLE;2020;0;72693;18020;0
6104367;PLACOPLATRE;2020;177524;0;2026;0
10000951;CGES (Cie Générale d'Eau de Source);2020;395020;0;0;0
6301021;Fromageries BEL Production France;2020;0;0;93223;0
6103644;SANOFI PASTEUR MARCY;2020;0;0;279051;0
5501682;GROUPE ROCHER OPERATIONS;2020;0;0;98885;0
52901390;GAEC DU VOULIC;2020;8700;0;0;0
6600227;SARL CARRIERES DE LA 113;2020;0;57124;0;0
5300452;CPO_COMPAGNIE PETROLIERE DE L'OUEST;2020;0;6420;253;0
6104306;GRID Solutions;2020;7108;0;4509;0
7300024;EDF Corse;2020;0;0;315184;0
5800416;POCHET DU COURVAL;2020;216549;0;12501;0
6505964;REP le Plessis-Gassot carrière;2020;42747;0;1188;0
6301117;ArcelorMittal Atlantique et Lorraine;2020;0;898673;33313;0
6302554;VILMORIN;2020;122739;0;15968;0
7000772;PREFERE RESINS FRANCE (ex DYNEA);2020;0;10818;437;0
6400451;GB FOODS PRODUCTION FRANCE SAS / LIEBIG;2020;110256;0;0;0
5703027;CEMOI;2020;581980;0;24422;0
6301046;ARRIVE;2020;0;0;57568;0
6200067;EDF - CCG Blénod;2020;0;2250796;2370;0
5206028;MONDELEZ FRANCE BISCUITS PRODUCTION;2020;0;0;34517;0
6400928;APPRYL;2020;0;75329;2852;35218140
6103636;BAYER SAS;2020;226349;0;4564;0
10001378;ORRION CHEMICALS ORGAFORM;2020;41332;0;2221;0
5106144;Laboratoire Unither;2020;0;0;185063;0
5302775;GILLOT SAS;2020;282918;95467;5539;0
5202760;YARA France SAS;2020;0;0;204;0
10006622;NOVANDIE;2020;434875;0;0;0
5105788;WEYLCHEM LAMOTTE (ex CLARIANT SFC);2020;0;3209959;29367;0
6102993;ARKEMA;2020;24070268;0;187941;0
7001050;CENTRE HOSPITALIER DE VALENCIENNES;2020;0;0;216552;0
6101808;GRANULATS VICAT;2020;117455;0;0;0
5801305;FERRERO FRANCE;2020;36250;0;16609;0
7000610;ROYAL CANIN SAS;2020;0;0;61460;0
6503170;ITON SEINE;2020;0;445436;5587;0
5501400;CSR SA (Cidrerie Loïc Raison);2020;0;0;101526;0
6200932;SARAYA EUROPE;2020;14343;0;1402;0
52904383;ETABLISSEMENTS PAUL PAULET;2020;0;0;72669;0
51700542;ARMOR PROTEINES;2020;1012970;0;382;0
5801044;DS SMITH;2020;4539500;0;0;0
6000385;INTERNATIONAL PAPER;2020;0;22750588;0;0
6410873;KEM ONE;2020;0;0;285473;0
6802285;SAS GELATINES WEISHARDT;2020;381097;915469;0;0
10600063;GERFLOR TARARE SNC;2020;0;0;75724;0
9069904;EDF - CNPE de Paluel;2020;0;599000;0;4093797120
6206235;PAPETERIES DES VOSGES;2020;0;455323;1301;0
6501929;SILEC CABLE;2020;1;391715;9496;0
57900192;SCEA APPORCS;2020;16050;0;0;0
5301223;ANETT 2;2020;58110;0;1050;0
5701339;FORGES DE COURCELLES;2020;0;56316;4637;0
6200942;CFR Compagnie des Fromages & Richemonts;2020;337249;0;26251;0
5200259;YARA FRANCE;2020;31420;154159;4659;0
6502168;OFFREDY (BEAUDELET);2020;0;0;8512;0
6600672;SIRAP GEMA;2020;10932;0;1297;0
6200938;VALTRIS ENTERPRISES FRANCE SAS;2020;246860;89898;9279;0
6400913;IMERYS PCC France (ex Solvay SF ex-CCP);2020;0;1110416;139236;0
5901243;EUROSERUM;2020;0;1453574;0;0
5300806;ARKEMA;2020;0;0;301072;0
6104028;CHROMALPES;2020;8421;0;3098;0
6102443;FABRICATION CHIMIQUE ARDECHOISE;2020;199888;0;12216;0
5401151;INDUSTEEL FRANCE site du Creusot (secteur Breuil);2020;0;0;174313;0
51800202;SCEA DU CORMIER;2020;8000;0;0;0
5204554;SAS GROUPE DANIEL;2020;0;9822;0;0
6102185;SAICA PACK;2020;16044;0;762;0
5100757;SAICA PAPER FRANCE (ROCHETTE VENIZEL);2020;0;2896052;4433;0
5200251;SANOFI WINTHROP INDUSTRIE;2020;115435;0;11747;0
5601749;TOTAL DIRECT ENERGIE CENTRALE ELECTRIQUE BAYET;2020;0;0;6029;0
5800429;AHLSTROM-MUNKSJO SPECIALTIES;2020;0;497546;0;0
5401845;ALFA LAVAL PACKINOX SAS;2020;0;7210;492;0
6301411;CARGILL France;2020;0;0;214630;0
6700404;ROQUETTE FRERES;2020;8199530;21401832;0;0
10013144;MONIN Georges SAS;2020;0;0;48568;0
6101092;BUDILLON RABATEL;2020;29193;0;0;0
6700652;TIMKEN EUROPE;2020;25559;0;28765;0
7002398;LIBERTY ASCOVAL;2020;0;300979;38251;0
6200720;KIMBERLY CLARK SAS;2020;0;1356743;0;0
6504594;DARBONNE;2020;340054;0;0;0
5102169;DAILYCER FRANCE SAS;2020;0;0;66787;0
5401144;APERAM STAINLESS FRANCE;2020;0;849172;31674;0
57201034;CAVOL;2020;141327;0;151645;0
6202417;PAPETERIE RAON;2020;10066;553660;0;0
6410379;INEOS DERIVATIVES LAVERA;2020;0;502308;8497;34962192
6202307;LUCART SAS;2020;580085;0;2191;0
7001045;CARGILL HAUBOURDIN SAS;2020;0;10223695;1133339;0
9076903;STEP - VILLEFRANCHE SUR SAONE;2020;19961;0;14672;0
6202551;BONGRAIN GERARD;2020;79067;149873;192252;0
6302829;LAFARGE GRANULATS FRANCE - Secteur Ouest;2020;3955;80957;5052;0
7201208;TIMAC AGRO;2020;0;8740;4048;0
57201569;ESPRI Restauration;2020;0;0;73795;0
7000658;TEREOS France;2020;459022;0;2713;0
5500609;BUNGE France;2020;0;0;211766;0
55600175;RONSARD;2020;188763;0;51701;0
50100364;BRESSOR SA;2020;351585;0;10513;0
6802818;AEROPORT de Toulouse Blagnac;2020;24;0;0;0
6102760;AGRANA FRUIT FRANCE;2020;149809;0;16043;0
6506270;ENERTHERM;2020;0;209739;6139;0
7000437;HAAGEN DAZS;2020;0;0;195296;0
6102152;CARRIER SCS;2020;15827;0;12547;0
58600141;BONILAIT PROTEINES;2020;582188;102511;4239;0
6702681;TECHNIQUES SURFACES EW;2020;0;0;583;0
6103062;AHLSTROM MUNKSJO LA GERE;2020;2971759;0;0;0
5302798;SOCIETE LAITIERE DU PAYS D'AUGE - SOLAIPA;2020;0;4404;118400;0
10000451;Cristal Union - Etablissement Toury;2020;329530;0;8263;0
5201623;NANKAI PLYWOOD ROLPIN (NP ROLPIN);2020;16141;0;0;0
6402363;Air Liquide France Industrie;2020;0;0;54876;0
6400350;GRANULATS VICAT;2020;95258;0;0;0
6103643;BioMerieux SA;2020;0;0;36817;0
7000761;AGC FRANCE SAS;2020;33905;745760;5332;0
53800603;CANDIA/YOPLAIT;2020;1184506;0;60;0
7000445;DSM Food Specialties;2020;812800;0;22200;0
53500475;LAITERIE CORALIS;2020;125738;0;120703;0
6103523;OI FRANCE SAS;2020;0;49095;6464;0
5500334;SECANIM BRETAGNE;2020;17699;0;1647;0
6104259;Givaudan Lavirotte (Groupe ISALTIS);2020;67418;0;144406;0
5501798;SOCIETE KERLYS;2020;222116;0;167591;0
6504202;SAFRAN AIRCRAFT ENGINES ( ex SNECMA);2020;23567;149615;3524;0
6200869;DHS BLANCHISSERIE HYRIS;2020;19555;0;0;0
6802302;STE TUELACAU;2020;136721;0;0;0
50100832;BRESSOR SA;2020;393558;0;140252;0
10003244;VAL DE LOIRE GRANULATS;2020;4664;0;0;0
7203048;CPK Production France (ex Mondelez);2020;0;0;50129;0
5202713;SOBEGI SAS;2020;0;708717;35081;0
53502694;SECANIM BRETAGNE (ex-SIFDDA);2020;0;0;756;0
5701421;CRISTAL UNION;2020;2363620;0;9323;0
5701226;MANQUILLET PARIZEL & CIE;2020;0;6210;321;0
5100466;INTERSNACK FRANCE ex-VICO SA;2020;347271;0;6400;0
5800520;NOVACEL;2020;23489;0;4198;0
7005038;WEPA FRANCE;2020;0;587014;10303;0
58501547;EURALIS GASTRONOMIE;2020;1417;0;86138;0
6402211;Petroineos Manufacturing France SAS;2020;0;4354673;32351;4500000
25200036;NEXANS FRANCE SA;2020;0;0;7083;0
6802459;PECHDO SA TANNERIES NOUVELLES;2020;0;34149;436;0
6302265;TOQUE ANGEVINE (LA);2020;0;0;81433;0
6405412;GDF SUEZ THERMIQUE FRANCE;2020;0;0;38154;160014752
52903521;VOLEFI;2020;19319;0;36716;0
5703184;EQIOM GRANULATS Région Nord Ouest;2020;46424;0;0;0
6102822;PCAS - SEQENS;2020;864374;0;7095;0
6104439;CARBONE SAVOIE;2020;565680;266601;51699;0
6701518;FAURECIA INSPIRING MOBILITY;2020;38048;0;1857;0
6202229;PAPETERIES DE CLAIREFONTAINE;2020;0;2449530;9765;0
6601281;SAIPOL;2020;0;0;328373;0
7000778;MAXAM TAN;2020;1114930;0;8699;0
5501602;ANETT 2 (Blanchisserie);2020;34083;0;386;0
5204565;DRAGAGES DU PONT DE LESCAR;2020;42230;0;1092;0
6100622;GRANULATS DE LA DROME;2020;27645;0;0;0
6207572;INEOS Polymers SARRALBE SAS;2020;0;2238579;43769;0
52903106;AQUADIS NATURELLEMENT;2020;0;323497;10059;0
6702200;Linde France Usine de Chalampé;2020;0;1692468;32;0
54201363;SAEM EVIAN SOURCE BADOIT;2020;247995;0;54845;0
5202274;RAYNAL ET ROQUELAURE;2020;0;95550;5745;0
6103809;EUROCAST LYON;2020;102312;0;4573;0
6103061;CALOR S.A.;2020;0;17285;4725;0
5304386;NESTLE HEALTH SCIENCE FRANCE;2020;216518;0;178;0
7002325;GLAXOSMITHKLINE;2020;0;0;182507;0
5101506;BOSTIK;2020;0;54360;3637;0
5500400;SAINT-BRIEUC FONDERIE (ex MANOIR);2020;0;883610;1;0
6114519;HEXCEL FIBERS;2020;0;0;195000;0
9076702;Station d'épuration des eaux usées de l'Eurométropole de Strasbourg;2020;726891;0;6682;0
7001044;LNUF Marques - Cuincy;2020;353134;0;27;0
6601744;SA des EAUX MINERALES d'EVIAN;2020;220285;0;20024;0
10100165;EUROCAST REYRIEUX;2020;0;0;9307;0
52900432;SOCOPA VIANDES;2020;0;0;282345;0
6601279;Communauté Agglomération Bassin de Thau;2020;0;0;269648;0
5800413;REVIMA;2020;0;12197;27191;0
6700516;BRASSERIE LICORNE;2020;0;0;290245;0
6302797;DIANA FOOD SAS (DIANA NATURALS);2020;0;0;144132;0
5804127;BIO COGELYO NORMANDIE;2020;0;0;9661;0
5103922;SAICA PACK (ex RCO);2020;35158;0;550;0
6301125;SOFIVO SAS;2020;0;100801;288926;0
6700794;WIENERBERGER;2020;0;0;68960;0
5101029;TEREOS FRANCE;2020;262361;0;9658;0
7201529;LAFARGE CIMENTS;2020;19391;0;1740;0
5202000;RAYONIER A.M. TARTAS;2020;4605897;5732990;67305;0
7000712;INVEHO UAB;2020;0;0;2480;0
6702475;NOVARTIS PHARMA SAS (biotechnologie);2020;0;704736;246686;0
6506444;SNCF TECHNICENTRE LE LANDY;2020;0;0;186326;0
6506498;VALO'MARNE (EX CIE);2020;395419;0;4085;0
6515749;EQIOM Granulats;2020;12848;0;0;0
7000832;MAUBEUGE CONSTRUCTION AUTOMOBILE (MCA);2020;0;0;147458;0
54200986;CANDIA;2020;0;0;226728;0
5401254;APERAM ALLOYS IMPHY;2020;0;407000;34507;0
5201996;TIMAC AGRO SA;2020;12939;36227;4212;0
5517250;STALAVEN SA;2020;0;0;229818;0
6506240;Chaufferie de GRENELLE;2020;0;1281585;14365;0
6300905;SABOURIN SAS;2020;74727;0;216832;0
5600328;MFP MICHELIN - Site de Cataroux;2020;0;0;200042;0
7001186;SIB (ex CEMA);2020;7143;0;10088;0
5600245;FAREVA LA VALLEE;2020;0;0;111073;0
5101339;UNILEVER FRANCE HPC Industries;2020;0;0;172926;0
7000991;HERTA;2020;0;0;459611;0
10000689;INDENA;2020;0;0;103616;0
6501812;AGRANA FRUITS FRANCE (ex ATYS);2020;138886;0;24972;0
7001033;PINGUIN (ex SICA DE LA VALLEE DE LA LYS);2020;0;0;279024;0
10000740;STMICROELECTRONICS SAS;2020;0;0;442447;0
6103907;BRUN;2020;14416;0;0;0
7006131;RECYCO;2020;1075;209774;0;0
6115210;AMOEBA;2020;0;0;1000;0
6103724;KEM ONE ETABLISSEMENT DE SAINT FONS;2020;2357773;2346490;17545;0
6411266;INEOS CHEMICALS LAVERA;2020;0;469022;32809;12297600
6506454;CPCU ST OUEN I & II;2020;0;751593;5322;0
6100956;BUDILLON RABATEL;2020;42814;0;0;0
5600040;SAGEM DEFENSE SECURITE SA;2020;0;58470;11504;0
6201561;UEM;2020;11275;10780671;50629;0
6502284;SAS ARMABESSAIRE;2020;615;0;0;0
7100111;TGBR- Site du Port;2020;0;0;149000;0
7000621;ARC FRANCE;2020;497323;1165153;796;0
6102992;SOGIF;2020;0;0;4388;0
5701246;FORGES DE FRONCLES;2020;0;3352;36944;0
7005525;EDF Bouchain_CCG;2020;0;2429997;2024;0
5401901;REFRESCO France;2020;0;0;152382;0
10300110;REFRESCO Site de Margès;2020;610528;0;11779;0
6202256;OI Manufacturing France;2020;0;301412;29445;0
6407117;ENGIE Thermique France;2020;0;0;41972;225076384
6400879;Rizerie SOUFFLET ALIMENTAIRE CAMARGUE;2020;88939;0;360;0
5401368;PLASTIPACK PACKAGING FRANCE;2020;0;0;120220;0
6000348;PANNEAUX DE CORREZE;2020;0;108767;1374;0
5800355;ARKEMA;2020;0;339047;5687;0
5509019;QUARTZ ET MINERAUX;2020;0;2300;0;0
7000846;MC CAIN ALIMENTAIRE;2020;1411427;0;3386;0
5300573;MAISON JOHANES BOUBEE BAYEUX;2020;0;0;81183;0
6501956;SAFRAN AIRCRAFT ENGINES;2020;91214;0;0;0
5100494;NOVABION;2020;0;51390;967;0
5901195;CF2P SAS (ex IKEA INDUSTRY FRANCE);2020;0;0;226772;0
5805710;COLLET SAS;2020;0;45831;3341;0
5600087;DECO-GALVA;2020;0;0;3257;0
24600028;INDUSTEEL FRANCE site du Creusot (Secteur Creusot);2020;0;0;186878;0
6400772;ARDAGH METAL BEVERAGE FRANCE SAS;2020;0;0;120953;0
6400411;RAYNAL et ROQUELAURE Provence;2020;483058;0;0;0
5204118;CEMEX GRANULATS Sud-Ouest SAS;2020;0;161554;0;0
5204674;DRAGAGES PONT DE LESCAR S.A.S;2020;206812;0;0;0
6803194;PROLAINAT SA;2020;0;0;125376;0
10300109;VALRHONA;2020;24448;0;19407;0
6108628;BOIRON FRERES;2020;0;300;74525;0
6400196;SAS ZEPHIRE;2020;0;0;80152;0
6804179;NUTRITION & SANTE;2020;0;0;111755;0
6506552;Centre de Production de Vitry-sur-Seine;2020;1221;1481953;274086;0
6700379;CHEMET-GLI;2020;8507;0;8277;0
5200010;POLYREY S.A.S. (usine);2020;0;396098;392;0
5702271;WEPA France;2020;414460;0;17119;0
6200031;MANUFACTURE DE BACCARAT;2020;135681;26486;0;0
6301264;FLEURY MICHON LS;2020;0;0;69649;0
5700724;MAC CAIN ALIMENTAIRE SAS;2020;807360;0;0;0
6301446;FRAMATOME;2020;0;0;90052;0
10004439;NEXANS France;2020;30510;0;7318;0
5300057;TIMAB PRODUITS INDUSTRIELS;2020;0;0;200;0
5101157;Amphastar France Pharmaceuticals;2020;240355;0;0;0
6103731;RHODIA OPERATIONS;2020;11370460;6713203;56915;0
5101610;SAINT GOBAIN GLASS;2020;185821;0;4496;0
54902244;ESPERANCE (GAEC DE L');2020;10490;0;0;0
5601336;Cie FROMAGERE VALLEE DE L'ANCE;2020;0;0;263655;0
5800699;COOPER STANDARD FRANCE Etb LILLEBONNE;2020;0;523965;1516;0
5701253;SAINT-GOBAIN PAM;2020;0;591017;4107;0
5300884;DANONE PRODUITS FRAIS FRANCE;2020;0;0;248953;0
55602952;LORCO;2020;0;0;167610;0
6400001;ALTEO GARDANNE;2020;22756;2346198;60000;0
7000821;NYRSTAR FRANCE;2020;0;1885042;80373;0
6700463;PUNCH POWERGLIDE (Ex GM);2020;3535131;0;4263;0
10002253;Etablissement de PITHIVIERS LE VIEIL;2020;19030;0;4641;0
5105839;SYNTHOMER (ex HEXION MOMENTIVE);2020;102954;56452;4701;0
5100497;LES FROMAGERS DE THIERACHE;2020;0;0;379093;0
5600377;SAIPOL;2020;0;0;52108;0
5518409;GROUPE SODIAAL B;2020;0;0;788698;0
6102074;CIAT;2020;2617870;0;3637;0
7001673;DURAND PRODUCTION;2020;33337;0;16154;0
5600543;IMERYS CERAMICS FRANCE Echassieres;2020;0;9435;0;0
6000336;PHOTONIS FRANCE SAS;2020;0;0;60897;0
5101010;SNCF EIV MOULIN NEUF;2020;1200;0;83034;0
6802159;BROWN EUROPE Sas;2020;0;46883;361;0
6401033;Air Liquide France Industrie;2020;0;0;447710;0
9069922;Orano Cycle Tricastin;2020;1891841;424496;62458;0
5101901;GOODYEAR DUNLOP TIRES Amiens SUD;2020;350100;0;7044;0
6506067;SEPANOR;2020;0;0;50;0
55700590;CHARAL;2020;0;0;126124;0
6305478;BONILAIT PROTEINES;2020;0;0;74485;0
6503241;SAINT GOBAIN ABRASIFS;2020;16012;0;23994;0
5401208;PRYSMIAN;2020;92023;0;0;0
6400486;NATUREX;2020;8978;0;52938;0
6802516;IMERYS;2020;15556;1559140;0;0
9069940;EDF - CNPE de FESSENHEIM;2020;82936;1045713152;0;0
5601318;LES FROMAGERIES OCCITANES;2020;0;244510;0;0
6803636;Imerys Talc Luzenac France;2020;749879;240183;10000;0
6802467;SOCIETE FROMAGERE DE RODEZ;2020;0;359757;39808;0
5500062;dominique Riou;2020;0;0;77984;0
52903139;SARL Hubert Simon;2020;89247;0;0;0
6512368;EDF TAC VAIRES SUR MARNE;2020;0;0;7755;0
5600212;PAPETERIES D'ESPALY S.A.;2020;0;17235;16164;0
6700176;HELMBACHER SABLIERES Valff;2020;920540;0;0;0
7003919;Vandemoortele Bakery Products France;2020;0;0;124048;0
6300911;HUHTAMAKI LA ROCHELLE - HLR;2020;0;633260;35401;0
54901225;GALLIN'OEUF (SCEA);2020;9191;0;1009;0
54401496;SCEA LES COTEAUX;2020;6000;1000;6500;0
7004733;MINAKEM DUNKERQUE PRODUCTION;2020;0;0;75143;0
5401305;Aluminium France Extrusion ST-FLORENTI;2020;0;104426;19407;0
6700503;BASF;2020;0;1580971;15661;0
5206066;DRAGAGES PONT DE LESCAR S.A.;2020;55504;0;0;0
7001833;TATA STEEL MAUBEUGE SAS;2020;0;309365;21920;0
55602604;PEP CAMAGNON;2020;0;0;142590;0
10000953;CHAMBON (générale eaux minérales nature);2020;660071;0;0;0
6700433;Vynova PPC SAS;2020;0;5274393;184467;0
5400431;CARRIERES ET MATERIAUX;2020;0;23833;2602;0
7000955;ARCELORMITTAL ATLANTIQUE et LORRAINE;2020;0;506511;42439;0
5200592;SAFT SAS;2020;0;0;78600;0
57400291;FROMAGERIE DES HAUTS DE SAVOIE;2020;0;0;114485;0
5701609;SAS GIVAUDAN France;2020;127495;0;458;0

64101
Basedonnées_Net/InstallationPolluantes-Nettoyé/ProdProp_Dechets_Dangereux.csv
File diff suppressed because it is too large
View File

13193
Basedonnées_Net/InstallationPolluantes-Nettoyé/Prod_dechets_nondangereux.csv
File diff suppressed because it is too large
View File

49005
Basedonnées_Net/InstallationPolluantes-Nettoyé/Trait_dechets_non_dangereux.csv
File diff suppressed because it is too large
View File

7192
Basedonnées_Net/InstallationPolluantes-Nettoyé/emissions-nettoye.csv
File diff suppressed because it is too large
View File

4212
Basedonnées_Net/InstallationPolluantes-Nettoyé/rejets.csv
File diff suppressed because it is too large
View File

82908
Basedonnées_Net/InstallationPolluantes-Nettoyé/trait_dechets_dangereux.csv
File diff suppressed because it is too large
View File

832576
Basedonnées_Net/SirenAdminNetFinal1.csv
File diff suppressed because it is too large
View File

58607
Basedonnées_Net/egalite-nettoye.csv
File diff suppressed because it is too large
View File

10016
Basedonnées_Net/etablissements.csv
File diff suppressed because it is too large
View File

733
Basedonnées_Net/naf2008_5_niveaux.csv

@ -0,0 +1,733 @@
NIV5;NIV1
01.11Z;A
01.12Z;A
01.13Z;A
01.14Z;A
01.15Z;A
01.16Z;A
01.19Z;A
01.21Z;A
01.22Z;A
01.23Z;A
01.24Z;A
01.25Z;A
01.26Z;A
01.27Z;A
01.28Z;A
01.29Z;A
01.30Z;A
01.41Z;A
01.42Z;A
01.43Z;A
01.44Z;A
01.45Z;A
01.46Z;A
01.47Z;A
01.49Z;A
01.50Z;A
01.61Z;A
01.62Z;A
01.63Z;A
01.64Z;A
01.70Z;A
02.10Z;A
02.20Z;A
02.30Z;A
02.40Z;A
03.11Z;A
03.12Z;A
03.21Z;A
03.22Z;A
05.10Z;B
05.20Z;B
06.10Z;B
06.20Z;B
07.10Z;B
07.21Z;B
07.29Z;B
08.11Z;B
08.12Z;B
08.91Z;B
08.92Z;B
08.93Z;B
08.99Z;B
09.10Z;B
09.90Z;B
10.11Z;C
10.12Z;C
10.13A;C
10.13B;C
10.20Z;C
10.31Z;C
10.32Z;C
10.39A;C
10.39B;C
10.41A;C
10.41B;C
10.42Z;C
10.51A;C
10.51B;C
10.51C;C
10.51D;C
10.52Z;C
10.61A;C
10.61B;C
10.62Z;C
10.71A;C
10.71B;C
10.71C;C
10.71D;C
10.72Z;C
10.73Z;C
10.81Z;C
10.82Z;C
10.83Z;C
10.84Z;C
10.85Z;C
10.86Z;C
10.89Z;C
10.91Z;C
10.92Z;C
11.01Z;C
11.02A;C
11.02B;C
11.03Z;C
11.04Z;C
11.05Z;C
11.06Z;C
11.07A;C
11.07B;C
12.00Z;C
13.10Z;C
13.20Z;C
13.30Z;C
13.91Z;C
13.92Z;C
13.93Z;C
13.94Z;C
13.95Z;C
13.96Z;C
13.99Z;C
14.11Z;C
14.12Z;C
14.13Z;C
14.14Z;C
14.19Z;C
14.20Z;C
14.31Z;C
14.39Z;C
15.11Z;C
15.12Z;C
15.20Z;C
16.10A;C
16.10B;C
16.21Z;C
16.22Z;C
16.23Z;C
16.24Z;C
16.29Z;C
17.11Z;C
17.12Z;C
17.21A;C
17.21B;C
17.21C;C
17.22Z;C
17.23Z;C
17.24Z;C
17.29Z;C
18.11Z;C
18.12Z;C
18.13Z;C
18.14Z;C
18.20Z;C
19.10Z;C
19.20Z;C
20.11Z;C
20.12Z;C
20.13A;C
20.13B;C
20.14Z;C
20.15Z;C
20.16Z;C
20.17Z;C
20.20Z;C
20.30Z;C
20.41Z;C
20.42Z;C
20.51Z;C
20.52Z;C
20.53Z;C
20.59Z;C
20.60Z;C
21.10Z;C
21.20Z;C
22.11Z;C
22.19Z;C
22.21Z;C
22.22Z;C
22.23Z;C
22.29A;C
22.29B;C
23.11Z;C
23.12Z;C
23.13Z;C
23.14Z;C
23.19Z;C
23.20Z;C
23.31Z;C
23.32Z;C
23.41Z;C
23.42Z;C
23.43Z;C
23.44Z;C
23.49Z;C
23.51Z;C
23.52Z;C
23.61Z;C
23.62Z;C
23.63Z;C
23.64Z;C
23.65Z;C
23.69Z;C
23.70Z;C
23.91Z;C
23.99Z;C
24.10Z;C
24.20Z;C
24.31Z;C
24.32Z;C
24.33Z;C
24.34Z;C
24.41Z;C
24.42Z;C
24.43Z;C
24.44Z;C
24.45Z;C
24.46Z;C
24.51Z;C
24.52Z;C
24.53Z;C
24.54Z;C
25.11Z;C
25.12Z;C
25.21Z;C
25.29Z;C
25.30Z;C
25.40Z;C
25.50A;C
25.50B;C
25.61Z;C
25.62A;C
25.62B;C
25.71Z;C
25.72Z;C
25.73A;C
25.73B;C
25.91Z;C
25.92Z;C
25.93Z;C
25.94Z;C
25.99A;C
25.99B;C
26.11Z;C
26.12Z;C
26.20Z;C
26.30Z;C
26.40Z;C
26.51A;C
26.51B;C
26.52Z;C
26.60Z;C
26.70Z;C
26.80Z;C
27.11Z;C
27.12Z;C
27.20Z;C
27.31Z;C
27.32Z;C
27.33Z;C
27.40Z;C
27.51Z;C
27.52Z;C
27.90Z;C
28.11Z;C
28.12Z;C
28.13Z;C
28.14Z;C
28.15Z;C
28.21Z;C
28.22Z;C
28.23Z;C
28.24Z;C
28.25Z;C
28.29A;C
28.29B;C
28.30Z;C
28.41Z;C
28.49Z;C
28.91Z;C
28.92Z;C
28.93Z;C
28.94Z;C
28.95Z;C
28.96Z;C
28.99A;C
28.99B;C
29.10Z;C
29.20Z;C
29.31Z;C
29.32Z;C
30.11Z;C
30.12Z;C
30.20Z;C
30.30Z;C
30.40Z;C
30.91Z;C
30.92Z;C
30.99Z;C
31.01Z;C
31.02Z;C
31.03Z;C
31.09A;C
31.09B;C
32.11Z;C
32.12Z;C
32.13Z;C
32.20Z;C
32.30Z;C
32.40Z;C
32.50A;C
32.50B;C
32.91Z;C
32.99Z;C
33.11Z;C
33.12Z;C
33.13Z;C
33.14Z;C
33.15Z;C
33.16Z;C
33.17Z;C
33.19Z;C
33.20A;C
33.20B;C
33.20C;C
33.20D;C
35.11Z;D
35.12Z;D
35.13Z;D
35.14Z;D
35.21Z;D
35.22Z;D
35.23Z;D
35.30Z;D
36.00Z;E
37.00Z;E
38.11Z;E
38.12Z;E
38.21Z;E
38.22Z;E
38.31Z;E
38.32Z;E
39.00Z;E
41.10A;F
41.10B;F
41.10C;F
41.10D;F
41.20A;F
41.20B;F
42.11Z;F
42.12Z;F
42.13A;F
42.13B;F
42.21Z;F
42.22Z;F
42.91Z;F
42.99Z;F
43.11Z;F
43.12A;F
43.12B;F
43.13Z;F
43.21A;F
43.21B;F
43.22A;F
43.22B;F
43.29A;F
43.29B;F
43.31Z;F
43.32A;F
43.32B;F
43.32C;F
43.33Z;F
43.34Z;F
43.39Z;F
43.91A;F
43.91B;F
43.99A;F
43.99B;F
43.99C;F
43.99D;F
43.99E;F
45.11Z;G
45.19Z;G
45.20A;G
45.20B;G
45.31Z;G
45.32Z;G
45.40Z;G
46.11Z;G
46.12A;G
46.12B;G
46.13Z;G
46.14Z;G
46.15Z;G
46.16Z;G
46.17A;G
46.17B;G
46.18Z;G
46.19A;G
46.19B;G
46.21Z;G
46.22Z;G
46.23Z;G
46.24Z;G
46.31Z;G
46.32A;G
46.32B;G
46.32C;G
46.33Z;G
46.34Z;G
46.35Z;G
46.36Z;G
46.37Z;G
46.38A;G
46.38B;G
46.39A;G
46.39B;G
46.41Z;G
46.42Z;G
46.43Z;G
46.44Z;G
46.45Z;G
46.46Z;G
46.47Z;G
46.48Z;G
46.49Z;G
46.51Z;G
46.52Z;G
46.61Z;G
46.62Z;G
46.63Z;G
46.64Z;G
46.65Z;G
46.66Z;G
46.69A;G
46.69B;G
46.69C;G
46.71Z;G
46.72Z;G
46.73A;G
46.73B;G
46.74A;G
46.74B;G
46.75Z;G
46.76Z;G
46.77Z;G
46.90Z;G
47.11A;G
47.11B;G
47.11C;G
47.11D;G
47.11E;G
47.11F;G
47.19A;G
47.19B;G
47.21Z;G
47.22Z;G
47.23Z;G
47.24Z;G
47.25Z;G
47.26Z;G
47.29Z;G
47.30Z;G
47.41Z;G
47.42Z;G
47.43Z;G
47.51Z;G
47.52A;G
47.52B;G
47.53Z;G
47.54Z;G
47.59A;G
47.59B;G
47.61Z;G
47.62Z;G
47.63Z;G
47.64Z;G
47.65Z;G
47.71Z;G
47.72A;G
47.72B;G
47.73Z;G
47.74Z;G
47.75Z;G
47.76Z;G
47.77Z;G
47.78A;G
47.78B;G
47.78C;G
47.79Z;G
47.81Z;G
47.82Z;G
47.89Z;G
47.91A;G
47.91B;G
47.99A;G
47.99B;G
49.10Z;H
49.20Z;H
49.31Z;H
49.32Z;H
49.39A;H
49.39B;H
49.39C;H
49.41A;H
49.41B;H
49.41C;H
49.42Z;H
49.50Z;H
50.10Z;H
50.20Z;H
50.30Z;H
50.40Z;H
51.10Z;H
51.21Z;H
51.22Z;H
52.10A;H
52.10B;H
52.21Z;H
52.22Z;H
52.23Z;H
52.24A;H
52.24B;H
52.29A;H
52.29B;H
53.10Z;H
53.20Z;H
55.10Z;I
55.20Z;I
55.30Z;I
55.90Z;I
56.10A;I
56.10B;I
56.10C;I
56.21Z;I
56.29A;I
56.29B;I
56.30Z;I
58.11Z;J
58.12Z;J
58.13Z;J
58.14Z;J
58.19Z;J
58.21Z;J
58.29A;J
58.29B;J
58.29C;J
59.11A;J
59.11B;J
59.11C;J
59.12Z;J
59.13A;J
59.13B;J
59.14Z;J
59.20Z;J
60.10Z;J
60.20A;J
60.20B;J
61.10Z;J
61.20Z;J
61.30Z;J
61.90Z;J
62.01Z;J
62.02A;J
62.02B;J
62.03Z;J
62.09Z;J
63.11Z;J
63.12Z;J
63.91Z;J
63.99Z;J
64.11Z;K
64.19Z;K
64.20Z;K
64.30Z;K
64.91Z;K
64.92Z;K
64.99Z;K
65.11Z;K
65.12Z;K
65.20Z;K
65.30Z;K
66.11Z;K
66.12Z;K
66.19A;K
66.19B;K
66.21Z;K
66.22Z;K
66.29Z;K
66.30Z;K
68.10Z;L
68.20A;L
68.20B;L
68.31Z;L
68.32A;L
68.32B;L
69.10Z;M
69.20Z;M
70.10Z;M
70.21Z;M
70.22Z;M
71.11Z;M
71.12A;M
71.12B;M
71.20A;M
71.20B;M
72.11Z;M
72.19Z;M
72.20Z;M
73.11Z;M
73.12Z;M
73.20Z;M
74.10Z;M
74.20Z;M
74.30Z;M
74.90A;M
74.90B;M
75.00Z;M
77.11A;N
77.11B;N
77.12Z;N
77.21Z;N
77.22Z;N
77.29Z;N
77.31Z;N
77.32Z;N
77.33Z;N
77.34Z;N
77.35Z;N
77.39Z;N
77.40Z;N
78.10Z;N
78.20Z;N
78.30Z;N
79.11Z;N
79.12Z;N
79.90Z;N
80.10Z;N
80.20Z;N
80.30Z;N
81.10Z;N
81.21Z;N
81.22Z;N
81.29A;N
81.29B;N
81.30Z;N
82.11Z;N
82.19Z;N
82.20Z;N
82.30Z;N
82.91Z;N
82.92Z;N
82.99Z;N
84.11Z;O
84.12Z;O
84.13Z;O
84.21Z;O
84.22Z;O
84.23Z;O
84.24Z;O
84.25Z;O
84.30A;O
84.30B;O
84.30C;O
85.10Z;P
85.20Z;P
85.31Z;P
85.32Z;P
85.41Z;P
85.42Z;P
85.51Z;P
85.52Z;P
85.53Z;P
85.59A;P
85.59B;P
85.60Z;P
86.10Z;Q
86.21Z;Q
86.22A;Q
86.22B;Q
86.22C;Q
86.23Z;Q
86.90A;Q
86.90B;Q
86.90C;Q
86.90D;Q
86.90E;Q
86.90F;Q
87.10A;Q
87.10B;Q
87.10C;Q
87.20A;Q
87.20B;Q
87.30A;Q
87.30B;Q
87.90A;Q
87.90B;Q
88.10A;Q
88.10B;Q
88.10C;Q
88.91A;Q
88.91B;Q
88.99A;Q
88.99B;Q
90.01Z;R
90.02Z;R
90.03A;R
90.03B;R
90.04Z;R
91.01Z;R
91.02Z;R
91.03Z;R
91.04Z;R
92.00Z;R
93.11Z;R
93.12Z;R
93.13Z;R
93.19Z;R
93.21Z;R
93.29Z;R
94.11Z;S
94.12Z;S
94.20Z;S
94.91Z;S
94.92Z;S
94.99Z;S
95.11Z;S
95.12Z;S
95.21Z;S
95.22Z;S
95.23Z;S
95.24Z;S
95.25Z;S
95.29Z;S
96.01A;S
96.01B;S
96.02A;S
96.02B;S
96.03Z;S
96.04Z;S
96.09Z;S
97.00Z;T
98.10Z;T
98.20Z;T
99.00Z;U

22
Basedonnées_Net/naf2008_liste_n1.csv

@ -0,0 +1,22 @@
Code;Libelle
A;Agriculture, sylviculture et peche
B;Industries extractives
C;Industrie manufacturiere
D;Production et distribution d'electricite, de gaz, de vapeur et d'air conditionne
E;Production et distribution d'eau , assainissement, gestion des dechets et depollution
F;Construction
G;Commerce , reparation d'automobiles et de motocycles
H;Transports et entreposage
I;Hebergement et restauration
J;Information et communication
K;Activites financieres et d'assurance
L;Activites immobilieres
M;Activites specialisees, scientifiques et techniques
N;Activites de services administratifs et de soutien
O;Administration publique
P;Enseignement
Q;Sante humaine et action sociale
R;Arts, spectacles et activites recreatives
S;Autres activites de services
T;Activites des menages en tant qu'employeurs , activites indifferenciees des menages en tant que producteurs de biens et services pour usage propre
U;Activites extra-territoriales

BIN
Basedonnées_initiale/.DS_Store

82448
Basedonnées_initiale/Entreprisedeplusde50salrié.csv
File diff suppressed because it is too large
View File

BIN
Basedonnées_initiale/InstallationPolluantes/.DS_Store

BIN
Basedonnées_initiale/InstallationPolluantes/Architectures_Prel_ProdDangereux.docx

2405
Basedonnées_initiale/InstallationPolluantes/Prelevements.csv
File diff suppressed because it is too large
View File

77863
Basedonnées_initiale/InstallationPolluantes/Prod_dechets_dangereux.csv
File diff suppressed because it is too large
View File

13193
Basedonnées_initiale/InstallationPolluantes/Prod_dechets_non_dangereux.csv
File diff suppressed because it is too large
View File

83613
Basedonnées_initiale/InstallationPolluantes/Trait_dechets_dangereux.csv
File diff suppressed because it is too large
View File

49813
Basedonnées_initiale/InstallationPolluantes/Trait_dechets_non_dangereux.csv
File diff suppressed because it is too large
View File

7192
Basedonnées_initiale/InstallationPolluantes/emissions.csv
File diff suppressed because it is too large
View File

10016
Basedonnées_initiale/InstallationPolluantes/etablissements.csv
File diff suppressed because it is too large
View File

4212
Basedonnées_initiale/InstallationPolluantes/rejets.csv
File diff suppressed because it is too large
View File

BIN
Basedonnées_initiale/SirenAdminNet2.xlsx

90148
Basedonnées_initiale/index-egalite-fh.csv
File diff suppressed because it is too large
View File

BIN
Basedonnées_initiale/sirenentr.xlsx

1095682
Basedonnées_initiale/te_siren_admin.csv
File diff suppressed because it is too large
View File

BIN
CodePython_Nettoyage/.DS_Store

1584
CodePython_Nettoyage/.ipynb_checkpoints/NetSirenplus-checkpoint.ipynb
File diff suppressed because it is too large
View File

955
CodePython_Nettoyage/.ipynb_checkpoints/Netadmin_siren-checkpoint.ipynb

@ -0,0 +1,955 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "cf14db47",
"metadata": {},
"outputs": [],
"source": [
"#import de pandas\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "78c7afbb",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/angecharbelledurand/opt/anaconda3/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3444: DtypeWarning: Columns (6,14,15) have mixed types.Specify dtype option on import or set low_memory=False.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095676</th>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095677</th>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095678</th>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095679</th>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095680</th>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1095681 rows × 19 columns</p>\n",
"</div>"
],
"text/plain": [
" siren nic siret dateCreationEtablissement \\\n",
"0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... \n",
"1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"1095676 32 2018.0 \n",
"1095677 12 2018.0 \n",
"1095678 22 2018.0 \n",
"1095679 21 2018.0 \n",
"1095680 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"1095676 NaN \n",
"1095677 NaN \n",
"1095678 NaN \n",
"1095679 NaN \n",
"1095680 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"1095676 2021-08-01 20:15:35 True \n",
"1095677 2021-02-23 18:21:09 True \n",
"1095678 2021-04-04 20:15:10 True \n",
"1095679 2021-02-23 18:21:09 True \n",
"1095680 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"1095676 5 2010-12-15 00:00:00 \n",
"1095677 2 2008-01-01 00:00:00 \n",
"1095678 4 2008-01-01 00:00:00 \n",
"1095679 1 2014-03-31 00:00:00 \n",
"1095680 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"1095676 A NaN \n",
"1095677 A NaN \n",
"1095678 A NaN \n",
"1095679 A NaN \n",
"1095680 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"1095676 NaN NaN \n",
"1095677 NaN NaN \n",
"1095678 NaN NaN \n",
"1095679 NaN NaN \n",
"1095680 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"1095676 NaN 49.41A \n",
"1095677 NaN 64.19Z \n",
"1095678 NaN 55.10Z \n",
"1095679 NaN 66.30Z \n",
"1095680 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"1095676 NAFRev2 \n",
"1095677 NAFRev2 \n",
"1095678 NAFRev2 \n",
"1095679 NAFRev2 \n",
"1095680 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"1095676 O \n",
"1095677 O \n",
"1095678 O \n",
"1095679 O \n",
"1095680 O \n",
"\n",
"[1095681 rows x 19 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#import du fichier csv\n",
"data = pd.read_csv('te_siren_admin.csv')\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "0ddc4c99",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095676</th>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095677</th>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095678</th>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095679</th>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095680</th>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>965958 rows × 19 columns</p>\n",
"</div>"
],
"text/plain": [
" siren nic siret dateCreationEtablissement \\\n",
"0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... \n",
"1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"1095676 32 2018.0 \n",
"1095677 12 2018.0 \n",
"1095678 22 2018.0 \n",
"1095679 21 2018.0 \n",
"1095680 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"1095676 NaN \n",
"1095677 NaN \n",
"1095678 NaN \n",
"1095679 NaN \n",
"1095680 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"1095676 2021-08-01 20:15:35 True \n",
"1095677 2021-02-23 18:21:09 True \n",
"1095678 2021-04-04 20:15:10 True \n",
"1095679 2021-02-23 18:21:09 True \n",
"1095680 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"1095676 5 2010-12-15 00:00:00 \n",
"1095677 2 2008-01-01 00:00:00 \n",
"1095678 4 2008-01-01 00:00:00 \n",
"1095679 1 2014-03-31 00:00:00 \n",
"1095680 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"1095676 A NaN \n",
"1095677 A NaN \n",
"1095678 A NaN \n",
"1095679 A NaN \n",
"1095680 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"1095676 NaN NaN \n",
"1095677 NaN NaN \n",
"1095678 NaN NaN \n",
"1095679 NaN NaN \n",
"1095680 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"1095676 NaN 49.41A \n",
"1095677 NaN 64.19Z \n",
"1095678 NaN 55.10Z \n",
"1095679 NaN 66.30Z \n",
"1095680 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"1095676 NAFRev2 \n",
"1095677 NAFRev2 \n",
"1095678 NAFRev2 \n",
"1095679 NAFRev2 \n",
"1095680 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"1095676 O \n",
"1095677 O \n",
"1095678 O \n",
"1095679 O \n",
"1095680 O \n",
"\n",
"[965958 rows x 19 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#filtrer sur les etatAdministratifEtablissement Actif\n",
"data=data.loc[data.etatAdministratifEtablissement=='A']\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "ca5a157e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"DataFrame is written to Excel File successfully.\n"
]
}
],
"source": [
"#export du fichier en .xlsx\n",
"file_name = 'SirenAdminNet.xlsx'\n",
"data.to_excel(file_name)\n",
"print('DataFrame is written to Excel File successfully.')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d6213677",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

979
CodePython_Nettoyage/.ipynb_checkpoints/Netadmin_sirenfinal-checkpoint.ipynb

@ -0,0 +1,979 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"id": "33e83475",
"metadata": {},
"outputs": [],
"source": [
"#import de la bibliothèque pandas\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f091507f",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/angecharbelledurand/opt/anaconda3/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3444: DtypeWarning: Columns (7,15,16) have mixed types.Specify dtype option on import or set low_memory=False.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965953</th>\n",
" <td>1095676</td>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965954</th>\n",
" <td>1095677</td>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965955</th>\n",
" <td>1095678</td>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965956</th>\n",
" <td>1095679</td>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965957</th>\n",
" <td>1095680</td>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>965958 rows × 20 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 siren nic siret dateCreationEtablissement \\\n",
"0 0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... ... \n",
"965953 1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"965954 1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"965955 1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"965956 1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"965957 1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"965953 32 2018.0 \n",
"965954 12 2018.0 \n",
"965955 22 2018.0 \n",
"965956 21 2018.0 \n",
"965957 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"965953 NaN \n",
"965954 NaN \n",
"965955 NaN \n",
"965956 NaN \n",
"965957 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"965953 2021-08-01 20:15:35 True \n",
"965954 2021-02-23 18:21:09 True \n",
"965955 2021-04-04 20:15:10 True \n",
"965956 2021-02-23 18:21:09 True \n",
"965957 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"965953 5 2010-12-15 00:00:00 \n",
"965954 2 2008-01-01 00:00:00 \n",
"965955 4 2008-01-01 00:00:00 \n",
"965956 1 2014-03-31 00:00:00 \n",
"965957 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"965953 A NaN \n",
"965954 A NaN \n",
"965955 A NaN \n",
"965956 A NaN \n",
"965957 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"965953 NaN NaN \n",
"965954 NaN NaN \n",
"965955 NaN NaN \n",
"965956 NaN NaN \n",
"965957 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"965953 NaN 49.41A \n",
"965954 NaN 64.19Z \n",
"965955 NaN 55.10Z \n",
"965956 NaN 66.30Z \n",
"965957 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"965953 NAFRev2 \n",
"965954 NAFRev2 \n",
"965955 NAFRev2 \n",
"965956 NAFRev2 \n",
"965957 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"965953 O \n",
"965954 O \n",
"965955 O \n",
"965956 O \n",
"965957 O \n",
"\n",
"[965958 rows x 20 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#import du fichier csv\n",
"dt = pd.read_csv('SirenAdminNet.csv')\n",
"dt"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b430c37b",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965953</th>\n",
" <td>1095676</td>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965954</th>\n",
" <td>1095677</td>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965955</th>\n",
" <td>1095678</td>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965956</th>\n",
" <td>1095679</td>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965957</th>\n",
" <td>1095680</td>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>832575 rows × 20 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 siren nic siret dateCreationEtablissement \\\n",
"0 0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... ... \n",
"965953 1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"965954 1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"965955 1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"965956 1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"965957 1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"965953 32 2018.0 \n",
"965954 12 2018.0 \n",
"965955 22 2018.0 \n",
"965956 21 2018.0 \n",
"965957 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"965953 NaN \n",
"965954 NaN \n",
"965955 NaN \n",
"965956 NaN \n",
"965957 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"965953 2021-08-01 20:15:35 True \n",
"965954 2021-02-23 18:21:09 True \n",
"965955 2021-04-04 20:15:10 True \n",
"965956 2021-02-23 18:21:09 True \n",
"965957 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"965953 5 2010-12-15 00:00:00 \n",
"965954 2 2008-01-01 00:00:00 \n",
"965955 4 2008-01-01 00:00:00 \n",
"965956 1 2014-03-31 00:00:00 \n",
"965957 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"965953 A NaN \n",
"965954 A NaN \n",
"965955 A NaN \n",
"965956 A NaN \n",
"965957 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"965953 NaN NaN \n",
"965954 NaN NaN \n",
"965955 NaN NaN \n",
"965956 NaN NaN \n",
"965957 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"965953 NaN 49.41A \n",
"965954 NaN 64.19Z \n",
"965955 NaN 55.10Z \n",
"965956 NaN 66.30Z \n",
"965957 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"965953 NAFRev2 \n",
"965954 NAFRev2 \n",
"965955 NAFRev2 \n",
"965956 NAFRev2 \n",
"965957 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"965953 O \n",
"965954 O \n",
"965955 O \n",
"965956 O \n",
"965957 O \n",
"\n",
"[832575 rows x 20 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#filtrer sur les caractereEmployeurEtablissement O : unité légale employeuse\n",
"dt=dt.loc[dt.caractereEmployeurEtablissement=='O']\n",
"dt"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "b16cdb56",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"DataFrame is written to Excel File successfully.\n"
]
}
],
"source": [
"#export du fichier en .xlsx\n",
"file_name = 'SirenAdminNetFinal.xlsx'\n",
"dt.to_excel(file_name)\n",
"print('DataFrame is written to Excel File successfully.')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9ecdee25",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

1740
CodePython_Nettoyage/NetProddechets.ipynb
File diff suppressed because it is too large
View File

1584
CodePython_Nettoyage/NetSirenplus.ipynb
File diff suppressed because it is too large
View File

955
CodePython_Nettoyage/Netadmin_siren.ipynb

@ -0,0 +1,955 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "cf14db47",
"metadata": {},
"outputs": [],
"source": [
"#import de pandas\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "78c7afbb",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/angecharbelledurand/opt/anaconda3/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3444: DtypeWarning: Columns (6,14,15) have mixed types.Specify dtype option on import or set low_memory=False.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095676</th>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095677</th>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095678</th>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095679</th>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095680</th>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1095681 rows × 19 columns</p>\n",
"</div>"
],
"text/plain": [
" siren nic siret dateCreationEtablissement \\\n",
"0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... \n",
"1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"1095676 32 2018.0 \n",
"1095677 12 2018.0 \n",
"1095678 22 2018.0 \n",
"1095679 21 2018.0 \n",
"1095680 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"1095676 NaN \n",
"1095677 NaN \n",
"1095678 NaN \n",
"1095679 NaN \n",
"1095680 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"1095676 2021-08-01 20:15:35 True \n",
"1095677 2021-02-23 18:21:09 True \n",
"1095678 2021-04-04 20:15:10 True \n",
"1095679 2021-02-23 18:21:09 True \n",
"1095680 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"1095676 5 2010-12-15 00:00:00 \n",
"1095677 2 2008-01-01 00:00:00 \n",
"1095678 4 2008-01-01 00:00:00 \n",
"1095679 1 2014-03-31 00:00:00 \n",
"1095680 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"1095676 A NaN \n",
"1095677 A NaN \n",
"1095678 A NaN \n",
"1095679 A NaN \n",
"1095680 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"1095676 NaN NaN \n",
"1095677 NaN NaN \n",
"1095678 NaN NaN \n",
"1095679 NaN NaN \n",
"1095680 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"1095676 NaN 49.41A \n",
"1095677 NaN 64.19Z \n",
"1095678 NaN 55.10Z \n",
"1095679 NaN 66.30Z \n",
"1095680 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"1095676 NAFRev2 \n",
"1095677 NAFRev2 \n",
"1095678 NAFRev2 \n",
"1095679 NAFRev2 \n",
"1095680 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"1095676 O \n",
"1095677 O \n",
"1095678 O \n",
"1095679 O \n",
"1095680 O \n",
"\n",
"[1095681 rows x 19 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#import du fichier csv\n",
"data = pd.read_csv('te_siren_admin.csv')\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "0ddc4c99",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095676</th>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095677</th>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095678</th>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095679</th>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1095680</th>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>965958 rows × 19 columns</p>\n",
"</div>"
],
"text/plain": [
" siren nic siret dateCreationEtablissement \\\n",
"0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... \n",
"1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"1095676 32 2018.0 \n",
"1095677 12 2018.0 \n",
"1095678 22 2018.0 \n",
"1095679 21 2018.0 \n",
"1095680 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"1095676 NaN \n",
"1095677 NaN \n",
"1095678 NaN \n",
"1095679 NaN \n",
"1095680 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"1095676 2021-08-01 20:15:35 True \n",
"1095677 2021-02-23 18:21:09 True \n",
"1095678 2021-04-04 20:15:10 True \n",
"1095679 2021-02-23 18:21:09 True \n",
"1095680 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"1095676 5 2010-12-15 00:00:00 \n",
"1095677 2 2008-01-01 00:00:00 \n",
"1095678 4 2008-01-01 00:00:00 \n",
"1095679 1 2014-03-31 00:00:00 \n",
"1095680 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"1095676 A NaN \n",
"1095677 A NaN \n",
"1095678 A NaN \n",
"1095679 A NaN \n",
"1095680 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"1095676 NaN NaN \n",
"1095677 NaN NaN \n",
"1095678 NaN NaN \n",
"1095679 NaN NaN \n",
"1095680 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"1095676 NaN 49.41A \n",
"1095677 NaN 64.19Z \n",
"1095678 NaN 55.10Z \n",
"1095679 NaN 66.30Z \n",
"1095680 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"1095676 NAFRev2 \n",
"1095677 NAFRev2 \n",
"1095678 NAFRev2 \n",
"1095679 NAFRev2 \n",
"1095680 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"1095676 O \n",
"1095677 O \n",
"1095678 O \n",
"1095679 O \n",
"1095680 O \n",
"\n",
"[965958 rows x 19 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#filtrer sur les etatAdministratifEtablissement Actif\n",
"data=data.loc[data.etatAdministratifEtablissement=='A']\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "ca5a157e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"DataFrame is written to Excel File successfully.\n"
]
}
],
"source": [
"#export du fichier en .xlsx\n",
"file_name = 'SirenAdminNet.xlsx'\n",
"data.to_excel(file_name)\n",
"print('DataFrame is written to Excel File successfully.')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d6213677",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

979
CodePython_Nettoyage/Netadmin_sirenfinal.ipynb

@ -0,0 +1,979 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"id": "33e83475",
"metadata": {},
"outputs": [],
"source": [
"#import de la bibliothèque pandas\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f091507f",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/angecharbelledurand/opt/anaconda3/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3444: DtypeWarning: Columns (7,15,16) have mixed types.Specify dtype option on import or set low_memory=False.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965953</th>\n",
" <td>1095676</td>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965954</th>\n",
" <td>1095677</td>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965955</th>\n",
" <td>1095678</td>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965956</th>\n",
" <td>1095679</td>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965957</th>\n",
" <td>1095680</td>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>965958 rows × 20 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 siren nic siret dateCreationEtablissement \\\n",
"0 0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... ... \n",
"965953 1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"965954 1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"965955 1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"965956 1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"965957 1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"965953 32 2018.0 \n",
"965954 12 2018.0 \n",
"965955 22 2018.0 \n",
"965956 21 2018.0 \n",
"965957 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"965953 NaN \n",
"965954 NaN \n",
"965955 NaN \n",
"965956 NaN \n",
"965957 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"965953 2021-08-01 20:15:35 True \n",
"965954 2021-02-23 18:21:09 True \n",
"965955 2021-04-04 20:15:10 True \n",
"965956 2021-02-23 18:21:09 True \n",
"965957 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"965953 5 2010-12-15 00:00:00 \n",
"965954 2 2008-01-01 00:00:00 \n",
"965955 4 2008-01-01 00:00:00 \n",
"965956 1 2014-03-31 00:00:00 \n",
"965957 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"965953 A NaN \n",
"965954 A NaN \n",
"965955 A NaN \n",
"965956 A NaN \n",
"965957 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"965953 NaN NaN \n",
"965954 NaN NaN \n",
"965955 NaN NaN \n",
"965956 NaN NaN \n",
"965957 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"965953 NaN 49.41A \n",
"965954 NaN 64.19Z \n",
"965955 NaN 55.10Z \n",
"965956 NaN 66.30Z \n",
"965957 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"965953 NAFRev2 \n",
"965954 NAFRev2 \n",
"965955 NAFRev2 \n",
"965956 NAFRev2 \n",
"965957 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"965953 O \n",
"965954 O \n",
"965955 O \n",
"965956 O \n",
"965957 O \n",
"\n",
"[965958 rows x 20 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#import du fichier csv\n",
"dt = pd.read_csv('SirenAdminNet.csv')\n",
"dt"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b430c37b",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>siren</th>\n",
" <th>nic</th>\n",
" <th>siret</th>\n",
" <th>dateCreationEtablissement</th>\n",
" <th>trancheEffectifsEtablissement</th>\n",
" <th>anneeEffectifsEtablissement</th>\n",
" <th>activitePrincipaleRegistreMetiersEtablissement</th>\n",
" <th>dateDernierTraitementEtablissement</th>\n",
" <th>etablissementSiege</th>\n",
" <th>nombrePeriodesEtablissement</th>\n",
" <th>dateDebut</th>\n",
" <th>etatAdministratifEtablissement</th>\n",
" <th>enseigne1Etablissement</th>\n",
" <th>enseigne2Etablissement</th>\n",
" <th>enseigne3Etablissement</th>\n",
" <th>denominationUsuelleEtablissement</th>\n",
" <th>activitePrincipaleEtablissement</th>\n",
" <th>nomenclatureActivitePrincipaleEtablissement</th>\n",
" <th>caractereEmployeurEtablissement</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>5420120</td>\n",
" <td>15</td>\n",
" <td>542012000015</td>\n",
" <td>1989-01-27 00:00:00</td>\n",
" <td>2</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10.81Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>5420120</td>\n",
" <td>31</td>\n",
" <td>542012000031</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-01-01 03:35:01</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2008-04-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>70.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>5520176</td>\n",
" <td>16</td>\n",
" <td>552017600016</td>\n",
" <td>1955-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>5520176</td>\n",
" <td>32</td>\n",
" <td>552017600032</td>\n",
" <td>1999-08-30 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2020-08-25 10:10:13</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>17.21A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>5520242</td>\n",
" <td>16</td>\n",
" <td>552024200016</td>\n",
" <td>1900-01-01 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 21:30:57</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965953</th>\n",
" <td>1095676</td>\n",
" <td>999990005</td>\n",
" <td>38</td>\n",
" <td>99999000500038</td>\n",
" <td>1993-07-01 00:00:00</td>\n",
" <td>32</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-08-01 20:15:35</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2010-12-15 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>49.41A</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965954</th>\n",
" <td>1095677</td>\n",
" <td>999990062</td>\n",
" <td>39</td>\n",
" <td>99999006200039</td>\n",
" <td>2007-11-05 00:00:00</td>\n",
" <td>12</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>64.19Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965955</th>\n",
" <td>1095678</td>\n",
" <td>999990286</td>\n",
" <td>18</td>\n",
" <td>99999028600018</td>\n",
" <td>1979-11-30 00:00:00</td>\n",
" <td>22</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-04-04 20:15:10</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2008-01-01 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.10Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965956</th>\n",
" <td>1095679</td>\n",
" <td>999990369</td>\n",
" <td>87</td>\n",
" <td>99999036900087</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>21</td>\n",
" <td>2018.0</td>\n",
" <td>NaN</td>\n",
" <td>2021-02-23 18:21:09</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2014-03-31 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>66.30Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>965957</th>\n",
" <td>1095680</td>\n",
" <td>999990401</td>\n",
" <td>96</td>\n",
" <td>99999040100096</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>3</td>\n",
" <td>2018.0</td>\n",
" <td>2712ZZ</td>\n",
" <td>2021-03-19 03:37:02</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2009-06-23 00:00:00</td>\n",
" <td>A</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>27.12Z</td>\n",
" <td>NAFRev2</td>\n",
" <td>O</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>832575 rows × 20 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 siren nic siret dateCreationEtablissement \\\n",
"0 0 5420120 15 542012000015 1989-01-27 00:00:00 \n",
"1 1 5420120 31 542012000031 1900-01-01 00:00:00 \n",
"2 2 5520176 16 552017600016 1955-01-01 00:00:00 \n",
"3 3 5520176 32 552017600032 1999-08-30 00:00:00 \n",
"4 4 5520242 16 552024200016 1900-01-01 00:00:00 \n",
"... ... ... ... ... ... \n",
"965953 1095676 999990005 38 99999000500038 1993-07-01 00:00:00 \n",
"965954 1095677 999990062 39 99999006200039 2007-11-05 00:00:00 \n",
"965955 1095678 999990286 18 99999028600018 1979-11-30 00:00:00 \n",
"965956 1095679 999990369 87 99999036900087 2014-03-31 00:00:00 \n",
"965957 1095680 999990401 96 99999040100096 2009-06-23 00:00:00 \n",
"\n",
" trancheEffectifsEtablissement anneeEffectifsEtablissement \\\n",
"0 2 2018.0 \n",
"1 3 2018.0 \n",
"2 12 2018.0 \n",
"3 12 2018.0 \n",
"4 12 2018.0 \n",
"... ... ... \n",
"965953 32 2018.0 \n",
"965954 12 2018.0 \n",
"965955 22 2018.0 \n",
"965956 21 2018.0 \n",
"965957 3 2018.0 \n",
"\n",
" activitePrincipaleRegistreMetiersEtablissement \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"... ... \n",
"965953 NaN \n",
"965954 NaN \n",
"965955 NaN \n",
"965956 NaN \n",
"965957 2712ZZ \n",
"\n",
" dateDernierTraitementEtablissement etablissementSiege \\\n",
"0 2020-08-25 10:10:13 False \n",
"1 2021-01-01 03:35:01 True \n",
"2 2021-08-01 21:30:57 True \n",
"3 2020-08-25 10:10:13 False \n",
"4 2021-08-01 21:30:57 True \n",
"... ... ... \n",
"965953 2021-08-01 20:15:35 True \n",
"965954 2021-02-23 18:21:09 True \n",
"965955 2021-04-04 20:15:10 True \n",
"965956 2021-02-23 18:21:09 True \n",
"965957 2021-03-19 03:37:02 True \n",
"\n",
" nombrePeriodesEtablissement dateDebut \\\n",
"0 4 2008-01-01 00:00:00 \n",
"1 6 2008-04-23 00:00:00 \n",
"2 4 2008-01-01 00:00:00 \n",
"3 4 2008-01-01 00:00:00 \n",
"4 4 2008-01-01 00:00:00 \n",
"... ... ... \n",
"965953 5 2010-12-15 00:00:00 \n",
"965954 2 2008-01-01 00:00:00 \n",
"965955 4 2008-01-01 00:00:00 \n",
"965956 1 2014-03-31 00:00:00 \n",
"965957 1 2009-06-23 00:00:00 \n",
"\n",
" etatAdministratifEtablissement enseigne1Etablissement \\\n",
"0 A NaN \n",
"1 A NaN \n",
"2 A NaN \n",
"3 A NaN \n",
"4 A NaN \n",
"... ... ... \n",
"965953 A NaN \n",
"965954 A NaN \n",
"965955 A NaN \n",
"965956 A NaN \n",
"965957 A NaN \n",
"\n",
" enseigne2Etablissement enseigne3Etablissement \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"965953 NaN NaN \n",
"965954 NaN NaN \n",
"965955 NaN NaN \n",
"965956 NaN NaN \n",
"965957 NaN NaN \n",
"\n",
" denominationUsuelleEtablissement activitePrincipaleEtablissement \\\n",
"0 NaN 10.81Z \n",
"1 NaN 70.10Z \n",
"2 NaN 17.21A \n",
"3 NaN 17.21A \n",
"4 NaN 20.30Z \n",
"... ... ... \n",
"965953 NaN 49.41A \n",
"965954 NaN 64.19Z \n",
"965955 NaN 55.10Z \n",
"965956 NaN 66.30Z \n",
"965957 NaN 27.12Z \n",
"\n",
" nomenclatureActivitePrincipaleEtablissement \\\n",
"0 NAFRev2 \n",
"1 NAFRev2 \n",
"2 NAFRev2 \n",
"3 NAFRev2 \n",
"4 NAFRev2 \n",
"... ... \n",
"965953 NAFRev2 \n",
"965954 NAFRev2 \n",
"965955 NAFRev2 \n",
"965956 NAFRev2 \n",
"965957 NAFRev2 \n",
"\n",
" caractereEmployeurEtablissement \n",
"0 O \n",
"1 O \n",
"2 O \n",
"3 O \n",
"4 O \n",
"... ... \n",
"965953 O \n",
"965954 O \n",
"965955 O \n",
"965956 O \n",
"965957 O \n",
"\n",
"[832575 rows x 20 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#filtrer sur les caractereEmployeurEtablissement O : unité légale employeuse\n",
"dt=dt.loc[dt.caractereEmployeurEtablissement=='O']\n",
"dt"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "b16cdb56",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"DataFrame is written to Excel File successfully.\n"
]
}
],
"source": [
"#export du fichier en .xlsx\n",
"file_name = 'SirenAdminNetFinal.xlsx'\n",
"dt.to_excel(file_name)\n",
"print('DataFrame is written to Excel File successfully.')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9ecdee25",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

85
CodeSQL.sql

@ -0,0 +1,85 @@
--Nombre de sous catégories par secteur dactivité
SELECT COUNT(*) "Nombre de sous catégories",NIV1,Libellé
FROM Naf1
JOIN Naf5 ON Naf5.NIV1=Naf1.Code
GROUP BY NIV1,Libellé
;
--Nombres dentreprises par secteur:
SELECT COUNT(*) "Nombre d'entreprises",Code,Libellé
FROM Siren
JOIN Naf5 ON Siren.activitePrincipaleEtablissement = Naf5.NIV5
JOIN Naf1 ON Naf1.Code=Naf5.NIV1
GROUP BY Code,Libellé
;
--Nombres dentreprises par tranches deffectifs
SELECT COUNT(*),Siren.trancheEffectifsEtablissement,effectif
FROM Siren
JOIN TailleEntreprise ON Siren.trancheEffectifsEtablissement=TailleEntreprise.trancheEffectifsEtablissement
GROUP BY Siren.trancheEffectifsEtablissement,effectif
;
SELECT SUM(quantite)"quantité totale",unite
FROM Emissions
GROUP BY unite
;
--Quantité démissions par polluant:
SELECT SUM(quantite)"quantité totale",polluant,unite
FROM Emissions
GROUP BY polluant,unite
ORDER BY 1 DESC
;
--Quantité de pollution par région
SELECT SUM(quantite)"Quantité",region
FROM Emissions
JOIN Etablissements ON Etablissements.identifiant=Emissions.identifiant
GROUP BY region
ORDER BY 1
;
--Moyenne des notes par année:
SELECT AVG(Note)"Moyenne",Annee
FROM IndexEgalite
GROUP BY Annee
;
--Nombre dentreprises qui sont au dessus de la moyenne par année:
SELECT siret,Note
FROM Siren
JOIN IndexEgalite ON IndexEgalite.SIREN=Siren.siren
WHERE siret IN (SELECT numero_siret
FROM Etablissements)
;
--Moyenne des entreprises qui ont des installations industrielles par année:
SELECT AVG(Note)"Moyenne",Annee
FROM IndexEgalite
GROUP BY Annee
;
SELECT Note,siret,Annee
FROM IndexEgalite
JOIN Siren ON Siren.siren=IndexEgalite.SIREN
WHERE siret IN (SELECT numero_siret
FROM Etablissements)
GROUP BY Note,siret,Annee
;
--Ratio de déchets dangereux traités par rapport aux déchets dangereux admis par région:
SELECT SUM(quantite_traitee)/ SUM(quantite_admise),region
FROM Trait_dechets_dangereux
JOIN Etablissements ON Etablissements.identifiant=Trait_dechets_dangereux.identifiant
GROUP BY region
ORDER BY 1
;
--Quantité déliminations réalisées en fonction des différentes techniques déliminations:
SELECT COUNT(*)"quantité",code_operation_eliminatio_valorisation,libelle_operation_eliminatio_valorisation
FROM Trait_dechets_non_dangereux
JOIN Etablissements ON Etablissements.identifiant=Trait_dechets_non_dangereux.identifiant
GROUP BY code_operation_eliminatio_valorisation,libelle_operation_eliminatio_valorisation
;
Loading…
Cancel
Save