From 6911847d34f633b76d4ef8ec46de52e54eb51fd0 Mon Sep 17 00:00:00 2001 From: Veit Schiele Date: Tue, 19 Nov 2024 23:13:59 +0100 Subject: [PATCH] :memo: Update dedupe section --- docs/clean-prep/deduplicate.ipynb | 945 +++++++++++++++++++++++++++++- 1 file changed, 935 insertions(+), 10 deletions(-) diff --git a/docs/clean-prep/deduplicate.ipynb b/docs/clean-prep/deduplicate.ipynb index 4d780e37..28b12c6a 100644 --- a/docs/clean-prep/deduplicate.ipynb +++ b/docs/clean-prep/deduplicate.ipynb @@ -464,7 +464,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Offenbar gibt es keine duplizierten Datensätze." + "Offenbar gibt es keine identischen Datensätze." ] }, { @@ -473,12 +473,12 @@ "source": [ "### 2.5 Duplizierte Daten löschen\n", "\n", - "Das Löschen duplizierter Datensätze mit `drop_duplicates` sollte demnach nichts ändern und die Anzahl der Datensätze bei 2080 belassen:" + "Das Löschen doppelter Datensätze mit `drop_duplicates` sollte demnach nichts ändern und die Anzahl der Datensätze bei 2080 belassen:" ] }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -695,7 +695,7 @@ "[2080 rows x 8 columns]" ] }, - "execution_count": 7, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -708,12 +708,937 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Nun wollen wir nur diejenigen Datensätze löschen, deren `user_name` identisch ist:" + "Nun wollen wir uns diejenigen Datensätze anzeigen lassen, bei denen `user_name` identisch ist:" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
namejobcompanystreet_addresscitystateemailuser_name
337Aysel BinnerReccig officerKuhl Kalleww Swifwunw & Co. KGaABatix-Kanz-Staß 5/4FuldaBerlifrncoise@wgnercochristinefinke
377Jolanta RoggeAccommodation managrScholl e.V.Lrchplz 4/6MettmnnThüringeninrharff@yah.dwalentinabeier
506Mrs. Frances PetersFuiue desieRsgers, Lawrence and RichardsStudio \\nCarpntr kysWes SimnBOhalenewilliams@wilson-sandes.ogamy17
545Gerhart Krebs MBA.SurgeonRoskothKühnertweg 863StadeBayernolav44@bolander.debettyhahn
592Folkert GnatzMeteorologistBolnbachHeinfried-Austermühle-Ring 05EilenburgThüringenjaentschbirgitt@boerner.orgfrancesco44
633Manon JacquotIngénieur en aéronautiqueJacob8, chemin Éléonore EvrardMarechal-les-BainsARilemaitre@voila.frastrid58
658Austin WallerInsurance risk surveyorSexton Group11097 Hansen FieldDavidmouthTexaschristina74@doyle-baker.bizolynn
723Wanda MoranSolicitor, ScotlandEstes PLC08011 Hernandez Streets Apt. 149NatalieshireOregonhowardreginald@gmail.comdana91
762Charles RussellScientist, research (physical sciences)Preston-Wilson6709 Ashley Circle Apt. 309DanielbergSouth Dakotanancyescobar@brown.netruben71
772Waltrud WohlgemutDesigner, fashion/clothingNerger AGElmar-Ullmann-Allee 6SchlüchternRheinland-Pfalzauch-schlauchindietlind@gmx.dezitakuhl
783Caroline MataEngineer, elecricalGrimes Grrur80157 Whte Alley Sute 79Soh MarkIwjared52@aoo.comthomasthompson
889Ricardo Ripoll LucenaTeevisi camera peratrLuzq Estraqa anq GalinqqCaejón Rosario Viapana 16PalenciaLgoev0@oo.comcolomerenrique
928Sophie Letellier du CarpentierCnucteu e étValle7 SARL3, boulvard Jan AugrSaint DaviddanBSrdorm@dbmi.comanne28
979Irene Roda DávilaEitor, maazine featresDaza IncRoda Carla Miró 5ViyLa Rioasldrpére@ps.cmipeñalver
995Abigail HernandezMechanical engineerSmith Ltd766 Adrian RanchEllismouthColoradojordan60@gmail.commendozajody
1015Mr. Paul NewtonGovernment soa researh offerLemnardmWatsmnStudi 86\\nKaty illWest JueVEem@mil.cmbbennett
1043Anna AdamsProgrammer alcatonsJones Gjoup22 Kateen ovaNoth JoaKZasleig65@aisay.colloydann
1052Aurélie VidalMagistratMartins88, rue Stéphanie LetellierRouxnecSEboutineric@blin.friwagner
1062Regina Schacht-KuschHerbalistHartung GmbH & Co. KGaAWenke-Hörle-Ring 36EggenfeldenSachsen-Anhaltoluebs@troest.dexklotz
1120Jeffrey BenjaminPubl house managerChcn Inc27 Rodgrs Rdgs Apt. 269Suth JefferergIinoisstepanie90@rogers.colori67
1170Julio Agustín AmayaTax aviserPiñolk Belmonke and CodinaCalleón de Gregorio Bustamante 28 Piso 7La PalaSalamancausolana@jáuregui-pedraza.omgloriaolmo
1339Ing. Andrew Schleich B.A.LnHolt Putz GnRHugasse 8/8HainichnNeersachsenjun@putz.comjesselmaja
1360Frédérique Lejeune-DanielTecce cseSctmittchemin Denise FerrandSaint ChalotteVilleIEjchretien@costacomjoseph60
1384Kenneth MooreMagazine journalistCross, Bfll anf Diaz753 Lindsey PineThompsonsheColoraoashey28@rice.cotodd72
1423Thomas CoulonCollecteur de fondsLevy91, rue Laetitia ColletDias-sur-NormandSCdeschampsgabriel@guyot.frmichelepetit
1433Jerry BarnesTour mnerCol-Wllllams30 Mpy OvepassJeiferviewUtahinsnashl@gas-hais.cmchristopher62
1452Karen WeeksPsychotherapist, childRodriguez, Brady and Jackson233 Kevin StreetLarrysideIndianagregg39@hernandez-gomez.comknapprobert
1489Herr Johann EigenwilligImmigration officerSüßebier Hänel GmbHLangernplatz 0StadtsteinachThüringenhaasemarieluise@noack.comistoll
1544Pasquale SchwitalTrade mark attorneyFinkeDetlef-Binner-Platz 0/1BurgNiedersachsenhanne-lore98@gmx.dethomas14
1557Stephanie YoungHerpetologistBryant and Sons5163 Rebecca Creek Suite 421North TheresabergAlaskastephenwilliams@summers.comahawkins
1567Carolina Reguera SanzFam manaeCami77, C7aparr7 a7d N7gu7raVil e Imel Oorio 25MaddVicayamordóñ@cámara.infoeva16
1616Sonia AmoresSenir tax prfessina/tax inspectrJ5an-NúñezAvnida d Grgorio Manón 344 Prta 8PonevedrLugoicent4@montenero-brroso.infosanmartínguillermo
1647Juan Carlos Iker Boix RosPre phtgrapherPont, P44om4r4s 4nd Arjon4Pasadzo de Josep Bentez PsoLas PalmasMiasrgio24@gail.coluis-miguel23
1652Jörg HenschelChaity officeSchicke AGHennyLorchRng 484Hohensein-EnshBadenWürtteberghuerhes@hmal.deanne-katrin51
1703Marc TateShip brokerWagner, Mitchell and Grimes721 Christopher View Suite 840WatsonmouthConnecticutchenjessica@hotmail.compatricia34
1707Joseph HinesPyhiatri nreCr4ig, G4rci4 4nd Rich4rds85663 Savage GlesMcgeeonAlsbcaldern@htmail.cmemilytorres
1722Julie BaldwinSet deignerW5ll55mson-G5rz558513 Paricia Res Suie 45So MeAlaskadiuez@uess.cmoss
1759Sarah HoffmanExhibitin designeHensont Wiley and Ryan9490 Curts Spur Sute 82JseptwnArizonancole@yahoo.comcsmith
1796Valentine Devaux-RogerDireceur d'ôialLeiris57, enue de GrosBenadBouALrogrlro@munoz.omxherve
1809Slavica SeidelPsychotherapist, childWulff Hande KGPreißgasse 0/4SoestRheinland-Pfalztloos@krause.netabien
1820Wenke SchweitzerEnginr, automotiWesa4k KGEies. 7Ba LnwraThürigersthveriue@mies.rgkwernecke
1829Dr. Thomas HeinCopyGeiselLadeckgasse 11RockenhausenNordrhein-Westfalengrein-grotharnim@kallert.desiegmar08
1837Andrew HartEngineer, civil (contracting)Barnett LLC258 Day Hollow Suite 410KimberlyhavenColoradobrandy00@yahoo.comamy30
1914Shelby FowlerAir traffic controllerFields-Sanchez533 Fitzpatrick BypassFrancesbergMichiganterrystephen@anderson.orggcain
1938Susan AubryDirecteur d'agence bancairePayet Georges S.A.S.67, rue Inès ValentinNicolasFImilletedith@sfr.frtthierry
1948Richard Karge-KobeltJunalist maaineAbberb Keubeb AGMitschkeee 8MßSachsnAnhaltnrejwgner@gmx.emuehlehenni
1960Anna de LobatoMedcl techcl ocerMaciag PLCCalleón de Dolore Parea 21 At 7PalnciaCantariavázqzlornzo@al.omdaniel70
1968Zoltan Wähner B.A.Professor EmeritsTh8e8Stotr. 1SaulgauShlsg-Holstarlenpruschke@salz.orkklemm
1995Kenneth DunnProgrammer, systemsLeonard Inc5361 Patterson Mission Suite 504VillaburghRhode Islandkristen54@gmail.comjkent
2010Gertraude SchomberInsurance risk surveyorBruderChrista-Ullrich-Allee 0/1Schwäbisch HallHessengumprichalice@schmidt.defruppert
2075Maurice SteySystems developerLinke Margraf GmbH & Co. OHGLaila-Scheibe-Allee 2/0LuckenwaldeHamburggutknechtevelyn@niemeier.comdkreusel
\n", + "
" + ], + "text/plain": [ + " name job \\\n", + "337 Aysel Binner Reccig officer \n", + "377 Jolanta Rogge Accommodation managr \n", + "506 Mrs. Frances Peters Fuiue desie \n", + "545 Gerhart Krebs MBA. Surgeon \n", + "592 Folkert Gnatz Meteorologist \n", + "633 Manon Jacquot Ingénieur en aéronautique \n", + "658 Austin Waller Insurance risk surveyor \n", + "723 Wanda Moran Solicitor, Scotland \n", + "762 Charles Russell Scientist, research (physical sciences) \n", + "772 Waltrud Wohlgemut Designer, fashion/clothing \n", + "783 Caroline Mata Engineer, elecrical \n", + "889 Ricardo Ripoll Lucena Teevisi camera peratr \n", + "928 Sophie Letellier du Carpentier Cnucteu e ét \n", + "979 Irene Roda Dávila Eitor, maazine featres \n", + "995 Abigail Hernandez Mechanical engineer \n", + "1015 Mr. Paul Newton Government soa researh offer \n", + "1043 Anna Adams Programmer alcatons \n", + "1052 Aurélie Vidal Magistrat \n", + "1062 Regina Schacht-Kusch Herbalist \n", + "1120 Jeffrey Benjamin Publ house manager \n", + "1170 Julio Agustín Amaya Tax aviser \n", + "1339 Ing. Andrew Schleich B.A. Ln \n", + "1360 Frédérique Lejeune-Daniel Tecce cse \n", + "1384 Kenneth Moore Magazine journalist \n", + "1423 Thomas Coulon Collecteur de fonds \n", + "1433 Jerry Barnes Tour mner \n", + "1452 Karen Weeks Psychotherapist, child \n", + "1489 Herr Johann Eigenwillig Immigration officer \n", + "1544 Pasquale Schwital Trade mark attorney \n", + "1557 Stephanie Young Herpetologist \n", + "1567 Carolina Reguera Sanz Fam manae \n", + "1616 Sonia Amores Senir tax prfessina/tax inspectr \n", + "1647 Juan Carlos Iker Boix Ros Pre phtgrapher \n", + "1652 Jörg Henschel Chaity office \n", + "1703 Marc Tate Ship broker \n", + "1707 Joseph Hines Pyhiatri nre \n", + "1722 Julie Baldwin Set deigner \n", + "1759 Sarah Hoffman Exhibitin designe \n", + "1796 Valentine Devaux-Roger Direceur d'ôial \n", + "1809 Slavica Seidel Psychotherapist, child \n", + "1820 Wenke Schweitzer Enginr, automoti \n", + "1829 Dr. Thomas Hein Copy \n", + "1837 Andrew Hart Engineer, civil (contracting) \n", + "1914 Shelby Fowler Air traffic controller \n", + "1938 Susan Aubry Directeur d'agence bancaire \n", + "1948 Richard Karge-Kobelt Junalist maaine \n", + "1960 Anna de Lobato Medcl techcl ocer \n", + "1968 Zoltan Wähner B.A. Professor Emerits \n", + "1995 Kenneth Dunn Programmer, systems \n", + "2010 Gertraude Schomber Insurance risk surveyor \n", + "2075 Maurice Stey Systems developer \n", + "\n", + " company \\\n", + "337 Kuhl Kalleww Swifwunw & Co. KGaA \n", + "377 Scholl e.V. \n", + "506 Rsgers, Lawrence and Richards \n", + "545 Roskoth \n", + "592 Bolnbach \n", + "633 Jacob \n", + "658 Sexton Group \n", + "723 Estes PLC \n", + "762 Preston-Wilson \n", + "772 Nerger AG \n", + "783 Grimes Grrur \n", + "889 Luzq Estraqa anq Galinqq \n", + "928 Valle7 SARL \n", + "979 Daza Inc \n", + "995 Smith Ltd \n", + "1015 LemnardmWatsmn \n", + "1043 Jones Gjoup \n", + "1052 Martins \n", + "1062 Hartung GmbH & Co. KGaA \n", + "1120 Chcn Inc \n", + "1170 Piñolk Belmonke and Codina \n", + "1339 Holt Putz GnR \n", + "1360 Sctmitt \n", + "1384 Cross, Bfll anf Diaz \n", + "1423 Levy \n", + "1433 Col-Wllllams \n", + "1452 Rodriguez, Brady and Jackson \n", + "1489 Süßebier Hänel GmbH \n", + "1544 Finke \n", + "1557 Bryant and Sons \n", + "1567 Cami77, C7aparr7 a7d N7gu7ra \n", + "1616 J5an-Núñez \n", + "1647 Pont, P44om4r4s 4nd Arjon4 \n", + "1652 Schicke AG \n", + "1703 Wagner, Mitchell and Grimes \n", + "1707 Cr4ig, G4rci4 4nd Rich4rds \n", + "1722 W5ll55mson-G5rz5 \n", + "1759 Hensont Wiley and Ryan \n", + "1796 Leiris \n", + "1809 Wulff Hande KG \n", + "1820 Wesa4k KG \n", + "1829 Geisel \n", + "1837 Barnett LLC \n", + "1914 Fields-Sanchez \n", + "1938 Payet Georges S.A.S. \n", + "1948 Abberb Keubeb AG \n", + "1960 Maciag PLC \n", + "1968 Th8e8 \n", + "1995 Leonard Inc \n", + "2010 Bruder \n", + "2075 Linke Margraf GmbH & Co. OHG \n", + "\n", + " street_address city \\\n", + "337 Batix-Kanz-Staß 5/4 Fulda \n", + "377 Lrchplz 4/6 Mettmnn \n", + "506 Studio \\nCarpntr kys Wes Simn \n", + "545 Kühnertweg 863 Stade \n", + "592 Heinfried-Austermühle-Ring 05 Eilenburg \n", + "633 8, chemin Éléonore Evrard Marechal-les-Bains \n", + "658 11097 Hansen Field Davidmouth \n", + "723 08011 Hernandez Streets Apt. 149 Natalieshire \n", + "762 6709 Ashley Circle Apt. 309 Danielberg \n", + "772 Elmar-Ullmann-Allee 6 Schlüchtern \n", + "783 80157 Whte Alley Sute 79 Soh Mark \n", + "889 Caejón Rosario Viapana 16 Palencia \n", + "928 3, boulvard Jan Augr Saint Daviddan \n", + "979 Roda Carla Miró 5 Viy \n", + "995 766 Adrian Ranch Ellismouth \n", + "1015 Studi 86\\nKaty ill West Jue \n", + "1043 22 Kateen ova Noth Joa \n", + "1052 88, rue Stéphanie Letellier Rouxnec \n", + "1062 Wenke-Hörle-Ring 36 Eggenfelden \n", + "1120 27 Rodgrs Rdgs Apt. 269 Suth Jeffererg \n", + "1170 Calleón de Gregorio Bustamante 28 Piso 7 La Pala \n", + "1339 Hugasse 8/8 Hainichn \n", + "1360 chemin Denise Ferrand Saint ChalotteVille \n", + "1384 753 Lindsey Pine Thompsonshe \n", + "1423 91, rue Laetitia Collet Dias-sur-Normand \n", + "1433 30 Mpy Ovepass Jeiferview \n", + "1452 233 Kevin Street Larryside \n", + "1489 Langernplatz 0 Stadtsteinach \n", + "1544 Detlef-Binner-Platz 0/1 Burg \n", + "1557 5163 Rebecca Creek Suite 421 North Theresaberg \n", + "1567 Vil e Imel Oorio 25 Madd \n", + "1616 Avnida d Grgorio Manón 344 Prta 8 Ponevedr \n", + "1647 Pasadzo de Josep Bentez Pso Las Palmas \n", + "1652 HennyLorchRng 484 Hohensein-Ensh \n", + "1703 721 Christopher View Suite 840 Watsonmouth \n", + "1707 85663 Savage Gles Mcgeeon \n", + "1722 58513 Paricia Res Suie 45 So Me \n", + "1759 9490 Curts Spur Sute 82 Jseptwn \n", + "1796 57, enue de Gros BenadBou \n", + "1809 Preißgasse 0/4 Soest \n", + "1820 Eies. 7 Ba Lnwra \n", + "1829 Ladeckgasse 11 Rockenhausen \n", + "1837 258 Day Hollow Suite 410 Kimberlyhaven \n", + "1914 533 Fitzpatrick Bypass Francesberg \n", + "1938 67, rue Inès Valentin Nicolas \n", + "1948 Mitschkeee 8 Mß \n", + "1960 Calleón de Dolore Parea 21 At 7 Palncia \n", + "1968 Stotr. 1 Saulgau \n", + "1995 5361 Patterson Mission Suite 504 Villaburgh \n", + "2010 Christa-Ullrich-Allee 0/1 Schwäbisch Hall \n", + "2075 Laila-Scheibe-Allee 2/0 Luckenwalde \n", + "\n", + " state email user_name \n", + "337 Berli frncoise@wgnerco christinefinke \n", + "377 Thüringen inrharff@yah.d walentinabeier \n", + "506 BO halenewilliams@wilson-sandes.og amy17 \n", + "545 Bayern olav44@bolander.de bettyhahn \n", + "592 Thüringen jaentschbirgitt@boerner.org francesco44 \n", + "633 AR ilemaitre@voila.fr astrid58 \n", + "658 Texas christina74@doyle-baker.biz olynn \n", + "723 Oregon howardreginald@gmail.com dana91 \n", + "762 South Dakota nancyescobar@brown.net ruben71 \n", + "772 Rheinland-Pfalz auch-schlauchindietlind@gmx.de zitakuhl \n", + "783 Iw jared52@aoo.com thomasthompson \n", + "889 Lgo ev0@oo.com colomerenrique \n", + "928 BS rdorm@dbmi.com anne28 \n", + "979 La Rioa sldrpére@ps.cm ipeñalver \n", + "995 Colorado jordan60@gmail.com mendozajody \n", + "1015 VE em@mil.cm bbennett \n", + "1043 KZ asleig65@aisay.co lloydann \n", + "1052 SE boutineric@blin.fr iwagner \n", + "1062 Sachsen-Anhalt oluebs@troest.de xklotz \n", + "1120 Iinois stepanie90@rogers.co lori67 \n", + "1170 Salamanca usolana@jáuregui-pedraza.om gloriaolmo \n", + "1339 Neersachsen jun@putz.com jesselmaja \n", + "1360 IE jchretien@costacom joseph60 \n", + "1384 Colorao ashey28@rice.co todd72 \n", + "1423 SC deschampsgabriel@guyot.fr michelepetit \n", + "1433 Utah insnashl@gas-hais.cm christopher62 \n", + "1452 Indiana gregg39@hernandez-gomez.com knapprobert \n", + "1489 Thüringen haasemarieluise@noack.com istoll \n", + "1544 Niedersachsen hanne-lore98@gmx.de thomas14 \n", + "1557 Alaska stephenwilliams@summers.com ahawkins \n", + "1567 Vicaya mordóñ@cámara.info eva16 \n", + "1616 Lugo icent4@montenero-brroso.info sanmartínguillermo \n", + "1647 Mia srgio24@gail.co luis-miguel23 \n", + "1652 BadenWürtteberg huerhes@hmal.de anne-katrin51 \n", + "1703 Connecticut chenjessica@hotmail.com patricia34 \n", + "1707 Als bcaldern@htmail.cm emilytorres \n", + "1722 Alaska diuez@uess. cmoss \n", + "1759 Arizona ncole@yahoo.com csmith \n", + "1796 AL rogrlro@munoz.om xherve \n", + "1809 Rheinland-Pfalz tloos@krause.net abien \n", + "1820 Thürige rsthveriue@mies.rg kwernecke \n", + "1829 Nordrhein-Westfalen grein-grotharnim@kallert.de siegmar08 \n", + "1837 Colorado brandy00@yahoo.com amy30 \n", + "1914 Michigan terrystephen@anderson.org gcain \n", + "1938 FI milletedith@sfr.fr tthierry \n", + "1948 SachsnAnhalt nrejwgner@gmx.e muehlehenni \n", + "1960 Cantaria vázqzlornzo@al.om daniel70 \n", + "1968 Shlsg-Holst arlenpruschke@salz.or kklemm \n", + "1995 Rhode Island kristen54@gmail.com jkent \n", + "2010 Hessen gumprichalice@schmidt.de fruppert \n", + "2075 Hamburg gutknechtevelyn@niemeier.com dkreusel " + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "customers[customers.duplicated([\"user_name\"])]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Nun können wir uns die zugehörigen Datensätze anzeigen lassen, z.B. mit:" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
namejobcompanystreet_addresscitystateemailuser_name
236Aysel BinnerRecycling officerKuhl Kallert Stiftung & Co. KGaABeatrix-Kranz-Straße 5/4FuldaBerlinfrancoise22@wagner.comchristinefinke
337Aysel BinnerReccig officerKuhl Kalleww Swifwunw & Co. KGaABatix-Kanz-Staß 5/4FuldaBerlifrncoise@wgnercochristinefinke
\n", + "
" + ], + "text/plain": [ + " name job company \\\n", + "236 Aysel Binner Recycling officer Kuhl Kallert Stiftung & Co. KGaA \n", + "337 Aysel Binner Reccig officer Kuhl Kalleww Swifwunw & Co. KGaA \n", + "\n", + " street_address city state email \\\n", + "236 Beatrix-Kranz-Straße 5/4 Fulda Berlin francoise22@wagner.com \n", + "337 Batix-Kanz-Staß 5/4 Fulda Berli frncoise@wgnerco \n", + "\n", + " user_name \n", + "236 christinefinke \n", + "337 christinefinke " + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "customers[customers[\"user_name\"] == \"christinefinke\"]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + " Schließlich können wir diejenigen Datensätze löschen, deren `user_name` identisch ist:" + ] + }, + { + "cell_type": "code", + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -930,7 +1855,7 @@ "[2029 rows x 8 columns]" ] }, - "execution_count": 8, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -1499,9 +2424,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3.11 Kernel", + "display_name": "Python 3.13 Kernel", "language": "python", - "name": "python311" + "name": "python313" }, "language_info": { "codemirror_mode": { @@ -1513,7 +2438,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.4" + "version": "3.13.0" }, "latex_envs": { "LaTeX_envs_menu_present": true,