diff --git a/Daten/Vorhersagen/Complete_BE_Years.xlsx b/Daten/Vorhersagen/Complete_BE_Years.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..c8878cbf852d9de05ae899f25836c6e04acd2113 Binary files /dev/null and b/Daten/Vorhersagen/Complete_BE_Years.xlsx differ diff --git a/Notebooks/Remaining_barcodes_and_metadata.ipynb b/Notebooks/Remaining_barcodes_and_metadata.ipynb index 9701a7adf35484d52ad65547b5d606a8d50e01a7..0ab9f09d2efe7d9db938cc34633a7b082974db79 100644 --- a/Notebooks/Remaining_barcodes_and_metadata.ipynb +++ b/Notebooks/Remaining_barcodes_and_metadata.ipynb @@ -7447,7 +7447,7 @@ }, { "cell_type": "code", - "execution_count": 199, + "execution_count": 561, "id": "e8fdecc0-c8b8-4fc8-8cd0-02b430388d4e", "metadata": { "tags": [] @@ -7459,36 +7459,148 @@ }, { "cell_type": "code", - "execution_count": 200, - "id": "4b425ec4-6344-4eea-9dbd-4a0208d5e845", + "execution_count": 562, + "id": "d0cb9692-62cc-4c3a-81d4-ebbf02194201", "metadata": { "tags": [] }, "outputs": [], "source": [ - "signatur_dup = comp_BE[comp_BE.duplicated('Signatur', keep=False)]" + "add_ABO_bc = comp_BE.dropna(subset='identifier')['identifier']" ] }, { "cell_type": "code", - "execution_count": 201, - "id": "87f9820c-b2b9-45b6-a6cd-0826df8e14be", + "execution_count": 244, + "id": "df81627d-be27-4b30-9bb2-bc8658c811b5", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "737289c4330a43138c81cc60280b4191", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/804 [00:00<?, ?it/s]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "astor_disc_bc = []\n", + "\n", + "for bc in tqdm(add_ABO_bc):\n", + " astor_request = f'https://astor.onb.ac.at/discovery/internal/search?query=barcode%3A%5C%2B{bc}&from=1&rows=10&apikey={os.getenv(\"ASTOR_API_KEY\")}'\n", + " resp = requests.get(astor_request)\n", + " if resp.status_code == 200:\n", + " astor_disc_bc.append(resp.content)\n", + " else:\n", + " print(resp.status_code)" + ] + }, + { + "cell_type": "code", + "execution_count": 563, + "id": "410dd3bf-7aae-44e2-9bbf-68ac78572c17", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "astor_df = pd.DataFrame(astor_disc_bc)" + ] + }, + { + "cell_type": "code", + "execution_count": 564, + "id": "fb655133-61e7-4f0e-9961-27c99f625074", "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", + "def extract_signature_from_astor_resp(resp):\n", + " resp_dict = json.loads(resp)\n", + " if 'documents' in resp_dict:\n", + " return resp_dict['documents'][0]['signature']\n", + " else:\n", + " return np.nan\n", "\n", - "bc_or_id = signatur_dup.loc[comb_index]" + "astor_df['identifier'] = add_ABO_bc.values\n", + "astor_df['Signatur'] = astor_df[0].apply(lambda x: extract_signature_from_astor_resp(x))" + ] + }, + { + "cell_type": "code", + "execution_count": 565, + "id": "e27eb6e7-9d8f-4c91-969f-377853a878e2", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "astor_sig = astor_df.dropna(subset='Signatur')[['identifier', 'Signatur']]" + ] + }, + { + "cell_type": "code", + "execution_count": 566, + "id": "1e00c711-cdef-48aa-9ef3-1d51c417019d", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "astor_index = add_ABO_bc[add_ABO_bc.isin(astor_sig['identifier'])].index" + ] + }, + { + "cell_type": "code", + "execution_count": 567, + "id": "ce1ad061-c541-4008-92d4-61bf59c098ec", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "astor_sig['BE_index'] = astor_index" + ] + }, + { + "cell_type": "code", + "execution_count": 568, + "id": "508eb802-8122-4de3-b3c2-aed9c0872024", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "for i, row in astor_sig.iterrows():\n", + " comp_BE.at[row['BE_index'], 'Signatur'] = row['Signatur']" + ] + }, + { + "cell_type": "code", + "execution_count": 569, + "id": "10eb31d1-a47c-4bcb-bc27-0208365fabc7", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "dups = comp_BE[comp_BE.duplicated('Signatur', keep=False)].sort_values('Signatur')" ] }, { "cell_type": "code", - "execution_count": 202, - "id": "2b5e1649-0c3f-4966-a1b9-d018fafa963e", + "execution_count": 570, + "id": "1ca5f88a-682c-4653-a9c1-6e406dd2f122", "metadata": { "tags": [] }, @@ -7497,1543 +7609,205 @@ "name": "stdout", "output_type": "stream", "text": [ - "BE.11.O.3\n", - "61.C.8\n" + "397395-D\n", + "BE.11.K.43.(Vol.1.1816/17,1)\n", + "SA.71.E.58\n" ] } ], "source": [ - "test_strs = [\"<a href='http://data.onb.ac.at/rec/AC10305302'>Han BE.11.O.3</a> - ÖNB\",\n", - " \"<a href='http://data.onb.ac.at/rec/AC09707593'>Alt Prunk 61.C.8</a> - 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])" + "t_lis = ['397395-D / Han Kat. 2o 35', 'BE.11.K.43.(Vol.1.1816/17,1)', 'SA.71.E.58 / 13']\n", + "\n", + "slash_re = re.compile(' / .*\\Z')\n", + "for t in t_lis:\n", + " print(re.sub(' / .*\\Z', '', t))" + ] + }, + { + "cell_type": "code", + "execution_count": 571, + "id": "1226b0f2-f33f-45e2-8ace-d3d94ffbd082", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "for i, row in comp_BE.iterrows():\n", + " comp_BE.at[i, 'Signatur'] = re.sub(' / .*\\Z', '', row['Signatur'].replace(';', ''))" + ] + }, + { + "cell_type": "code", + "execution_count": 575, + "id": "a9171adc-217c-4589-a5fe-79aab4cafe40", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "list_of_identifier = comp_BE_no_dup['identifier'].dropna()" + ] + }, + { + "cell_type": "code", + "execution_count": 576, + "id": "3a82a55c-1744-4cee-81fc-a9d3ce5c1554", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "for i, row in list_of_identifier.items():\n", + " comp_BE.at[i, 'Barcode'] = row" ] }, { "cell_type": "code", - "execution_count": 88, - "id": "7f69c459-d24c-4b0c-99bd-ba82651729d0", + "execution_count": 584, + "id": "10bff902-01f1-4e72-98c5-fef5c136041e", "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" + "['1502', '1504']\n", + "1502\n", + "1504\n", + "1521\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" + "import roman\n", + "\n", + "year_str = 'Mense Ianuario. M.D.XXI.'\n", + "year_str_2 = 'Mense Iulio M.D.XXII.'\n", + "year_str_3 = 'M. D.XX. Mense Octobri'\n", + "year_str_4 = 'Mense Decembri. M.D.XX.'\n", + "y5 = 'mense februario 1502 [erschienen 1504]'\n", + "year_re = re.compile('\\d{4}')\n", + "match = re.findall(year_re, y5)\n", + "print(match)\n", + "print(min(match))\n", + "print(max(match))\n", + "roman_re = re.compile('[MDCLXVI]{2,}')\n", + "roman_match = re.search(roman_re, year_str.replace('.', '').replace(' ', '').replace('Mense', ''))\n", + "if roman_match:\n", + " from_roman = roman.fromRoman(roman_match[0])\n", + " print(from_roman)" ] }, { "cell_type": "code", - "execution_count": 127, - "id": "4cd3b69a-f056-47b1-9839-7af995f31533", + "execution_count": 592, + "id": "24ac35ec-c1c3-4828-963a-10c9e585f1f2", "metadata": { "tags": [] }, "outputs": [ { - "data": { - "text/html": [ - "<div>\n", - "<style scoped>\n", - " .dataframe tbody tr th:only-of-type {\n", - " vertical-align: middle;\n", - " }\n", - "\n", - " .dataframe tbody tr th {\n", - " vertical-align: top;\n", - " }\n", - "\n", - " .dataframe thead th {\n", - " text-align: right;\n", - " }\n", - "</style>\n", - "<table border=\"1\" class=\"dataframe\">\n", - " <thead>\n", - " <tr style=\"text-align: right;\">\n", - " <th></th>\n", - " <th>Signatur</th>\n", - " <th>Barcode</th>\n", - " <th>Titel</th>\n", - " <th>Autor</th>\n", - " <th>Mitwirkender</th>\n", - " <th>Anfang Veröffentlichungsdatum</th>\n", - " <th>Ende Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsort</th>\n", - " <th>Veröffentlichungsort (normiert)</th>\n", - " <th>...</th>\n", - " <th>hs. Katalogseite Digitalisat</th>\n", - " <th>Wissensklasse</th>\n", - " <th>Wissensunterklasse</th>\n", - " <th>Formatangabe</th>\n", - " <th>hs. Katalogseite Handschrift</th>\n", - " <th>hs. Katalogeintrag ID</th>\n", - " <th>hs. Katalogeintrag</th>\n", - " <th>hs. Katalog Image URL</th>\n", - " <th>identifier</th>\n", - " <th>ABO-Barcode</th>\n", - " </tr>\n", - " </thead>\n", - " <tbody>\n", - " <tr>\n", - " <th>23092</th>\n", - " <td>51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691507</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23093</th>\n", - " <td>51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691702</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " </tbody>\n", - "</table>\n", - "<p>2 rows × 40 columns</p>\n", - "</div>" - ], - "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" + "name": "stdout", + "output_type": "stream", + "text": [ + "22932 MDLCCCII\n" + ] } ], "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)']" + "for i, row in comp_BE_no_dup.iterrows():\n", + " if pd.isna(row['Anfang Veröffentlichungsdatum']):\n", + " if not pd.isna(row['Veröffentlichungsdatum']):\n", + " year_str = row['Veröffentlichungsdatum']\n", + " year_re = re.compile('\\d{4}')\n", + " match = re.findall(year_re, year_str)\n", + " if match:\n", + " begin = int(min(match))\n", + " comp_BE.at[i, 'Anfang Veröffentlichungsdatum'] = begin\n", + " end = int(max(match))\n", + " if end > begin:\n", + " comp_BE.at[i, 'Ende Veröffentlichungsdatum'] = end\n", + " roman_re = re.compile('[MDCLXVI]{2,}')\n", + " roman_match = re.search(roman_re, year_str.replace('.', '').replace(' ', '').replace('Mense', ''))\n", + " if roman_match:\n", + " try:\n", + " from_roman = roman.fromRoman(roman_match[0])\n", + " comp_BE.at[i, 'Anfang Veröffentlichungsdatum'] = from_roman\n", + " except:\n", + " print(i, roman_match[0])" ] }, { "cell_type": "code", - "execution_count": 99, - "id": "2bcd8b36-3b74-498a-8726-39a9757cbda4", + "execution_count": 597, + "id": "d2827ce0-e51c-47d6-94df-14d104f51c00", "metadata": { "tags": [] }, - "outputs": [ - { - "data": { - "text/html": [ - "<div>\n", - "<style scoped>\n", - " .dataframe tbody tr th:only-of-type {\n", - " vertical-align: middle;\n", - " }\n", - "\n", - " .dataframe tbody tr th {\n", - " vertical-align: top;\n", - " }\n", - "\n", - " .dataframe thead th {\n", - " text-align: right;\n", - " }\n", - "</style>\n", - "<table border=\"1\" class=\"dataframe\">\n", - " <thead>\n", - " <tr style=\"text-align: right;\">\n", - " <th></th>\n", - " <th>Signatur</th>\n", - " <th>Barcode</th>\n", - " <th>Titel</th>\n", - " <th>Autor</th>\n", - " <th>Mitwirkender</th>\n", - " <th>Anfang Veröffentlichungsdatum</th>\n", - " <th>Ende Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsort</th>\n", - " <th>Veröffentlichungsort (normiert)</th>\n", - " <th>...</th>\n", - " <th>hs. Katalogseite Digitalisat</th>\n", - " <th>Wissensklasse</th>\n", - " <th>Wissensunterklasse</th>\n", - " <th>Formatangabe</th>\n", - " <th>hs. Katalogseite Handschrift</th>\n", - " <th>hs. Katalogeintrag ID</th>\n", - " <th>hs. Katalogeintrag</th>\n", - " <th>hs. Katalog Image URL</th>\n", - " <th>identifier</th>\n", - " <th>ABO-Barcode</th>\n", - " </tr>\n", - " </thead>\n", - " <tbody>\n", - " <tr>\n", - " <th>22664</th>\n", - " <td>BE.8.P.19.20.(Vol.2)</td>\n", - " <td>NaN</td>\n", - " <td>Histoire Vniverselle Des Gverres Dv Tvrc, Depv...</td>\n", - " <td>Montreux, Nicolas <<de>></td>\n", - " <td>Heinrich; Mousson, Pierre; Orléans, Louis <<d'...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>MDCVIII</td>\n", - " <td>A Paris</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>rep_131EA36A</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22671</th>\n", - " <td>MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1)</td>\n", - " <td>NaN</td>\n", - " <td>La bible en francoiz</td>\n", - " <td>Petrus</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>[s.a. um 1520]</td>\n", - " <td>Paris</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z150809303</td>\n", - " <td>Z150809303; Z150809406</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22672</th>\n", - " <td>MF 1774; 2.D.2.(Vol.2); 2.D.2.(Vol.1)</td>\n", - " <td>NaN</td>\n", - " <td>La bible en francoiz</td>\n", - " <td>Petrus</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>[s.a. um 1520]</td>\n", - " <td>Paris</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z150809406</td>\n", - " <td>Z150809303; Z150809406</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22681</th>\n", - " <td>49.D.18.(Vol.2); 49.D.18.(Vol.1)</td>\n", - " <td>NaN</td>\n", - " <td>Joannis Trithemij ... Et Postea Divi Jacobi a...</td>\n", - " <td>Trithemius, Johannes</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1690</td>\n", - " <td>Typis Monasterij S. Galli</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z156354802</td>\n", - " <td>Z156354802; Z156354905</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22682</th>\n", - " <td>49.D.18.(Vol.2); 49.D.18.(Vol.1)</td>\n", - " <td>NaN</td>\n", - " <td>Joannis Trithemij ... Et Postea Divi Jacobi a...</td>\n", - " <td>Trithemius, Johannes</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1690</td>\n", - " <td>Typis Monasterij S. Galli</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z156354905</td>\n", - " <td>Z156354802; Z156354905</td>\n", - " </tr>\n", - " <tr>\n", - " <th>...</th>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23391</th>\n", - " <td>*28.A.79.(Vol.21)</td>\n", - " <td>NaN</td>\n", - " <td>Histoire des ouvrages des scavans</td>\n", - " <td>Basnage de Beauval, Henri</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1687-1709</td>\n", - " <td>Rotterdam</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z222909207</td>\n", - " <td>Z222909402; Z222908707; Z22290720X; Z222907107...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23392</th>\n", - " <td>*28.A.79.(Vol.22)</td>\n", - " <td>NaN</td>\n", - " <td>Histoire des ouvrages des scavans</td>\n", - " <td>Basnage de Beauval, Henri</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1687-1709</td>\n", - " <td>Rotterdam</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z22290930X</td>\n", - " <td>Z222909402; Z222908707; Z22290720X; Z222907107...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23393</th>\n", - " <td>*28.A.79.(Vol.23)</td>\n", - " <td>NaN</td>\n", - " <td>Histoire des ouvrages des scavans</td>\n", - " <td>Basnage de Beauval, Henri</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1687-1709</td>\n", - " <td>Rotterdam</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z222909402</td>\n", - " <td>Z222909402; Z222908707; Z22290720X; Z222907107...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23394</th>\n", - " <td>*28.A.79.(Vol.24)</td>\n", - " <td>NaN</td>\n", - " <td>Histoire des ouvrages des scavans</td>\n", - " <td>Basnage de Beauval, Henri</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1687-1709</td>\n", - " <td>Rotterdam</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z222909505</td>\n", - " <td>Z222909402; Z222908707; Z22290720X; Z222907107...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23395</th>\n", - " <td>*28.A.79.(Vol.25)</td>\n", - " <td>NaN</td>\n", - " <td>Histoire des ouvrages des scavans</td>\n", - " <td>Basnage de Beauval, Henri</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1687-1709</td>\n", - " <td>Rotterdam</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z222909608</td>\n", - " <td>Z222909402; Z222908707; Z22290720X; Z222907107...</td>\n", - " </tr>\n", - " </tbody>\n", - "</table>\n", - "<p>229 rows × 40 columns</p>\n", - "</div>" - ], - "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 <<de>> \\\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 <<d'... \\\n", - "22671 NaN \n", - "22672 NaN \n", - "22681 NaN \n", - "22682 NaN \n", - "... ... \n", - "23391 NaN \n", - "23392 NaN \n", - "23393 NaN \n", - "23394 NaN \n", - "23395 NaN \n", - "\n", - " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", - "22664 NaN NaN \\\n", - "22671 NaN NaN \n", - "22672 NaN NaN \n", - "22681 NaN NaN \n", - "22682 NaN NaN \n", - "... ... ... \n", - "23391 NaN NaN \n", - "23392 NaN NaN \n", - "23393 NaN NaN \n", - "23394 NaN NaN \n", - "23395 NaN NaN \n", - "\n", - " Veröffentlichungsdatum Veröffentlichungsort \n", - "22664 MDCVIII A Paris \\\n", - "22671 [s.a. um 1520] Paris \n", - "22672 [s.a. um 1520] Paris \n", - "22681 1690 Typis Monasterij S. Galli \n", - "22682 1690 Typis Monasterij S. Galli \n", - "... ... ... \n", - "23391 1687-1709 Rotterdam \n", - "23392 1687-1709 Rotterdam \n", - "23393 1687-1709 Rotterdam \n", - "23394 1687-1709 Rotterdam \n", - "23395 1687-1709 Rotterdam \n", - "\n", - " Veröffentlichungsort (normiert) ... hs. Katalogseite Digitalisat \n", - "22664 NaN ... NaN \\\n", - "22671 NaN ... NaN \n", - "22672 NaN ... NaN \n", - "22681 NaN ... NaN \n", - "22682 NaN ... NaN \n", - "... ... ... ... \n", - "23391 NaN ... NaN \n", - "23392 NaN ... NaN \n", - "23393 NaN ... NaN \n", - "23394 NaN ... NaN \n", - "23395 NaN ... NaN \n", - "\n", - " Wissensklasse Wissensunterklasse Formatangabe \n", - "22664 NaN NaN NaN \\\n", - "22671 NaN NaN NaN \n", - "22672 NaN NaN NaN \n", - "22681 NaN NaN NaN \n", - "22682 NaN NaN NaN \n", - "... ... ... ... \n", - "23391 NaN NaN NaN \n", - "23392 NaN NaN NaN \n", - "23393 NaN NaN NaN \n", - "23394 NaN NaN NaN \n", - "23395 NaN NaN NaN \n", - "\n", - " hs. Katalogseite Handschrift hs. Katalogeintrag ID hs. Katalogeintrag \n", - "22664 NaN NaN NaN \\\n", - "22671 NaN NaN NaN \n", - "22672 NaN NaN NaN \n", - "22681 NaN NaN NaN \n", - "22682 NaN NaN NaN \n", - "... ... ... ... \n", - "23391 NaN NaN NaN \n", - "23392 NaN NaN NaN \n", - "23393 NaN NaN NaN \n", - "23394 NaN NaN NaN \n", - "23395 NaN NaN NaN \n", - "\n", - " hs. Katalog Image URL identifier \n", - "22664 NaN rep_131EA36A \\\n", - "22671 NaN Z150809303 \n", - "22672 NaN Z150809406 \n", - "22681 NaN Z156354802 \n", - "22682 NaN Z156354905 \n", - "... ... ... \n", - "23391 NaN Z222909207 \n", - "23392 NaN Z22290930X \n", - "23393 NaN Z222909402 \n", - "23394 NaN Z222909505 \n", - "23395 NaN Z222909608 \n", - "\n", - " ABO-Barcode \n", - "22664 NaN \n", - "22671 Z150809303; Z150809406 \n", - "22672 Z150809303; Z150809406 \n", - "22681 Z156354802; Z156354905 \n", - "22682 Z156354802; Z156354905 \n", - "... ... \n", - "23391 Z222909402; Z222908707; Z22290720X; Z222907107... \n", - "23392 Z222909402; Z222908707; Z22290720X; Z222907107... \n", - "23393 Z222909402; Z222908707; Z22290720X; Z222907107... \n", - "23394 Z222909402; Z222908707; Z22290720X; Z222907107... \n", - "23395 Z222909402; Z222908707; Z22290720X; Z222907107... \n", - "\n", - "[229 rows x 40 columns]" - ] - }, - "execution_count": 99, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ - "signatur_dup[signatur_dup['Barcode'].isna()].dropna(subset=['identifier'])" + "comp_BE.at[22932, 'Anfang Veröffentlichungsdatum'] = 1582" ] }, { "cell_type": "code", - "execution_count": 135, - "id": "089d8056-b97f-4672-86a2-e70347af00b2", + "execution_count": 604, + "id": "62c21c7a-633e-48f5-aba1-a54590e9df16", "metadata": { "tags": [] }, - "outputs": [ - { - "data": { - "text/html": [ - "<div>\n", - "<style scoped>\n", - " .dataframe tbody tr th:only-of-type {\n", - " vertical-align: middle;\n", - " }\n", - "\n", - " .dataframe tbody tr th {\n", - " vertical-align: top;\n", - " }\n", - "\n", - " .dataframe thead th {\n", - " text-align: right;\n", - " }\n", - "</style>\n", - "<table border=\"1\" class=\"dataframe\">\n", - " <thead>\n", - " <tr style=\"text-align: right;\">\n", - " <th></th>\n", - " <th>Signatur</th>\n", - " <th>Barcode</th>\n", - " <th>Titel</th>\n", - " <th>Autor</th>\n", - " <th>Mitwirkender</th>\n", - " <th>Anfang Veröffentlichungsdatum</th>\n", - " <th>Ende Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsort</th>\n", - " <th>Veröffentlichungsort (normiert)</th>\n", - " <th>...</th>\n", - " <th>hs. Katalogseite Digitalisat</th>\n", - " <th>Wissensklasse</th>\n", - " <th>Wissensunterklasse</th>\n", - " <th>Formatangabe</th>\n", - " <th>hs. Katalogseite Handschrift</th>\n", - " <th>hs. Katalogeintrag ID</th>\n", - " <th>hs. Katalogeintrag</th>\n", - " <th>hs. Katalog Image URL</th>\n", - " <th>identifier</th>\n", - " <th>ABO-Barcode</th>\n", - " </tr>\n", - " </thead>\n", - " <tbody>\n", - " <tr>\n", - " <th>23089</th>\n", - " <td>51.O.14-19.(Vol.1)</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691209</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23090</th>\n", - " <td>51.O.14-19.(Vol.2)</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691301</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23091</th>\n", - " <td>51.O.14-19.(Vol.3)</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691404</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23092</th>\n", - " <td>51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691507</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23093</th>\n", - " <td>51.O.14-19.(Vol.4); 51.O.14-19.(Vol.3); 51.O.1...</td>\n", - " <td>NaN</td>\n", - " <td>Historiarum sui temporis av anno 1543 usque ad...</td>\n", - " <td>Thou, Jacques Auguste de</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>1620-1621</td>\n", - " <td>Aurelianae</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Z169691702</td>\n", - " <td>Z169691507; Z16969160X; Z169691702; Z169691209...</td>\n", - " </tr>\n", - " </tbody>\n", - "</table>\n", - "<p>5 rows × 40 columns</p>\n", - "</div>" - ], - "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" - } - ], + "outputs": [], "source": [ - "signatur_dup.loc[23089:23093]" + "# Drop wrong catalog item\n", + "comp_BE.drop(22498, inplace=True)" ] }, { "cell_type": "code", - "execution_count": 157, - "id": "c1f1b4a5-3d05-44b3-83fa-f238b6e6e1d2", + "execution_count": 623, + "id": "3399ab3c-13f5-4bc9-b38d-e61adde2229a", "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" - } - ], + "outputs": [], "source": [ - "comp_BE_sig = comp_BE.dropna(subset='Signatur')\n", - "comp_BE_sig[comp_BE_sig['Signatur'].str.contains('BE.1.A.4')].values" + "def obtain_barcode_category(bc):\n", + " if pd.isna(bc):\n", + " return 'NaN'\n", + " if 'B' in bc:\n", + " cat = 'B'\n", + " elif 'Z' in bc:\n", + " cat = 'Z'\n", + " else:\n", + " cat = '\\d'\n", + " return cat\n", + "\n", + "comp_BE['Barcode category'] = comp_BE['Barcode'].apply(lambda x: obtain_barcode_category(x))\n", + "comp_BE['Barcode category'] = comp_BE['Barcode category'].astype('category')\n", + "comp_BE['Barcode category'] = comp_BE['Barcode category'].cat.set_categories(['Z', 'B', '\\d', 'NaN'], ordered=True)\n", + "comp_BE.sort_values(['Signatur', 'Barcode category'], inplace=True, ascending=True)\n", + "comp_BE_no_dup = comp_BE.drop_duplicates('Signatur', keep='first')" ] }, { "cell_type": "code", - "execution_count": 155, - "id": "176540c8-773d-4201-a1f4-b8e92cf271ac", + "execution_count": 617, + "id": "91236684-de60-4478-ad7c-c2282aa276f3", "metadata": { "tags": [] }, - "outputs": [ - { - "data": { - "text/html": [ - "<div>\n", - "<style scoped>\n", - " .dataframe tbody tr th:only-of-type {\n", - " vertical-align: middle;\n", - " }\n", - "\n", - " .dataframe tbody tr th {\n", - " vertical-align: top;\n", - " }\n", - "\n", - " .dataframe thead th {\n", - " text-align: right;\n", - " }\n", - "</style>\n", - "<table border=\"1\" class=\"dataframe\">\n", - " <thead>\n", - " <tr style=\"text-align: right;\">\n", - " <th></th>\n", - " <th>Signatur</th>\n", - " <th>Barcode</th>\n", - " <th>Titel</th>\n", - " <th>Autor</th>\n", - " <th>Mitwirkender</th>\n", - " <th>Anfang Veröffentlichungsdatum</th>\n", - " <th>Ende Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsdatum</th>\n", - " <th>Veröffentlichungsort</th>\n", - " <th>Veröffentlichungsort (normiert)</th>\n", - " <th>...</th>\n", - " <th>hs. Katalogseite Digitalisat</th>\n", - " <th>Wissensklasse</th>\n", - " <th>Wissensunterklasse</th>\n", - " <th>Formatangabe</th>\n", - " <th>hs. Katalogseite Handschrift</th>\n", - " <th>hs. Katalogeintrag ID</th>\n", - " <th>hs. Katalogeintrag</th>\n", - " <th>hs. Katalog Image URL</th>\n", - " <th>identifier</th>\n", - " <th>ABO-Barcode</th>\n", - " </tr>\n", - " </thead>\n", - " <tbody>\n", - " <tr>\n", - " <th>22498</th>\n", - " <td>Wien, ÖNB (2: BE.12.K.1; 657.936-C. Neu Mag)</td>\n", - " <td>NaN</td>\n", - " <td>Decades rerum Venetarum [Italian] Croniche che...</td>\n", - " <td>Sabellicus, Marcus Antonius</td>\n", - " <td>Gotardus da Ponte, for Oldradus Lampugnanus</td>\n", - " <td>1510.0</td>\n", - " <td>NaN</td>\n", - " <td>about 1510?</td>\n", - " <td>NaN</td>\n", - " <td>Milan</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22499</th>\n", - " <td>BE.1.A.4.(Vol.1);</td>\n", - " <td>NaN</td>\n", - " <td>Voyage Pittoresque De La Syrie, De La Phœnicie...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Paris</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22500</th>\n", - " <td>BE.1.A.4.(Vol.2);</td>\n", - " <td>NaN</td>\n", - " <td>Voyage Pittoresque De La Syrie, De La Phœnicie...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Paris</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22501</th>\n", - " <td>BE.9.L.1;</td>\n", - " <td>NaN</td>\n", - " <td>Voyages De Monsieur Le Chevalier Chardin, En P...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>Paris</td>\n", - " <td>...</td>\n", - " <td>306.0</td>\n", - " <td>Geographia</td>\n", - " <td>Peregrinationes, Navigationes, & Itinera</td>\n", - " <td>Quarto</td>\n", - " <td>700</td>\n", - " <td>14.377_306_02</td>\n", - " <td>Voyages du Chevalier Chardin en Perse & autres...</td>\n", - " <td>https://iiif.onb.ac.at/images/DOD/51184/000003...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>22502</th>\n", - " <td>BE.5.T.65a;</td>\n", - " <td>NaN</td>\n", - " <td>Vorlesungen über die Militairgraphik in besond...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>...</th>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " <td>...</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23645</th>\n", - " <td>Ink 32-126; Ink 4.H.35</td>\n", - " <td>NaN</td>\n", - " <td>Polyhistor, sive De mirabilibus mundi. Add: Mi...</td>\n", - " <td>Solinus, Gaius Iulius</td>\n", - " <td>Ragazonibus, Theodorus <<de>></td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>23. Aug. 1491; [1491.08.23]</td>\n", - " <td>Venedig</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23654</th>\n", - " <td>Ink 23.E.10; Ink 4.F.42</td>\n", - " <td>NaN</td>\n", - " <td>Comoediae. Cum directorio vocabulorum, glossa ...</td>\n", - " <td>Terentius Afer, Publius</td>\n", - " <td>Donatus, Aelius; Jouenneaux, Guy; Badius Ascen...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>11 Feb. 1499</td>\n", - " <td>Strassburg</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23657</th>\n", - " <td>Ink 21.A.23; Ink 5.C.13</td>\n", - " <td>NaN</td>\n", - " <td>Quaestiones de duodecim quodlibet</td>\n", - " <td>Thomas</td>\n", - " <td>Sensenschmidt, Johann; Frisner, Andreas</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>15 Apr. 1474</td>\n", - " <td>Nuremberg</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23658</th>\n", - " <td>Ink 6.B.10; Ink 6.B.9</td>\n", - " <td>NaN</td>\n", - " <td>Super quarto libro Sententiarum</td>\n", - " <td>Thomas Aquinas</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>13 June 1469</td>\n", - " <td>Mainz</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " <tr>\n", - " <th>23661</th>\n", - " <td>Ink 7.F.26; Ink 32-108</td>\n", - " <td>NaN</td>\n", - " <td>Orthographia. (Ed: Hieronymus Bononius)</td>\n", - " <td>Tortellius, Johannes</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>2 Apr. 1477</td>\n", - " <td>Treviso</td>\n", - " <td>NaN</td>\n", - " <td>...</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " <td>NaN</td>\n", - " </tr>\n", - " </tbody>\n", - "</table>\n", - "<p>471 rows × 40 columns</p>\n", - "</div>" - ], - "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 <<de>> \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" - } - ], + "outputs": [], "source": [ - "comp_BE_sig[comp_BE_sig['Signatur'].str.contains(';')]" + "# Zwischenstand abspeichern\n", + "comp_BE_no_dup.to_excel('../Daten/Vorhersagen/Complete_BE_Years.xlsx')" ] }, { "cell_type": "code", "execution_count": null, - "id": "3ed0a9bd-7828-4140-b865-13b9f52bf7f7", + "id": "85e24615-b3f9-4e5f-b1a7-a1e4eedd18ef", "metadata": {}, "outputs": [], "source": [] diff --git a/Notebooks/String_matching.ipynb b/Notebooks/String_matching.ipynb index e0747044ca011d9277e569728c603a4f8f1cba7c..a10ecb03d9c63c7f466d40c12eb2995322d6b319 100644 --- a/Notebooks/String_matching.ipynb +++ b/Notebooks/String_matching.ipynb @@ -114,7 +114,7 @@ }, { "cell_type": "code", - "execution_count": 98, + "execution_count": 114, "id": "c0f4a42a-7e21-41e8-833c-2dd2f9d1985e", "metadata": { "tags": [] @@ -161,39 +161,39 @@ " </thead>\n", " <tbody>\n", " <tr>\n", - " <th>7058</th>\n", - " <td>14.378</td>\n", - " <td>205</td>\n", - " <td>Historia Nova Europæ</td>\n", - " <td>Historia Hispanica generalis & aliquot temporum; Vitæ Regum; aliaque</td>\n", + " <th>2147</th>\n", + " <td>14.376</td>\n", + " <td>364</td>\n", + " <td>Artes</td>\n", + " <td>Ars Militaris, cum tractatibus de Tormentis Bellicis</td>\n", " <td>Folio</td>\n", - " <td>1043</td>\n", - " <td>14.378_205_04</td>\n", - " <td>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.</td>\n", - " <td>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</td>\n", + " <td>318</td>\n", + " <td>14.376_364_00</td>\n", + " <td>611 Carte generale de l'Histoire Militaire de France depuis Clovis jusqu'a la XV.e Année du Regne de Louis XV. par le S. Lemau de la Iaisse. 1733. chez l'Autheur. n. CCXLVIII</td>\n", + " <td>Carte generale de l'Histoire Militaire de France depuis Clovis jusqu'a la XVe Annee du Regne de Louis XV par le S Lemau de la Iaisse 1733 chez l'Autheur n CCXLVIII</td>\n", " </tr>\n", " </tbody>\n", "</table>\n", "</div>" ], "text/plain": [ - " volume page number category \n", - "7058 14.378 205 Historia Nova Europæ \\\n", + " volume page number category \n", + "2147 14.376 364 Artes \\\n", "\n", - " subcategory \n", - "7058 Historia Hispanica generalis & aliquot temporum; Vitæ Regum; aliaque \\\n", + " subcategory format \n", + "2147 Ars Militaris, cum tractatibus de Tormentis Bellicis Folio \\\n", "\n", - " format handwritten page number entry_ID \n", - "7058 Folio 1043 14.378_205_04 \\\n", + " handwritten page number entry_ID \n", + "2147 318 14.376_364_00 \\\n", "\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", + " entry \n", + "2147 611 Carte generale de l'Histoire Militaire de France depuis Clovis jusqu'a la XV.e Année du Regne de Louis XV. par le S. Lemau de la Iaisse. 1733. chez l'Autheur. n. CCXLVIII \\\n", "\n", - " 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 " + " cleaned entry \n", + "2147 Carte generale de l'Histoire Militaire de France depuis Clovis jusqu'a la XVe Annee du Regne de Louis XV par le S Lemau de la Iaisse 1733 chez l'Autheur n CCXLVIII " ] }, - "execution_count": 98, + "execution_count": 114, "metadata": {}, "output_type": "execute_result" } @@ -202,7 +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, 'Beuter'), '')\n", + "info = search_in_entry(search_in_entry(entry_df, 'Carte'), '1733')\n", "print(len(info))\n", "info" ] diff --git a/requirements.txt b/requirements.txt index c2f2a8930fdc705b30d85b6d7bcb1be8d1c33513..75247b6c6e2b26be1a37f7ff7182ad908c13b305 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,9 +1,10 @@ matplotlib opencv-python openpyxl -progress pandas +progress +python-dotenv requests +roman sickle -python-dotenv thefuzz