diff --git a/Daten/Vorhersagen/WIP_complete_BE.xlsx b/Daten/Vorhersagen/WIP_complete_BE.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..2fccd99211ca209864bddc055f445ba5f50ad799 Binary files /dev/null and b/Daten/Vorhersagen/WIP_complete_BE.xlsx differ diff --git a/Notebooks/Remaining_barcodes_and_metadata.ipynb b/Notebooks/Remaining_barcodes_and_metadata.ipynb index e02fdf2d42fb069d61a487213878faa018985a69..03970f1add29db284158fb5dfbad7fc8c4447fb7 100644 --- a/Notebooks/Remaining_barcodes_and_metadata.ipynb +++ b/Notebooks/Remaining_barcodes_and_metadata.ipynb @@ -48,6 +48,7 @@ "from sklearn.model_selection import KFold\n", "from dotenv import load_dotenv\n", "import shutil\n", + "from lxml import etree\n", "\n", "dotenv_path = '../.env'\n", "load_dotenv(dotenv_path)\n", @@ -2911,6 +2912,167 @@ "most_final_drop_dup.to_csv('data/predictions/all_pred_final.csv', index=False)" ] }, + { + "cell_type": "code", + "execution_count": 444, + "id": "eedf9265-8b9d-451e-b576-eedd5b7dd7a7", + "metadata": { + "tags": [] + }, + "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", + "
identifierfilenamepredictionman_predictionp_Ap_Bp_Cp_Ncolorman_colorp_bluep_redp_yellow
563988Z158720500Z158720500_00000001.jpgNNaN0.0716880.0876970.0763880.764227NaNNaNNaNNaNNaN
563989Z158720500Z158720500_00000002.jpgNNaN0.0544580.0471840.0904210.807938NaNNaNNaNNaNNaN
563990Z158720500Z158720500_00000003.jpgNNaN0.0447330.0392330.0766730.839361NaNNaNNaNNaNNaN
563991Z158720500Z158720500_00000004.jpgNNaN0.1350320.0625500.0768180.725600NaNNaNNaNNaNNaN
563992Z158720500Z158720500_00000005.jpgNNaN0.0629340.0483610.0496180.839087NaNNaNNaNNaNNaN
\n", + "
" + ], + "text/plain": [ + " identifier filename prediction man_prediction \n", + "563988 Z158720500 Z158720500_00000001.jpg N NaN \\\n", + "563989 Z158720500 Z158720500_00000002.jpg N NaN \n", + "563990 Z158720500 Z158720500_00000003.jpg N NaN \n", + "563991 Z158720500 Z158720500_00000004.jpg N NaN \n", + "563992 Z158720500 Z158720500_00000005.jpg N NaN \n", + "\n", + " p_A p_B p_C p_N color man_color p_blue p_red \n", + "563988 0.071688 0.087697 0.076388 0.764227 NaN NaN NaN NaN \\\n", + "563989 0.054458 0.047184 0.090421 0.807938 NaN NaN NaN NaN \n", + "563990 0.044733 0.039233 0.076673 0.839361 NaN NaN NaN NaN \n", + "563991 0.135032 0.062550 0.076818 0.725600 NaN NaN NaN NaN \n", + "563992 0.062934 0.048361 0.049618 0.839087 NaN NaN NaN NaN \n", + "\n", + " p_yellow \n", + "563988 NaN \n", + "563989 NaN \n", + "563990 NaN \n", + "563991 NaN \n", + "563992 NaN " + ] + }, + "execution_count": 444, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "most_final_drop_dup[most_final_drop_dup['identifier'].str.contains('Z158720500')]" + ] + }, { "cell_type": "code", "execution_count": 71, @@ -3216,10 +3378,3641 @@ "final_supralibros.to_csv('data/predictions/supralibros_pred_final.csv', index=False)" ] }, + { + "cell_type": "markdown", + "id": "97c9d080-fef4-41a4-b45c-b75785017c48", + "metadata": {}, + "source": [ + "# Extraktion der Metadaten aus dem Katalog für nicht-BE-Signaturen" + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 94, "id": "2c090fa7-f6be-474c-9e20-e92b75418183", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "wappen = final_supralibros[final_supralibros['man_prediction'] != 'N']" + ] + }, + { + "cell_type": "code", + "execution_count": 104, + "id": "e8ea4fe0-dd29-4005-8503-3c3feee93d25", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "BE_df = pd.read_excel('../Daten/Vorhersagen/Katalogauszug, Vorhersagen und hs. Katalogverbindungen.xlsx')" + ] + }, + { + "cell_type": "code", + "execution_count": 115, + "id": "1faa1f80-d284-4c6f-86a7-a1f230576ea3", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['Signatur', 'Barcode', 'Titel', 'Autor', 'Mitwirkender',\n", + " 'Anfang Veröffentlichungsdatum', 'Ende Veröffentlichungsdatum',\n", + " 'Veröffentlichungsdatum', 'Veröffentlichungsort',\n", + " 'Veröffentlichungsort (normiert)', 'Sprache', 'Schlagwörter',\n", + " 'Schlagwörter (mit GND)', 'Vorbesitzer', 'Typ', 'Bemerkungen',\n", + " 'Gültiger Barcode', 'Dateiname', 'Wappenklassifizierung', 'p_A', 'p_B',\n", + " 'p_C', 'p_N', 'Farbklassifizierung', 'p_blue', 'p_red', 'p_yellow',\n", + " 'hs. Katalog', 'hs. Katalog Konfidenz', 'hs. Katalogband',\n", + " 'hs. Katalogseite Digitalisat', 'Wissensklasse', 'Wissensunterklasse',\n", + " 'Formatangabe', 'hs. Katalogseite Handschrift', 'hs. Katalogeintrag ID',\n", + " 'hs. Katalogeintrag', 'hs. Katalog Image URL'],\n", + " dtype='object')" + ] + }, + "execution_count": 115, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "BE_df.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 149, + "id": "96ae8472-5308-4506-b69f-94650beb5d95", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "BE_wappen = BE_df[BE_df['Wappenklassifizierung'] != 'N']['Gültiger Barcode'].dropna()" + ] + }, + { + "cell_type": "code", + "execution_count": 151, + "id": "63a33898-5fb0-47b0-8662-f8163131ca3a", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "non_BE_wappen = wappen[~wappen['identifier'].isin(BE_wappen)]" + ] + }, + { + "cell_type": "code", + "execution_count": 226, + "id": "b0f03031-5d5f-483f-b7d2-770fdd9f563f", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "571770 Z165045809\n", + "573009 Z16691330X\n", + "574380 Z16907760X\n", + "574405 Z169084305\n", + "575078 Z169788400\n", + "575506 Z170820001\n", + "577395 Z175251203\n", + "601298 Z251589102\n", + "601303 Z251589205\n", + "601970 Z252861302\n", + "Name: identifier, dtype: object" + ] + }, + "execution_count": 226, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_barcodes = non_BE_wappen['identifier']\n", + "non_BE_barcodes[:10]" + ] + }, + { + "cell_type": "code", + "execution_count": 213, + "id": "bb150371-3990-4a72-8a3c-451478083d54", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "French\n", + "French\n", + "German\n", + "German\n" + ] + } + ], + "source": [ + "lang_data = pd.read_csv('data/iso-639-3.tab', sep='\\t')\n", + "\n", + "def english_language_from_code(lang_code):\n", + " find_by_Id = lang_data[lang_data['Id'] == lang_code]\n", + " find_by_Part2b = lang_data[lang_data['Part2b'] == lang_code]\n", + " if len(find_by_Id):\n", + " name = find_by_Id['Ref_Name'].values[0]\n", + " elif len(find_by_Part2b):\n", + " name = find_by_Part2b['Ref_Name'].values[0]\n", + " else:\n", + " name = ''\n", + " return name\n", + "\n", + "print(english_language_from_code('fra'))\n", + "print(english_language_from_code('fre'))\n", + "print(english_language_from_code('ger'))\n", + "print(english_language_from_code('deu'))" + ] + }, + { + "cell_type": "code", + "execution_count": 282, + "id": "7b90d595-ad11-477a-b3a8-8662191ec55e", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "610206 rep_131EA36A\n", + "Name: identifier, dtype: object" + ] + }, + "execution_count": 282, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_barcodes[non_BE_barcodes.str.contains('rep')]" + ] + }, + { + "cell_type": "code", + "execution_count": 414, + "id": "4a2f570d-fca7-49fb-8f84-c6a6a435a9f7", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'identifier': 'Z259430205', 'ABO-Barcode': 'Z259430205', 'Signatur': '622174-C', 'Titel': 'La pratique du theatre', 'Autor': \"Aubignac, François-Hédelin <>\", 'Mitwirkender': '', 'Veröffentlichungsdatum': '1669', 'Veröffentlichungsort': 'Paris', 'Sprache': 'French'}\n", + "{'identifier': 'Z260077107', 'ABO-Barcode': 'Z260077107', 'Signatur': '393274-B', 'Titel': 'Abrahami Ortelii Antverpiani Synonymia Geographica, Sive: Popvlorvm, Regionvm, Insularvm, Vrbium, Oppidorum, Montium ... appellationes & nomina', 'Autor': 'Ortelius, Abraham', 'Mitwirkender': '', 'Veröffentlichungsdatum': '1578', 'Veröffentlichungsort': 'Antverpiae', 'Sprache': 'Latin'}\n", + "{'identifier': 'Z204965809', 'ABO-Barcode': '', 'Signatur': 'MF 5495; BE.2.E.4.(Vol.1)', 'Titel': 'Conciliorum (Concilia) collectio regia maxima ad Philippi Labbei et Gabrielis Cossartii labores haud modica accessione Facta et emendationibus plurimis additis ... Studio Joannis Harduini. Tomis duodecim', 'Autor': '', 'Mitwirkender': 'Hardouin, Jean', 'Veröffentlichungsdatum': '1715', 'Veröffentlichungsort': 'Parisiis', 'Sprache': 'Latin'}\n", + "{'identifier': 'dtl_4968937', 'Titel': 'Les gra[n]des croniques de Bretaigne, nouvellement imprimees a Paris ... de puis le roy Brutus ... jusques au temps de Cadualadrus dernier roy breton', 'Autor': 'Bouchard, Alain [VerfasserIn]', 'Mitwirkender': '', 'Veröffentlichungsort': 'Paris', 'Veröffentlichungsdatum': '1514', 'Signatur': 'BE.4.L.38', 'Sprache': 'French', 'Barcode': 'Z18422390X'}\n", + "{'identifier': 'dtl_6529095', 'Titel': 'Theriaca et Alexipharmaca cum scholiis, interprete Johanne Lonicero', 'Autor': \"Nicander, Colophonius, ca. v2. Jh. [VerfasserIn]\", 'Mitwirkender': '', 'Veröffentlichungsort': 'Coloniae, Köln', 'Veröffentlichungsdatum': '1531', 'Signatur': 'BE.5.N.37', 'Sprache': 'Latin', 'Barcode': 'Z173254304'}\n", + "{'identifier': 'rep_131EA36A', 'ABO-Barcode': '', 'Signatur': 'BE.8.P.19.20.(Vol.2)', 'Titel': \"Histoire Vniverselle Des Gverres Dv Tvrc, Depvis L'An 1565 Ivsqves A La Trefve, faicte l'annee 1606\", 'Autor': 'Montreux, Nicolas <>', 'Mitwirkender': \"Heinrich; Mousson, Pierre; Orléans, Louis <>; Rosset, François <>; Sieur de la Vallee; Argenten, N. Christianus; Fouet, Robert\", 'Veröffentlichungsdatum': 'MDCVIII', 'Veröffentlichungsort': 'A Paris', 'Sprache': 'French; Latin'}\n" + ] + } + ], + "source": [ + "ns = {\n", + " 'srw': 'http://www.loc.gov/zing/srw/',\n", + " 'marc': 'http://www.loc.gov/MARC21/slim'\n", + "}\n", + "sample_bcs = [\n", + " 'Z259430205',\n", + " 'Z260077107',\n", + " 'Z204965809',\n", + " 'dtl_4968937',\n", + " 'dtl_6529095',\n", + " 'rep_131EA36A'\n", + "]\n", + "\n", + "rep_id_to_BC = {\n", + " 'rep_131EA36A': 'Z202834207'\n", + "}\n", + "\n", + "def extract_catalog_data_from_identifier(idf):\n", + " metadata = {\n", + " 'identifier': idf\n", + " }\n", + " \n", + " if idf in rep_id_to_BC:\n", + " idf = rep_id_to_BC[idf]\n", + "\n", + " abo_re = re.compile('Z[0-9X]+')\n", + " abo_match = re.search(abo_re, idf)\n", + " dtl_re = re.compile('dtl_([0-9]+)')\n", + " dtl_match = re.search(dtl_re, idf)\n", + " rep_re = re.compile('rep_([0-9A-Z]+)')\n", + " rep_match = re.search(rep_re, idf)\n", + " \n", + " if abo_match:\n", + " sru = f'https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB?version=1.2&query=alma.barcode%3D{idf}&startRecord=0&maximumRecords=3&operation=searchRetrieve&recordSchema=marcxml'\n", + " sru_request = requests.get(sru)\n", + " marcxml = sru_request.content\n", + " tree = etree.fromstring(marcxml)\n", + " marc_paths = {\n", + " 'ABO-Barcode': './/marc:datafield[@tag=\"856\" and @ind1=\"4\" and @ind2=\"0\"]/marc:subfield[@code=\"u\"]',\n", + " 'Signatur': './/marc:datafield[@tag=\"AVA\"]/marc:subfield[@code=\"d\"]',\n", + " 'Titel': './/marc:datafield[@tag=\"245\"]/marc:subfield[@code=\"a\"]',\n", + " 'Autor': './/marc:datafield[@tag=\"100\"]/marc:subfield[@code=\"a\"]',\n", + " 'Mitwirkender': './/marc:datafield[@tag=\"700\"]/marc:subfield[@code=\"a\"]',\n", + " 'Veröffentlichungsdatum': './/marc:datafield[@tag=\"264\"]/marc:subfield[@code=\"c\"]',\n", + " 'Veröffentlichungsort': './/marc:datafield[@tag=\"264\"]/marc:subfield[@code=\"a\"]',\n", + " 'Sprache': './/marc:datafield[@tag=\"041\"]/marc:subfield[@code=\"a\"]'\n", + " }\n", + "\n", + "\n", + " for key, path in marc_paths.items():\n", + " values = [elm.text for elm in tree.xpath(path, namespaces=ns)]\n", + " if key == 'ABO-Barcode':\n", + " values = [val.split('/')[-1].replace('%2B', '') for val in values]\n", + " elif key == 'Sprache':\n", + " values = [english_language_from_code(val) for val in values]\n", + "\n", + " metadata[key] = '; '.join(values)\n", + " elif dtl_match:\n", + " dtl_id = dtl_match[1]\n", + " iiif_url = f'https://iiif.onb.ac.at/presentation/REPO/{dtl_id}/manifest'\n", + " manifest_metadata = json.loads(requests.get(iiif_url).content)['metadata']\n", + " for dic in manifest_metadata:\n", + " for key, val in dic.items():\n", + " if val == [{'@value': 'Title', '@language': 'en'}, {'@value': 'Titel', '@language': 'ger'}]:\n", + " metadata['Titel'] = dic['value']\n", + " if val == [{'@value': 'Contributor', '@language': 'en'}, {'@value': 'Mitwirkender', '@language': 'ger'}]:\n", + " if '[VerfasserIn]' in dic['value']:\n", + " metadata['Autor'] = dic['value']\n", + " metadata['Mitwirkender'] = ''\n", + " else:\n", + " metadata['Autor'] = ''\n", + " metadata['Mitwirkender'] = dic['value']\n", + " if val == 'Barcode':\n", + " metadata['Barcode'] = dic['value'].replace('+', '')\n", + " if val == [{'@value': 'Place', '@language': 'en'}, {'@value': 'Erscheinungsort', '@language': 'ger'}]:\n", + " metadata['Veröffentlichungsort'] = dic['value']\n", + " if val == [{'@value': 'Date Issued', '@language': 'en'}, {'@value': 'Erscheinungsdatum', '@language': 'ger'}]:\n", + " metadata['Veröffentlichungsdatum'] = dic['value']\n", + " if val == [{'@value': 'Location', '@language': 'en'}, {'@value': 'Ort', '@language': 'ger'}]:\n", + " sign_re = re.compile('\\w+ \\w+ ([A-Z0-9\\.\\-\\(Vol\\)]+)')\n", + " sign_match = re.search(sign_re, dic['value'])\n", + " metadata['Signatur'] = sign_match[1]\n", + " if val == [{'@value': 'Languages', '@language': 'en'}, {'@value': 'Sprachen', '@language': 'ger'}]:\n", + " metadata['Sprache'] = english_language_from_code(dic['value'])\n", + " elif rep_match:\n", + " print('REPO Ids not implemented for id', idf)\n", + " else:\n", + " print('no match found for', idf)\n", + " return metadata\n", + "\n", + "for bc in sample_bcs:\n", + " print(extract_catalog_data_from_identifier(bc))" + ] + }, + { + "cell_type": "code", + "execution_count": 415, + "id": "6f6d2e5e-c056-4d72-b890-7247fb42b7f1", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "3619fbbb5b6349cdbb02ca667bb19359", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/804 [00:00\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
identifierfilenamepredictionman_predictionp_Ap_Bp_Cp_Ncolorman_color...p_yellowABO-BarcodeSignaturTitelAutorMitwirkenderVeröffentlichungsdatumVeröffentlichungsortSpracheBarcode
0Z165045809Z165045809_00000001.jpgBB0.0023510.9924410.0014750.003733redred...0.063229Z16504580943.R.10Les armes et blasons des chevaliers de l'ordre...Morin de la Masserie, Jacques[ohne Jahresangabe]ParisFrenchNaN
1Z16691330XZ16691330X_00000001.jpgAA0.9897870.0020230.0036160.004575redred...0.013185Z16691330X56.F.25Memorial historico, juridico, politico de la S...Calderon, Juan Alonso[ohne Jahresangabe]o.O.SpanishNaN
2Z16907760XZ16907760X_00000001.jpgAA0.9988060.0003390.0003040.000550redred...0.013297Z16907760X66.E.20Teatro della gloria, consagrato a S. Felice Sa...[ohne Jahresangabe]o.O.ItalianNaN
3Z169084305Z169084305_00000001.jpgBB0.0020390.9928770.0018860.003197redred...0.094729Z16908430566.E.45Les vigilles de la mort du roi Charles VII a 9...Martial d'Auvergne[ohne Jahresangabe]ParisFrenchNaN
4Z169788400Z169788400_00000001.jpgBB0.0016860.9933890.0027140.002212redred...0.006627Z16978840062.E.12Historiæ Flandriæ ChristianæVredius, Olivarius[ohne Jahresangabe]Brugis FlandrorumLatinNaN
..................................................................
799Z259430205Z259430205_00000001.jpgBB0.0014760.9920150.0021370.004372redred...0.009999Z259430205622174-CLa pratique du theatreAubignac, François-Hédelin <<d'>>1669ParisFrenchNaN
800Z259431209Z259431209_00000001.jpgBB0.0012450.9953590.0025070.000890redred...0.007521Z259431209622186-CLe nozze degli dei. Favola rappresentata in mu...Coppola, Giovanni-CarloMassi, Amador1637FirenzeItalianNaN
801Z260077107Z260077107_00000001.jpgBB0.0002480.9984840.0004420.000827redred...0.005469Z260077107393274-BAbrahami Ortelii Antverpiani Synonymia Geograp...Ortelius, Abraham1578AntverpiaeLatinNaN
802Z43163301Z43163301_00000001.jpgBB0.0008720.9981390.0005830.000406redred...0.001197Z43163404; Z4316330122.N.27.(Vol.2); 22.N.26.(Vol.2); 22.N.26.(Vol...Poetae Christiani VeteresSedulius; Manuzio, Aldo Pio; Clarius, Daniel; ...1501 [1502]VenetiisLatin; Ancient Greek (to 1453)NaN
803Z43169509Z43169509_00000001.jpgAA0.9951560.0017110.0021910.000941redred...0.000170Z4316950922.M.5Continentvr hoc volvmine Georgii Trapezuntii R...GeorgiusFortunatianus, Consultus; Rutilius Lupus, Publ...Mense Aprili 1523VenetiisLatinNaN
\n", + "

804 rows × 22 columns

\n", + "" + ], + "text/plain": [ + " identifier filename prediction man_prediction p_A \n", + "0 Z165045809 Z165045809_00000001.jpg B B 0.002351 \\\n", + "1 Z16691330X Z16691330X_00000001.jpg A A 0.989787 \n", + "2 Z16907760X Z16907760X_00000001.jpg A A 0.998806 \n", + "3 Z169084305 Z169084305_00000001.jpg B B 0.002039 \n", + "4 Z169788400 Z169788400_00000001.jpg B B 0.001686 \n", + ".. ... ... ... ... ... \n", + "799 Z259430205 Z259430205_00000001.jpg B B 0.001476 \n", + "800 Z259431209 Z259431209_00000001.jpg B B 0.001245 \n", + "801 Z260077107 Z260077107_00000001.jpg B B 0.000248 \n", + "802 Z43163301 Z43163301_00000001.jpg B B 0.000872 \n", + "803 Z43169509 Z43169509_00000001.jpg A A 0.995156 \n", + "\n", + " p_B p_C p_N color man_color ... p_yellow \n", + "0 0.992441 0.001475 0.003733 red red ... 0.063229 \\\n", + "1 0.002023 0.003616 0.004575 red red ... 0.013185 \n", + "2 0.000339 0.000304 0.000550 red red ... 0.013297 \n", + "3 0.992877 0.001886 0.003197 red red ... 0.094729 \n", + "4 0.993389 0.002714 0.002212 red red ... 0.006627 \n", + ".. ... ... ... ... ... ... ... \n", + "799 0.992015 0.002137 0.004372 red red ... 0.009999 \n", + "800 0.995359 0.002507 0.000890 red red ... 0.007521 \n", + "801 0.998484 0.000442 0.000827 red red ... 0.005469 \n", + "802 0.998139 0.000583 0.000406 red red ... 0.001197 \n", + "803 0.001711 0.002191 0.000941 red red ... 0.000170 \n", + "\n", + " ABO-Barcode Signatur \n", + "0 Z165045809 43.R.10 \\\n", + "1 Z16691330X 56.F.25 \n", + "2 Z16907760X 66.E.20 \n", + "3 Z169084305 66.E.45 \n", + "4 Z169788400 62.E.12 \n", + ".. ... ... \n", + "799 Z259430205 622174-C \n", + "800 Z259431209 622186-C \n", + "801 Z260077107 393274-B \n", + "802 Z43163404; Z43163301 22.N.27.(Vol.2); 22.N.26.(Vol.2); 22.N.26.(Vol... \n", + "803 Z43169509 22.M.5 \n", + "\n", + " Titel \n", + "0 Les armes et blasons des chevaliers de l'ordre... \\\n", + "1 Memorial historico, juridico, politico de la S... \n", + "2 Teatro della gloria, consagrato a S. Felice Sa... \n", + "3 Les vigilles de la mort du roi Charles VII a 9... \n", + "4 Historiæ Flandriæ Christianæ \n", + ".. ... \n", + "799 La pratique du theatre \n", + "800 Le nozze degli dei. Favola rappresentata in mu... \n", + "801 Abrahami Ortelii Antverpiani Synonymia Geograp... \n", + "802 Poetae Christiani Veteres \n", + "803 Continentvr hoc volvmine Georgii Trapezuntii R... \n", + "\n", + " Autor \n", + "0 Morin de la Masserie, Jacques \\\n", + "1 Calderon, Juan Alonso \n", + "2 \n", + "3 Martial d'Auvergne \n", + "4 Vredius, Olivarius \n", + ".. ... \n", + "799 Aubignac, François-Hédelin <> \n", + "800 Coppola, Giovanni-Carlo \n", + "801 Ortelius, Abraham \n", + "802 \n", + "803 Georgius \n", + "\n", + " Mitwirkender Veröffentlichungsdatum \n", + "0 [ohne Jahresangabe] \\\n", + "1 [ohne Jahresangabe] \n", + "2 [ohne Jahresangabe] \n", + "3 [ohne Jahresangabe] \n", + "4 [ohne Jahresangabe] \n", + ".. ... ... \n", + "799 1669 \n", + "800 Massi, Amador 1637 \n", + "801 1578 \n", + "802 Sedulius; Manuzio, Aldo Pio; Clarius, Daniel; ... 1501 [1502] \n", + "803 Fortunatianus, Consultus; Rutilius Lupus, Publ... Mense Aprili 1523 \n", + "\n", + " Veröffentlichungsort Sprache Barcode \n", + "0 Paris French NaN \n", + "1 o.O. Spanish NaN \n", + "2 o.O. Italian NaN \n", + "3 Paris French NaN \n", + "4 Brugis Flandrorum Latin NaN \n", + ".. ... ... ... \n", + "799 Paris French NaN \n", + "800 Firenze Italian NaN \n", + "801 Antverpiae Latin NaN \n", + "802 Venetiis Latin; Ancient Greek (to 1453) NaN \n", + "803 Venetiis Latin NaN \n", + "\n", + "[804 rows x 22 columns]" + ] + }, + "execution_count": 416, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_metadata_df = pd.DataFrame(non_BE_metadata)\n", + "non_BE_merged = non_BE_wappen.merge(non_BE_metadata_df, on='identifier')\n", + "\n", + "non_BE_merged" + ] + }, + { + "cell_type": "code", + "execution_count": 417, + "id": "8f74b754-71ef-4386-b398-da991d47c44c", + "metadata": { + "tags": [] + }, + "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", + "
identifierfilenamepredictionman_predictionp_Ap_Bp_Cp_Ncolorman_color...p_yellowABO-BarcodeSignaturTitelAutorMitwirkenderVeröffentlichungsdatumVeröffentlichungsortSpracheBarcode
15dtl_4968937dtl_4968937_00000001.jpgBB0.0033260.9885030.0027070.005464yellowred...0.988632NaNBE.4.L.38Les gra[n]des croniques de Bretaigne, nouvelle...Bouchard, Alain [VerfasserIn]1514ParisFrenchZ18422390X
16dtl_6528437dtl_6528437_00000001.jpgAA0.8170140.0575430.0122960.113147redred...0.321906NaN58.B.8Carte generale de la monarchie francaise conte...Le-Mau de la Jaisse, Pierre [VerfasserIn]1733ParisFrenchZ173240007
17dtl_6529055dtl_6529055_00000001.jpgAA0.9804000.0044960.0035950.011509redred...0.098123NaNBE.2.E.4.(Vol.1)Conciliorum (Concilia) collectio regia maxima ...<a href='http://d-nb.info/gnd/122664485'>Hardo...1715Parisiis, ParisLatinZ204965809
18dtl_6529095dtl_6529095_00000001.jpgBB0.0001720.9970730.0004320.002323yellowyellow...1.000000NaNBE.5.N.37Theriaca et Alexipharmaca cum scholiis, interp...<a href='http://d-nb.info/gnd/https://d-nb.inf...1531Coloniae, KölnLatinZ173254304
19dtl_6529123dtl_6529123_00000001.jpgBB0.0003880.9936250.0006760.005310yellowblue...0.975191NaNBE.8.S.34Dialogi IV, de praedestinatione, de electione,...Chateillon, Sebastianus [VerfasserIn]1578Aresdorffij, Basileae, BaselLatinZ173255205
20dtl_6529127dtl_6529127_00000001.jpgCC0.0005800.0005180.9979570.000944yellowyellow...1.000000NaNBE.8.S.53Entretiens de Maxime et de Themiste, ou repons...Bayle, Pierre [VerfasserIn]1707RotterdamNaNZ173255102
21dtl_6529135dtl_6529135_00000001.jpgBB0.0003300.9984380.0007120.000520yellowred...0.999965NaNBE.9.V.41La Loy Salique, liuret de la premiere humaine ...Postel, Guillaume [VerfasserIn]1552ParisFrenchZ173256209
22dtl_6529147dtl_6529147_00000001.jpgBB0.0022730.9942770.0010910.002358yellowblue...0.668259NaNBE.10.O.3De vita et moribus sacerdotum opusculum: singu...<a href='http://d-nb.info/gnd/https://d-nb.inf...1520Parisiis, ParisLatinZ173252605
\n", + "

8 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " identifier filename prediction man_prediction p_A \n", + "15 dtl_4968937 dtl_4968937_00000001.jpg B B 0.003326 \\\n", + "16 dtl_6528437 dtl_6528437_00000001.jpg A A 0.817014 \n", + "17 dtl_6529055 dtl_6529055_00000001.jpg A A 0.980400 \n", + "18 dtl_6529095 dtl_6529095_00000001.jpg B B 0.000172 \n", + "19 dtl_6529123 dtl_6529123_00000001.jpg B B 0.000388 \n", + "20 dtl_6529127 dtl_6529127_00000001.jpg C C 0.000580 \n", + "21 dtl_6529135 dtl_6529135_00000001.jpg B B 0.000330 \n", + "22 dtl_6529147 dtl_6529147_00000001.jpg B B 0.002273 \n", + "\n", + " p_B p_C p_N color man_color ... p_yellow \n", + "15 0.988503 0.002707 0.005464 yellow red ... 0.988632 \\\n", + "16 0.057543 0.012296 0.113147 red red ... 0.321906 \n", + "17 0.004496 0.003595 0.011509 red red ... 0.098123 \n", + "18 0.997073 0.000432 0.002323 yellow yellow ... 1.000000 \n", + "19 0.993625 0.000676 0.005310 yellow blue ... 0.975191 \n", + "20 0.000518 0.997957 0.000944 yellow yellow ... 1.000000 \n", + "21 0.998438 0.000712 0.000520 yellow red ... 0.999965 \n", + "22 0.994277 0.001091 0.002358 yellow blue ... 0.668259 \n", + "\n", + " ABO-Barcode Signatur \n", + "15 NaN BE.4.L.38 \\\n", + "16 NaN 58.B.8 \n", + "17 NaN BE.2.E.4.(Vol.1) \n", + "18 NaN BE.5.N.37 \n", + "19 NaN BE.8.S.34 \n", + "20 NaN BE.8.S.53 \n", + "21 NaN BE.9.V.41 \n", + "22 NaN BE.10.O.3 \n", + "\n", + " Titel \n", + "15 Les gra[n]des croniques de Bretaigne, nouvelle... \\\n", + "16 Carte generale de la monarchie francaise conte... \n", + "17 Conciliorum (Concilia) collectio regia maxima ... \n", + "18 Theriaca et Alexipharmaca cum scholiis, interp... \n", + "19 Dialogi IV, de praedestinatione, de electione,... \n", + "20 Entretiens de Maxime et de Themiste, ou repons... \n", + "21 La Loy Salique, liuret de la premiere humaine ... \n", + "22 De vita et moribus sacerdotum opusculum: singu... \n", + "\n", + " Autor \n", + "15 Bouchard, Alain [VerfasserIn] \\\n", + "16 Le-Mau de la Jaisse, Pierre [VerfasserIn] \n", + "17 \n", + "18 Hardo... 1715 \n", + "18 1531 \n", + "19 1578 \n", + "20 1707 \n", + "21 1552 \n", + "22 1520 \n", + "\n", + " Veröffentlichungsort Sprache Barcode \n", + "15 Paris French Z18422390X \n", + "16 Paris French Z173240007 \n", + "17 Parisiis, Paris Latin Z204965809 \n", + "18 Coloniae, Köln Latin Z173254304 \n", + "19 Aresdorffij, Basileae, Basel Latin Z173255205 \n", + "20 Rotterdam NaN Z173255102 \n", + "21 Paris French Z173256209 \n", + "22 Parisiis, Paris Latin Z173252605 \n", + "\n", + "[8 rows x 22 columns]" + ] + }, + "execution_count": 417, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_merged[~non_BE_merged['Barcode'].isna()]" + ] + }, + { + "cell_type": "code", + "execution_count": 433, + "id": "03f93d26-69ba-4576-a9d5-eab1658db033", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "15 BE.4.L.38\n", + "17 BE.2.E.4.(Vol.1)\n", + "18 BE.5.N.37\n", + "19 BE.8.S.34\n", + "20 BE.8.S.53\n", + "21 BE.9.V.41\n", + "22 BE.10.O.3\n", + "23 BE.8.P.19.20.(Vol.2)\n", + "Name: Signatur, dtype: object" + ] + }, + "execution_count": 433, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_merged[non_BE_merged['Signatur'].str.contains('BE')]['Signatur']" + ] + }, + { + "cell_type": "markdown", + "id": "113212c8-1c52-4146-b283-953086855d00", + "metadata": {}, + "source": [ + "# Extraktion der Metadaten aus dem Katalog für Inkunabeln" + ] + }, + { + "cell_type": "code", + "execution_count": 142, + "id": "d9d94a3c-03c2-4ab3-a36e-71de47d95563", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "inkunabeln = pd.read_excel('../Daten/Katalog/Eugeniana_Inkunabeln.xlsx')\n", + "inkunabeln['clean_signature'] = inkunabeln['Signatur'].apply(lambda x: x.replace('.', '').replace(' ', ''))" + ] + }, + { + "cell_type": "code", + "execution_count": 143, + "id": "5b39cc07-2906-4841-ac30-9df293ab2fba", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 Ink5B12\n", + "1 Ink3C8\n", + "2 Ink3E4\n", + "3 Ink7E28\n", + "4 Ink4D3\n", + " ... \n", + "247 Ink5E23\n", + "248 Ink4E4\n", + "249 Ink5H38\n", + "250 Ink8F35\n", + "251 Ink3E15\n", + "Name: clean_signature, Length: 252, dtype: object" + ] + }, + "execution_count": 143, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "inkunabeln['clean_signature']" + ] + }, + { + "cell_type": "code", + "execution_count": 144, + "id": "a0f1db41-696c-4716-a006-cef7e4e1b2fb", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "BE_df['clean_signature'] = BE_df['Signatur'].apply(lambda x: x.replace('.', '').replace(' ', ''))" + ] + }, + { + "cell_type": "code", + "execution_count": 307, + "id": "44e1ca58-6466-43e0-b6f0-68513718477e", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "new_inkunabeln = inkunabeln[~inkunabeln['clean_signature'].isin(BE_df['clean_signature'])]['Signatur']" + ] + }, + { + "cell_type": "code", + "execution_count": 333, + "id": "e9f62a92-5ccd-4b2e-916a-0bd3430b0867", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "def clean_ink_signature(sig):\n", + " ink_re = re.compile('Ink\\. ?(\\d+\\.[A-Z]\\. ?\\d+)')\n", + " ink_match = re.search(ink_re, sig)\n", + " if ink_match:\n", + " new_sig = 'Ink ' + ink_match[1].replace(' ', '')\n", + " else:\n", + " new_sig = ''\n", + " return new_sig\n", + "\n", + "clean_ink_signatures = [clean_ink_signature(sig) for sig in new_inkunabeln]" + ] + }, + { + "cell_type": "code", + "execution_count": 353, + "id": "af90c6f4-0aec-4b5d-80f6-03bdc3b38bd9", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'Signatur': 'Ink 5.B.12', 'Titel': 'De civitate dei', 'Autor': 'Augustinus, Aurelius', 'Mitwirkender': '', 'Veröffentlichungsdatum': '1470', 'Veröffentlichungsort': 'Rom', 'Sprache': 'Latin'}\n" + ] + } + ], + "source": [ + "def extract_catalog_data_from_signature(sig):\n", + " metadata = {}\n", + " sru = f'https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB?version=1.2&query=alma.accessionNumber%3D%22{sig}%22&operation=searchRetrieve'\n", + " sru_request = requests.get(sru)\n", + " marcxml = sru_request.content\n", + " tree = etree.fromstring(marcxml)\n", + " marc_paths = {\n", + " 'Signatur': './/marc:datafield[@tag=\"AVA\"]/marc:subfield[@code=\"d\"]',\n", + " 'Titel': './/marc:datafield[@tag=\"245\"]/marc:subfield[@code=\"a\"]',\n", + " 'Autor': './/marc:datafield[@tag=\"100\"]/marc:subfield[@code=\"a\"]',\n", + " 'Mitwirkender': './/marc:datafield[@tag=\"700\"]/marc:subfield[@code=\"a\"]',\n", + " 'Veröffentlichungsdatum': './/marc:datafield[@tag=\"264\"]/marc:subfield[@code=\"c\"]',\n", + " 'Veröffentlichungsort': './/marc:datafield[@tag=\"264\"]/marc:subfield[@code=\"a\"]',\n", + " 'Sprache': './/marc:datafield[@tag=\"041\"]/marc:subfield[@code=\"a\"]'\n", + " }\n", + "\n", + " for key, path in marc_paths.items():\n", + " values = [elm.text for elm in tree.xpath(path, namespaces=ns)]\n", + " # if key == 'ABO-Barcode':\n", + " # values = [val.split('/')[-1].replace('%2B', '') for val in values]\n", + " if key == 'Sprache':\n", + " values = [english_language_from_code(val) for val in values]\n", + "\n", + " metadata[key] = '; '.join(values)\n", + " if metadata['Signatur'] == '':\n", + " metadata['Signatur'] = sig\n", + " return metadata\n", + "\n", + "print(extract_catalog_data_from_signature('Ink. 5.B.12'))" + ] + }, + { + "cell_type": "code", + "execution_count": 354, + "id": "a1b09796-5790-48e4-a752-dbff8f074ee5", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "72b341b99a294462addeb5a872149658", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/232 [00:00\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SignaturTitelAutorMitwirkenderVeröffentlichungsdatumVeröffentlichungsortSprache
0Ink 5.B.12De civitate deiAugustinus, Aurelius1470RomLatin
1Ink 24.B.8; Ink 3.C.8De trinitateAugustinus, AureliusReyser, Georg[nicht nach 1471][Straßburg]Latin
2Ink 3.E.4; Ink 31-45; Ink 24.F.30Summa de ecclesiastica potestateAugustinusHongre, Pierre[nicht nach 1480][Lyon]Latin
3Ink 7.E.28OperaAusonius, Decimus MagnusFerrarius, Julius Aemilius11. Aug. 1494; [1494.08.11]VenedigLatin
4Ink 4.D.3De proprietatibus rerum (französ.) Le propriet...Bartholomaeus7. Apr. 1487; [1487.04.07]LyonFrench
........................
227Ink 4.D.15Facta et dicta memorabiliaValerius1471[Venice]Latin
228Ink 5.E.23Facta et dicta memorabiliaValerius Maximus, Gaius24 Dec. 1476BolognaLatin
229Ink 5.H.38De viris illustribusAurelius Victor, Sextus (Pseudo-)5. Juni 1477; [1477.06.05]VenedigLatin
230Ink 8.F.35Opera [Bucolica, Georgica, Aeneis, with argume...Vergilius Maro, PubliusSept. 1478ParisLatin
231Ink 3.E.15OperaXenophonabout 1501-02][MilanLatin
\n", + "

225 rows × 7 columns

\n", + "" + ], + "text/plain": [ + " Signatur \n", + "0 Ink 5.B.12 \\\n", + "1 Ink 24.B.8; Ink 3.C.8 \n", + "2 Ink 3.E.4; Ink 31-45; Ink 24.F.30 \n", + "3 Ink 7.E.28 \n", + "4 Ink 4.D.3 \n", + ".. ... \n", + "227 Ink 4.D.15 \n", + "228 Ink 5.E.23 \n", + "229 Ink 5.H.38 \n", + "230 Ink 8.F.35 \n", + "231 Ink 3.E.15 \n", + "\n", + " Titel \n", + "0 De civitate dei \\\n", + "1 De trinitate \n", + "2 Summa de ecclesiastica potestate \n", + "3 Opera \n", + "4 De proprietatibus rerum (französ.) Le propriet... \n", + ".. ... \n", + "227 Facta et dicta memorabilia \n", + "228 Facta et dicta memorabilia \n", + "229 De viris illustribus \n", + "230 Opera [Bucolica, Georgica, Aeneis, with argume... \n", + "231 Opera \n", + "\n", + " Autor Mitwirkender \n", + "0 Augustinus, Aurelius \\\n", + "1 Augustinus, Aurelius Reyser, Georg \n", + "2 Augustinus Hongre, Pierre \n", + "3 Ausonius, Decimus Magnus Ferrarius, Julius Aemilius \n", + "4 Bartholomaeus \n", + ".. ... ... \n", + "227 Valerius \n", + "228 Valerius Maximus, Gaius \n", + "229 Aurelius Victor, Sextus (Pseudo-) \n", + "230 Vergilius Maro, Publius \n", + "231 Xenophon \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort Sprache \n", + "0 1470 Rom Latin \n", + "1 [nicht nach 1471] [Straßburg] Latin \n", + "2 [nicht nach 1480] [Lyon] Latin \n", + "3 11. Aug. 1494; [1494.08.11] Venedig Latin \n", + "4 7. Apr. 1487; [1487.04.07] Lyon French \n", + ".. ... ... ... \n", + "227 1471 [Venice] Latin \n", + "228 24 Dec. 1476 Bologna Latin \n", + "229 5. Juni 1477; [1477.06.05] Venedig Latin \n", + "230 Sept. 1478 Paris Latin \n", + "231 about 1501-02] [Milan Latin \n", + "\n", + "[225 rows x 7 columns]" + ] + }, + "execution_count": 460, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ink_to_be_dropped = [23, 24, 25, 26, 27, 28, 196]\n", + "\n", + "inkunabeln_reduced = inkunabel_metadata_df.drop(ink_to_be_dropped)\n", + "inkunabeln_reduced" + ] + }, + { + "cell_type": "code", + "execution_count": 463, + "id": "584cedc1-0eb7-45d6-9535-e79867f4249b", + "metadata": { + "tags": [] + }, + "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", + "
SignaturTitelAutorMitwirkenderVeröffentlichungsdatumVeröffentlichungsortSprache
0Ink 5.B.12De civitate deiAugustinus, Aurelius1470RomLatin
1Ink 24.B.8; Ink 3.C.8De trinitateAugustinus, AureliusReyser, Georg[nicht nach 1471][Straßburg]Latin
2Ink 3.E.4; Ink 31-45; Ink 24.F.30Summa de ecclesiastica potestateAugustinusHongre, Pierre[nicht nach 1480][Lyon]Latin
3Ink 7.E.28OperaAusonius, Decimus MagnusFerrarius, Julius Aemilius11. Aug. 1494; [1494.08.11]VenedigLatin
4Ink 4.D.3De proprietatibus rerum (französ.) Le propriet...Bartholomaeus7. Apr. 1487; [1487.04.07]LyonFrench
........................
227Ink 4.D.15Facta et dicta memorabiliaValerius1471[Venice]Latin
228Ink 5.E.23Facta et dicta memorabiliaValerius Maximus, Gaius24 Dec. 1476BolognaLatin
229Ink 5.H.38De viris illustribusAurelius Victor, Sextus (Pseudo-)5. Juni 1477; [1477.06.05]VenedigLatin
230Ink 8.F.35Opera [Bucolica, Georgica, Aeneis, with argume...Vergilius Maro, PubliusSept. 1478ParisLatin
231Ink 3.E.15OperaXenophonabout 1501-02][MilanLatin
\n", + "

232 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " Signatur \n", + "0 Ink 5.B.12 \\\n", + "1 Ink 24.B.8; Ink 3.C.8 \n", + "2 Ink 3.E.4; Ink 31-45; Ink 24.F.30 \n", + "3 Ink 7.E.28 \n", + "4 Ink 4.D.3 \n", + ".. ... \n", + "227 Ink 4.D.15 \n", + "228 Ink 5.E.23 \n", + "229 Ink 5.H.38 \n", + "230 Ink 8.F.35 \n", + "231 Ink 3.E.15 \n", + "\n", + " Titel \n", + "0 De civitate dei \\\n", + "1 De trinitate \n", + "2 Summa de ecclesiastica potestate \n", + "3 Opera \n", + "4 De proprietatibus rerum (französ.) Le propriet... \n", + ".. ... \n", + "227 Facta et dicta memorabilia \n", + "228 Facta et dicta memorabilia \n", + "229 De viris illustribus \n", + "230 Opera [Bucolica, Georgica, Aeneis, with argume... \n", + "231 Opera \n", + "\n", + " Autor Mitwirkender \n", + "0 Augustinus, Aurelius \\\n", + "1 Augustinus, Aurelius Reyser, Georg \n", + "2 Augustinus Hongre, Pierre \n", + "3 Ausonius, Decimus Magnus Ferrarius, Julius Aemilius \n", + "4 Bartholomaeus \n", + ".. ... ... \n", + "227 Valerius \n", + "228 Valerius Maximus, Gaius \n", + "229 Aurelius Victor, Sextus (Pseudo-) \n", + "230 Vergilius Maro, Publius \n", + "231 Xenophon \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort Sprache \n", + "0 1470 Rom Latin \n", + "1 [nicht nach 1471] [Straßburg] Latin \n", + "2 [nicht nach 1480] [Lyon] Latin \n", + "3 11. Aug. 1494; [1494.08.11] Venedig Latin \n", + "4 7. Apr. 1487; [1487.04.07] Lyon French \n", + ".. ... ... ... \n", + "227 1471 [Venice] Latin \n", + "228 24 Dec. 1476 Bologna Latin \n", + "229 5. Juni 1477; [1477.06.05] Venedig Latin \n", + "230 Sept. 1478 Paris Latin \n", + "231 about 1501-02] [Milan Latin \n", + "\n", + "[232 rows x 7 columns]" + ] + }, + "execution_count": 463, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "inkunabel_metadata_df" + ] + }, + { + "cell_type": "markdown", + "id": "83e84987-b664-433e-9260-92413037164a", + "metadata": {}, + "source": [ + "# Anreichern der Tabelle mit neuen Metadaten" + ] + }, + { + "cell_type": "code", + "execution_count": 465, + "id": "f048ed87-4541-4613-9683-227a820d7321", + "metadata": { + "tags": [] + }, + "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", + "
identifierfilenamepredictionman_predictionp_Ap_Bp_Cp_Ncolorman_color...p_yellowABO-BarcodeSignaturTitelAutorMitwirkenderVeröffentlichungsdatumVeröffentlichungsortSpracheBarcode
15dtl_4968937dtl_4968937_00000001.jpgBB0.0033260.9885030.0027070.005464yellowred...0.988632NaNBE.4.L.38Les gra[n]des croniques de Bretaigne, nouvelle...Bouchard, Alain [VerfasserIn]1514ParisFrenchZ18422390X
17dtl_6529055dtl_6529055_00000001.jpgAA0.9804000.0044960.0035950.011509redred...0.098123NaNBE.2.E.4.(Vol.1)Conciliorum (Concilia) collectio regia maxima ...<a href='http://d-nb.info/gnd/122664485'>Hardo...1715Parisiis, ParisLatinZ204965809
18dtl_6529095dtl_6529095_00000001.jpgBB0.0001720.9970730.0004320.002323yellowyellow...1.000000NaNBE.5.N.37Theriaca et Alexipharmaca cum scholiis, interp...<a href='http://d-nb.info/gnd/https://d-nb.inf...1531Coloniae, KölnLatinZ173254304
19dtl_6529123dtl_6529123_00000001.jpgBB0.0003880.9936250.0006760.005310yellowblue...0.975191NaNBE.8.S.34Dialogi IV, de praedestinatione, de electione,...Chateillon, Sebastianus [VerfasserIn]1578Aresdorffij, Basileae, BaselLatinZ173255205
20dtl_6529127dtl_6529127_00000001.jpgCC0.0005800.0005180.9979570.000944yellowyellow...1.000000NaNBE.8.S.53Entretiens de Maxime et de Themiste, ou repons...Bayle, Pierre [VerfasserIn]1707RotterdamNaNZ173255102
21dtl_6529135dtl_6529135_00000001.jpgBB0.0003300.9984380.0007120.000520yellowred...0.999965NaNBE.9.V.41La Loy Salique, liuret de la premiere humaine ...Postel, Guillaume [VerfasserIn]1552ParisFrenchZ173256209
22dtl_6529147dtl_6529147_00000001.jpgBB0.0022730.9942770.0010910.002358yellowblue...0.668259NaNBE.10.O.3De vita et moribus sacerdotum opusculum: singu...<a href='http://d-nb.info/gnd/https://d-nb.inf...1520Parisiis, ParisLatinZ173252605
23rep_131EA36Arep_131EA36A_00000002.jpgBB0.0040500.9859520.0052810.004717yellowred...0.861824BE.8.P.19.20.(Vol.2)Histoire Vniverselle Des Gverres Dv Tvrc, Depv...Montreux, Nicolas <<de>>Heinrich; Mousson, Pierre; Orléans, Louis <<d'...MDCVIIIA ParisFrench; LatinNaN
\n", + "

8 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " identifier filename prediction man_prediction \n", + "15 dtl_4968937 dtl_4968937_00000001.jpg B B \\\n", + "17 dtl_6529055 dtl_6529055_00000001.jpg A A \n", + "18 dtl_6529095 dtl_6529095_00000001.jpg B B \n", + "19 dtl_6529123 dtl_6529123_00000001.jpg B B \n", + "20 dtl_6529127 dtl_6529127_00000001.jpg C C \n", + "21 dtl_6529135 dtl_6529135_00000001.jpg B B \n", + "22 dtl_6529147 dtl_6529147_00000001.jpg B B \n", + "23 rep_131EA36A rep_131EA36A_00000002.jpg B B \n", + "\n", + " p_A p_B p_C p_N color man_color ... p_yellow \n", + "15 0.003326 0.988503 0.002707 0.005464 yellow red ... 0.988632 \\\n", + "17 0.980400 0.004496 0.003595 0.011509 red red ... 0.098123 \n", + "18 0.000172 0.997073 0.000432 0.002323 yellow yellow ... 1.000000 \n", + "19 0.000388 0.993625 0.000676 0.005310 yellow blue ... 0.975191 \n", + "20 0.000580 0.000518 0.997957 0.000944 yellow yellow ... 1.000000 \n", + "21 0.000330 0.998438 0.000712 0.000520 yellow red ... 0.999965 \n", + "22 0.002273 0.994277 0.001091 0.002358 yellow blue ... 0.668259 \n", + "23 0.004050 0.985952 0.005281 0.004717 yellow red ... 0.861824 \n", + "\n", + " ABO-Barcode Signatur \n", + "15 NaN BE.4.L.38 \\\n", + "17 NaN BE.2.E.4.(Vol.1) \n", + "18 NaN BE.5.N.37 \n", + "19 NaN BE.8.S.34 \n", + "20 NaN BE.8.S.53 \n", + "21 NaN BE.9.V.41 \n", + "22 NaN BE.10.O.3 \n", + "23 BE.8.P.19.20.(Vol.2) \n", + "\n", + " Titel \n", + "15 Les gra[n]des croniques de Bretaigne, nouvelle... \\\n", + "17 Conciliorum (Concilia) collectio regia maxima ... \n", + "18 Theriaca et Alexipharmaca cum scholiis, interp... \n", + "19 Dialogi IV, de praedestinatione, de electione,... \n", + "20 Entretiens de Maxime et de Themiste, ou repons... \n", + "21 La Loy Salique, liuret de la premiere humaine ... \n", + "22 De vita et moribus sacerdotum opusculum: singu... \n", + "23 Histoire Vniverselle Des Gverres Dv Tvrc, Depv... \n", + "\n", + " Autor \n", + "15 Bouchard, Alain [VerfasserIn] \\\n", + "17 \n", + "18
> \n", + "\n", + " Mitwirkender Veröffentlichungsdatum \n", + "15 1514 \\\n", + "17 Hardo... 1715 \n", + "18 1531 \n", + "19 1578 \n", + "20 1707 \n", + "21 1552 \n", + "22 1520 \n", + "23 Heinrich; Mousson, Pierre; Orléans, Louis <\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SignaturBarcodeTitelAutorMitwirkenderAnfang VeröffentlichungsdatumEnde VeröffentlichungsdatumVeröffentlichungsdatumVeröffentlichungsortVeröffentlichungsort (normiert)...hs. Katalogbandhs. Katalogseite DigitalisatWissensklasseWissensunterklasseFormatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLclean_signature
2668BE.10.O.3+Z173252605De vita et moribus sacerdotum opusculum: singu...Clicthove, Josse 1472-1543NaN1520.0NaN1520ParisiisParis...14.376105.0TheologiaTheologi Morales, Ascetici, & ParæneticiQuarto8114.376_105_00Clichtovei (Iodoci) de vitâ & moribus Sacerdot...https://iiif.onb.ac.at/images/DOD/51202/000001...BE10O3
7325BE.2.E.4.(Vol.1)+Z204965809Conciliorum (Concilia) collectio regia maxima ...NaNHardouin, Jean 1646-17291715.0NaN1715ParisiisParis...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE2E4(Vol1)
7326BE.2.E.4.(Vol.1)NaNConciliorum (Concilia) collectio regia maxima ...NaNHardouin, Jean 1646-17291715.0NaN1715ParisiisParis...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE2E4(Vol1)
11419BE.4.L.38+Z18422390XLes gra[n]des croniques de Bretaigne, nouvelle...Bouchard, AlainNaN1514.0NaN1514ParisNaN...14.378132.0Historia Nova EuropæHistoria Provinciarum & Urbium GalliæFolio97214.378_132_071759 Les grandes Chroniques de Bretagne depuis...https://iiif.onb.ac.at/images/DOD/51219/000001...BE4L38
13416BE.5.N.37+Z173254304Theriaca et Alexipharmaca cum scholiis, interp...Nicander Colophonius ca. v2. Jh.NaN1531.0NaN1531ColoniaeKöln...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE5N37
19481BE.8.P.19.20.(Vol.2)+Z202834207Histoire Vniverselle Des Gverres Dv Tvrc, Depv...Montreux, Nicolas <<de>> 1561-1610Fouet, Robert 15XX-1642; Argenten, N. Christia...1608.0NaNMDCVIIIA ParisParis...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE8P1920(Vol2)
19851BE.8.S.34+Z173255205Dialogi IV, de praedestinatione, de electione,...Chateillon, SebastianusNaN1578.0NaN1578Aresdorffij BasileaeBasel...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE8S34
19873BE.8.S.53+Z173255102Entretiens de Maxime et de Themiste, ou repons...Bayle, PierreNaN1707.0NaN1707RotterdamNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE8S53
21991BE.9.V.41+Z173256209La Loy Salique, liuret de la premiere humaine ...Postel, GuillaumeNaN1552.0NaN1552ParisNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNBE9V41
\n", + "

9 rows × 39 columns

\n", + "" + ], + "text/plain": [ + " Signatur Barcode \n", + "2668 BE.10.O.3 +Z173252605 \\\n", + "7325 BE.2.E.4.(Vol.1) +Z204965809 \n", + "7326 BE.2.E.4.(Vol.1) NaN \n", + "11419 BE.4.L.38 +Z18422390X \n", + "13416 BE.5.N.37 +Z173254304 \n", + "19481 BE.8.P.19.20.(Vol.2) +Z202834207 \n", + "19851 BE.8.S.34 +Z173255205 \n", + "19873 BE.8.S.53 +Z173255102 \n", + "21991 BE.9.V.41 +Z173256209 \n", + "\n", + " Titel \n", + "2668 De vita et moribus sacerdotum opusculum: singu... \\\n", + "7325 Conciliorum (Concilia) collectio regia maxima ... \n", + "7326 Conciliorum (Concilia) collectio regia maxima ... \n", + "11419 Les gra[n]des croniques de Bretaigne, nouvelle... \n", + "13416 Theriaca et Alexipharmaca cum scholiis, interp... \n", + "19481 Histoire Vniverselle Des Gverres Dv Tvrc, Depv... \n", + "19851 Dialogi IV, de praedestinatione, de electione,... \n", + "19873 Entretiens de Maxime et de Themiste, ou repons... \n", + "21991 La Loy Salique, liuret de la premiere humaine ... \n", + "\n", + " Autor \n", + "2668 Clicthove, Josse 1472-1543 \\\n", + "7325 NaN \n", + "7326 NaN \n", + "11419 Bouchard, Alain \n", + "13416 Nicander Colophonius ca. v2. Jh. \n", + "19481 Montreux, Nicolas <> 1561-1610 \n", + "19851 Chateillon, Sebastianus \n", + "19873 Bayle, Pierre \n", + "21991 Postel, Guillaume \n", + "\n", + " Mitwirkender \n", + "2668 NaN \\\n", + "7325 Hardouin, Jean 1646-1729 \n", + "7326 Hardouin, Jean 1646-1729 \n", + "11419 NaN \n", + "13416 NaN \n", + "19481 Fouet, Robert 15XX-1642; Argenten, N. Christia... \n", + "19851 NaN \n", + "19873 NaN \n", + "21991 NaN \n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "2668 1520.0 NaN \\\n", + "7325 1715.0 NaN \n", + "7326 1715.0 NaN \n", + "11419 1514.0 NaN \n", + "13416 1531.0 NaN \n", + "19481 1608.0 NaN \n", + "19851 1578.0 NaN \n", + "19873 1707.0 NaN \n", + "21991 1552.0 NaN \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "2668 1520 Parisiis \\\n", + "7325 1715 Parisiis \n", + "7326 1715 Parisiis \n", + "11419 1514 Paris \n", + "13416 1531 Coloniae \n", + "19481 MDCVIII A Paris \n", + "19851 1578 Aresdorffij Basileae \n", + "19873 1707 Rotterdam \n", + "21991 1552 Paris \n", + "\n", + " Veröffentlichungsort (normiert) ... hs. Katalogband \n", + "2668 Paris ... 14.376 \\\n", + "7325 Paris ... NaN \n", + "7326 Paris ... NaN \n", + "11419 NaN ... 14.378 \n", + "13416 Köln ... NaN \n", + "19481 Paris ... NaN \n", + "19851 Basel ... NaN \n", + "19873 NaN ... NaN \n", + "21991 NaN ... NaN \n", + "\n", + " hs. Katalogseite Digitalisat Wissensklasse \n", + "2668 105.0 Theologia \\\n", + "7325 NaN NaN \n", + "7326 NaN NaN \n", + "11419 132.0 Historia Nova Europæ \n", + "13416 NaN NaN \n", + "19481 NaN NaN \n", + "19851 NaN NaN \n", + "19873 NaN NaN \n", + "21991 NaN NaN \n", + "\n", + " Wissensunterklasse Formatangabe \n", + "2668 Theologi Morales, Ascetici, & Parænetici Quarto \\\n", + "7325 NaN NaN \n", + "7326 NaN NaN \n", + "11419 Historia Provinciarum & Urbium Galliæ Folio \n", + "13416 NaN NaN \n", + "19481 NaN NaN \n", + "19851 NaN NaN \n", + "19873 NaN NaN \n", + "21991 NaN NaN \n", + "\n", + " hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "2668 81 14.376_105_00 \\\n", + "7325 NaN NaN \n", + "7326 NaN NaN \n", + "11419 972 14.378_132_07 \n", + "13416 NaN NaN \n", + "19481 NaN NaN \n", + "19851 NaN NaN \n", + "19873 NaN NaN \n", + "21991 NaN NaN \n", + "\n", + " hs. Katalogeintrag \n", + "2668 Clichtovei (Iodoci) de vitâ & moribus Sacerdot... \\\n", + "7325 NaN \n", + "7326 NaN \n", + "11419 1759 Les grandes Chroniques de Bretagne depuis... \n", + "13416 NaN \n", + "19481 NaN \n", + "19851 NaN \n", + "19873 NaN \n", + "21991 NaN \n", + "\n", + " hs. Katalog Image URL clean_signature \n", + "2668 https://iiif.onb.ac.at/images/DOD/51202/000001... BE10O3 \n", + "7325 NaN BE2E4(Vol1) \n", + "7326 NaN BE2E4(Vol1) \n", + "11419 https://iiif.onb.ac.at/images/DOD/51219/000001... BE4L38 \n", + "13416 NaN BE5N37 \n", + "19481 NaN BE8P1920(Vol2) \n", + "19851 NaN BE8S34 \n", + "19873 NaN BE8S53 \n", + "21991 NaN BE9V41 \n", + "\n", + "[9 rows x 39 columns]" + ] + }, + "execution_count": 468, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "BE_df[BE_df['Signatur'].isin(non_BE_merged['Signatur'])]" + ] + }, + { + "cell_type": "code", + "execution_count": 484, + "id": "79ed2426-daa4-46df-b148-c4773234a853", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['identifier', 'filename', 'prediction', 'man_prediction', 'p_A', 'p_B',\n", + " 'p_C', 'p_N', 'color', 'man_color', 'p_blue', 'p_red', 'p_yellow',\n", + " 'ABO-Barcode', 'Signatur', 'Titel', 'Autor', 'Mitwirkender',\n", + " 'Veröffentlichungsdatum', 'Veröffentlichungsort', 'Sprache', 'Barcode'],\n", + " dtype='object')" + ] + }, + "execution_count": 484, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_merged.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 485, + "id": "07290446-3cde-417a-8ba0-6f10959ea50e", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['Signatur', 'Barcode', 'Titel', 'Autor', 'Mitwirkender',\n", + " 'Anfang Veröffentlichungsdatum', 'Ende Veröffentlichungsdatum',\n", + " 'Veröffentlichungsdatum', 'Veröffentlichungsort',\n", + " 'Veröffentlichungsort (normiert)', 'Sprache', 'Schlagwörter',\n", + " 'Schlagwörter (mit GND)', 'Vorbesitzer', 'Typ', 'Bemerkungen',\n", + " 'Gültiger Barcode', 'Dateiname', 'Wappenklassifizierung', 'p_A', 'p_B',\n", + " 'p_C', 'p_N', 'Farbklassifizierung', 'p_blue', 'p_red', 'p_yellow',\n", + " 'hs. Katalog', 'hs. Katalog Konfidenz', 'hs. Katalogband',\n", + " 'hs. Katalogseite Digitalisat', 'Wissensklasse', 'Wissensunterklasse',\n", + " 'Formatangabe', 'hs. Katalogseite Handschrift', 'hs. Katalogeintrag ID',\n", + " 'hs. Katalogeintrag', 'hs. Katalog Image URL', 'clean_signature'],\n", + " dtype='object')" + ] + }, + "execution_count": 485, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "BE_df.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 486, + "id": "6f42f938-db2b-4854-800a-521c6845d545", + "metadata": { + "tags": [] + }, + "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", + "
SignaturBarcodeTitelAutorMitwirkenderAnfang VeröffentlichungsdatumEnde VeröffentlichungsdatumVeröffentlichungsdatumVeröffentlichungsortVeröffentlichungsort (normiert)...Formatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLclean_signatureidentifierpredictioncolorABO-Barcode
0BE.1.A.13537581-20Flora Napolitana, ossia descrizione delle pian...Tenore, MicheleNaN1811.01836.01811-36NapoliNaN...NaNNaNNaNNaNNaNBE1A1NaNNaNNaNNaN
1BE.1.C.10B1711164Flora Napolitana, ossia descrizione delle pian...Tenore, MicheleNaN1811.01836.01811-36NapoliNaN...NaNNaNNaNNaNNaNBE1C10NaNNaNNaNNaN
2BE.1.A.10B1214205Antiquites du Bosphore Cimmerien conservees au...NaNGosudarstvennyj ĖrmitažNaNNaNNaNSt. PetersburgNaN...NaNNaNNaNNaNNaNBE1A10NaNNaNNaNNaN
3BE.1.A.11B1475984Musee des antiques dessine et grave par P. Bou...Bouillon, PierreSaint-Victor, Jacques Maximilien Renjamin Bins de1811.01827.01811-1827ParisNaN...NaNNaNNaNNaNNaNBE1A11NaNNaNNaNNaN
4BE.1.A.12B1771764Divers works of early masters in christian dec...Weale, JohnNaN1846.0NaN1846LondonNaN...NaNNaNNaNNaNNaNBE1A12NaNNaNNaNNaN
..................................................................
23665Ink 4.D.15NaNFacta et dicta memorabiliaValeriusNaNNaN1471[Venice]NaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23666Ink 5.E.23NaNFacta et dicta memorabiliaValerius Maximus, GaiusNaNNaN24 Dec. 1476BolognaNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23667Ink 5.H.38NaNDe viris illustribusAurelius Victor, Sextus (Pseudo-)NaNNaN5. Juni 1477; [1477.06.05]VenedigNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23668Ink 8.F.35NaNOpera [Bucolica, Georgica, Aeneis, with argume...Vergilius Maro, PubliusNaNNaNSept. 1478ParisNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23669Ink 3.E.15NaNOperaXenophonNaNNaNabout 1501-02][MilanNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

23670 rows × 43 columns

\n", + "
" + ], + "text/plain": [ + " Signatur Barcode \n", + "0 BE.1.A.1 3537581-20 \\\n", + "1 BE.1.C.10 B1711164 \n", + "2 BE.1.A.10 B1214205 \n", + "3 BE.1.A.11 B1475984 \n", + "4 BE.1.A.12 B1771764 \n", + "... ... ... \n", + "23665 Ink 4.D.15 NaN \n", + "23666 Ink 5.E.23 NaN \n", + "23667 Ink 5.H.38 NaN \n", + "23668 Ink 8.F.35 NaN \n", + "23669 Ink 3.E.15 NaN \n", + "\n", + " Titel \n", + "0 Flora Napolitana, ossia descrizione delle pian... \\\n", + "1 Flora Napolitana, ossia descrizione delle pian... \n", + "2 Antiquites du Bosphore Cimmerien conservees au... \n", + "3 Musee des antiques dessine et grave par P. Bou... \n", + "4 Divers works of early masters in christian dec... \n", + "... ... \n", + "23665 Facta et dicta memorabilia \n", + "23666 Facta et dicta memorabilia \n", + "23667 De viris illustribus \n", + "23668 Opera [Bucolica, Georgica, Aeneis, with argume... \n", + "23669 Opera \n", + "\n", + " Autor \n", + "0 Tenore, Michele \\\n", + "1 Tenore, Michele \n", + "2 NaN \n", + "3 Bouillon, Pierre \n", + "4 Weale, John \n", + "... ... \n", + "23665 Valerius \n", + "23666 Valerius Maximus, Gaius \n", + "23667 Aurelius Victor, Sextus (Pseudo-) \n", + "23668 Vergilius Maro, Publius \n", + "23669 Xenophon \n", + "\n", + " Mitwirkender \n", + "0 NaN \\\n", + "1 NaN \n", + "2 Gosudarstvennyj Ėrmitaž \n", + "3 Saint-Victor, Jacques Maximilien Renjamin Bins de \n", + "4 NaN \n", + "... ... \n", + "23665 \n", + "23666 \n", + "23667 \n", + "23668 \n", + "23669 \n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "0 1811.0 1836.0 \\\n", + "1 1811.0 1836.0 \n", + "2 NaN NaN \n", + "3 1811.0 1827.0 \n", + "4 1846.0 NaN \n", + "... ... ... \n", + "23665 NaN NaN \n", + "23666 NaN NaN \n", + "23667 NaN NaN \n", + "23668 NaN NaN \n", + "23669 NaN NaN \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "0 1811-36 Napoli \\\n", + "1 1811-36 Napoli \n", + "2 NaN St. Petersburg \n", + "3 1811-1827 Paris \n", + "4 1846 London \n", + "... ... ... \n", + "23665 1471 [Venice] \n", + "23666 24 Dec. 1476 Bologna \n", + "23667 5. Juni 1477; [1477.06.05] Venedig \n", + "23668 Sept. 1478 Paris \n", + "23669 about 1501-02] [Milan \n", + "\n", + " Veröffentlichungsort (normiert) ... Formatangabe \n", + "0 NaN ... NaN \\\n", + "1 NaN ... NaN \n", + "2 NaN ... NaN \n", + "3 NaN ... NaN \n", + "4 NaN ... NaN \n", + "... ... ... ... \n", + "23665 NaN ... NaN \n", + "23666 NaN ... NaN \n", + "23667 NaN ... NaN \n", + "23668 NaN ... NaN \n", + "23669 NaN ... NaN \n", + "\n", + " hs. Katalogseite Handschrift hs. Katalogeintrag ID hs. Katalogeintrag \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", + "23665 NaN NaN NaN \n", + "23666 NaN NaN NaN \n", + "23667 NaN NaN NaN \n", + "23668 NaN NaN NaN \n", + "23669 NaN NaN NaN \n", + "\n", + " hs. Katalog Image URL clean_signature identifier prediction color \n", + "0 NaN BE1A1 NaN NaN NaN \\\n", + "1 NaN BE1C10 NaN NaN NaN \n", + "2 NaN BE1A10 NaN NaN NaN \n", + "3 NaN BE1A11 NaN NaN NaN \n", + "4 NaN BE1A12 NaN NaN NaN \n", + "... ... ... ... ... ... \n", + "23665 NaN NaN NaN NaN NaN \n", + "23666 NaN NaN NaN NaN NaN \n", + "23667 NaN NaN NaN NaN NaN \n", + "23668 NaN NaN NaN NaN NaN \n", + "23669 NaN NaN NaN NaN NaN \n", + "\n", + " ABO-Barcode \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "... ... \n", + "23665 NaN \n", + "23666 NaN \n", + "23667 NaN \n", + "23668 NaN \n", + "23669 NaN \n", + "\n", + "[23670 rows x 43 columns]" + ] + }, + "execution_count": 486, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "non_BE_merged_cols_rename = non_BE_merged.rename(columns={'filename': 'Dateiname', 'man_prediction': 'Wappenklassifizierung', 'man_color': 'Farbklassifizierung'})\n", + "\n", + "complete_BE_df = pd.concat([BE_df, non_BE_merged_cols_rename, inkunabeln_reduced], ignore_index=True)\n", + "complete_BE_df" + ] + }, + { + "cell_type": "code", + "execution_count": 487, + "id": "0c398ac9-cd34-49a2-b6d0-d1d057d33593", + "metadata": { + "tags": [] + }, + "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", + "
SignaturBarcodeTitelAutorMitwirkenderAnfang VeröffentlichungsdatumEnde VeröffentlichungsdatumVeröffentlichungsdatumVeröffentlichungsortVeröffentlichungsort (normiert)...Formatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLclean_signatureidentifierpredictioncolorABO-Barcode
2264143.R.10NaNLes armes et blasons des chevaliers de l'ordre...Morin de la Masserie, JacquesNaNNaN[ohne Jahresangabe]ParisNaN...NaNNaNNaNNaNNaNNaNZ165045809BredZ165045809
2264256.F.25NaNMemorial historico, juridico, politico de la S...Calderon, Juan AlonsoNaNNaN[ohne Jahresangabe]o.O.NaN...NaNNaNNaNNaNNaNNaNZ16691330XAredZ16691330X
2264366.E.20NaNTeatro della gloria, consagrato a S. Felice Sa...NaNNaN[ohne Jahresangabe]o.O.NaN...NaNNaNNaNNaNNaNNaNZ16907760XAredZ16907760X
2264466.E.45NaNLes vigilles de la mort du roi Charles VII a 9...Martial d'AuvergneNaNNaN[ohne Jahresangabe]ParisNaN...NaNNaNNaNNaNNaNNaNZ169084305BredZ169084305
2264562.E.12NaNHistoriæ Flandriæ ChristianæVredius, OlivariusNaNNaN[ohne Jahresangabe]Brugis FlandrorumNaN...NaNNaNNaNNaNNaNNaNZ169788400BredZ169788400
..................................................................
23440622174-CNaNLa pratique du theatreAubignac, François-Hédelin <<d'>>NaNNaN1669ParisNaN...NaNNaNNaNNaNNaNNaNZ259430205BredZ259430205
23441622186-CNaNLe nozze degli dei. Favola rappresentata in mu...Coppola, Giovanni-CarloMassi, AmadorNaNNaN1637FirenzeNaN...NaNNaNNaNNaNNaNNaNZ259431209BredZ259431209
23442393274-BNaNAbrahami Ortelii Antverpiani Synonymia Geograp...Ortelius, AbrahamNaNNaN1578AntverpiaeNaN...NaNNaNNaNNaNNaNNaNZ260077107BredZ260077107
2344322.N.27.(Vol.2); 22.N.26.(Vol.2); 22.N.26.(Vol...NaNPoetae Christiani VeteresSedulius; Manuzio, Aldo Pio; Clarius, Daniel; ...NaNNaN1501 [1502]VenetiisNaN...NaNNaNNaNNaNNaNNaNZ43163301BredZ43163404; Z43163301
2344422.M.5NaNContinentvr hoc volvmine Georgii Trapezuntii R...GeorgiusFortunatianus, Consultus; Rutilius Lupus, Publ...NaNNaNMense Aprili 1523VenetiisNaN...NaNNaNNaNNaNNaNNaNZ43169509AredZ43169509
\n", + "

804 rows × 43 columns

\n", + "
" + ], + "text/plain": [ + " Signatur Barcode \n", + "22641 43.R.10 NaN \\\n", + "22642 56.F.25 NaN \n", + "22643 66.E.20 NaN \n", + "22644 66.E.45 NaN \n", + "22645 62.E.12 NaN \n", + "... ... ... \n", + "23440 622174-C NaN \n", + "23441 622186-C NaN \n", + "23442 393274-B NaN \n", + "23443 22.N.27.(Vol.2); 22.N.26.(Vol.2); 22.N.26.(Vol... NaN \n", + "23444 22.M.5 NaN \n", + "\n", + " Titel \n", + "22641 Les armes et blasons des chevaliers de l'ordre... \\\n", + "22642 Memorial historico, juridico, politico de la S... \n", + "22643 Teatro della gloria, consagrato a S. Felice Sa... \n", + "22644 Les vigilles de la mort du roi Charles VII a 9... \n", + "22645 Historiæ Flandriæ Christianæ \n", + "... ... \n", + "23440 La pratique du theatre \n", + "23441 Le nozze degli dei. Favola rappresentata in mu... \n", + "23442 Abrahami Ortelii Antverpiani Synonymia Geograp... \n", + "23443 Poetae Christiani Veteres \n", + "23444 Continentvr hoc volvmine Georgii Trapezuntii R... \n", + "\n", + " Autor \n", + "22641 Morin de la Masserie, Jacques \\\n", + "22642 Calderon, Juan Alonso \n", + "22643 \n", + "22644 Martial d'Auvergne \n", + "22645 Vredius, Olivarius \n", + "... ... \n", + "23440 Aubignac, François-Hédelin <> \n", + "23441 Coppola, Giovanni-Carlo \n", + "23442 Ortelius, Abraham \n", + "23443 \n", + "23444 Georgius \n", + "\n", + " Mitwirkender \n", + "22641 \\\n", + "22642 \n", + "22643 \n", + "22644 \n", + "22645 \n", + "... ... \n", + "23440 \n", + "23441 Massi, Amador \n", + "23442 \n", + "23443 Sedulius; Manuzio, Aldo Pio; Clarius, Daniel; ... \n", + "23444 Fortunatianus, Consultus; Rutilius Lupus, Publ... \n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "22641 NaN NaN \\\n", + "22642 NaN NaN \n", + "22643 NaN NaN \n", + "22644 NaN NaN \n", + "22645 NaN NaN \n", + "... ... ... \n", + "23440 NaN NaN \n", + "23441 NaN NaN \n", + "23442 NaN NaN \n", + "23443 NaN NaN \n", + "23444 NaN NaN \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "22641 [ohne Jahresangabe] Paris \\\n", + "22642 [ohne Jahresangabe] o.O. \n", + "22643 [ohne Jahresangabe] o.O. \n", + "22644 [ohne Jahresangabe] Paris \n", + "22645 [ohne Jahresangabe] Brugis Flandrorum \n", + "... ... ... \n", + "23440 1669 Paris \n", + "23441 1637 Firenze \n", + "23442 1578 Antverpiae \n", + "23443 1501 [1502] Venetiis \n", + "23444 Mense Aprili 1523 Venetiis \n", + "\n", + " Veröffentlichungsort (normiert) ... Formatangabe \n", + "22641 NaN ... NaN \\\n", + "22642 NaN ... NaN \n", + "22643 NaN ... NaN \n", + "22644 NaN ... NaN \n", + "22645 NaN ... NaN \n", + "... ... ... ... \n", + "23440 NaN ... NaN \n", + "23441 NaN ... NaN \n", + "23442 NaN ... NaN \n", + "23443 NaN ... NaN \n", + "23444 NaN ... NaN \n", + "\n", + " hs. Katalogseite Handschrift hs. Katalogeintrag ID hs. Katalogeintrag \n", + "22641 NaN NaN NaN \\\n", + "22642 NaN NaN NaN \n", + "22643 NaN NaN NaN \n", + "22644 NaN NaN NaN \n", + "22645 NaN NaN NaN \n", + "... ... ... ... \n", + "23440 NaN NaN NaN \n", + "23441 NaN NaN NaN \n", + "23442 NaN NaN NaN \n", + "23443 NaN NaN NaN \n", + "23444 NaN NaN NaN \n", + "\n", + " hs. Katalog Image URL clean_signature identifier prediction color \n", + "22641 NaN NaN Z165045809 B red \\\n", + "22642 NaN NaN Z16691330X A red \n", + "22643 NaN NaN Z16907760X A red \n", + "22644 NaN NaN Z169084305 B red \n", + "22645 NaN NaN Z169788400 B red \n", + "... ... ... ... ... ... \n", + "23440 NaN NaN Z259430205 B red \n", + "23441 NaN NaN Z259431209 B red \n", + "23442 NaN NaN Z260077107 B red \n", + "23443 NaN NaN Z43163301 B red \n", + "23444 NaN NaN Z43169509 A red \n", + "\n", + " ABO-Barcode \n", + "22641 Z165045809 \n", + "22642 Z16691330X \n", + "22643 Z16907760X \n", + "22644 Z169084305 \n", + "22645 Z169788400 \n", + "... ... \n", + "23440 Z259430205 \n", + "23441 Z259431209 \n", + "23442 Z260077107 \n", + "23443 Z43163404; Z43163301 \n", + "23444 Z43169509 \n", + "\n", + "[804 rows x 43 columns]" + ] + }, + "execution_count": 487, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# original BE_df\n", + "complete_BE_df.loc[0:22640]\n", + "# non_BE_merged\n", + "complete_BE_df.loc[22641:23444]\n", + "# inkunabeln_reduced\n", + "# complete_BE_df.loc[23445:]" + ] + }, + { + "cell_type": "code", + "execution_count": 488, + "id": "c4a51434-6356-4d5b-9bb4-7737dc26046a", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['Signatur', 'Barcode', 'Titel', 'Autor', 'Mitwirkender',\n", + " 'Anfang Veröffentlichungsdatum', 'Ende Veröffentlichungsdatum',\n", + " 'Veröffentlichungsdatum', 'Veröffentlichungsort',\n", + " 'Veröffentlichungsort (normiert)', 'Sprache', 'Schlagwörter',\n", + " 'Schlagwörter (mit GND)', 'Vorbesitzer', 'Typ', 'Bemerkungen',\n", + " 'Gültiger Barcode', 'Dateiname', 'Wappenklassifizierung', 'p_A', 'p_B',\n", + " 'p_C', 'p_N', 'Farbklassifizierung', 'p_blue', 'p_red', 'p_yellow',\n", + " 'hs. Katalog', 'hs. Katalog Konfidenz', 'hs. Katalogband',\n", + " 'hs. Katalogseite Digitalisat', 'Wissensklasse', 'Wissensunterklasse',\n", + " 'Formatangabe', 'hs. Katalogseite Handschrift', 'hs. Katalogeintrag ID',\n", + " 'hs. Katalogeintrag', 'hs. Katalog Image URL', 'clean_signature',\n", + " 'identifier', 'prediction', 'color', 'ABO-Barcode'],\n", + " dtype='object')" + ] + }, + "execution_count": 488, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "complete_BE_df.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 493, + "id": "d4d83256-5d0d-433f-b3fa-f7ea01ad4ca8", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "to_be_saved = complete_BE_df.drop(['prediction', 'color', 'clean_signature'], axis=1)" + ] + }, + { + "cell_type": "code", + "execution_count": 494, + "id": "8f4eab54-4475-4b8e-a4f0-1397290d28f1", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "to_be_saved.to_excel('../Daten/Vorhersagen/WIP_complete_BE.xlsx', index=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "332be4f7-e0e1-4a7c-9aac-a1f42c1df383", "metadata": {}, "outputs": [], "source": [] diff --git a/Notebooks/String_matching.ipynb b/Notebooks/String_matching.ipynb index 35a997eb2e79d7a627c8013cf6fa7119652140b3..f47ceca69e8e8fc82ae84f54d93fdf1afefaa2d1 100644 --- a/Notebooks/String_matching.ipynb +++ b/Notebooks/String_matching.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 2, + "execution_count": 17, "id": "7a3837ac-cced-4e01-bf57-265e40729692", "metadata": { "tags": [] @@ -23,7 +23,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 18, "id": "29ca0dc8-cae7-4f12-bd60-fd74ea6ae5ac", "metadata": { "tags": [] @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 19, "id": "c1e1c42a-962f-40bc-bb17-b62e8089feb7", "metadata": { "tags": [] @@ -47,7 +47,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 20, "id": "50d15898-4687-46b7-b7e0-528d7cf9aec0", "metadata": { "tags": [] @@ -69,7 +69,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 21, "id": "990dfeee-1141-4acb-8a3d-a7af0573f5be", "metadata": { "tags": [] @@ -84,7 +84,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 22, "id": "bcd301fe-cb80-4b1c-b65f-465fce5ed915", "metadata": { "tags": [] @@ -104,7 +104,7 @@ " 0.0307618118822574]], dtype=object)" ] }, - "execution_count": 7, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } @@ -115,7 +115,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 38, "id": "c0f4a42a-7e21-41e8-833c-2dd2f9d1985e", "metadata": { "tags": [] @@ -125,7 +125,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "5\n" + "3\n" ] }, { @@ -162,107 +162,73 @@ " \n", " \n", " \n", - " 104\n", + " 1824\n", " 14.376\n", - " 39\n", - " Theologia\n", - " Critici Sacri\n", + " 307\n", + " Historia Naturalis\n", + " Animalium Historia\n", " Folio\n", - " 15\n", - " 14.376_039_05\n", - " 51 Lamy (Bernardi) de Tabernaculo foederis, de Sanctâ Civitate Ierusalem, ac de Templo ejus Libri VII. cum fig. chartâ M. Parisiis. 1720. Ioan. Mariette n. 44.\n", - " Lamy Bernardi de Tabernaculo foederis de Sancta Civitate Ierusalem ac de Templo ejus Libri VII cum fig charta M Parisiis 1720 Ioan Mariette n 44\n", + " 267\n", + " 14.376_307_05\n", + " 505 xAlberti Magni Opera de Animalibus, chartâ magnâ, Mantuæ. 1479. Paul. I. de Burschbach. n. 2111. Cotesby (Marc.) Histoire naturelle ele la Ca= roline, la Floride et les Istes Baliama, London 1731. 2. Vol. nro CXCIIX. * Recueil des Oiseaux terrestres et aquatiques dela menagerie Imple de Schönbrun. peints au naturel depuis l'anneé 1752. fol sur velin. 4 vol -----\n", + " xAlberti Magni Opera de Animalibus charta magna Mantuae 1479 Paul I de Burschbach n 2111 Cotesby Marc Histoire naturelle ele la Caroline la Floride et les Istes Baliama London 1731 2 Vol nro CXCIIX * Recueil des Oiseaux terrestres et aquatiques dela menagerie Imple de Schönbrun peints au naturel depuis l'annee 1752 fol sur velin 4 vol -----\n", " \n", " \n", - " 280\n", + " 1924\n", " 14.376\n", - " 76\n", - " Theologia\n", - " Sanctissimi Patres Latini\n", - " Folio\n", - " 52\n", - " 14.376_076_05\n", - " 113.......... Ejusdem de Civitate Dei opus. chartâ M. Rom. 1470. Sweynheym & Pannart. n. 2100. XI. P. 10*\n", - " Ejusdem de Civitate Dei opus charta M Rom 1470 Sweynheym & Pannart n 2100 XI P 10*\n", + " 326\n", + " Medicina\n", + " Medicina, Chirurgia, Anatomia, Pharmacia & Chimia\n", + " Quarto\n", + " 284\n", + " 14.376_326_05\n", + " Alberti Magni Liber Aggregationis, seu Secretorum de virtutibus Herbarum, Lapidum, & Animalium. editio antiqua sine loco & anno. n. 2421.\n", + " Alberti Magni Liber Aggregationis seu Secretorum de virtutibus Herbarum Lapidum & Animalium editio antiqua sine loco & anno n 2421\n", " \n", " \n", - " 281\n", + " 1955\n", " 14.376\n", - " 76\n", - " Theologia\n", - " Sanctissimi Patres Latini\n", - " Folio\n", - " 52\n", - " 14.376_076_06\n", - " 114......... Ejusdem de Civitate Dei opus. in membranis. Venet. 1475. Nic. Ienson. 2225 XI. P. 22.\n", - " Ejusdem de Civitate Dei opus in membranis Venet 1475 Nic Ienson 2225 XI P 22\n", - " \n", - " \n", - " 4793\n", - " 14.377\n", - " 256\n", - " Philologia\n", - " Satyræ, Apologiæ, ac dissertationes variæ\n", + " 330\n", + " Medicina\n", + " Medicina, Chirurgia, Anatomia, Pharmacia & Chimia\n", " Octavo und kleiner\n", - " 652\n", - " 14.377_256_05\n", - " Arntzenij Dissertationes binæ quarum prior de Colore ac tincturâ Comarum, postetior vero de Civitate Rom: Pauli Apostoli. 12.° Trajecti ad Rhen. 1725. Kroon. n. 1693\n", - " Arntzenij Dissertationes binae quarum prior de Colore ac tinctura Comarum postetior vero de Civitate Rom Pauli Apostoli 12° Trajecti ad Rhen 1725 Kroon n 1693\n", - " \n", - " \n", - " 6885\n", - " 14.378\n", - " 170\n", - " Historia Nova Europæ\n", - " Historia & descriptio Regionum Germaniæ\n", - " Quarto\n", - " 1008\n", - " 14.378_170_05\n", - " Nullitas Iniquitasque reünionis Alsatiæ; seu revisio Actorum demonstrantium Gallos supremum Imperium territoriale non magis in X Civitates Imperiales¬ unitas, quam in reliquos per utramque Alsatiam, Romano Imperio immediaté Subjectos ordines hactenùs tenuisse. 1707. absque loco Editionis. n. 720.*.\n", - " Nullitas Iniquitasque reünionis Alsatiae seu revisio Actorum demonstrantium Gallos supremum Imperium territoriale non magis in X Civitates Imperiales unitas quam in reliquos per utramque Alsatiam Romano Imperio immediate Subjectos ordines hactenus tenuisse 1707 absque loco Editionis n 720*\n", + " 288\n", + " 14.376_330_00\n", + " xAlberti Magni Secreta Mulierum ac Virorum, necnon de virtutibus Herbarum, Lapidum, & Animal. Tractat 12°. Editio perantïqua sine loco & anno. n. 680.\n", + " xAlberti Magni Secreta Mulierum ac Virorum necnon de virtutibus Herbarum Lapidum & Animal Tractat 12° Editio perantiqua sine loco & anno n 680\n", " \n", " \n", "\n", "" ], "text/plain": [ - " volume page number category \n", - "104 14.376 39 Theologia \\\n", - "280 14.376 76 Theologia \n", - "281 14.376 76 Theologia \n", - "4793 14.377 256 Philologia \n", - "6885 14.378 170 Historia Nova Europæ \n", + " volume page number category \n", + "1824 14.376 307 Historia Naturalis \\\n", + "1924 14.376 326 Medicina \n", + "1955 14.376 330 Medicina \n", "\n", - " subcategory format \n", - "104 Critici Sacri Folio \\\n", - "280 Sanctissimi Patres Latini Folio \n", - "281 Sanctissimi Patres Latini Folio \n", - "4793 Satyræ, Apologiæ, ac dissertationes variæ Octavo und kleiner \n", - "6885 Historia & descriptio Regionum Germaniæ Quarto \n", + " subcategory format \n", + "1824 Animalium Historia Folio \\\n", + "1924 Medicina, Chirurgia, Anatomia, Pharmacia & Chimia Quarto \n", + "1955 Medicina, Chirurgia, Anatomia, Pharmacia & Chimia Octavo und kleiner \n", "\n", " handwritten page number entry_ID \n", - "104 15 14.376_039_05 \\\n", - "280 52 14.376_076_05 \n", - "281 52 14.376_076_06 \n", - "4793 652 14.377_256_05 \n", - "6885 1008 14.378_170_05 \n", + "1824 267 14.376_307_05 \\\n", + "1924 284 14.376_326_05 \n", + "1955 288 14.376_330_00 \n", "\n", - " entry \n", - "104 51 Lamy (Bernardi) de Tabernaculo foederis, de Sanctâ Civitate Ierusalem, ac de Templo ejus Libri VII. cum fig. chartâ M. Parisiis. 1720. Ioan. Mariette n. 44. \\\n", - "280 113.......... Ejusdem de Civitate Dei opus. chartâ M. Rom. 1470. Sweynheym & Pannart. n. 2100. XI. P. 10* \n", - "281 114......... Ejusdem de Civitate Dei opus. in membranis. Venet. 1475. Nic. Ienson. 2225 XI. P. 22. \n", - "4793 Arntzenij Dissertationes binæ quarum prior de Colore ac tincturâ Comarum, postetior vero de Civitate Rom: Pauli Apostoli. 12.° Trajecti ad Rhen. 1725. Kroon. n. 1693 \n", - "6885 Nullitas Iniquitasque reünionis Alsatiæ; seu revisio Actorum demonstrantium Gallos supremum Imperium territoriale non magis in X Civitates Imperiales¬ unitas, quam in reliquos per utramque Alsatiam, Romano Imperio immediaté Subjectos ordines hactenùs tenuisse. 1707. absque loco Editionis. n. 720.*. \n", + " entry \n", + "1824 505 xAlberti Magni Opera de Animalibus, chartâ magnâ, Mantuæ. 1479. Paul. I. de Burschbach. n. 2111. Cotesby (Marc.) Histoire naturelle ele la Ca= roline, la Floride et les Istes Baliama, London 1731. 2. Vol. nro CXCIIX. * Recueil des Oiseaux terrestres et aquatiques dela menagerie Imple de Schönbrun. peints au naturel depuis l'anneé 1752. fol sur velin. 4 vol ----- \\\n", + "1924 Alberti Magni Liber Aggregationis, seu Secretorum de virtutibus Herbarum, Lapidum, & Animalium. editio antiqua sine loco & anno. n. 2421. \n", + "1955 xAlberti Magni Secreta Mulierum ac Virorum, necnon de virtutibus Herbarum, Lapidum, & Animal. Tractat 12°. Editio perantïqua sine loco & anno. n. 680. \n", "\n", - " cleaned entry \n", - "104 Lamy Bernardi de Tabernaculo foederis de Sancta Civitate Ierusalem ac de Templo ejus Libri VII cum fig charta M Parisiis 1720 Ioan Mariette n 44 \n", - "280 Ejusdem de Civitate Dei opus charta M Rom 1470 Sweynheym & Pannart n 2100 XI P 10* \n", - "281 Ejusdem de Civitate Dei opus in membranis Venet 1475 Nic Ienson 2225 XI P 22 \n", - "4793 Arntzenij Dissertationes binae quarum prior de Colore ac tinctura Comarum postetior vero de Civitate Rom Pauli Apostoli 12° Trajecti ad Rhen 1725 Kroon n 1693 \n", - "6885 Nullitas Iniquitasque reünionis Alsatiae seu revisio Actorum demonstrantium Gallos supremum Imperium territoriale non magis in X Civitates Imperiales unitas quam in reliquos per utramque Alsatiam Romano Imperio immediate Subjectos ordines hactenus tenuisse 1707 absque loco Editionis n 720* " + " cleaned entry \n", + "1824 xAlberti Magni Opera de Animalibus charta magna Mantuae 1479 Paul I de Burschbach n 2111 Cotesby Marc Histoire naturelle ele la Caroline la Floride et les Istes Baliama London 1731 2 Vol nro CXCIIX * Recueil des Oiseaux terrestres et aquatiques dela menagerie Imple de Schönbrun peints au naturel depuis l'annee 1752 fol sur velin 4 vol ----- \n", + "1924 Alberti Magni Liber Aggregationis seu Secretorum de virtutibus Herbarum Lapidum & Animalium editio antiqua sine loco & anno n 2421 \n", + "1955 xAlberti Magni Secreta Mulierum ac Virorum necnon de virtutibus Herbarum Lapidum & Animal Tractat 12° Editio perantiqua sine loco & anno n 680 " ] }, - "execution_count": 32, + "execution_count": 38, "metadata": {}, "output_type": "execute_result" } @@ -271,17 +237,19 @@ "def search_in_entry(df, string):\n", " return df[df['cleaned entry'].str.contains(string)]\n", "\n", - "info = search_in_entry(search_in_entry(entry_df, 'Civitate'), '')\n", + "info = search_in_entry(search_in_entry(entry_df, 'Albert'), '')\n", "print(len(info))\n", "info" ] }, { - "cell_type": "markdown", - "id": "2dd8e294-541c-4fb1-9dfe-949db3dbaf39", + "cell_type": "code", + "execution_count": null, + "id": "4131e38a-a4cd-4bdf-b39e-8e79ffa3f665", "metadata": { "tags": [] }, + "outputs": [], "source": [ "entry_df.loc[185]" ]