{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from lxml import etree\n", "import requests\n", "import os\n", "import glob\n", "import re\n", "import numpy as np\n", "import sys" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "sys.path.append(os.path.abspath(\"C:/Users/calvotello/Dropbox/MTB/Göttingen/research/\"))\n", "\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "from librarian_robot import transform_formats, basic_functions\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ " = pd." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['./../data/parquets/sachgruppen\\\\pica_sgt_440',\n", " './../data/parquets/sachgruppen\\\\pica_sgt_450',\n", " './../data/parquets/sachgruppen\\\\pica_sgt_460',\n", " './../data/parquets/sachgruppen\\\\pica_sgt_840',\n", " './../data/parquets/sachgruppen\\\\pica_sgt_850',\n", " './../data/parquets/sachgruppen\\\\pica_sgt_860']" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "folders = glob.glob(\"./../data/parquets/sachgruppen/*\")\n", "folders\n" ] }, { "cell_type": "code", "execution_count": 6, "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", "
ppnmediumtitletitle_supplementyearentry_firstauthor_first_nameauthor_last_nameauthor_gnd_ideditor_first_name...keyword_BDSL_pkeyword_BDSL_tkeyword_BDSL_skeyword_Fremddatenlieferanten_lieferantenkeyword_Fremddatenlieferantenlcc_notationsignatur_placesignatursignatur_dateapi_query
0484825402OaxLes @Arts et les Lettres en Provence au temps ...None20206055:27-08-21JeanArrouyeNoneGabriel|Marion|Chantal|Noël|Barbara|Marie-Clau......NaNNaNNaNNaNf Kongress|g Aix-en-Provence <2009>NoneNoneNone27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2...pica_rvp_IA
1469727594AauMédiations et construction de l'Antiquité dans...None20200026:22-09-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|11291.220.68|Za 195 (101)30-11-20|22-09-20pica_rvp_IA
2466221029AbvcLire magazine littéraireNone20206050:02-07-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|022|019|07401/IA 6450|28 Rom Z 15707|Z 603|Z 87209-08-01|11-08-20|05-08-20|16-12-20pica_rvp_IA
3450873676AbvcFrancophonies du mondeNone20196050:18-07-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|02216/IA 5021a|28 Frz Z 1775[Suppl.14-06-07|24-07-19pica_rvp_IA
4442132174AauLe @\"théâtre provincial\" en France(XVIe-XVIIIe siècle)20180026:31-01-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|112291.535|Za 195 (97)19-09-19|31-01-19pica_rvp_IA
..................................................................
34446288128AfuDe Breogán al fin del mundoNone19810077:12-03-19NoneNone326114106None...NaNNaNNaNNaNNoneNone074Sp2 / 1981,6 prim.|FB 15.1 Sp2 / 1981,6 prim.|...22-03-19pica_rvp_IZ
35383679192AafInforme-dramático-sobre la lengua gallegaNone19732077:06-07-16NoneNone10581895XNone...NaNNaNNaNNaNNoneNone01973.392106-07-16pica_rvp_IZ
37334614104AarRomanceiro popular galego de tradizon oralTraballo galardoado cô premio \"Padre Feijóo\" d...19590004:12-12-13NoneNone286469804None...NaNNaNNaNNaNNoneNone000|000001 LCZ L 79|070 8 2021/0809612-12-13|31-01-17pica_rvp_IZ
3809528706XAfrA - ChNone19580077:17-01-01NoneNone162723458None...NaNNaNNaNNaNf Wörterbuch <mehrsprachig>None000|000|074|000HB 4: P 251 Bd. 1|60/1236 Bd. 1|LING A 2845-1|...01-01-06|17-01-01|25-10-04|05-05-17pica_rvp_IZ
40047619554AbvcNósboletin mensual da cultura galega19206050:19-06-96NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000Zsq 262206-10-98pica_rvp_IZ
\n", "

176205 rows × 47 columns

\n", "
" ], "text/plain": [ " ppn medium title \\\n", "0 484825402 Oax Les @Arts et les Lettres en Provence au temps ... \n", "1 469727594 Aau Médiations et construction de l'Antiquité dans... \n", "2 466221029 Abvc Lire magazine littéraire \n", "3 450873676 Abvc Francophonies du monde \n", "4 442132174 Aau Le @\"théâtre provincial\" en France \n", ".. ... ... ... \n", "34 446288128 Afu De Breogán al fin del mundo \n", "35 383679192 Aaf Informe-dramático-sobre la lengua gallega \n", "37 334614104 Aar Romanceiro popular galego de tradizon oral \n", "38 09528706X Afr A - Ch \n", "40 047619554 Abvc Nós \n", "\n", " title_supplement year entry_first \\\n", "0 None 2020 6055:27-08-21 \n", "1 None 2020 0026:22-09-20 \n", "2 None 2020 6050:02-07-20 \n", "3 None 2019 6050:18-07-19 \n", "4 (XVIe-XVIIIe siècle) 2018 0026:31-01-19 \n", ".. ... ... ... \n", "34 None 1981 0077:12-03-19 \n", "35 None 1973 2077:06-07-16 \n", "37 Traballo galardoado cô premio \"Padre Feijóo\" d... 1959 0004:12-12-13 \n", "38 None 1958 0077:17-01-01 \n", "40 boletin mensual da cultura galega 1920 6050:19-06-96 \n", "\n", " author_first_name author_last_name author_gnd_id \\\n", "0 Jean Arrouye None \n", "1 None None None \n", "2 None None None \n", "3 None None None \n", "4 None None None \n", ".. ... ... ... \n", "34 None None 326114106 \n", "35 None None 10581895X \n", "37 None None 286469804 \n", "38 None None 162723458 \n", "40 None None None \n", "\n", " editor_first_name ... keyword_BDSL_p \\\n", "0 Gabriel|Marion|Chantal|Noël|Barbara|Marie-Clau... ... NaN \n", "1 None ... NaN \n", "2 None ... NaN \n", "3 None ... NaN \n", "4 None ... NaN \n", ".. ... ... ... \n", "34 None ... NaN \n", "35 None ... NaN \n", "37 None ... NaN \n", "38 None ... NaN \n", "40 None ... NaN \n", "\n", " keyword_BDSL_t keyword_BDSL_s keyword_Fremddatenlieferanten_lieferanten \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", ".. ... ... ... \n", "34 NaN NaN NaN \n", "35 NaN NaN NaN \n", "37 NaN NaN NaN \n", "38 NaN NaN NaN \n", "40 NaN NaN NaN \n", "\n", " keyword_Fremddatenlieferanten lcc_notation signatur_place \\\n", "0 f Kongress|g Aix-en-Provence <2009> None None \n", "1 None None 000|112 \n", "2 None None 330|022|019|074 \n", "3 None None 330|022 \n", "4 None None 000|112 \n", ".. ... ... ... \n", "34 None None 074 \n", "35 None None 019 \n", "37 None None 000|000 \n", "38 f Wörterbuch None 000|000|074|000 \n", "40 None None 000 \n", "\n", " signatur \\\n", "0 None \n", "1 91.220.68|Za 195 (101) \n", "2 01/IA 6450|28 Rom Z 15707|Z 603|Z 872 \n", "3 16/IA 5021a|28 Frz Z 1775[Suppl. \n", "4 291.535|Za 195 (97) \n", ".. ... \n", "34 Sp2 / 1981,6 prim.|FB 15.1 Sp2 / 1981,6 prim.|... \n", "35 73.3921 \n", "37 001 LCZ L 79|070 8 2021/08096 \n", "38 HB 4: P 251 Bd. 1|60/1236 Bd. 1|LING A 2845-1|... \n", "40 Zsq 2622 \n", "\n", " signatur_date api_query \n", "0 27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2... pica_rvp_IA \n", "1 30-11-20|22-09-20 pica_rvp_IA \n", "2 09-08-01|11-08-20|05-08-20|16-12-20 pica_rvp_IA \n", "3 14-06-07|24-07-19 pica_rvp_IA \n", "4 19-09-19|31-01-19 pica_rvp_IA \n", ".. ... ... \n", "34 22-03-19 pica_rvp_IZ \n", "35 06-07-16 pica_rvp_IZ \n", "37 12-12-13|31-01-17 pica_rvp_IZ \n", "38 01-01-06|17-01-01|25-10-04|05-05-17 pica_rvp_IZ \n", "40 06-10-98 pica_rvp_IZ \n", "\n", "[176205 rows x 47 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rvk_df = pd.read_parquet(\"./../data/parquets/rvk/pica_rvp_IA-IZ.parquet\")\n", "rvk_df" ] }, { "cell_type": "code", "execution_count": 8, "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", "
ppnmediumtitletitle_supplementyearentry_firstauthor_first_nameauthor_last_nameauthor_gnd_ideditor_first_name...keyword_BDSL_pkeyword_BDSL_tkeyword_BDSL_skeyword_Fremddatenlieferanten_lieferantenkeyword_Fremddatenlieferantenlcc_notationsignatur_placesignatursignatur_dateapi_query
048836583XOaxManual of Romance Phonetics and PhonologyNone20226055:06-12-21NoneNoneNoneHelene N.|Travis G.|Joaquim|Andrea|Marie-Hélèn......NaNNaNNaNNaNNonePC76NoneNone07-12-21|06-12-21|13-12-21|07-12-21pica_sgt_440
1488070945AacAugust Wilhelm Schlegel und die Episteme der G...Eine Ringvorlesung zum 200jährigen Jubiläum de...20226000:25-11-21NoneNoneNoneFranz...NaNNaNNaNNaNNoneNone000/GK 9074 L45403-12-21pica_sgt_440
2476670101AauManual of Romance phonetics and phonologyNone20220026:09-03-21NoneNoneNoneNone...NaNNaNNaNNaNNoneNone112Aa 2014/2 (27)22-11-21pica_sgt_440
3488377803OaxFlauberts SalammbôDer Tod der schönen Antike20216055:06-12-21NoneNoneNoneDavid|Martin|Bardo Maria|Therese|Pia Claudia|C......NaNNaNNaNNaNNoneNoneNoneNone06-12-21|06-12-21pica_sgt_440
4488365775OaxSabers per als laicsVernacularització, formació, transmissió (Coro...20216055:06-12-21NoneNoneNoneGerrit|Rosanna|Antònia|Lluís|Maria Sofia|Cesc|......NaNNaNNaNNaNNoneNoneNoneNone07-12-21|06-12-21|13-12-21|07-12-21pica_sgt_440
..................................................................
177234515929AauPedro PáramoNone19813030:06-04-11NoneNone087091046None...NaNNaNNaNNaNf Belletristische DarstellungNone042Ff II 2160, A206-04-11pica_sgt_860
244047829680AbvcLateinamerika-StudienNone19766050:20-06-96NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|000|000|002|000|000Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0...06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0...pica_sgt_860
250076438953AauPedro PáramoRoman19756000:05-07-99NoneNone087091046None...NaNNaNNaNNaNf Belletristische DarstellungNone000|04280.706.91|Gc II 444, B43401-01-11|06-04-11pica_sgt_860
307097167126AauHundert Jahre EinsamkeitRoman19703017:22-03-01NoneNone086878662None...NaNNaNNaNNaNNoneNone042|004Ff II 1987|40/IQ 38420 G21618-07-18|03-12-96pica_sgt_860
473386319588OauDer @Troubadour der spanischen FalangeNone19656000:27-08-16NoneNone140900845None...NaNNaNNaNNaNNoneNone900/24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2...pica_sgt_860
\n", "

22437 rows × 47 columns

\n", "
" ], "text/plain": [ " ppn medium title \\\n", "0 48836583X Oax Manual of Romance Phonetics and Phonology \n", "1 488070945 Aac August Wilhelm Schlegel und die Episteme der G... \n", "2 476670101 Aau Manual of Romance phonetics and phonology \n", "3 488377803 Oax Flauberts Salammbô \n", "4 488365775 Oax Sabers per als laics \n", ".. ... ... ... \n", "177 234515929 Aau Pedro Páramo \n", "244 047829680 Abvc Lateinamerika-Studien \n", "250 076438953 Aau Pedro Páramo \n", "307 097167126 Aau Hundert Jahre Einsamkeit \n", "473 386319588 Oau Der @Troubadour der spanischen Falange \n", "\n", " title_supplement year entry_first \\\n", "0 None 2022 6055:06-12-21 \n", "1 Eine Ringvorlesung zum 200jährigen Jubiläum de... 2022 6000:25-11-21 \n", "2 None 2022 0026:09-03-21 \n", "3 Der Tod der schönen Antike 2021 6055:06-12-21 \n", "4 Vernacularització, formació, transmissió (Coro... 2021 6055:06-12-21 \n", ".. ... ... ... \n", "177 None 1981 3030:06-04-11 \n", "244 None 1976 6050:20-06-96 \n", "250 Roman 1975 6000:05-07-99 \n", "307 Roman 1970 3017:22-03-01 \n", "473 None 1965 6000:27-08-16 \n", "\n", " author_first_name author_last_name author_gnd_id \\\n", "0 None None None \n", "1 None None None \n", "2 None None None \n", "3 None None None \n", "4 None None None \n", ".. ... ... ... \n", "177 None None 087091046 \n", "244 None None None \n", "250 None None 087091046 \n", "307 None None 086878662 \n", "473 None None 140900845 \n", "\n", " editor_first_name ... keyword_BDSL_p \\\n", "0 Helene N.|Travis G.|Joaquim|Andrea|Marie-Hélèn... ... NaN \n", "1 Franz ... NaN \n", "2 None ... NaN \n", "3 David|Martin|Bardo Maria|Therese|Pia Claudia|C... ... NaN \n", "4 Gerrit|Rosanna|Antònia|Lluís|Maria Sofia|Cesc|... ... NaN \n", ".. ... ... ... \n", "177 None ... NaN \n", "244 None ... NaN \n", "250 None ... NaN \n", "307 None ... NaN \n", "473 None ... NaN \n", "\n", " keyword_BDSL_t keyword_BDSL_s keyword_Fremddatenlieferanten_lieferanten \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", ".. ... ... ... \n", "177 NaN NaN NaN \n", "244 NaN NaN NaN \n", "250 NaN NaN NaN \n", "307 NaN NaN NaN \n", "473 NaN NaN NaN \n", "\n", " keyword_Fremddatenlieferanten lcc_notation signatur_place \\\n", "0 None PC76 None \n", "1 None None 000 \n", "2 None None 112 \n", "3 None None None \n", "4 None None None \n", ".. ... ... ... \n", "177 f Belletristische Darstellung None 042 \n", "244 None None 000|000|000|002|000|000 \n", "250 f Belletristische Darstellung None 000|042 \n", "307 None None 042|004 \n", "473 None None 900 \n", "\n", " signatur \\\n", "0 None \n", "1 /GK 9074 L454 \n", "2 Aa 2014/2 (27) \n", "3 None \n", "4 None \n", ".. ... \n", "177 Ff II 2160, A2 \n", "244 Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0... \n", "250 80.706.91|Gc II 444, B434 \n", "307 Ff II 1987|40/IQ 38420 G216 \n", "473 / \n", "\n", " signatur_date api_query \n", "0 07-12-21|06-12-21|13-12-21|07-12-21 pica_sgt_440 \n", "1 03-12-21 pica_sgt_440 \n", "2 22-11-21 pica_sgt_440 \n", "3 06-12-21|06-12-21 pica_sgt_440 \n", "4 07-12-21|06-12-21|13-12-21|07-12-21 pica_sgt_440 \n", ".. ... ... \n", "177 06-04-11 pica_sgt_860 \n", "244 06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0... pica_sgt_860 \n", "250 01-01-11|06-04-11 pica_sgt_860 \n", "307 18-07-18|03-12-96 pica_sgt_860 \n", "473 24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2... pica_sgt_860 \n", "\n", "[22437 rows x 47 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "sachgruppen_df = pd.read_parquet(\"./../data/parquets/sachgruppen/pica_sgt_440_860.parquet\")\n", "sachgruppen_df" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "concat_df = pd.concat([rvk_df,sachgruppen_df])" ] }, { "cell_type": "code", "execution_count": 12, "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", "
ppnmediumtitletitle_supplementyearentry_firstauthor_first_nameauthor_last_nameauthor_gnd_ideditor_first_name...keyword_BDSL_pkeyword_BDSL_tkeyword_BDSL_skeyword_Fremddatenlieferanten_lieferantenkeyword_Fremddatenlieferantenlcc_notationsignatur_placesignatursignatur_dateapi_query
0484825402OaxLes @Arts et les Lettres en Provence au temps ...None20206055:27-08-21JeanArrouyeNoneGabriel|Marion|Chantal|Noël|Barbara|Marie-Clau......NaNNaNNaNNaNf Kongress|g Aix-en-Provence <2009>NoneNoneNone27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2...pica_rvp_IA
1469727594AauMédiations et construction de l'Antiquité dans...None20200026:22-09-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|11291.220.68|Za 195 (101)30-11-20|22-09-20pica_rvp_IA
2466221029AbvcLire magazine littéraireNone20206050:02-07-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|022|019|07401/IA 6450|28 Rom Z 15707|Z 603|Z 87209-08-01|11-08-20|05-08-20|16-12-20pica_rvp_IA
3450873676AbvcFrancophonies du mondeNone20196050:18-07-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|02216/IA 5021a|28 Frz Z 1775[Suppl.14-06-07|24-07-19pica_rvp_IA
4442132174AauLe @\"théâtre provincial\" en France(XVIe-XVIIIe siècle)20180026:31-01-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|112291.535|Za 195 (97)19-09-19|31-01-19pica_rvp_IA
..................................................................
177234515929AauPedro PáramoNone19813030:06-04-11NoneNone087091046None...NaNNaNNaNNaNf Belletristische DarstellungNone042Ff II 2160, A206-04-11pica_sgt_860
244047829680AbvcLateinamerika-StudienNone19766050:20-06-96NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|000|000|002|000|000Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0...06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0...pica_sgt_860
250076438953AauPedro PáramoRoman19756000:05-07-99NoneNone087091046None...NaNNaNNaNNaNf Belletristische DarstellungNone000|04280.706.91|Gc II 444, B43401-01-11|06-04-11pica_sgt_860
307097167126AauHundert Jahre EinsamkeitRoman19703017:22-03-01NoneNone086878662None...NaNNaNNaNNaNNoneNone042|004Ff II 1987|40/IQ 38420 G21618-07-18|03-12-96pica_sgt_860
473386319588OauDer @Troubadour der spanischen FalangeNone19656000:27-08-16NoneNone140900845None...NaNNaNNaNNaNNoneNone900/24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2...pica_sgt_860
\n", "

198642 rows × 47 columns

\n", "
" ], "text/plain": [ " ppn medium title \\\n", "0 484825402 Oax Les @Arts et les Lettres en Provence au temps ... \n", "1 469727594 Aau Médiations et construction de l'Antiquité dans... \n", "2 466221029 Abvc Lire magazine littéraire \n", "3 450873676 Abvc Francophonies du monde \n", "4 442132174 Aau Le @\"théâtre provincial\" en France \n", ".. ... ... ... \n", "177 234515929 Aau Pedro Páramo \n", "244 047829680 Abvc Lateinamerika-Studien \n", "250 076438953 Aau Pedro Páramo \n", "307 097167126 Aau Hundert Jahre Einsamkeit \n", "473 386319588 Oau Der @Troubadour der spanischen Falange \n", "\n", " title_supplement year entry_first author_first_name \\\n", "0 None 2020 6055:27-08-21 Jean \n", "1 None 2020 0026:22-09-20 None \n", "2 None 2020 6050:02-07-20 None \n", "3 None 2019 6050:18-07-19 None \n", "4 (XVIe-XVIIIe siècle) 2018 0026:31-01-19 None \n", ".. ... ... ... ... \n", "177 None 1981 3030:06-04-11 None \n", "244 None 1976 6050:20-06-96 None \n", "250 Roman 1975 6000:05-07-99 None \n", "307 Roman 1970 3017:22-03-01 None \n", "473 None 1965 6000:27-08-16 None \n", "\n", " author_last_name author_gnd_id \\\n", "0 Arrouye None \n", "1 None None \n", "2 None None \n", "3 None None \n", "4 None None \n", ".. ... ... \n", "177 None 087091046 \n", "244 None None \n", "250 None 087091046 \n", "307 None 086878662 \n", "473 None 140900845 \n", "\n", " editor_first_name ... keyword_BDSL_p \\\n", "0 Gabriel|Marion|Chantal|Noël|Barbara|Marie-Clau... ... NaN \n", "1 None ... NaN \n", "2 None ... NaN \n", "3 None ... NaN \n", "4 None ... NaN \n", ".. ... ... ... \n", "177 None ... NaN \n", "244 None ... NaN \n", "250 None ... NaN \n", "307 None ... NaN \n", "473 None ... NaN \n", "\n", " keyword_BDSL_t keyword_BDSL_s keyword_Fremddatenlieferanten_lieferanten \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", ".. ... ... ... \n", "177 NaN NaN NaN \n", "244 NaN NaN NaN \n", "250 NaN NaN NaN \n", "307 NaN NaN NaN \n", "473 NaN NaN NaN \n", "\n", " keyword_Fremddatenlieferanten lcc_notation \\\n", "0 f Kongress|g Aix-en-Provence <2009> None \n", "1 None None \n", "2 None None \n", "3 None None \n", "4 None None \n", ".. ... ... \n", "177 f Belletristische Darstellung None \n", "244 None None \n", "250 f Belletristische Darstellung None \n", "307 None None \n", "473 None None \n", "\n", " signatur_place \\\n", "0 None \n", "1 000|112 \n", "2 330|022|019|074 \n", "3 330|022 \n", "4 000|112 \n", ".. ... \n", "177 042 \n", "244 000|000|000|002|000|000 \n", "250 000|042 \n", "307 042|004 \n", "473 900 \n", "\n", " signatur \\\n", "0 None \n", "1 91.220.68|Za 195 (101) \n", "2 01/IA 6450|28 Rom Z 15707|Z 603|Z 872 \n", "3 16/IA 5021a|28 Frz Z 1775[Suppl. \n", "4 291.535|Za 195 (97) \n", ".. ... \n", "177 Ff II 2160, A2 \n", "244 Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0... \n", "250 80.706.91|Gc II 444, B434 \n", "307 Ff II 1987|40/IQ 38420 G216 \n", "473 / \n", "\n", " signatur_date api_query \n", "0 27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2... pica_rvp_IA \n", "1 30-11-20|22-09-20 pica_rvp_IA \n", "2 09-08-01|11-08-20|05-08-20|16-12-20 pica_rvp_IA \n", "3 14-06-07|24-07-19 pica_rvp_IA \n", "4 19-09-19|31-01-19 pica_rvp_IA \n", ".. ... ... \n", "177 06-04-11 pica_sgt_860 \n", "244 06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0... pica_sgt_860 \n", "250 01-01-11|06-04-11 pica_sgt_860 \n", "307 18-07-18|03-12-96 pica_sgt_860 \n", "473 24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2... pica_sgt_860 \n", "\n", "[198642 rows x 47 columns]" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "concat_df" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "concat_df = concat_df.groupby(\"ppn\").head(1)" ] }, { "cell_type": "code", "execution_count": 15, "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", "
ppnmediumtitletitle_supplementyearentry_firstauthor_first_nameauthor_last_nameauthor_gnd_ideditor_first_name...keyword_BDSL_pkeyword_BDSL_tkeyword_BDSL_skeyword_Fremddatenlieferanten_lieferantenkeyword_Fremddatenlieferantenlcc_notationsignatur_placesignatursignatur_dateapi_query
0484825402OaxLes @Arts et les Lettres en Provence au temps ...None20206055:27-08-21JeanArrouyeNoneGabriel|Marion|Chantal|Noël|Barbara|Marie-Clau......NaNNaNNaNNaNf Kongress|g Aix-en-Provence <2009>NoneNoneNone27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2...pica_rvp_IA
1469727594AauMédiations et construction de l'Antiquité dans...None20200026:22-09-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|11291.220.68|Za 195 (101)30-11-20|22-09-20pica_rvp_IA
2466221029AbvcLire magazine littéraireNone20206050:02-07-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|022|019|07401/IA 6450|28 Rom Z 15707|Z 603|Z 87209-08-01|11-08-20|05-08-20|16-12-20pica_rvp_IA
3450873676AbvcFrancophonies du mondeNone20196050:18-07-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|02216/IA 5021a|28 Frz Z 1775[Suppl.14-06-07|24-07-19pica_rvp_IA
4442132174AauLe @\"théâtre provincial\" en France(XVIe-XVIIIe siècle)20180026:31-01-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|112291.535|Za 195 (97)19-09-19|31-01-19pica_rvp_IA
..................................................................
7448323834OaxAvantgarde und RevolutionMexikanische Lyrik von López Velarde bis Octav...19876055:07-05-19NoneNoneNoneKlaus...NaNNaNNaNNaNNoneNoneNoneNone16-11-20|09-05-19|24-09-19|07-02-20pica_sgt_860
80363749462AauIn einer fremden StadtGedichte und Fragmente19836000:03-09-15NoneNone363316256None...NaNNaNNaNNaNNoneNone112P 2 19 MENE a 1983/126-05-21pica_sgt_860
10344832184XOaxDie @Frau im spanischen Roman nach dem Bürgerk...Camilo José Cela, Carmen Laforet, Ana María Ma...19826055:07-05-19SylviaTruxaNoneNone...NaNNaNNaNNaNNoneNoneNoneNone16-11-20|09-05-19|24-09-19|07-02-20pica_sgt_860
244047829680AbvcLateinamerika-StudienNone19766050:20-06-96NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|000|000|002|000|000Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0...06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0...pica_sgt_860
473386319588OauDer @Troubadour der spanischen FalangeNone19656000:27-08-16NoneNone140900845None...NaNNaNNaNNaNNoneNone900/24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2...pica_sgt_860
\n", "

189763 rows × 47 columns

\n", "
" ], "text/plain": [ " ppn medium title \\\n", "0 484825402 Oax Les @Arts et les Lettres en Provence au temps ... \n", "1 469727594 Aau Médiations et construction de l'Antiquité dans... \n", "2 466221029 Abvc Lire magazine littéraire \n", "3 450873676 Abvc Francophonies du monde \n", "4 442132174 Aau Le @\"théâtre provincial\" en France \n", ".. ... ... ... \n", "7 448323834 Oax Avantgarde und Revolution \n", "80 363749462 Aau In einer fremden Stadt \n", "103 44832184X Oax Die @Frau im spanischen Roman nach dem Bürgerk... \n", "244 047829680 Abvc Lateinamerika-Studien \n", "473 386319588 Oau Der @Troubadour der spanischen Falange \n", "\n", " title_supplement year entry_first \\\n", "0 None 2020 6055:27-08-21 \n", "1 None 2020 0026:22-09-20 \n", "2 None 2020 6050:02-07-20 \n", "3 None 2019 6050:18-07-19 \n", "4 (XVIe-XVIIIe siècle) 2018 0026:31-01-19 \n", ".. ... ... ... \n", "7 Mexikanische Lyrik von López Velarde bis Octav... 1987 6055:07-05-19 \n", "80 Gedichte und Fragmente 1983 6000:03-09-15 \n", "103 Camilo José Cela, Carmen Laforet, Ana María Ma... 1982 6055:07-05-19 \n", "244 None 1976 6050:20-06-96 \n", "473 None 1965 6000:27-08-16 \n", "\n", " author_first_name author_last_name author_gnd_id \\\n", "0 Jean Arrouye None \n", "1 None None None \n", "2 None None None \n", "3 None None None \n", "4 None None None \n", ".. ... ... ... \n", "7 None None None \n", "80 None None 363316256 \n", "103 Sylvia Truxa None \n", "244 None None None \n", "473 None None 140900845 \n", "\n", " editor_first_name ... keyword_BDSL_p \\\n", "0 Gabriel|Marion|Chantal|Noël|Barbara|Marie-Clau... ... NaN \n", "1 None ... NaN \n", "2 None ... NaN \n", "3 None ... NaN \n", "4 None ... NaN \n", ".. ... ... ... \n", "7 Klaus ... NaN \n", "80 None ... NaN \n", "103 None ... NaN \n", "244 None ... NaN \n", "473 None ... NaN \n", "\n", " keyword_BDSL_t keyword_BDSL_s keyword_Fremddatenlieferanten_lieferanten \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", ".. ... ... ... \n", "7 NaN NaN NaN \n", "80 NaN NaN NaN \n", "103 NaN NaN NaN \n", "244 NaN NaN NaN \n", "473 NaN NaN NaN \n", "\n", " keyword_Fremddatenlieferanten lcc_notation \\\n", "0 f Kongress|g Aix-en-Provence <2009> None \n", "1 None None \n", "2 None None \n", "3 None None \n", "4 None None \n", ".. ... ... \n", "7 None None \n", "80 None None \n", "103 None None \n", "244 None None \n", "473 None None \n", "\n", " signatur_place \\\n", "0 None \n", "1 000|112 \n", "2 330|022|019|074 \n", "3 330|022 \n", "4 000|112 \n", ".. ... \n", "7 None \n", "80 112 \n", "103 None \n", "244 000|000|000|002|000|000 \n", "473 900 \n", "\n", " signatur \\\n", "0 None \n", "1 91.220.68|Za 195 (101) \n", "2 01/IA 6450|28 Rom Z 15707|Z 603|Z 872 \n", "3 16/IA 5021a|28 Frz Z 1775[Suppl. \n", "4 291.535|Za 195 (97) \n", ".. ... \n", "7 None \n", "80 P 2 19 MENE a 1983/1 \n", "103 None \n", "244 Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0... \n", "473 / \n", "\n", " signatur_date api_query \n", "0 27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2... pica_rvp_IA \n", "1 30-11-20|22-09-20 pica_rvp_IA \n", "2 09-08-01|11-08-20|05-08-20|16-12-20 pica_rvp_IA \n", "3 14-06-07|24-07-19 pica_rvp_IA \n", "4 19-09-19|31-01-19 pica_rvp_IA \n", ".. ... ... \n", "7 16-11-20|09-05-19|24-09-19|07-02-20 pica_sgt_860 \n", "80 26-05-21 pica_sgt_860 \n", "103 16-11-20|09-05-19|24-09-19|07-02-20 pica_sgt_860 \n", "244 06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0... pica_sgt_860 \n", "473 24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2... pica_sgt_860 \n", "\n", "[189763 rows x 47 columns]" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "concat_df" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 None\n", "1 None\n", "2 None\n", "3 None\n", "4 None\n", " ... \n", "7 860\n", "80 860|B\n", "103 860\n", "244 860\n", "473 860\n", "Name: DDC_sachgruppe_c, Length: 189763, dtype: object" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "concat_df[\"DDC_sachgruppe_c\"]" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "concat_df.reset_index(inplace=True)" ] }, { "cell_type": "code", "execution_count": 24, "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", "
indexppnmediumtitletitle_supplementyearentry_firstauthor_first_nameauthor_last_nameauthor_gnd_id...keyword_BDSL_pkeyword_BDSL_tkeyword_BDSL_skeyword_Fremddatenlieferanten_lieferantenkeyword_Fremddatenlieferantenlcc_notationsignatur_placesignatursignatur_dateapi_query
00484825402OaxLes @Arts et les Lettres en Provence au temps ...None20206055:27-08-21JeanArrouyeNone...NaNNaNNaNNaNf Kongress|g Aix-en-Provence <2009>NoneNoneNone27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2...pica_rvp_IA
11469727594AauMédiations et construction de l'Antiquité dans...None20200026:22-09-20NoneNoneNone...NaNNaNNaNNaNNoneNone000|11291.220.68|Za 195 (101)30-11-20|22-09-20pica_rvp_IA
22466221029AbvcLire magazine littéraireNone20206050:02-07-20NoneNoneNone...NaNNaNNaNNaNNoneNone330|022|019|07401/IA 6450|28 Rom Z 15707|Z 603|Z 87209-08-01|11-08-20|05-08-20|16-12-20pica_rvp_IA
33450873676AbvcFrancophonies du mondeNone20196050:18-07-19NoneNoneNone...NaNNaNNaNNaNNoneNone330|02216/IA 5021a|28 Frz Z 1775[Suppl.14-06-07|24-07-19pica_rvp_IA
44442132174AauLe @\"théâtre provincial\" en France(XVIe-XVIIIe siècle)20180026:31-01-19NoneNoneNone...NaNNaNNaNNaNNoneNone000|112291.535|Za 195 (97)19-09-19|31-01-19pica_rvp_IA
..................................................................
1897587448323834OaxAvantgarde und RevolutionMexikanische Lyrik von López Velarde bis Octav...19876055:07-05-19NoneNoneNone...NaNNaNNaNNaNNoneNoneNoneNone16-11-20|09-05-19|24-09-19|07-02-20pica_sgt_860
18975980363749462AauIn einer fremden StadtGedichte und Fragmente19836000:03-09-15NoneNone363316256...NaNNaNNaNNaNNoneNone112P 2 19 MENE a 1983/126-05-21pica_sgt_860
18976010344832184XOaxDie @Frau im spanischen Roman nach dem Bürgerk...Camilo José Cela, Carmen Laforet, Ana María Ma...19826055:07-05-19SylviaTruxaNone...NaNNaNNaNNaNNoneNoneNoneNone16-11-20|09-05-19|24-09-19|07-02-20pica_sgt_860
189761244047829680AbvcLateinamerika-StudienNone19766050:20-06-96NoneNoneNone...NaNNaNNaNNaNNoneNone000|000|000|002|000|000Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0...06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0...pica_sgt_860
189762473386319588OauDer @Troubadour der spanischen FalangeNone19656000:27-08-16NoneNone140900845...NaNNaNNaNNaNNoneNone900/24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2...pica_sgt_860
\n", "

189763 rows × 48 columns

\n", "
" ], "text/plain": [ " index ppn medium \\\n", "0 0 484825402 Oax \n", "1 1 469727594 Aau \n", "2 2 466221029 Abvc \n", "3 3 450873676 Abvc \n", "4 4 442132174 Aau \n", "... ... ... ... \n", "189758 7 448323834 Oax \n", "189759 80 363749462 Aau \n", "189760 103 44832184X Oax \n", "189761 244 047829680 Abvc \n", "189762 473 386319588 Oau \n", "\n", " title \\\n", "0 Les @Arts et les Lettres en Provence au temps ... \n", "1 Médiations et construction de l'Antiquité dans... \n", "2 Lire magazine littéraire \n", "3 Francophonies du monde \n", "4 Le @\"théâtre provincial\" en France \n", "... ... \n", "189758 Avantgarde und Revolution \n", "189759 In einer fremden Stadt \n", "189760 Die @Frau im spanischen Roman nach dem Bürgerk... \n", "189761 Lateinamerika-Studien \n", "189762 Der @Troubadour der spanischen Falange \n", "\n", " title_supplement year \\\n", "0 None 2020 \n", "1 None 2020 \n", "2 None 2020 \n", "3 None 2019 \n", "4 (XVIe-XVIIIe siècle) 2018 \n", "... ... ... \n", "189758 Mexikanische Lyrik von López Velarde bis Octav... 1987 \n", "189759 Gedichte und Fragmente 1983 \n", "189760 Camilo José Cela, Carmen Laforet, Ana María Ma... 1982 \n", "189761 None 1976 \n", "189762 None 1965 \n", "\n", " entry_first author_first_name author_last_name author_gnd_id ... \\\n", "0 6055:27-08-21 Jean Arrouye None ... \n", "1 0026:22-09-20 None None None ... \n", "2 6050:02-07-20 None None None ... \n", "3 6050:18-07-19 None None None ... \n", "4 0026:31-01-19 None None None ... \n", "... ... ... ... ... ... \n", "189758 6055:07-05-19 None None None ... \n", "189759 6000:03-09-15 None None 363316256 ... \n", "189760 6055:07-05-19 Sylvia Truxa None ... \n", "189761 6050:20-06-96 None None None ... \n", "189762 6000:27-08-16 None None 140900845 ... \n", "\n", " keyword_BDSL_p keyword_BDSL_t keyword_BDSL_s \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", "... ... ... ... \n", "189758 NaN NaN NaN \n", "189759 NaN NaN NaN \n", "189760 NaN NaN NaN \n", "189761 NaN NaN NaN \n", "189762 NaN NaN NaN \n", "\n", " keyword_Fremddatenlieferanten_lieferanten \\\n", "0 NaN \n", "1 NaN \n", "2 NaN \n", "3 NaN \n", "4 NaN \n", "... ... \n", "189758 NaN \n", "189759 NaN \n", "189760 NaN \n", "189761 NaN \n", "189762 NaN \n", "\n", " keyword_Fremddatenlieferanten lcc_notation \\\n", "0 f Kongress|g Aix-en-Provence <2009> None \n", "1 None None \n", "2 None None \n", "3 None None \n", "4 None None \n", "... ... ... \n", "189758 None None \n", "189759 None None \n", "189760 None None \n", "189761 None None \n", "189762 None None \n", "\n", " signatur_place \\\n", "0 None \n", "1 000|112 \n", "2 330|022|019|074 \n", "3 330|022 \n", "4 000|112 \n", "... ... \n", "189758 None \n", "189759 112 \n", "189760 None \n", "189761 000|000|000|002|000|000 \n", "189762 900 \n", "\n", " signatur \\\n", "0 None \n", "1 91.220.68|Za 195 (101) \n", "2 01/IA 6450|28 Rom Z 15707|Z 603|Z 872 \n", "3 16/IA 5021a|28 Frz Z 1775[Suppl. \n", "4 291.535|Za 195 (97) \n", "... ... \n", "189758 None \n", "189759 P 2 19 MENE a 1983/1 \n", "189760 None \n", "189761 Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0... \n", "189762 / \n", "\n", " signatur_date api_query \n", "0 27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2... pica_rvp_IA \n", "1 30-11-20|22-09-20 pica_rvp_IA \n", "2 09-08-01|11-08-20|05-08-20|16-12-20 pica_rvp_IA \n", "3 14-06-07|24-07-19 pica_rvp_IA \n", "4 19-09-19|31-01-19 pica_rvp_IA \n", "... ... ... \n", "189758 16-11-20|09-05-19|24-09-19|07-02-20 pica_sgt_860 \n", "189759 26-05-21 pica_sgt_860 \n", "189760 16-11-20|09-05-19|24-09-19|07-02-20 pica_sgt_860 \n", "189761 06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0... pica_sgt_860 \n", "189762 24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2... pica_sgt_860 \n", "\n", "[189763 rows x 48 columns]" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "concat_df" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [], "source": [ "concat_df.to_parquet(\"./../data/parquets/pica_rvp_IA-IZ_pica_sgt_440_860.parquet\")" ] }, { "cell_type": "code", "execution_count": 22, "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", "
ppnmediumtitletitle_supplementyearentry_firstauthor_first_nameauthor_last_nameauthor_gnd_ideditor_first_name...keyword_BDSL_pkeyword_BDSL_tkeyword_BDSL_skeyword_Fremddatenlieferanten_lieferantenkeyword_Fremddatenlieferantenlcc_notationsignatur_placesignatursignatur_dateapi_query
0484825402OaxLes @Arts et les Lettres en Provence au temps ...None20206055:27-08-21JeanArrouyeNoneGabriel|Marion|Chantal|Noël|Barbara|Marie-Clau......NaNNaNNaNNaNf Kongress|g Aix-en-Provence <2009>NoneNoneNone27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2...pica_rvp_IA
1469727594AauMédiations et construction de l'Antiquité dans...None20200026:22-09-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|11291.220.68|Za 195 (101)30-11-20|22-09-20pica_rvp_IA
2466221029AbvcLire magazine littéraireNone20206050:02-07-20NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|022|019|07401/IA 6450|28 Rom Z 15707|Z 603|Z 87209-08-01|11-08-20|05-08-20|16-12-20pica_rvp_IA
3450873676AbvcFrancophonies du mondeNone20196050:18-07-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone330|02216/IA 5021a|28 Frz Z 1775[Suppl.14-06-07|24-07-19pica_rvp_IA
4442132174AauLe @\"théâtre provincial\" en France(XVIe-XVIIIe siècle)20180026:31-01-19NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|112291.535|Za 195 (97)19-09-19|31-01-19pica_rvp_IA
..................................................................
7448323834OaxAvantgarde und RevolutionMexikanische Lyrik von López Velarde bis Octav...19876055:07-05-19NoneNoneNoneKlaus...NaNNaNNaNNaNNoneNoneNoneNone16-11-20|09-05-19|24-09-19|07-02-20pica_sgt_860
80363749462AauIn einer fremden StadtGedichte und Fragmente19836000:03-09-15NoneNone363316256None...NaNNaNNaNNaNNoneNone112P 2 19 MENE a 1983/126-05-21pica_sgt_860
10344832184XOaxDie @Frau im spanischen Roman nach dem Bürgerk...Camilo José Cela, Carmen Laforet, Ana María Ma...19826055:07-05-19SylviaTruxaNoneNone...NaNNaNNaNNaNNoneNoneNoneNone16-11-20|09-05-19|24-09-19|07-02-20pica_sgt_860
244047829680AbvcLateinamerika-StudienNone19766050:20-06-96NoneNoneNoneNone...NaNNaNNaNNaNNoneNone000|000|000|002|000|000Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0...06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0...pica_sgt_860
473386319588OauDer @Troubadour der spanischen FalangeNone19656000:27-08-16NoneNone140900845None...NaNNaNNaNNaNNoneNone900/24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2...pica_sgt_860
\n", "

189763 rows × 47 columns

\n", "
" ], "text/plain": [ " ppn medium title \\\n", "0 484825402 Oax Les @Arts et les Lettres en Provence au temps ... \n", "1 469727594 Aau Médiations et construction de l'Antiquité dans... \n", "2 466221029 Abvc Lire magazine littéraire \n", "3 450873676 Abvc Francophonies du monde \n", "4 442132174 Aau Le @\"théâtre provincial\" en France \n", ".. ... ... ... \n", "7 448323834 Oax Avantgarde und Revolution \n", "80 363749462 Aau In einer fremden Stadt \n", "103 44832184X Oax Die @Frau im spanischen Roman nach dem Bürgerk... \n", "244 047829680 Abvc Lateinamerika-Studien \n", "473 386319588 Oau Der @Troubadour der spanischen Falange \n", "\n", " title_supplement year entry_first \\\n", "0 None 2020 6055:27-08-21 \n", "1 None 2020 0026:22-09-20 \n", "2 None 2020 6050:02-07-20 \n", "3 None 2019 6050:18-07-19 \n", "4 (XVIe-XVIIIe siècle) 2018 0026:31-01-19 \n", ".. ... ... ... \n", "7 Mexikanische Lyrik von López Velarde bis Octav... 1987 6055:07-05-19 \n", "80 Gedichte und Fragmente 1983 6000:03-09-15 \n", "103 Camilo José Cela, Carmen Laforet, Ana María Ma... 1982 6055:07-05-19 \n", "244 None 1976 6050:20-06-96 \n", "473 None 1965 6000:27-08-16 \n", "\n", " author_first_name author_last_name author_gnd_id \\\n", "0 Jean Arrouye None \n", "1 None None None \n", "2 None None None \n", "3 None None None \n", "4 None None None \n", ".. ... ... ... \n", "7 None None None \n", "80 None None 363316256 \n", "103 Sylvia Truxa None \n", "244 None None None \n", "473 None None 140900845 \n", "\n", " editor_first_name ... keyword_BDSL_p \\\n", "0 Gabriel|Marion|Chantal|Noël|Barbara|Marie-Clau... ... NaN \n", "1 None ... NaN \n", "2 None ... NaN \n", "3 None ... NaN \n", "4 None ... NaN \n", ".. ... ... ... \n", "7 Klaus ... NaN \n", "80 None ... NaN \n", "103 None ... NaN \n", "244 None ... NaN \n", "473 None ... NaN \n", "\n", " keyword_BDSL_t keyword_BDSL_s keyword_Fremddatenlieferanten_lieferanten \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", ".. ... ... ... \n", "7 NaN NaN NaN \n", "80 NaN NaN NaN \n", "103 NaN NaN NaN \n", "244 NaN NaN NaN \n", "473 NaN NaN NaN \n", "\n", " keyword_Fremddatenlieferanten lcc_notation \\\n", "0 f Kongress|g Aix-en-Provence <2009> None \n", "1 None None \n", "2 None None \n", "3 None None \n", "4 None None \n", ".. ... ... \n", "7 None None \n", "80 None None \n", "103 None None \n", "244 None None \n", "473 None None \n", "\n", " signatur_place \\\n", "0 None \n", "1 000|112 \n", "2 330|022|019|074 \n", "3 330|022 \n", "4 000|112 \n", ".. ... \n", "7 None \n", "80 112 \n", "103 None \n", "244 000|000|000|002|000|000 \n", "473 900 \n", "\n", " signatur \\\n", "0 None \n", "1 91.220.68|Za 195 (101) \n", "2 01/IA 6450|28 Rom Z 15707|Z 603|Z 872 \n", "3 16/IA 5021a|28 Frz Z 1775[Suppl. \n", "4 291.535|Za 195 (97) \n", ".. ... \n", "7 None \n", "80 P 2 19 MENE a 1983/1 \n", "103 None \n", "244 Zs 14176|83.144.48|83.896.55|AZ 161|SS 78/43|0... \n", "473 / \n", "\n", " signatur_date api_query \n", "0 27-08-21|27-08-21|27-08-21|27-08-21|27-08-21|2... pica_rvp_IA \n", "1 30-11-20|22-09-20 pica_rvp_IA \n", "2 09-08-01|11-08-20|05-08-20|16-12-20 pica_rvp_IA \n", "3 14-06-07|24-07-19 pica_rvp_IA \n", "4 19-09-19|31-01-19 pica_rvp_IA \n", ".. ... ... \n", "7 16-11-20|09-05-19|24-09-19|07-02-20 pica_sgt_860 \n", "80 26-05-21 pica_sgt_860 \n", "103 16-11-20|09-05-19|24-09-19|07-02-20 pica_sgt_860 \n", "244 06-10-98|06-10-98|16-11-06|26-04-06|07-10-98|0... pica_sgt_860 \n", "473 24-09-19|21-11-16|24-09-19|24-09-19|24-09-19|2... pica_sgt_860 \n", "\n", "[189763 rows x 47 columns]" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "concat_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "interpreter": { "hash": "960f4d658457e0296618a96ff118bd2cbd6b6fed4373572a098ed4ec5a9be4c3" }, "kernelspec": { "display_name": "Python 3.7.6 64-bit ('base': conda)", "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": "3.7.6" } }, "nbformat": 4, "nbformat_minor": 2 }