diff --git a/Daten/Vorhersagen/Complete_BE.xlsx b/Daten/Vorhersagen/Complete_BE.xlsx index bcb86b3127f0d6bcef2c0a4e84981b6d18f1675b..3b9acd1d3aaf0e3ac2b33f7fe96155a45ace5e38 100644 Binary files a/Daten/Vorhersagen/Complete_BE.xlsx and b/Daten/Vorhersagen/Complete_BE.xlsx differ diff --git a/Notebooks/Remaining_barcodes_and_metadata.ipynb b/Notebooks/Remaining_barcodes_and_metadata.ipynb index 4fbe68ec9e6c5dd497be56663d93bbf30bb8c74c..9701a7adf35484d52ad65547b5d606a8d50e01a7 100644 --- a/Notebooks/Remaining_barcodes_and_metadata.ipynb +++ b/Notebooks/Remaining_barcodes_and_metadata.ipynb @@ -11,7 +11,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 1, @@ -2914,7 +2914,28 @@ }, { "cell_type": "code", - "execution_count": 444, + "execution_count": 161, + "id": "fae27a43-522a-496f-932c-c79106f90399", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_7777/2104561393.py:1: DtypeWarning: Columns (8,9) have mixed types. Specify dtype option on import or set low_memory=False.\n", + " most_final_drop_dup = pd.read_csv('data/predictions/all_pred_final.csv')\n" + ] + } + ], + "source": [ + "most_final_drop_dup = pd.read_csv('data/predictions/all_pred_final.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 162, "id": "eedf9265-8b9d-451e-b576-eedd5b7dd7a7", "metadata": { "tags": [] @@ -2958,7 +2979,7 @@ " \n", " \n", " \n", - " 563988\n", + " 557827\n", " Z158720500\n", " Z158720500_00000001.jpg\n", " N\n", @@ -2974,7 +2995,7 @@ " NaN\n", " \n", " \n", - " 563989\n", + " 557828\n", " Z158720500\n", " Z158720500_00000002.jpg\n", " N\n", @@ -2990,7 +3011,7 @@ " NaN\n", " \n", " \n", - " 563990\n", + " 557829\n", " Z158720500\n", " Z158720500_00000003.jpg\n", " N\n", @@ -3006,7 +3027,7 @@ " NaN\n", " \n", " \n", - " 563991\n", + " 557830\n", " Z158720500\n", " Z158720500_00000004.jpg\n", " N\n", @@ -3022,7 +3043,7 @@ " NaN\n", " \n", " \n", - " 563992\n", + " 557831\n", " Z158720500\n", " Z158720500_00000005.jpg\n", " N\n", @@ -3043,28 +3064,28 @@ ], "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", + "557827 Z158720500 Z158720500_00000001.jpg N NaN \\\n", + "557828 Z158720500 Z158720500_00000002.jpg N NaN \n", + "557829 Z158720500 Z158720500_00000003.jpg N NaN \n", + "557830 Z158720500 Z158720500_00000004.jpg N NaN \n", + "557831 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", + "557827 0.071688 0.087697 0.076388 0.764227 NaN NaN NaN NaN \\\n", + "557828 0.054458 0.047184 0.090421 0.807938 NaN NaN NaN NaN \n", + "557829 0.044733 0.039233 0.076673 0.839361 NaN NaN NaN NaN \n", + "557830 0.135032 0.062550 0.076818 0.725600 NaN NaN NaN NaN \n", + "557831 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 " + "557827 NaN \n", + "557828 NaN \n", + "557829 NaN \n", + "557830 NaN \n", + "557831 NaN " ] }, - "execution_count": 444, + "execution_count": 162, "metadata": {}, "output_type": "execute_result" } @@ -3075,7 +3096,7 @@ }, { "cell_type": "code", - "execution_count": 71, + "execution_count": 163, "id": "6abcfc24-9568-4729-a7ac-650a508babdf", "metadata": { "tags": [] @@ -3090,7 +3111,7 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 164, "id": "39d1c25b-efa4-4c9a-93a0-65b66b4d3259", "metadata": { "tags": [] @@ -3134,7 +3155,7 @@ " \n", " \n", " \n", - " 571770\n", + " 565609\n", " Z165045809\n", " Z165045809_00000001.jpg\n", " B\n", @@ -3150,7 +3171,7 @@ " 0.063229\n", " \n", " \n", - " 573009\n", + " 566848\n", " Z16691330X\n", " Z16691330X_00000001.jpg\n", " A\n", @@ -3166,7 +3187,7 @@ " 0.013185\n", " \n", " \n", - " 574380\n", + " 568219\n", " Z16907760X\n", " Z16907760X_00000001.jpg\n", " A\n", @@ -3182,7 +3203,7 @@ " 0.013297\n", " \n", " \n", - " 574405\n", + " 568244\n", " Z169084305\n", " Z169084305_00000001.jpg\n", " B\n", @@ -3198,7 +3219,7 @@ " 0.094729\n", " \n", " \n", - " 575078\n", + " 568917\n", " Z169788400\n", " Z169788400_00000001.jpg\n", " B\n", @@ -3230,7 +3251,7 @@ " ...\n", " \n", " \n", - " 616372\n", + " 610211\n", " Z43163301\n", " Z43163301_00000001.jpg\n", " B\n", @@ -3246,7 +3267,7 @@ " 0.001197\n", " \n", " \n", - " 616373\n", + " 610212\n", " Z43165504\n", " Z43165504_00000001.jpg\n", " B\n", @@ -3262,7 +3283,7 @@ " 0.002438\n", " \n", " \n", - " 616374\n", + " 610213\n", " Z43169509\n", " Z43169509_00000001.jpg\n", " A\n", @@ -3278,7 +3299,7 @@ " 0.000170\n", " \n", " \n", - " 616375\n", + " 610214\n", " Z43173306\n", " Z43173306_00000001.jpg\n", " B\n", @@ -3294,7 +3315,7 @@ " 0.000969\n", " \n", " \n", - " 616376\n", + " 610215\n", " Z95576003\n", " Z95576003_00000001.jpg\n", " A\n", @@ -3316,48 +3337,48 @@ ], "text/plain": [ " identifier filename prediction man_prediction \n", - "571770 Z165045809 Z165045809_00000001.jpg B B \\\n", - "573009 Z16691330X Z16691330X_00000001.jpg A A \n", - "574380 Z16907760X Z16907760X_00000001.jpg A A \n", - "574405 Z169084305 Z169084305_00000001.jpg B B \n", - "575078 Z169788400 Z169788400_00000001.jpg B B \n", + "565609 Z165045809 Z165045809_00000001.jpg B B \\\n", + "566848 Z16691330X Z16691330X_00000001.jpg A A \n", + "568219 Z16907760X Z16907760X_00000001.jpg A A \n", + "568244 Z169084305 Z169084305_00000001.jpg B B \n", + "568917 Z169788400 Z169788400_00000001.jpg B B \n", "... ... ... ... ... \n", - "616372 Z43163301 Z43163301_00000001.jpg B B \n", - "616373 Z43165504 Z43165504_00000001.jpg B B \n", - "616374 Z43169509 Z43169509_00000001.jpg A A \n", - "616375 Z43173306 Z43173306_00000001.jpg B B \n", - "616376 Z95576003 Z95576003_00000001.jpg A A \n", + "610211 Z43163301 Z43163301_00000001.jpg B B \n", + "610212 Z43165504 Z43165504_00000001.jpg B B \n", + "610213 Z43169509 Z43169509_00000001.jpg A A \n", + "610214 Z43173306 Z43173306_00000001.jpg B B \n", + "610215 Z95576003 Z95576003_00000001.jpg A A \n", "\n", " p_A p_B p_C p_N color man_color p_blue \n", - "571770 0.002351 0.992441 0.001475 0.003733 red red 0.012432 \\\n", - "573009 0.989787 0.002023 0.003616 0.004575 red red 0.000789 \n", - "574380 0.998806 0.000339 0.000304 0.000550 red red 0.000579 \n", - "574405 0.002039 0.992877 0.001886 0.003197 red red 0.032795 \n", - "575078 0.001686 0.993389 0.002714 0.002212 red red 0.001785 \n", + "565609 0.002351 0.992441 0.001475 0.003733 red red 0.012432 \\\n", + "566848 0.989787 0.002023 0.003616 0.004575 red red 0.000789 \n", + "568219 0.998806 0.000339 0.000304 0.000550 red red 0.000579 \n", + "568244 0.002039 0.992877 0.001886 0.003197 red red 0.032795 \n", + "568917 0.001686 0.993389 0.002714 0.002212 red red 0.001785 \n", "... ... ... ... ... ... ... ... \n", - "616372 0.000872 0.998139 0.000583 0.000406 red red 0.000331 \n", - "616373 0.000670 0.998324 0.000560 0.000445 red red 0.001188 \n", - "616374 0.995156 0.001711 0.002191 0.000941 red red 0.000120 \n", - "616375 0.000573 0.998986 0.000175 0.000266 red red 0.001646 \n", - "616376 0.997559 0.001285 0.000620 0.000536 yellow yellow 0.000414 \n", + "610211 0.000872 0.998139 0.000583 0.000406 red red 0.000331 \n", + "610212 0.000670 0.998324 0.000560 0.000445 red red 0.001188 \n", + "610213 0.995156 0.001711 0.002191 0.000941 red red 0.000120 \n", + "610214 0.000573 0.998986 0.000175 0.000266 red red 0.001646 \n", + "610215 0.997559 0.001285 0.000620 0.000536 yellow yellow 0.000414 \n", "\n", " p_red p_yellow \n", - "571770 0.924339 0.063229 \n", - "573009 0.986026 0.013185 \n", - "574380 0.986124 0.013297 \n", - "574405 0.872476 0.094729 \n", - "575078 0.991588 0.006627 \n", + "565609 0.924339 0.063229 \n", + "566848 0.986026 0.013185 \n", + "568219 0.986124 0.013297 \n", + "568244 0.872476 0.094729 \n", + "568917 0.991588 0.006627 \n", "... ... ... \n", - "616372 0.998473 0.001197 \n", - "616373 0.996374 0.002438 \n", - "616374 0.999710 0.000170 \n", - "616375 0.997385 0.000969 \n", - "616376 0.009923 0.989663 \n", + "610211 0.998473 0.001197 \n", + "610212 0.996374 0.002438 \n", + "610213 0.999710 0.000170 \n", + "610214 0.997385 0.000969 \n", + "610215 0.009923 0.989663 \n", "\n", "[6151 rows x 13 columns]" ] }, - "execution_count": 79, + "execution_count": 164, "metadata": {}, "output_type": "execute_result" } @@ -3380,7 +3401,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 165, "id": "563e1571-ba77-49e1-a886-c5b4537d3231", "metadata": { "tags": [] @@ -3392,7 +3413,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 166, "id": "50313913-feb6-428e-af42-5c7f677269af", "metadata": { "tags": [] @@ -3659,7 +3680,7 @@ "[6215 rows x 13 columns]" ] }, - "execution_count": 5, + "execution_count": 166, "metadata": {}, "output_type": "execute_result" } @@ -3678,7 +3699,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 167, "id": "2c090fa7-f6be-474c-9e20-e92b75418183", "metadata": { "tags": [] @@ -3690,7 +3711,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 168, "id": "e8ea4fe0-dd29-4005-8503-3c3feee93d25", "metadata": { "tags": [] @@ -3702,7 +3723,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 169, "id": "1faa1f80-d284-4c6f-86a7-a1f230576ea3", "metadata": { "tags": [] @@ -3725,7 +3746,7 @@ " dtype='object')" ] }, - "execution_count": 8, + "execution_count": 169, "metadata": {}, "output_type": "execute_result" } @@ -3736,7 +3757,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 170, "id": "96ae8472-5308-4506-b69f-94650beb5d95", "metadata": { "tags": [] @@ -3748,7 +3769,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 171, "id": "63a33898-5fb0-47b0-8662-f8163131ca3a", "metadata": { "tags": [] @@ -3760,7 +3781,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 172, "id": "b0f03031-5d5f-483f-b7d2-770fdd9f563f", "metadata": { "tags": [] @@ -3782,7 +3803,7 @@ "Name: identifier, dtype: object" ] }, - "execution_count": 11, + "execution_count": 172, "metadata": {}, "output_type": "execute_result" } @@ -3794,7 +3815,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 173, "id": "bb150371-3990-4a72-8a3c-451478083d54", "metadata": { "tags": [] @@ -3833,7 +3854,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 174, "id": "7b90d595-ad11-477a-b3a8-8662191ec55e", "metadata": { "tags": [] @@ -3846,7 +3867,7 @@ "Name: identifier, dtype: object" ] }, - "execution_count": 13, + "execution_count": 174, "metadata": {}, "output_type": "execute_result" } @@ -3857,7 +3878,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 175, "id": "4a2f570d-fca7-49fb-8f84-c6a6a435a9f7", "metadata": { "tags": [] @@ -3973,7 +3994,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 176, "id": "6f6d2e5e-c056-4d72-b890-7247fb42b7f1", "metadata": { "tags": [] @@ -3982,7 +4003,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "64070ce7edf24a94b4f28255b3f6cbd7", + "model_id": "bfe7fd3687ec4697bd75aa5cded700ff", "version_major": 2, "version_minor": 0 }, @@ -4003,7 +4024,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 177, "id": "94f3695b-1e69-4501-bf7a-bdc392f34b9e", "metadata": { "tags": [] @@ -4418,7 +4439,7 @@ "[804 rows x 22 columns]" ] }, - "execution_count": 16, + "execution_count": 177, "metadata": {}, "output_type": "execute_result" } @@ -4432,7 +4453,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 178, "id": "8f74b754-71ef-4386-b398-da991d47c44c", "metadata": { "tags": [] @@ -4754,7 +4775,7 @@ "[8 rows x 22 columns]" ] }, - "execution_count": 17, + "execution_count": 178, "metadata": {}, "output_type": "execute_result" } @@ -4765,7 +4786,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 179, "id": "03f93d26-69ba-4576-a9d5-eab1658db033", "metadata": { "tags": [] @@ -4785,7 +4806,7 @@ "Name: Signatur, dtype: object" ] }, - "execution_count": 18, + "execution_count": 179, "metadata": {}, "output_type": "execute_result" } @@ -4804,7 +4825,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 180, "id": "d9d94a3c-03c2-4ab3-a36e-71de47d95563", "metadata": { "tags": [] @@ -4817,7 +4838,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 181, "id": "5b39cc07-2906-4841-ac30-9df293ab2fba", "metadata": { "tags": [] @@ -4840,7 +4861,7 @@ "Name: clean_signature, Length: 252, dtype: object" ] }, - "execution_count": 20, + "execution_count": 181, "metadata": {}, "output_type": "execute_result" } @@ -4851,7 +4872,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 182, "id": "a0f1db41-696c-4716-a006-cef7e4e1b2fb", "metadata": { "tags": [] @@ -4863,7 +4884,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 183, "id": "44e1ca58-6466-43e0-b6f0-68513718477e", "metadata": { "tags": [] @@ -4875,7 +4896,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 184, "id": "e9f62a92-5ccd-4b2e-916a-0bd3430b0867", "metadata": { "tags": [] @@ -4896,7 +4917,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 185, "id": "af90c6f4-0aec-4b5d-80f6-03bdc3b38bd9", "metadata": { "tags": [] @@ -4906,7 +4927,7 @@ "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" + "{'Titel': 'De civitate dei', 'Signatur': 'Ink. 5.B.12', 'Autor': 'Augustinus, Aurelius', 'Mitwirkender': '', 'Veröffentlichungsdatum': '1470', 'Veröffentlichungsort': 'Rom', 'Sprache': 'Latin'}\n" ] } ], @@ -4918,7 +4939,7 @@ " marcxml = sru_request.content\n", " tree = etree.fromstring(marcxml)\n", " marc_paths = {\n", - " 'Signatur': './/marc:datafield[@tag=\"AVA\"]/marc:subfield[@code=\"d\"]',\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", @@ -4935,8 +4956,9 @@ " 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", + " metadata['Signatur'] = sig\n", + " # if metadata['Signatur'] == '':\n", + " # metadata['Signatur'] = sig\n", " return metadata\n", "\n", "print(extract_catalog_data_from_signature('Ink. 5.B.12'))" @@ -4944,7 +4966,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 186, "id": "a1b09796-5790-48e4-a752-dbff8f074ee5", "metadata": { "tags": [] @@ -4953,7 +4975,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "c070bc33faef43b98bf05ab2f5426f56", + "model_id": "08bcdf324ed349bbb3fb364915077674", "version_major": 2, "version_minor": 0 }, @@ -4974,7 +4996,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 187, "id": "36f0635b-e495-43cc-b821-495d0f89080f", "metadata": { "tags": [] @@ -4986,7 +5008,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 188, "id": "11c58f53-2958-4669-9210-949bcaba6bcf", "metadata": { "tags": [] @@ -5007,7 +5029,7 @@ "dtype: object" ] }, - "execution_count": 27, + "execution_count": 188, "metadata": {}, "output_type": "execute_result" } @@ -5018,7 +5040,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 189, "id": "70262b42-b0a8-442f-8d42-74e3013c2d22", "metadata": { "tags": [] @@ -5042,7 +5064,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 190, "id": "b7753144-b97d-4263-990c-997845300859", "metadata": { "tags": [] @@ -5069,8 +5091,8 @@ " \n", " \n", " \n", - " Signatur\n", " Titel\n", + " Signatur\n", " Autor\n", " Mitwirkender\n", " Veröffentlichungsdatum\n", @@ -5081,8 +5103,8 @@ " \n", " \n", " 0\n", - " Ink 5.B.12\n", " De civitate dei\n", + " Ink 5.B.12\n", " Augustinus, Aurelius\n", " \n", " 1470\n", @@ -5091,8 +5113,8 @@ " \n", " \n", " 1\n", - " Ink 24.B.8; Ink 3.C.8\n", " De trinitate\n", + " Ink 3.C.8\n", " Augustinus, Aurelius\n", " Reyser, Georg\n", " [nicht nach 1471]\n", @@ -5101,8 +5123,8 @@ " \n", " \n", " 2\n", - " Ink 3.E.4; Ink 31-45; Ink 24.F.30\n", " Summa de ecclesiastica potestate\n", + " Ink 3.E.4\n", " Augustinus\n", " Hongre, Pierre\n", " [nicht nach 1480]\n", @@ -5111,8 +5133,8 @@ " \n", " \n", " 3\n", - " Ink 7.E.28\n", " Opera\n", + " Ink 7.E.28\n", " Ausonius, Decimus Magnus\n", " Ferrarius, Julius Aemilius\n", " 11. Aug. 1494; [1494.08.11]\n", @@ -5121,8 +5143,8 @@ " \n", " \n", " 4\n", - " Ink 4.D.3\n", " De proprietatibus rerum (französ.) Le propriet...\n", + " Ink 4.D.3\n", " Bartholomaeus\n", " \n", " 7. Apr. 1487; [1487.04.07]\n", @@ -5141,8 +5163,8 @@ " \n", " \n", " 227\n", - " Ink 4.D.15\n", " Facta et dicta memorabilia\n", + " Ink 4.D.15\n", " Valerius\n", " \n", " 1471\n", @@ -5151,8 +5173,8 @@ " \n", " \n", " 228\n", - " Ink 5.E.23\n", " Facta et dicta memorabilia\n", + " Ink 5.E.23\n", " Valerius Maximus, Gaius\n", " \n", " 24 Dec. 1476\n", @@ -5161,8 +5183,8 @@ " \n", " \n", " 229\n", - " Ink 5.H.38\n", " De viris illustribus\n", + " Ink 5.H.38\n", " Aurelius Victor, Sextus (Pseudo-)\n", " \n", " 5. Juni 1477; [1477.06.05]\n", @@ -5171,8 +5193,8 @@ " \n", " \n", " 230\n", - " Ink 8.F.35\n", " Opera [Bucolica, Georgica, Aeneis, with argume...\n", + " Ink 8.F.35\n", " Vergilius Maro, Publius\n", " \n", " Sept. 1478\n", @@ -5181,8 +5203,8 @@ " \n", " \n", " 231\n", - " Ink 3.E.15\n", " Opera\n", + " Ink 3.E.15\n", " Xenophon\n", " \n", " about 1501-02]\n", @@ -5195,31 +5217,18 @@ "" ], "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", + " Titel Signatur \n", + "0 De civitate dei Ink 5.B.12 \\\n", + "1 De trinitate Ink 3.C.8 \n", + "2 Summa de ecclesiastica potestate Ink 3.E.4 \n", + "3 Opera Ink 7.E.28 \n", + "4 De proprietatibus rerum (französ.) Le propriet... Ink 4.D.3 \n", + ".. ... ... \n", + "227 Facta et dicta memorabilia Ink 4.D.15 \n", + "228 Facta et dicta memorabilia Ink 5.E.23 \n", + "229 De viris illustribus Ink 5.H.38 \n", + "230 Opera [Bucolica, Georgica, Aeneis, with argume... Ink 8.F.35 \n", + "231 Opera Ink 3.E.15 \n", "\n", " Autor Mitwirkender \n", "0 Augustinus, Aurelius \\\n", @@ -5250,7 +5259,7 @@ "[225 rows x 7 columns]" ] }, - "execution_count": 29, + "execution_count": 190, "metadata": {}, "output_type": "execute_result" } @@ -5264,7 +5273,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 191, "id": "584cedc1-0eb7-45d6-9535-e79867f4249b", "metadata": { "tags": [] @@ -5291,8 +5300,8 @@ " \n", " \n", " \n", - " Signatur\n", " Titel\n", + " Signatur\n", " Autor\n", " Mitwirkender\n", " Veröffentlichungsdatum\n", @@ -5303,8 +5312,8 @@ " \n", " \n", " 0\n", - " Ink 5.B.12\n", " De civitate dei\n", + " Ink 5.B.12\n", " Augustinus, Aurelius\n", " \n", " 1470\n", @@ -5313,8 +5322,8 @@ " \n", " \n", " 1\n", - " Ink 24.B.8; Ink 3.C.8\n", " De trinitate\n", + " Ink 3.C.8\n", " Augustinus, Aurelius\n", " Reyser, Georg\n", " [nicht nach 1471]\n", @@ -5323,8 +5332,8 @@ " \n", " \n", " 2\n", - " Ink 3.E.4; Ink 31-45; Ink 24.F.30\n", " Summa de ecclesiastica potestate\n", + " Ink 3.E.4\n", " Augustinus\n", " Hongre, Pierre\n", " [nicht nach 1480]\n", @@ -5333,8 +5342,8 @@ " \n", " \n", " 3\n", - " Ink 7.E.28\n", " Opera\n", + " Ink 7.E.28\n", " Ausonius, Decimus Magnus\n", " Ferrarius, Julius Aemilius\n", " 11. Aug. 1494; [1494.08.11]\n", @@ -5343,8 +5352,8 @@ " \n", " \n", " 4\n", - " Ink 4.D.3\n", " De proprietatibus rerum (französ.) Le propriet...\n", + " Ink 4.D.3\n", " Bartholomaeus\n", " \n", " 7. Apr. 1487; [1487.04.07]\n", @@ -5363,8 +5372,8 @@ " \n", " \n", " 227\n", - " Ink 4.D.15\n", " Facta et dicta memorabilia\n", + " Ink 4.D.15\n", " Valerius\n", " \n", " 1471\n", @@ -5373,8 +5382,8 @@ " \n", " \n", " 228\n", - " Ink 5.E.23\n", " Facta et dicta memorabilia\n", + " Ink 5.E.23\n", " Valerius Maximus, Gaius\n", " \n", " 24 Dec. 1476\n", @@ -5383,8 +5392,8 @@ " \n", " \n", " 229\n", - " Ink 5.H.38\n", " De viris illustribus\n", + " Ink 5.H.38\n", " Aurelius Victor, Sextus (Pseudo-)\n", " \n", " 5. Juni 1477; [1477.06.05]\n", @@ -5393,8 +5402,8 @@ " \n", " \n", " 230\n", - " Ink 8.F.35\n", " Opera [Bucolica, Georgica, Aeneis, with argume...\n", + " Ink 8.F.35\n", " Vergilius Maro, Publius\n", " \n", " Sept. 1478\n", @@ -5403,8 +5412,8 @@ " \n", " \n", " 231\n", - " Ink 3.E.15\n", " Opera\n", + " Ink 3.E.15\n", " Xenophon\n", " \n", " about 1501-02]\n", @@ -5417,31 +5426,18 @@ "" ], "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", + " Titel Signatur \n", + "0 De civitate dei Ink 5.B.12 \\\n", + "1 De trinitate Ink 3.C.8 \n", + "2 Summa de ecclesiastica potestate Ink 3.E.4 \n", + "3 Opera Ink 7.E.28 \n", + "4 De proprietatibus rerum (französ.) Le propriet... Ink 4.D.3 \n", + ".. ... ... \n", + "227 Facta et dicta memorabilia Ink 4.D.15 \n", + "228 Facta et dicta memorabilia Ink 5.E.23 \n", + "229 De viris illustribus Ink 5.H.38 \n", + "230 Opera [Bucolica, Georgica, Aeneis, with argume... Ink 8.F.35 \n", + "231 Opera Ink 3.E.15 \n", "\n", " Autor Mitwirkender \n", "0 Augustinus, Aurelius \\\n", @@ -5472,7 +5468,7 @@ "[232 rows x 7 columns]" ] }, - "execution_count": 30, + "execution_count": 191, "metadata": {}, "output_type": "execute_result" } @@ -5491,7 +5487,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 192, "id": "f048ed87-4541-4613-9683-227a820d7321", "metadata": { "tags": [] @@ -5813,7 +5809,7 @@ "[8 rows x 22 columns]" ] }, - "execution_count": 31, + "execution_count": 192, "metadata": {}, "output_type": "execute_result" } @@ -5824,7 +5820,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 193, "id": "b02e6456-5bf7-4f14-8e53-04e71c701159", "metadata": { "tags": [] @@ -6232,7 +6228,7 @@ "[9 rows x 39 columns]" ] }, - "execution_count": 32, + "execution_count": 193, "metadata": {}, "output_type": "execute_result" } @@ -6304,7 +6300,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 194, "id": "6f42f938-db2b-4854-800a-521c6845d545", "metadata": { "tags": [] @@ -6758,7 +6754,7 @@ "[23670 rows x 43 columns]" ] }, - "execution_count": 35, + "execution_count": 194, "metadata": {}, "output_type": "execute_result" } @@ -6772,7 +6768,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 195, "id": "0c398ac9-cd34-49a2-b6d0-d1d057d33593", "metadata": { "tags": [] @@ -7226,7 +7222,7 @@ "[804 rows x 43 columns]" ] }, - "execution_count": 36, + "execution_count": 195, "metadata": {}, "output_type": "execute_result" } @@ -7277,7 +7273,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 196, "id": "d4d83256-5d0d-433f-b3fa-f7ea01ad4ca8", "metadata": { "tags": [] @@ -7289,7 +7285,7 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 197, "id": "8f4eab54-4475-4b8e-a4f0-1397290d28f1", "metadata": { "tags": [] @@ -7301,7 +7297,7 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 198, "id": "332be4f7-e0e1-4a7c-9aac-a1f42c1df383", "metadata": { "tags": [] @@ -7397,7 +7393,7 @@ "[1 rows x 22 columns]" ] }, - "execution_count": 40, + "execution_count": 198, "metadata": {}, "output_type": "execute_result" } @@ -7441,10 +7437,1603 @@ "to_be_saved.columns" ] }, + { + "cell_type": "markdown", + "id": "43d16894-5add-42e0-9d68-f1cd19ba2033", + "metadata": {}, + "source": [ + "# Bereinigung der vervollstaendigten Tabelle" + ] + }, + { + "cell_type": "code", + "execution_count": 199, + "id": "e8fdecc0-c8b8-4fc8-8cd0-02b430388d4e", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "comp_BE = pd.read_excel('../Daten/Vorhersagen/Complete_BE.xlsx')" + ] + }, + { + "cell_type": "code", + "execution_count": 200, + "id": "4b425ec4-6344-4eea-9dbd-4a0208d5e845", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "signatur_dup = comp_BE[comp_BE.duplicated('Signatur', keep=False)]" + ] + }, + { + "cell_type": "code", + "execution_count": 201, + "id": "87f9820c-b2b9-45b6-a6cd-0826df8e14be", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "bc_index = signatur_dup['Barcode'].dropna().index\n", + "id_index = signatur_dup['identifier'].dropna().index\n", + "comb_index = bc_index.union(id_index)\n", + "\n", + "bc_or_id = signatur_dup.loc[comb_index]" + ] + }, + { + "cell_type": "code", + "execution_count": 202, + "id": "2b5e1649-0c3f-4966-a1b9-d018fafa963e", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "BE.11.O.3\n", + "61.C.8\n" + ] + } + ], + "source": [ + "test_strs = [\"Han BE.11.O.3 - ÖNB\",\n", + " \"Alt Prunk 61.C.8 - ÖNB\"]\n", + "sign_re = re.compile('(?:\\w+ )?\\w+ ([A-Z0-9\\.\\-\\(Vol\\)\\*]+)')\n", + "for s in test_strs:\n", + " sign_match = re.search(sign_re, s)\n", + " print(sign_match[1])" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "id": "7f69c459-d24c-4b0c-99bd-ba82651729d0", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "46ed3e2ae1ae4234b6f1170794f49921", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "0it [00:00, ?it/s]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "no IIIF manifest found for Z184241901\n", + "no IIIF manifest found for Z184241809\n", + "no IIIF manifest found for Z173252307\n", + "no IIIF manifest found for Z184242504\n", + "no IIIF manifest found for Z173252605\n", + "no signature found for Z206650206 BE.10.P.15.(Vol.1)\n", + "no IIIF manifest found for Z173252502\n", + "no IIIF manifest found for Z184243004\n", + "no IIIF manifest found for Z204965809\n", + "no IIIF manifest found for Z173253403\n", + "no IIIF manifest found for Z18422390X\n", + "no IIIF manifest found for Z173254602\n", + "no IIIF manifest found for Z173254407\n", + "no IIIF manifest found for Z184243107\n", + "no IIIF manifest found for Z18424320X\n", + "no IIIF manifest found for Z173254304\n", + "no IIIF manifest found for Z173255801\n", + "no IIIF manifest found for Z197485709\n", + "no IIIF manifest found for Z173255400\n", + "no IIIF manifest found for Z173255205\n", + "no IIIF manifest found for Z173255102\n", + "no IIIF manifest found for Z173256209\n", + "no IIIF manifest found for Z173256106\n", + "no IIIF manifest found for Z240265106\n", + "no signature found for Z150809303 MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1)\n", + "no signature found for Z150809406 MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1)\n", + "no signature found for Z156354802 49.D.18.(Vol.2); 49.D.18.(Vol.1)\n", + "no signature found for Z156354905 49.D.18.(Vol.2); 49.D.18.(Vol.1)\n", + "no signature found for Z164578208 74.Q.43.(Vol.1); 74.Q.43.(Vol.2)\n", + "no signature found for Z164578300 74.Q.43.(Vol.1); 74.Q.43.(Vol.2)\n", + "no signature found for Z164863407 24.H.1.(Vol.2); 24.H.1.(Vol.1)\n", + "no signature found for Z16486350X 24.H.1.(Vol.2); 24.H.1.(Vol.1)\n", + "no signature found for Z165394701 52.G.17.(Vol.1); 52.G.17.(Vol.2)\n", + "no signature found for Z169690904 51.O.10.11.(Vol.2); 51.O.10.11.(Vol.1)\n", + "no signature found for Z169691507 51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.14-19.(Vol.1); 51.O.14-19.(Vol.6); 51.O.14-19.(Vol.5); 51.O.14-19.(Vol.2)\n", + "no signature found for Z169691702 51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.14-19.(Vol.1); 51.O.14-19.(Vol.6); 51.O.14-19.(Vol.5); 51.O.14-19.(Vol.2)\n" + ] + } + ], + "source": [ + "for index, row in tqdm(bc_or_id.iterrows()):\n", + " bc = row['identifier']\n", + " if not pd.isna(row['identifier']):\n", + " bc = row['identifier']\n", + " elif not pd.isna(row['Barcode']):\n", + " bc = row['Barcode']\n", + " else:\n", + " print('skipping row, no barcode present')\n", + " continue\n", + " bc = bc.replace('+', '')\n", + " if ('B' in bc) or ('Z' not in bc):\n", + " # print('invalid barcode', bc)\n", + " continue\n", + " iiif_url = f'https://iiif.onb.ac.at/presentation/ABO/{bc}/manifest'\n", + " request = requests.get(iiif_url)\n", + " if request.status_code == 200:\n", + " manifest_metadata = json.loads(request.content)['metadata']\n", + " for dic in manifest_metadata:\n", + " for key, val in dic.items():\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", + " if sign_match:\n", + " signatur_dup.loc[index, 'Signatur'] = sign_match[1]\n", + " else:\n", + " print('no signature found for', bc, row['Signatur'])\n", + " else:\n", + " print('no IIIF manifest found for', bc)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 127, + "id": "4cd3b69a-f056-47b1-9839-7af995f31533", + "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", + "
SignaturBarcodeTitelAutorMitwirkenderAnfang VeröffentlichungsdatumEnde VeröffentlichungsdatumVeröffentlichungsdatumVeröffentlichungsortVeröffentlichungsort (normiert)...hs. Katalogseite DigitalisatWissensklasseWissensunterklasseFormatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLidentifierABO-Barcode
2309251.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691507Z169691507; Z16969160X; Z169691702; Z169691209...
2309351.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691702Z169691507; Z16969160X; Z169691702; Z169691209...
\n", + "

2 rows × 40 columns

\n", + "
" + ], + "text/plain": [ + " Signatur Barcode \n", + "23092 51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1... NaN \\\n", + "23093 51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1... NaN \n", + "\n", + " Titel \n", + "23092 Historiarum sui temporis av anno 1543 usque ad... \\\n", + "23093 Historiarum sui temporis av anno 1543 usque ad... \n", + "\n", + " Autor Mitwirkender Anfang Veröffentlichungsdatum \n", + "23092 Thou, Jacques Auguste de NaN NaN \\\n", + "23093 Thou, Jacques Auguste de NaN NaN \n", + "\n", + " Ende Veröffentlichungsdatum Veröffentlichungsdatum \n", + "23092 NaN 1620-1621 \\\n", + "23093 NaN 1620-1621 \n", + "\n", + " Veröffentlichungsort Veröffentlichungsort (normiert) ... \n", + "23092 Aurelianae NaN ... \\\n", + "23093 Aurelianae NaN ... \n", + "\n", + " hs. Katalogseite Digitalisat Wissensklasse Wissensunterklasse \n", + "23092 NaN NaN NaN \\\n", + "23093 NaN NaN NaN \n", + "\n", + " Formatangabe hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "23092 NaN NaN NaN \\\n", + "23093 NaN NaN NaN \n", + "\n", + " hs. Katalogeintrag hs. Katalog Image URL identifier \n", + "23092 NaN NaN Z169691507 \\\n", + "23093 NaN NaN Z169691702 \n", + "\n", + " ABO-Barcode \n", + "23092 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "23093 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "\n", + "[2 rows x 40 columns]" + ] + }, + "execution_count": 127, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "signatur_dup[signatur_dup['Signatur'] == '51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.14-19.(Vol.1); 51.O.14-19.(Vol.6); 51.O.14-19.(Vol.5); 51.O.14-19.(Vol.2)']" + ] + }, + { + "cell_type": "code", + "execution_count": 99, + "id": "2bcd8b36-3b74-498a-8726-39a9757cbda4", + "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)...hs. Katalogseite DigitalisatWissensklasseWissensunterklasseFormatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLidentifierABO-Barcode
22664BE.8.P.19.20.(Vol.2)NaNHistoire Vniverselle Des Gverres Dv Tvrc, Depv...Montreux, Nicolas <<de>>Heinrich; Mousson, Pierre; Orléans, Louis <<d'...NaNNaNMDCVIIIA ParisNaN...NaNNaNNaNNaNNaNNaNNaNNaNrep_131EA36ANaN
22671MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1)NaNLa bible en francoizPetrusNaNNaNNaN[s.a. um 1520]ParisNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ150809303Z150809303; Z150809406
22672MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1)NaNLa bible en francoizPetrusNaNNaNNaN[s.a. um 1520]ParisNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ150809406Z150809303; Z150809406
2268149.D.18.(Vol.2); 49.D.18.(Vol.1)NaNJoannis Trithemij ... Et Postea Divi Jacobi a...Trithemius, JohannesNaNNaNNaN1690Typis Monasterij S. GalliNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ156354802Z156354802; Z156354905
2268249.D.18.(Vol.2); 49.D.18.(Vol.1)NaNJoannis Trithemij ... Et Postea Divi Jacobi a...Trithemius, JohannesNaNNaNNaN1690Typis Monasterij S. GalliNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ156354905Z156354802; Z156354905
..................................................................
23391*28.A.79.(Vol.21)NaNHistoire des ouvrages des scavansBasnage de Beauval, HenriNaNNaNNaN1687-1709RotterdamNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ222909207Z222909402; Z222908707; Z22290720X; Z222907107...
23392*28.A.79.(Vol.22)NaNHistoire des ouvrages des scavansBasnage de Beauval, HenriNaNNaNNaN1687-1709RotterdamNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ22290930XZ222909402; Z222908707; Z22290720X; Z222907107...
23393*28.A.79.(Vol.23)NaNHistoire des ouvrages des scavansBasnage de Beauval, HenriNaNNaNNaN1687-1709RotterdamNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ222909402Z222909402; Z222908707; Z22290720X; Z222907107...
23394*28.A.79.(Vol.24)NaNHistoire des ouvrages des scavansBasnage de Beauval, HenriNaNNaNNaN1687-1709RotterdamNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ222909505Z222909402; Z222908707; Z22290720X; Z222907107...
23395*28.A.79.(Vol.25)NaNHistoire des ouvrages des scavansBasnage de Beauval, HenriNaNNaNNaN1687-1709RotterdamNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ222909608Z222909402; Z222908707; Z22290720X; Z222907107...
\n", + "

229 rows × 40 columns

\n", + "
" + ], + "text/plain": [ + " Signatur Barcode \n", + "22664 BE.8.P.19.20.(Vol.2) NaN \\\n", + "22671 MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1) NaN \n", + "22672 MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1) NaN \n", + "22681 49.D.18.(Vol.2); 49.D.18.(Vol.1) NaN \n", + "22682 49.D.18.(Vol.2); 49.D.18.(Vol.1) NaN \n", + "... ... ... \n", + "23391 *28.A.79.(Vol.21) NaN \n", + "23392 *28.A.79.(Vol.22) NaN \n", + "23393 *28.A.79.(Vol.23) NaN \n", + "23394 *28.A.79.(Vol.24) NaN \n", + "23395 *28.A.79.(Vol.25) NaN \n", + "\n", + " Titel \n", + "22664 Histoire Vniverselle Des Gverres Dv Tvrc, Depv... \\\n", + "22671 La bible en francoiz \n", + "22672 La bible en francoiz \n", + "22681 Joannis Trithemij ... Et Postea Divi Jacobi a... \n", + "22682 Joannis Trithemij ... Et Postea Divi Jacobi a... \n", + "... ... \n", + "23391 Histoire des ouvrages des scavans \n", + "23392 Histoire des ouvrages des scavans \n", + "23393 Histoire des ouvrages des scavans \n", + "23394 Histoire des ouvrages des scavans \n", + "23395 Histoire des ouvrages des scavans \n", + "\n", + " Autor \n", + "22664 Montreux, Nicolas <> \\\n", + "22671 Petrus \n", + "22672 Petrus \n", + "22681 Trithemius, Johannes \n", + "22682 Trithemius, Johannes \n", + "... ... \n", + "23391 Basnage de Beauval, Henri \n", + "23392 Basnage de Beauval, Henri \n", + "23393 Basnage de Beauval, Henri \n", + "23394 Basnage de Beauval, Henri \n", + "23395 Basnage de Beauval, Henri \n", + "\n", + " Mitwirkender \n", + "22664 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", + "
SignaturBarcodeTitelAutorMitwirkenderAnfang VeröffentlichungsdatumEnde VeröffentlichungsdatumVeröffentlichungsdatumVeröffentlichungsortVeröffentlichungsort (normiert)...hs. Katalogseite DigitalisatWissensklasseWissensunterklasseFormatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLidentifierABO-Barcode
2308951.O.14-19.(Vol.1)NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691209Z169691507; Z16969160X; Z169691702; Z169691209...
2309051.O.14-19.(Vol.2)NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691301Z169691507; Z16969160X; Z169691702; Z169691209...
2309151.O.14-19.(Vol.3)NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691404Z169691507; Z16969160X; Z169691702; Z169691209...
2309251.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691507Z169691507; Z16969160X; Z169691702; Z169691209...
2309351.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...NaNHistoriarum sui temporis av anno 1543 usque ad...Thou, Jacques Auguste deNaNNaNNaN1620-1621AurelianaeNaN...NaNNaNNaNNaNNaNNaNNaNNaNZ169691702Z169691507; Z16969160X; Z169691702; Z169691209...
\n", + "

5 rows × 40 columns

\n", + "" + ], + "text/plain": [ + " Signatur Barcode \n", + "23089 51.O.14-19.(Vol.1) NaN \\\n", + "23090 51.O.14-19.(Vol.2) NaN \n", + "23091 51.O.14-19.(Vol.3) NaN \n", + "23092 51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1... NaN \n", + "23093 51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1... NaN \n", + "\n", + " Titel \n", + "23089 Historiarum sui temporis av anno 1543 usque ad... \\\n", + "23090 Historiarum sui temporis av anno 1543 usque ad... \n", + "23091 Historiarum sui temporis av anno 1543 usque ad... \n", + "23092 Historiarum sui temporis av anno 1543 usque ad... \n", + "23093 Historiarum sui temporis av anno 1543 usque ad... \n", + "\n", + " Autor Mitwirkender Anfang Veröffentlichungsdatum \n", + "23089 Thou, Jacques Auguste de NaN NaN \\\n", + "23090 Thou, Jacques Auguste de NaN NaN \n", + "23091 Thou, Jacques Auguste de NaN NaN \n", + "23092 Thou, Jacques Auguste de NaN NaN \n", + "23093 Thou, Jacques Auguste de NaN NaN \n", + "\n", + " Ende Veröffentlichungsdatum Veröffentlichungsdatum \n", + "23089 NaN 1620-1621 \\\n", + "23090 NaN 1620-1621 \n", + "23091 NaN 1620-1621 \n", + "23092 NaN 1620-1621 \n", + "23093 NaN 1620-1621 \n", + "\n", + " Veröffentlichungsort Veröffentlichungsort (normiert) ... \n", + "23089 Aurelianae NaN ... \\\n", + "23090 Aurelianae NaN ... \n", + "23091 Aurelianae NaN ... \n", + "23092 Aurelianae NaN ... \n", + "23093 Aurelianae NaN ... \n", + "\n", + " hs. Katalogseite Digitalisat Wissensklasse Wissensunterklasse \n", + "23089 NaN NaN NaN \\\n", + "23090 NaN NaN NaN \n", + "23091 NaN NaN NaN \n", + "23092 NaN NaN NaN \n", + "23093 NaN NaN NaN \n", + "\n", + " Formatangabe hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "23089 NaN NaN NaN \\\n", + "23090 NaN NaN NaN \n", + "23091 NaN NaN NaN \n", + "23092 NaN NaN NaN \n", + "23093 NaN NaN NaN \n", + "\n", + " hs. Katalogeintrag hs. Katalog Image URL identifier \n", + "23089 NaN NaN Z169691209 \\\n", + "23090 NaN NaN Z169691301 \n", + "23091 NaN NaN Z169691404 \n", + "23092 NaN NaN Z169691507 \n", + "23093 NaN NaN Z169691702 \n", + "\n", + " ABO-Barcode \n", + "23089 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "23090 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "23091 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "23092 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "23093 Z169691507; Z16969160X; Z169691702; Z169691209... \n", + "\n", + "[5 rows x 40 columns]" + ] + }, + "execution_count": 135, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "signatur_dup.loc[23089:23093]" + ] + }, + { + "cell_type": "code", + "execution_count": 157, + "id": "c1f1b4a5-3d05-44b3-83fa-f238b6e6e1d2", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([['BE.1.A.4', 'B1376659',\n", + " 'Voyage pittoresque de la Syrie, de la Phoenicie, de la Palaestine, et de la basse Aegypte. 2 Vol.',\n", + " 'La-Porte du Theil, Francois Jean Gabriel',\n", + " 'Legrand, Jacques Guillaume; Langles, Louis Mathieu', 1799.0,\n", + " nan, '1799', 'Paris', nan, nan,\n", + " 'Geschichte 1787-; Reise; Orient', nan, nan, nan, nan, nan, nan,\n", + " nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan,\n", + " nan, nan, nan, nan, nan, nan, nan, nan, nan],\n", + " ['BE.1.A.4.(Vol.1);', nan,\n", + " \"Voyage Pittoresque De La Syrie, De La Phœnicie, De La Palæstine, Et De La Basse Ægypte Ouvrage divisé en trois Volumes : Contenant Environ Trois Cent Trent Planches : Gravées sur les dessins et sous la direction du C[itoy]en Cassas, peintre, l'un des artistes employés par l'auteur du Voyage de la Grèce : Un Discours Préliminaire Pour Chaque Volume Par le C[itoy]en Volney, membre de l'Institut national, auteur du Voyage en Syrie : Un Texte Rédigé Par Les C[itoyens] F.J.G. La Porte-Du Theil, membre de l'Institut, et du Conservatoire de la Bibliothèque nationale : pour la partie historique et la relation du Voyage : J.G. Legrand, architecte, de la Société libre des sciences, lettres et arts de Paris; pour la partie historique et descriptive de l'Architecture; L. Langlès, membre de l'Institut, et du Conservatoire de la Bibliothèque nationale, professeur de Persan à l'École spéciale des langues orientales vivantes; pour la partie des Langues et des Inscriptions orientales 1-15 Livraison\",\n", + " nan, nan, nan, nan, nan, nan, 'Paris', 'French', nan,\n", + " 'Orient$Dg--(DE-588)4075699-3;Reise$Ds--(DE-588)4049275-8;$Az--Geschichte 1787-;AT-OBV--ONB-AK;Reise$Ds--(DE-588)4049275-8;Orient$Dg--(DE-588)4075699-3;AT-OBV--ONB-AK',\n", + " nan, 'Reisebericht--(DE-588)4076645-7--gnd-content', nan, nan,\n", + " nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan,\n", + " nan, nan, nan, nan, nan, nan, nan, nan, nan, nan],\n", + " ['BE.1.A.4.(Vol.2);', nan,\n", + " \"Voyage Pittoresque De La Syrie, De La Phœnicie, De La Palæstine, Et De La Basse Ægypte Ouvrage divisé en trois Volumes : Contenant Environ Trois Cent Trent Planches : Gravées sur les dessins et sous la direction du C[itoy]en Cassas, peintre, l'un des artistes employés par l'auteur du Voyage de la Grèce : Un Discours Préliminaire Pour Chaque Volume Par le C[itoy]en Volney, membre de l'Institut national, auteur du Voyage en Syrie : Un Texte Rédigé Par Les C[itoyens] F.J.G. La Porte-Du Theil, membre de l'Institut, et du Conservatoire de la Bibliothèque nationale : pour la partie historique et la relation du Voyage : J.G. Legrand, architecte, de la Société libre des sciences, lettres et arts de Paris; pour la partie historique et descriptive de l'Architecture; L. Langlès, membre de l'Institut, et du Conservatoire de la Bibliothèque nationale, professeur de Persan à l'École spéciale des langues orientales vivantes; pour la partie des Langues et des Inscriptions orientales 16-30 Livraison\",\n", + " nan, nan, nan, nan, nan, nan, 'Paris', 'French', nan,\n", + " 'Orient$Dg--(DE-588)4075699-3;Reise$Ds--(DE-588)4049275-8;$Az--Geschichte 1787-;AT-OBV--ONB-AK;Reise$Ds--(DE-588)4049275-8;Orient$Dg--(DE-588)4075699-3;AT-OBV--ONB-AK',\n", + " nan, 'Reisebericht--(DE-588)4076645-7--gnd-content', nan, nan,\n", + " nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan,\n", + " nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]], dtype=object)" + ] + }, + "execution_count": 157, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "comp_BE_sig = comp_BE.dropna(subset='Signatur')\n", + "comp_BE_sig[comp_BE_sig['Signatur'].str.contains('BE.1.A.4')].values" + ] + }, + { + "cell_type": "code", + "execution_count": 155, + "id": "176540c8-773d-4201-a1f4-b8e92cf271ac", + "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)...hs. Katalogseite DigitalisatWissensklasseWissensunterklasseFormatangabehs. Katalogseite Handschrifths. Katalogeintrag IDhs. Katalogeintraghs. Katalog Image URLidentifierABO-Barcode
22498Wien, ÖNB (2: BE.12.K.1; 657.936-C. Neu Mag)NaNDecades rerum Venetarum [Italian] Croniche che...Sabellicus, Marcus AntoniusGotardus da Ponte, for Oldradus Lampugnanus1510.0NaNabout 1510?NaNMilan...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22499BE.1.A.4.(Vol.1);NaNVoyage Pittoresque De La Syrie, De La Phœnicie...NaNNaNNaNNaNNaNNaNParis...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22500BE.1.A.4.(Vol.2);NaNVoyage Pittoresque De La Syrie, De La Phœnicie...NaNNaNNaNNaNNaNNaNParis...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
22501BE.9.L.1;NaNVoyages De Monsieur Le Chevalier Chardin, En P...NaNNaNNaNNaNNaNNaNParis...306.0GeographiaPeregrinationes, Navigationes, & ItineraQuarto70014.377_306_02Voyages du Chevalier Chardin en Perse & autres...https://iiif.onb.ac.at/images/DOD/51184/000003...NaNNaN
22502BE.5.T.65a;NaNVorlesungen über die Militairgraphik in besond...NaNNaNNaNNaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
..................................................................
23645Ink 32-126; Ink 4.H.35NaNPolyhistor, sive De mirabilibus mundi. Add: Mi...Solinus, Gaius IuliusRagazonibus, Theodorus <<de>>NaNNaN23. Aug. 1491; [1491.08.23]VenedigNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23654Ink 23.E.10; Ink 4.F.42NaNComoediae. Cum directorio vocabulorum, glossa ...Terentius Afer, PubliusDonatus, Aelius; Jouenneaux, Guy; Badius Ascen...NaNNaN11 Feb. 1499StrassburgNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23657Ink 21.A.23; Ink 5.C.13NaNQuaestiones de duodecim quodlibetThomasSensenschmidt, Johann; Frisner, AndreasNaNNaN15 Apr. 1474NurembergNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23658Ink 6.B.10; Ink 6.B.9NaNSuper quarto libro SententiarumThomas AquinasNaNNaNNaN13 June 1469MainzNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
23661Ink 7.F.26; Ink 32-108NaNOrthographia. (Ed: Hieronymus Bononius)Tortellius, JohannesNaNNaNNaN2 Apr. 1477TrevisoNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

471 rows × 40 columns

\n", + "
" + ], + "text/plain": [ + " Signatur Barcode \n", + "22498 Wien, ÖNB (2: BE.12.K.1; 657.936-C. Neu Mag) NaN \\\n", + "22499 BE.1.A.4.(Vol.1); NaN \n", + "22500 BE.1.A.4.(Vol.2); NaN \n", + "22501 BE.9.L.1; NaN \n", + "22502 BE.5.T.65a; NaN \n", + "... ... ... \n", + "23645 Ink 32-126; Ink 4.H.35 NaN \n", + "23654 Ink 23.E.10; Ink 4.F.42 NaN \n", + "23657 Ink 21.A.23; Ink 5.C.13 NaN \n", + "23658 Ink 6.B.10; Ink 6.B.9 NaN \n", + "23661 Ink 7.F.26; Ink 32-108 NaN \n", + "\n", + " Titel \n", + "22498 Decades rerum Venetarum [Italian] Croniche che... \\\n", + "22499 Voyage Pittoresque De La Syrie, De La Phœnicie... \n", + "22500 Voyage Pittoresque De La Syrie, De La Phœnicie... \n", + "22501 Voyages De Monsieur Le Chevalier Chardin, En P... \n", + "22502 Vorlesungen über die Militairgraphik in besond... \n", + "... ... \n", + "23645 Polyhistor, sive De mirabilibus mundi. Add: Mi... \n", + "23654 Comoediae. Cum directorio vocabulorum, glossa ... \n", + "23657 Quaestiones de duodecim quodlibet \n", + "23658 Super quarto libro Sententiarum \n", + "23661 Orthographia. (Ed: Hieronymus Bononius) \n", + "\n", + " Autor \n", + "22498 Sabellicus, Marcus Antonius \\\n", + "22499 NaN \n", + "22500 NaN \n", + "22501 NaN \n", + "22502 NaN \n", + "... ... \n", + "23645 Solinus, Gaius Iulius \n", + "23654 Terentius Afer, Publius \n", + "23657 Thomas \n", + "23658 Thomas Aquinas \n", + "23661 Tortellius, Johannes \n", + "\n", + " Mitwirkender \n", + "22498 Gotardus da Ponte, for Oldradus Lampugnanus \\\n", + "22499 NaN \n", + "22500 NaN \n", + "22501 NaN \n", + "22502 NaN \n", + "... ... \n", + "23645 Ragazonibus, Theodorus <> \n", + "23654 Donatus, Aelius; Jouenneaux, Guy; Badius Ascen... \n", + "23657 Sensenschmidt, Johann; Frisner, Andreas \n", + "23658 NaN \n", + "23661 NaN \n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "22498 1510.0 NaN \\\n", + "22499 NaN NaN \n", + "22500 NaN NaN \n", + "22501 NaN NaN \n", + "22502 NaN NaN \n", + "... ... ... \n", + "23645 NaN NaN \n", + "23654 NaN NaN \n", + "23657 NaN NaN \n", + "23658 NaN NaN \n", + "23661 NaN NaN \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "22498 about 1510? NaN \\\n", + "22499 NaN NaN \n", + "22500 NaN NaN \n", + "22501 NaN NaN \n", + "22502 NaN NaN \n", + "... ... ... \n", + "23645 23. Aug. 1491; [1491.08.23] Venedig \n", + "23654 11 Feb. 1499 Strassburg \n", + "23657 15 Apr. 1474 Nuremberg \n", + "23658 13 June 1469 Mainz \n", + "23661 2 Apr. 1477 Treviso \n", + "\n", + " Veröffentlichungsort (normiert) ... hs. Katalogseite Digitalisat \n", + "22498 Milan ... NaN \\\n", + "22499 Paris ... NaN \n", + "22500 Paris ... NaN \n", + "22501 Paris ... 306.0 \n", + "22502 NaN ... NaN \n", + "... ... ... ... \n", + "23645 NaN ... NaN \n", + "23654 NaN ... NaN \n", + "23657 NaN ... NaN \n", + "23658 NaN ... NaN \n", + "23661 NaN ... NaN \n", + "\n", + " Wissensklasse Wissensunterklasse Formatangabe \n", + "22498 NaN NaN NaN \\\n", + "22499 NaN NaN NaN \n", + "22500 NaN NaN NaN \n", + "22501 Geographia Peregrinationes, Navigationes, & Itinera Quarto \n", + "22502 NaN NaN NaN \n", + "... ... ... ... \n", + "23645 NaN NaN NaN \n", + "23654 NaN NaN NaN \n", + "23657 NaN NaN NaN \n", + "23658 NaN NaN NaN \n", + "23661 NaN NaN NaN \n", + "\n", + " hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "22498 NaN NaN \\\n", + "22499 NaN NaN \n", + "22500 NaN NaN \n", + "22501 700 14.377_306_02 \n", + "22502 NaN NaN \n", + "... ... ... \n", + "23645 NaN NaN \n", + "23654 NaN NaN \n", + "23657 NaN NaN \n", + "23658 NaN NaN \n", + "23661 NaN NaN \n", + "\n", + " hs. Katalogeintrag \n", + "22498 NaN \\\n", + "22499 NaN \n", + "22500 NaN \n", + "22501 Voyages du Chevalier Chardin en Perse & autres... \n", + "22502 NaN \n", + "... ... \n", + "23645 NaN \n", + "23654 NaN \n", + "23657 NaN \n", + "23658 NaN \n", + "23661 NaN \n", + "\n", + " hs. Katalog Image URL identifier \n", + "22498 NaN NaN \\\n", + "22499 NaN NaN \n", + "22500 NaN NaN \n", + "22501 https://iiif.onb.ac.at/images/DOD/51184/000003... NaN \n", + "22502 NaN NaN \n", + "... ... ... \n", + "23645 NaN NaN \n", + "23654 NaN NaN \n", + "23657 NaN NaN \n", + "23658 NaN NaN \n", + "23661 NaN NaN \n", + "\n", + " ABO-Barcode \n", + "22498 NaN \n", + "22499 NaN \n", + "22500 NaN \n", + "22501 NaN \n", + "22502 NaN \n", + "... ... \n", + "23645 NaN \n", + "23654 NaN \n", + "23657 NaN \n", + "23658 NaN \n", + "23661 NaN \n", + "\n", + "[471 rows x 40 columns]" + ] + }, + "execution_count": 155, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "comp_BE_sig[comp_BE_sig['Signatur'].str.contains(';')]" + ] + }, { "cell_type": "code", "execution_count": null, - "id": "c1b062c4-1919-4672-8e2f-03f5a9a6c79c", + "id": "3ed0a9bd-7828-4140-b865-13b9f52bf7f7", "metadata": {}, "outputs": [], "source": [] diff --git a/Notebooks/String_matching.ipynb b/Notebooks/String_matching.ipynb index 52bed3cad30e0b49852d7b33d9a755290c83346f..e0747044ca011d9277e569728c603a4f8f1cba7c 100644 --- a/Notebooks/String_matching.ipynb +++ b/Notebooks/String_matching.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 73, + "execution_count": 1, "id": "7a3837ac-cced-4e01-bf57-265e40729692", "metadata": { "tags": [] @@ -23,7 +23,7 @@ }, { "cell_type": "code", - "execution_count": 176, + "execution_count": 20, "id": "29ca0dc8-cae7-4f12-bd60-fd74ea6ae5ac", "metadata": { "tags": [] @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": 75, + "execution_count": 10, "id": "c1e1c42a-962f-40bc-bb17-b62e8089feb7", "metadata": { "tags": [] @@ -47,7 +47,7 @@ }, { "cell_type": "code", - "execution_count": 76, + "execution_count": 19, "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": [] @@ -103,7 +103,7 @@ " 0.0102726686745882]], dtype=object)" ] }, - "execution_count": 7, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } @@ -114,7 +114,7 @@ }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 98, "id": "c0f4a42a-7e21-41e8-833c-2dd2f9d1985e", "metadata": { "tags": [] @@ -161,36 +161,39 @@ " \n", " \n", " \n", - " 3508\n", - " 14.377\n", - " 98\n", - " Poëtica\n", - " Poëtæ Gallici unà cum Dramaticis\n", - " Octavo und kleiner\n", - " 502\n", - " 14.377_098_09\n", - " Poësies de Jacques Poille. Paris. 1623. Th. Blaise n. 1257.\n", - " Poesies de Jacques Poille Paris 1623 Th Blaise n 1257\n", + " 7058\n", + " 14.378\n", + " 205\n", + " Historia Nova Europæ\n", + " Historia Hispanica generalis & aliquot temporum; Vitæ Regum; aliaque\n", + " Folio\n", + " 1043\n", + " 14.378_205_04\n", + " 2019 La Coronica general de toda España donde se tratan los estranos Acaccimientos que del diluvio hasta los tiempos del Rey D. Iayme de Aragon se seguieron, compuesta por Pero Antonio Beuter. 2 Vol. I Tom. en Valencia 1604. Pedro Patricio Mey. n. 1805.\n", + " La Coronica general de toda España donde se tratan los estranos Acaccimientos que del diluvio hasta los tiempos del Rey D Iayme de Aragon se seguieron compuesta por Pero Antonio Beuter 2 Vol I Tom en Valencia 1604 Pedro Patricio Mey n 1805\n", " \n", " \n", "\n", "" ], "text/plain": [ - " volume page number category subcategory \n", - "3508 14.377 98 Poëtica Poëtæ Gallici unà cum Dramaticis \\\n", + " volume page number category \n", + "7058 14.378 205 Historia Nova Europæ \\\n", + "\n", + " subcategory \n", + "7058 Historia Hispanica generalis & aliquot temporum; Vitæ Regum; aliaque \\\n", "\n", - " format handwritten page number entry_ID \n", - "3508 Octavo und kleiner 502 14.377_098_09 \\\n", + " format handwritten page number entry_ID \n", + "7058 Folio 1043 14.378_205_04 \\\n", "\n", - " entry \n", - "3508 Poësies de Jacques Poille. Paris. 1623. Th. Blaise n. 1257. \\\n", + " entry \n", + "7058 2019 La Coronica general de toda España donde se tratan los estranos Acaccimientos que del diluvio hasta los tiempos del Rey D. Iayme de Aragon se seguieron, compuesta por Pero Antonio Beuter. 2 Vol. I Tom. en Valencia 1604. Pedro Patricio Mey. n. 1805. \\\n", "\n", - " cleaned entry \n", - "3508 Poesies de Jacques Poille Paris 1623 Th Blaise n 1257 " + " cleaned entry \n", + "7058 La Coronica general de toda España donde se tratan los estranos Acaccimientos que del diluvio hasta los tiempos del Rey D Iayme de Aragon se seguieron compuesta por Pero Antonio Beuter 2 Vol I Tom en Valencia 1604 Pedro Patricio Mey n 1805 " ] }, - "execution_count": 77, + "execution_count": 98, "metadata": {}, "output_type": "execute_result" } @@ -199,7 +202,7 @@ "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, 'Poille'), '')\n", + "info = search_in_entry(search_in_entry(entry_df, 'Beuter'), '')\n", "print(len(info))\n", "info" ] @@ -1279,7 +1282,7 @@ }, { "cell_type": "code", - "execution_count": 108, + "execution_count": 185, "id": "836d1b5e-ef2f-4ff8-9c03-298b029f73b2", "metadata": { "tags": [] @@ -1292,7 +1295,8 @@ "5778 out of 8756 BE signatures from the appropriate time period were matched\n", "For 4564 matches the first one was correct\n", "For 5072 matches one of the five given ones in the table was correct\n", - "124 matches have two or more mentions in the handrwitten catalog\n" + "124 matches have two or more mentions in the handwritten catalog\n", + "403 connections are uncertain\n" ] } ], @@ -1310,7 +1314,10 @@ "print('For', any_matches, 'matches one of the five given ones in the table was correct')\n", "\n", "double_matches = man_matches['control'].str.contains(',').sum()\n", - "print(double_matches, 'matches have two or more mentions in the handrwitten catalog')" + "print(double_matches, 'matches have two or more mentions in the handwritten catalog')\n", + "\n", + "weak_matches = man_matches['control'].str.contains('/?').sum()\n", + "print(weak_matches, 'connections are uncertain')" ] }, { @@ -2370,10 +2377,18 @@ "without_years.to_excel('data/man_catalog/Ohne Jahresangabe.xlsx')" ] }, + { + "cell_type": "markdown", + "id": "36866c95-917c-48a6-9c2d-0ce1f9f9f8b2", + "metadata": {}, + "source": [ + "# String matching vom hs. Katalog ausgehend" + ] + }, { "cell_type": "code", "execution_count": null, - "id": "e0c65ab2-9951-4cab-a859-55b7d5427d57", + "id": "b8870950-aee8-42ab-9cc5-07f9d2e419ab", "metadata": {}, "outputs": [], "source": []