From e50a85fca86b3b832649a120bfc2a748a7bf1abb Mon Sep 17 00:00:00 2001 From: smayer <simon.mayer@onb.ac.at> Date: Thu, 22 Aug 2024 14:55:43 +0000 Subject: [PATCH] WIP Albertina books and plots --- Notebooks/Albertina_Bestaende.ipynb | 673 ++++++++++++++- Notebooks/Classifier_plots.ipynb | 985 +++++++++++++++++++++ Notebooks/String_matching.ipynb | 1234 ++++++++++++++++++++++++++- 3 files changed, 2851 insertions(+), 41 deletions(-) create mode 100644 Notebooks/Classifier_plots.ipynb diff --git a/Notebooks/Albertina_Bestaende.ipynb b/Notebooks/Albertina_Bestaende.ipynb index 8c2d83d..fc29ced 100644 --- a/Notebooks/Albertina_Bestaende.ipynb +++ b/Notebooks/Albertina_Bestaende.ipynb @@ -429,7 +429,7 @@ }, { "cell_type": "code", - "execution_count": 100, + "execution_count": 108, "id": "dac1e7bd-793c-4841-876c-09ce04c66e33", "metadata": { "tags": [] @@ -467,12 +467,512 @@ " </thead>\n", " <tbody>\n", " <tr>\n", - " <th>93</th>\n", + " <th>0</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach I, 19</td>\n", + " <td>Ingessus Clement. VII Papae</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach I, 29</td>\n", + " <td>Plantes de l'acades Scieno, Tom. I</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach I, 29</td>\n", + " <td>Plantes de l'acades Scieno, Tom. II</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach II, 27a</td>\n", + " <td>Histoire de la triomphante entrée de Roy […]</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach IV, 26a</td>\n", + " <td>Ulisse all'Isola di Circe.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>5</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach IV, 29a</td>\n", + " <td>Histoire de Psiche et Cupidon gravée sur les dessins de Raphael.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>6</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach IV, 38</td>\n", + " <td>Les heros de la Ligue</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>7</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach VII, 28 ; K.S.B-137</td>\n", + " <td>Archtypa studiaque patris. Jacobus F. genio duce ab ipso scalpta, omnibus philomusis amice D: ac perbenigne communicat.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>8</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Cimelien</td>\n", + " <td>Fach VII ,29 ; K.S.B-59</td>\n", + " <td>[Celsissimus ac illustrissimus princeps]</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>9</th>\n", + " <td>UG5</td>\n", + " <td>36.0</td>\n", + " <td>Vues Frankreich Richelieu R</td>\n", + " <td>K.S.B-7</td>\n", + " <td>Le magnifique chasteau de Richelieu</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>10</th>\n", + " <td>UG5</td>\n", + " <td>36.0</td>\n", + " <td>Vues Italien Rom R</td>\n", + " <td>K.S.B-61</td>\n", + " <td>Antiquae urbis splendor</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>11</th>\n", + " <td>UG5 Depot</td>\n", + " <td>95.0</td>\n", + " <td>Vues Italien Venezia</td>\n", + " <td>K.S.C-134</td>\n", + " <td>Fabriche e Vedvte di Venezia</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>12</th>\n", + " <td>UG5</td>\n", + " <td>36.0</td>\n", + " <td>Vues Frankreich Allgemein</td>\n", + " <td>K.S.C-139</td>\n", + " <td>Veues des plus beaux bâtimens de France</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>13</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>24.D.6</td>\n", + " <td>Festa eqvestria stvtgardiae celebrat</td>\n", + " <td>NaN</td>\n", + " <td>True</td>\n", + " </tr>\n", + " <tr>\n", + " <th>14</th>\n", + " <td>UG5 Depot</td>\n", + " <td>95.0</td>\n", + " <td>Vues Italien Rom</td>\n", + " <td>K.S.C-316</td>\n", + " <td>Vestigi antic. di Roma</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>15</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>587972-F</td>\n", + " <td>Architet di L. B. Alberti, Tom. I</td>\n", + " <td>NaN</td>\n", + " <td>True</td>\n", + " </tr>\n", + " <tr>\n", + " <th>16</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>587972-F</td>\n", + " <td>Architetv di L. B. Alberti, Tom. II</td>\n", + " <td>NaN</td>\n", + " <td>True</td>\n", + " </tr>\n", + " <tr>\n", + " <th>17</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>587972-F</td>\n", + " <td>Architet di L. B. Alberti, Tom. III</td>\n", + " <td>NaN</td>\n", + " <td>True</td>\n", + " </tr>\n", + " <tr>\n", + " <th>18</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-60</td>\n", + " <td>Nymphaevm</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>19</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-65</td>\n", + " <td>L'obelis. Vatican. dal cav.fontan.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>20</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-88</td>\n", + " <td>Oevvres de teniers</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>21</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-112</td>\n", + " <td>Fvner. Dvcis cliviae</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-116</td>\n", + " <td>Jnf. Ferdin. Jntroii in gandavu</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-126</td>\n", + " <td>Entr dell ambasc. di pol. in roma</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>24</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-140</td>\n", + " <td>Architet. Di Labaco & altri ornament</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>25</th>\n", + " <td>UG5 Depot</td>\n", + " <td>95.0</td>\n", + " <td>Vues Deutschland Ludwigsburg</td>\n", + " <td>K.S.D-141</td>\n", + " <td>Chat. De Lovisbovrg</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>26</th>\n", " <td>UG3 Depot</td>\n", " <td>NaN</td>\n", " <td>Galeriewerke</td>\n", - " <td>K.S.E-201</td>\n", - " <td>Bidloo Corpor Human Anatomia</td>\n", + " <td>K.S.D-147</td>\n", + " <td>Vasi antichi etarghe di Roma</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>27</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-158</td>\n", + " <td>Pompa Fvn. Ioan. Frid. Brvnsvicae Dvcis</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>28</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-160</td>\n", + " <td>Fvneral. principis aravsiac.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>29</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>24.D.7</td>\n", + " <td>Pompe funèbre du très-pieux et très-puissant Prince Albert</td>\n", + " <td>NaN</td>\n", + " <td>True</td>\n", + " </tr>\n", + " <tr>\n", + " <th>30</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-193</td>\n", + " <td>Gallerie du palais Magnani peinte par les Carrached</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>31</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-194</td>\n", + " <td>Archite civile di diveravtori, Tom. II</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>32</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-202</td>\n", + " <td>Rec. de vases antiqvae par errard</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>33</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-204</td>\n", + " <td>Galleria Givstiniana, Tom. I</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>34</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-204</td>\n", + " <td>Galleria Givstiniana, Tom. II</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>35</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-205</td>\n", + " <td>L'art de scvlptvre par Bossvi</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>36</th>\n", + " <td>UG5 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Illustrierte Bücher Custos</td>\n", + " <td>K.S.D-207</td>\n", + " <td>Portraits & vies de plvs. Princes & Generavy en Allemand</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>37</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-217</td>\n", + " <td>Pacificator orbis christiani</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>38</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-220</td>\n", + " <td>Medailles de Louis le grand</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>39</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-221</td>\n", + " <td>Histoire de Lovis XIV en medailles</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>40</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-222</td>\n", + " <td>Descr. De L'hot. Des Inval.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>41</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-223</td>\n", + " <td>Medaillo dv Cabinet dv Roy</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>42</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-360</td>\n", + " <td>Arc. Constantini</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>43</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>24.D.8</td>\n", + " <td>Fvner Car. V. Imper</td>\n", + " <td>NaN</td>\n", + " <td>True</td>\n", + " </tr>\n", + " <tr>\n", + " <th>44</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-363</td>\n", + " <td>Venet. Habit & specta</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>45</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-378</td>\n", + " <td>Pompa Fvn. Alberti PII</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>46</th>\n", + " <td>UG5 Depot</td>\n", + " <td>94.0</td>\n", + " <td>Illustrierte Bücher Mittelli</td>\n", + " <td>K.S.D-384</td>\n", + " <td>L'arti perviua di Bologna Caraci</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>47</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-413</td>\n", + " <td>Ingress. Deorv & Dearv Dresd.</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>48</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-418</td>\n", + " <td>100 Statvae antiqvae</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>49</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-421</td>\n", + " <td>Recveil d'oseav par Robert</td>\n", + " <td>NaN</td>\n", + " <td>False</td>\n", + " </tr>\n", + " <tr>\n", + " <th>50</th>\n", + " <td>UG3 Depot</td>\n", + " <td>NaN</td>\n", + " <td>Galeriewerke</td>\n", + " <td>K.S.D-464</td>\n", + " <td>Ingres legat Caesar & Portae</td>\n", " <td>NaN</td>\n", " <td>False</td>\n", " </tr>\n", @@ -481,20 +981,173 @@ "</div>" ], "text/plain": [ - " Standort Regal Systematik Signatur (rot: ÖNB) \n", - "93 UG3 Depot NaN Galeriewerke K.S.E-201 \\\n", + " Standort Regal Systematik Signatur (rot: ÖNB) \n", + "0 UG3 Depot NaN Cimelien Fach I, 19 \\\n", + "1 UG3 Depot NaN Cimelien Fach I, 29 \n", + "2 UG3 Depot NaN Cimelien Fach I, 29 \n", + "3 UG3 Depot NaN Cimelien Fach II, 27a \n", + "4 UG3 Depot NaN Cimelien Fach IV, 26a \n", + "5 UG3 Depot NaN Cimelien Fach IV, 29a \n", + "6 UG3 Depot NaN Cimelien Fach IV, 38 \n", + "7 UG3 Depot NaN Cimelien Fach VII, 28 ; K.S.B-137 \n", + "8 UG3 Depot NaN Cimelien Fach VII ,29 ; K.S.B-59 \n", + "9 UG5 36.0 Vues Frankreich Richelieu R K.S.B-7 \n", + "10 UG5 36.0 Vues Italien Rom R K.S.B-61 \n", + "11 UG5 Depot 95.0 Vues Italien Venezia K.S.C-134 \n", + "12 UG5 36.0 Vues Frankreich Allgemein K.S.C-139 \n", + "13 UG3 Depot NaN Galeriewerke 24.D.6 \n", + "14 UG5 Depot 95.0 Vues Italien Rom K.S.C-316 \n", + "15 UG3 Depot NaN Galeriewerke 587972-F \n", + "16 UG3 Depot NaN Galeriewerke 587972-F \n", + "17 UG3 Depot NaN Galeriewerke 587972-F \n", + "18 UG3 Depot NaN Galeriewerke K.S.D-60 \n", + "19 UG3 Depot NaN Galeriewerke K.S.D-65 \n", + "20 UG3 Depot NaN Galeriewerke K.S.D-88 \n", + "21 UG3 Depot NaN Galeriewerke K.S.D-112 \n", + "22 UG3 Depot NaN Galeriewerke K.S.D-116 \n", + "23 UG3 Depot NaN Galeriewerke K.S.D-126 \n", + "24 UG3 Depot NaN Galeriewerke K.S.D-140 \n", + "25 UG5 Depot 95.0 Vues Deutschland Ludwigsburg K.S.D-141 \n", + "26 UG3 Depot NaN Galeriewerke K.S.D-147 \n", + "27 UG3 Depot NaN Galeriewerke K.S.D-158 \n", + "28 UG3 Depot NaN Galeriewerke K.S.D-160 \n", + "29 UG3 Depot NaN Galeriewerke 24.D.7 \n", + "30 UG3 Depot NaN Galeriewerke K.S.D-193 \n", + "31 UG3 Depot NaN Galeriewerke K.S.D-194 \n", + "32 UG3 Depot NaN Galeriewerke K.S.D-202 \n", + "33 UG3 Depot NaN Galeriewerke K.S.D-204 \n", + "34 UG3 Depot NaN Galeriewerke K.S.D-204 \n", + "35 UG3 Depot NaN Galeriewerke K.S.D-205 \n", + "36 UG5 Depot NaN Illustrierte Bücher Custos K.S.D-207 \n", + "37 UG3 Depot NaN Galeriewerke K.S.D-217 \n", + "38 UG3 Depot NaN Galeriewerke K.S.D-220 \n", + "39 UG3 Depot NaN Galeriewerke K.S.D-221 \n", + "40 UG3 Depot NaN Galeriewerke K.S.D-222 \n", + "41 UG3 Depot NaN Galeriewerke K.S.D-223 \n", + "42 UG3 Depot NaN Galeriewerke K.S.D-360 \n", + "43 UG3 Depot NaN Galeriewerke 24.D.8 \n", + "44 UG3 Depot NaN Galeriewerke K.S.D-363 \n", + "45 UG3 Depot NaN Galeriewerke K.S.D-378 \n", + "46 UG5 Depot 94.0 Illustrierte Bücher Mittelli K.S.D-384 \n", + "47 UG3 Depot NaN Galeriewerke K.S.D-413 \n", + "48 UG3 Depot NaN Galeriewerke K.S.D-418 \n", + "49 UG3 Depot NaN Galeriewerke K.S.D-421 \n", + "50 UG3 Depot NaN Galeriewerke K.S.D-464 \n", + "\n", + " Kurztitel \n", + "0 Ingessus Clement. VII Papae \\\n", + "1 Plantes de l'acades Scieno, Tom. I \n", + "2 Plantes de l'acades Scieno, Tom. II \n", + "3 Histoire de la triomphante entrée de Roy […] \n", + "4 Ulisse all'Isola di Circe. \n", + "5 Histoire de Psiche et Cupidon gravée sur les dessins de Raphael. \n", + "6 Les heros de la Ligue \n", + "7 Archtypa studiaque patris. Jacobus F. genio duce ab ipso scalpta, omnibus philomusis amice D: ac perbenigne communicat. \n", + "8 [Celsissimus ac illustrissimus princeps] \n", + "9 Le magnifique chasteau de Richelieu \n", + "10 Antiquae urbis splendor \n", + "11 Fabriche e Vedvte di Venezia \n", + "12 Veues des plus beaux bâtimens de France \n", + "13 Festa eqvestria stvtgardiae celebrat \n", + "14 Vestigi antic. di Roma \n", + "15 Architet di L. B. Alberti, Tom. I \n", + "16 Architetv di L. B. Alberti, Tom. II \n", + "17 Architet di L. B. Alberti, Tom. III \n", + "18 Nymphaevm \n", + "19 L'obelis. Vatican. dal cav.fontan. \n", + "20 Oevvres de teniers \n", + "21 Fvner. Dvcis cliviae \n", + "22 Jnf. Ferdin. Jntroii in gandavu \n", + "23 Entr dell ambasc. di pol. in roma \n", + "24 Architet. Di Labaco & altri ornament \n", + "25 Chat. De Lovisbovrg \n", + "26 Vasi antichi etarghe di Roma \n", + "27 Pompa Fvn. Ioan. Frid. Brvnsvicae Dvcis \n", + "28 Fvneral. principis aravsiac. \n", + "29 Pompe funèbre du très-pieux et très-puissant Prince Albert \n", + "30 Gallerie du palais Magnani peinte par les Carrached \n", + "31 Archite civile di diveravtori, Tom. II \n", + "32 Rec. de vases antiqvae par errard \n", + "33 Galleria Givstiniana, Tom. I \n", + "34 Galleria Givstiniana, Tom. II \n", + "35 L'art de scvlptvre par Bossvi \n", + "36 Portraits & vies de plvs. Princes & Generavy en Allemand \n", + "37 Pacificator orbis christiani \n", + "38 Medailles de Louis le grand \n", + "39 Histoire de Lovis XIV en medailles \n", + "40 Descr. De L'hot. Des Inval. \n", + "41 Medaillo dv Cabinet dv Roy \n", + "42 Arc. Constantini \n", + "43 Fvner Car. V. Imper \n", + "44 Venet. Habit & specta \n", + "45 Pompa Fvn. Alberti PII \n", + "46 L'arti perviua di Bologna Caraci \n", + "47 Ingress. Deorv & Dearv Dresd. \n", + "48 100 Statvae antiqvae \n", + "49 Recveil d'oseav par Robert \n", + "50 Ingres legat Caesar & Portae \n", "\n", - " Kurztitel Anmerkungen ÖNB Signatur \n", - "93 Bidloo Corpor Human Anatomia NaN False " + " Anmerkungen ÖNB Signatur \n", + "0 NaN False \n", + "1 NaN False \n", + "2 NaN False \n", + "3 NaN False \n", + "4 NaN False \n", + "5 NaN False \n", + "6 NaN False \n", + "7 NaN False \n", + "8 NaN False \n", + "9 NaN False \n", + "10 NaN False \n", + "11 NaN False \n", + "12 NaN False \n", + "13 NaN True \n", + "14 NaN False \n", + "15 NaN True \n", + "16 NaN True \n", + "17 NaN True \n", + "18 NaN False \n", + "19 NaN False \n", + "20 NaN False \n", + "21 NaN False \n", + "22 NaN False \n", + "23 NaN False \n", + "24 NaN False \n", + "25 NaN False \n", + "26 NaN False \n", + "27 NaN False \n", + "28 NaN False \n", + "29 NaN True \n", + "30 NaN False \n", + "31 NaN False \n", + "32 NaN False \n", + "33 NaN False \n", + "34 NaN False \n", + "35 NaN False \n", + "36 NaN False \n", + "37 NaN False \n", + "38 NaN False \n", + "39 NaN False \n", + "40 NaN False \n", + "41 NaN False \n", + "42 NaN False \n", + "43 NaN True \n", + "44 NaN False \n", + "45 NaN False \n", + "46 NaN False \n", + "47 NaN False \n", + "48 NaN False \n", + "49 NaN False \n", + "50 NaN False " ] }, - "execution_count": 100, + "execution_count": 108, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "alb_df[alb_df['Kurztitel'].str.contains('Human')]" + "alb_df.loc[:50]" ] }, { diff --git a/Notebooks/Classifier_plots.ipynb b/Notebooks/Classifier_plots.ipynb new file mode 100644 index 0000000..e3e0e87 --- /dev/null +++ b/Notebooks/Classifier_plots.ipynb @@ -0,0 +1,985 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "id": "35ded88f-0bcd-42a8-b62b-e4a8456d59bf", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import re\n", + "import numpy as np\n", + "import thefuzz\n", + "from tqdm.notebook import tqdm\n", + "import matplotlib.pyplot as plt\n", + "import requests\n", + "import json\n", + "from IPython.display import display\n", + "\n", + "pd.set_option('display.max_colwidth', None)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "a9f0fa3e-dfa0-4ee5-9458-7401b62b3f91", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_82532/2205541700.py:1: DtypeWarning: Columns (8,9) have mixed types. Specify dtype option on import or set low_memory=False.\n", + " preds = pd.read_csv('data/predictions/all_pred_final.csv')\n" + ] + } + ], + "source": [ + "preds = pd.read_csv('data/predictions/all_pred_final.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "e61369ab-8dbb-4181-a14c-83c651c71ed3", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "N_preds = preds[preds['prediction'] == 'N'].drop_duplicates('identifier')" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "3d444dd2-7ef7-4bc8-ac3f-4f805dd9597e", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "BE_preds = pd.read_excel('../Daten/Vorhersagen/WIP_final_BE_3.xlsx', index_col=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "fe9ab426-1d3d-43ea-ab41-7650024bb03d", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "BE_preds['max_ABC'] = BE_preds[['p_A', 'p_B', 'p_C', 'p_N']].apply(lambda x: ['A', 'B', 'C', 'N'][np.argmax(x)], axis=1)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "ed1e4090-5c81-41f3-8373-b86f50ca0aad", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "ABC_preds = BE_preds[BE_preds['max_ABC'].isin(['A', 'B', 'C'])]" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "6f832730-1b46-4262-ac7c-651fa136d04b", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "12052 A\n", + "Name: Wappenklassifizierung, dtype: object" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "BE_preds[BE_preds['Dateiname'] == 'Z15831330X_00000001.jpg']['Wappenklassifizierung']" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "cf7a38aa-55fa-4d44-bcf1-3c7dc1044a43", + "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>identifier</th>\n", + " <th>filename</th>\n", + " <th>prediction</th>\n", + " <th>man_prediction</th>\n", + " <th>p_A</th>\n", + " <th>p_B</th>\n", + " <th>p_C</th>\n", + " <th>p_N</th>\n", + " <th>color</th>\n", + " <th>man_color</th>\n", + " <th>p_blue</th>\n", + " <th>p_red</th>\n", + " <th>p_yellow</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>778</th>\n", + " <td>Z10520809</td>\n", + " <td>Z10520809_00000004.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.150160</td>\n", + " <td>0.135397</td>\n", + " <td>0.362168</td>\n", + " <td>0.352275</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>19693</th>\n", + " <td>Z152357407</td>\n", + " <td>Z152357407_00000003.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.002158</td>\n", + " <td>0.001710</td>\n", + " <td>0.781663</td>\n", + " <td>0.214469</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>19708</th>\n", + " <td>Z152357705</td>\n", + " <td>Z152357705_00000003.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.022423</td>\n", + " <td>0.019239</td>\n", + " <td>0.582193</td>\n", + " <td>0.376145</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>23697</th>\n", + " <td>Z155078001</td>\n", + " <td>Z155078001_00000002.jpg</td>\n", + " <td>A</td>\n", + " <td>N</td>\n", + " <td>0.638692</td>\n", + " <td>0.013483</td>\n", + " <td>0.007171</td>\n", + " <td>0.340654</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>33048</th>\n", + " <td>Z155916602</td>\n", + " <td>Z155916602_00000001.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.002850</td>\n", + " <td>0.001018</td>\n", + " <td>0.934370</td>\n", + " <td>0.061763</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", + " </tr>\n", + " <tr>\n", + " <th>604132</th>\n", + " <td>Z15831330X</td>\n", + " <td>Z15831330X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.914168</td>\n", + " <td>0.083436</td>\n", + " <td>0.001004</td>\n", + " <td>0.001392</td>\n", + " <td>red</td>\n", + " <td>red</td>\n", + " <td>0.120726</td>\n", + " <td>0.845326</td>\n", + " <td>0.033948</td>\n", + " </tr>\n", + " <tr>\n", + " <th>604901</th>\n", + " <td>Z17539290X</td>\n", + " <td>Z17539290X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.520638</td>\n", + " <td>0.467463</td>\n", + " <td>0.003494</td>\n", + " <td>0.008405</td>\n", + " <td>red</td>\n", + " <td>red</td>\n", + " <td>0.000639</td>\n", + " <td>0.994352</td>\n", + " <td>0.005008</td>\n", + " </tr>\n", + " <tr>\n", + " <th>605363</th>\n", + " <td>Z176408203</td>\n", + " <td>Z176408203_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.736317</td>\n", + " <td>0.256974</td>\n", + " <td>0.000506</td>\n", + " <td>0.006203</td>\n", + " <td>yellow</td>\n", + " <td>yellow</td>\n", + " <td>0.004107</td>\n", + " <td>0.004642</td>\n", + " <td>0.991251</td>\n", + " </tr>\n", + " <tr>\n", + " <th>605364</th>\n", + " <td>Z176408306</td>\n", + " <td>Z176408306_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.937634</td>\n", + " <td>0.031341</td>\n", + " <td>0.007200</td>\n", + " <td>0.023825</td>\n", + " <td>yellow</td>\n", + " <td>yellow</td>\n", + " <td>0.006639</td>\n", + " <td>0.003798</td>\n", + " <td>0.989563</td>\n", + " </tr>\n", + " <tr>\n", + " <th>609722</th>\n", + " <td>Z221185404</td>\n", + " <td>Z221185404_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.873245</td>\n", + " <td>0.121658</td>\n", + " <td>0.002080</td>\n", + " <td>0.003017</td>\n", + " <td>red</td>\n", + " <td>red</td>\n", + " <td>0.105810</td>\n", + " <td>0.846481</td>\n", + " <td>0.047709</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>73 rows × 13 columns</p>\n", + "</div>" + ], + "text/plain": [ + " identifier filename prediction man_prediction \n", + "778 Z10520809 Z10520809_00000004.jpg C N \\\n", + "19693 Z152357407 Z152357407_00000003.jpg C N \n", + "19708 Z152357705 Z152357705_00000003.jpg C N \n", + "23697 Z155078001 Z155078001_00000002.jpg A N \n", + "33048 Z155916602 Z155916602_00000001.jpg C N \n", + "... ... ... ... ... \n", + "604132 Z15831330X Z15831330X_00000001.jpg A B \n", + "604901 Z17539290X Z17539290X_00000001.jpg A B \n", + "605363 Z176408203 Z176408203_00000001.jpg A B \n", + "605364 Z176408306 Z176408306_00000001.jpg A B \n", + "609722 Z221185404 Z221185404_00000001.jpg A B \n", + "\n", + " p_A p_B p_C p_N color man_color p_blue \n", + "778 0.150160 0.135397 0.362168 0.352275 NaN NaN NaN \\\n", + "19693 0.002158 0.001710 0.781663 0.214469 NaN NaN NaN \n", + "19708 0.022423 0.019239 0.582193 0.376145 NaN NaN NaN \n", + "23697 0.638692 0.013483 0.007171 0.340654 NaN NaN NaN \n", + "33048 0.002850 0.001018 0.934370 0.061763 NaN NaN NaN \n", + "... ... ... ... ... ... ... ... \n", + "604132 0.914168 0.083436 0.001004 0.001392 red red 0.120726 \n", + "604901 0.520638 0.467463 0.003494 0.008405 red red 0.000639 \n", + "605363 0.736317 0.256974 0.000506 0.006203 yellow yellow 0.004107 \n", + "605364 0.937634 0.031341 0.007200 0.023825 yellow yellow 0.006639 \n", + "609722 0.873245 0.121658 0.002080 0.003017 red red 0.105810 \n", + "\n", + " p_red p_yellow \n", + "778 NaN NaN \n", + "19693 NaN NaN \n", + "19708 NaN NaN \n", + "23697 NaN NaN \n", + "33048 NaN NaN \n", + "... ... ... \n", + "604132 0.845326 0.033948 \n", + "604901 0.994352 0.005008 \n", + "605363 0.004642 0.991251 \n", + "605364 0.003798 0.989563 \n", + "609722 0.846481 0.047709 \n", + "\n", + "[73 rows x 13 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "preds[(preds['prediction'] != preds['man_prediction']) & (preds['prediction'] != 'N')]" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "2db20ca5-6dda-4348-8c8f-a2d8bafcf1d5", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "check_df = ABC_preds[['Dateiname', 'Wappenklassifizierung']].merge(preds[preds['prediction'].isin(['A', 'B', 'C'])][['filename', 'prediction', 'man_prediction']], how='left', left_on='Dateiname', right_on='filename')" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "a69a6e70-3bc1-493b-829c-4a875e85f508", + "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>Dateiname</th>\n", + " <th>Wappenklassifizierung</th>\n", + " <th>filename</th>\n", + " <th>prediction</th>\n", + " <th>man_prediction</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>1747</th>\n", + " <td>Z221185404_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>Z221185404_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3521</th>\n", + " <td>Z176408203_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>Z176408203_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3522</th>\n", + " <td>Z176408306_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>Z176408306_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3545</th>\n", + " <td>Z15831330X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>Z15831330X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4132</th>\n", + " <td>Z17539290X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>Z17539290X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " Dateiname Wappenklassifizierung filename \n", + "1747 Z221185404_00000001.jpg A Z221185404_00000001.jpg \\\n", + "3521 Z176408203_00000001.jpg A Z176408203_00000001.jpg \n", + "3522 Z176408306_00000001.jpg A Z176408306_00000001.jpg \n", + "3545 Z15831330X_00000001.jpg A Z15831330X_00000001.jpg \n", + "4132 Z17539290X_00000001.jpg A Z17539290X_00000001.jpg \n", + "\n", + " prediction man_prediction \n", + "1747 A B \n", + "3521 A B \n", + "3522 A B \n", + "3545 A B \n", + "4132 A B " + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "check_df[check_df['prediction'] != check_df['man_prediction']]" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "b38be7cf-2911-4552-8662-732c97af7fa1", + "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>identifier</th>\n", + " <th>filename</th>\n", + " <th>prediction</th>\n", + " <th>man_prediction</th>\n", + " <th>p_A</th>\n", + " <th>p_B</th>\n", + " <th>p_C</th>\n", + " <th>p_N</th>\n", + " <th>color</th>\n", + " <th>man_color</th>\n", + " <th>p_blue</th>\n", + " <th>p_red</th>\n", + " <th>p_yellow</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>778</th>\n", + " <td>Z10520809</td>\n", + " <td>Z10520809_00000004.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.150160</td>\n", + " <td>0.135397</td>\n", + " <td>0.362168</td>\n", + " <td>0.352275</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>19693</th>\n", + " <td>Z152357407</td>\n", + " <td>Z152357407_00000003.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.002158</td>\n", + " <td>0.001710</td>\n", + " <td>0.781663</td>\n", + " <td>0.214469</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>19708</th>\n", + " <td>Z152357705</td>\n", + " <td>Z152357705_00000003.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.022423</td>\n", + " <td>0.019239</td>\n", + " <td>0.582193</td>\n", + " <td>0.376145</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>23697</th>\n", + " <td>Z155078001</td>\n", + " <td>Z155078001_00000002.jpg</td>\n", + " <td>A</td>\n", + " <td>N</td>\n", + " <td>0.638692</td>\n", + " <td>0.013483</td>\n", + " <td>0.007171</td>\n", + " <td>0.340654</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>33048</th>\n", + " <td>Z155916602</td>\n", + " <td>Z155916602_00000001.jpg</td>\n", + " <td>C</td>\n", + " <td>N</td>\n", + " <td>0.002850</td>\n", + " <td>0.001018</td>\n", + " <td>0.934370</td>\n", + " <td>0.061763</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", + " </tr>\n", + " <tr>\n", + " <th>604132</th>\n", + " <td>Z15831330X</td>\n", + " <td>Z15831330X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.914168</td>\n", + " <td>0.083436</td>\n", + " <td>0.001004</td>\n", + " <td>0.001392</td>\n", + " <td>red</td>\n", + " <td>red</td>\n", + " <td>0.120726</td>\n", + " <td>0.845326</td>\n", + " <td>0.033948</td>\n", + " </tr>\n", + " <tr>\n", + " <th>604901</th>\n", + " <td>Z17539290X</td>\n", + " <td>Z17539290X_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.520638</td>\n", + " <td>0.467463</td>\n", + " <td>0.003494</td>\n", + " <td>0.008405</td>\n", + " <td>red</td>\n", + " <td>red</td>\n", + " <td>0.000639</td>\n", + " <td>0.994352</td>\n", + " <td>0.005008</td>\n", + " </tr>\n", + " <tr>\n", + " <th>605363</th>\n", + " <td>Z176408203</td>\n", + " <td>Z176408203_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.736317</td>\n", + " <td>0.256974</td>\n", + " <td>0.000506</td>\n", + " <td>0.006203</td>\n", + " <td>yellow</td>\n", + " <td>yellow</td>\n", + " <td>0.004107</td>\n", + " <td>0.004642</td>\n", + " <td>0.991251</td>\n", + " </tr>\n", + " <tr>\n", + " <th>605364</th>\n", + " <td>Z176408306</td>\n", + " <td>Z176408306_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.937634</td>\n", + " <td>0.031341</td>\n", + " <td>0.007200</td>\n", + " <td>0.023825</td>\n", + " <td>yellow</td>\n", + " <td>yellow</td>\n", + " <td>0.006639</td>\n", + " <td>0.003798</td>\n", + " <td>0.989563</td>\n", + " </tr>\n", + " <tr>\n", + " <th>609722</th>\n", + " <td>Z221185404</td>\n", + " <td>Z221185404_00000001.jpg</td>\n", + " <td>A</td>\n", + " <td>B</td>\n", + " <td>0.873245</td>\n", + " <td>0.121658</td>\n", + " <td>0.002080</td>\n", + " <td>0.003017</td>\n", + " <td>red</td>\n", + " <td>red</td>\n", + " <td>0.105810</td>\n", + " <td>0.846481</td>\n", + " <td>0.047709</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>73 rows × 13 columns</p>\n", + "</div>" + ], + "text/plain": [ + " identifier filename prediction man_prediction \n", + "778 Z10520809 Z10520809_00000004.jpg C N \\\n", + "19693 Z152357407 Z152357407_00000003.jpg C N \n", + "19708 Z152357705 Z152357705_00000003.jpg C N \n", + "23697 Z155078001 Z155078001_00000002.jpg A N \n", + "33048 Z155916602 Z155916602_00000001.jpg C N \n", + "... ... ... ... ... \n", + "604132 Z15831330X Z15831330X_00000001.jpg A B \n", + "604901 Z17539290X Z17539290X_00000001.jpg A B \n", + "605363 Z176408203 Z176408203_00000001.jpg A B \n", + "605364 Z176408306 Z176408306_00000001.jpg A B \n", + "609722 Z221185404 Z221185404_00000001.jpg A B \n", + "\n", + " p_A p_B p_C p_N color man_color p_blue \n", + "778 0.150160 0.135397 0.362168 0.352275 NaN NaN NaN \\\n", + "19693 0.002158 0.001710 0.781663 0.214469 NaN NaN NaN \n", + "19708 0.022423 0.019239 0.582193 0.376145 NaN NaN NaN \n", + "23697 0.638692 0.013483 0.007171 0.340654 NaN NaN NaN \n", + "33048 0.002850 0.001018 0.934370 0.061763 NaN NaN NaN \n", + "... ... ... ... ... ... ... ... \n", + "604132 0.914168 0.083436 0.001004 0.001392 red red 0.120726 \n", + "604901 0.520638 0.467463 0.003494 0.008405 red red 0.000639 \n", + "605363 0.736317 0.256974 0.000506 0.006203 yellow yellow 0.004107 \n", + "605364 0.937634 0.031341 0.007200 0.023825 yellow yellow 0.006639 \n", + "609722 0.873245 0.121658 0.002080 0.003017 red red 0.105810 \n", + "\n", + " p_red p_yellow \n", + "778 NaN NaN \n", + "19693 NaN NaN \n", + "19708 NaN NaN \n", + "23697 NaN NaN \n", + "33048 NaN NaN \n", + "... ... ... \n", + "604132 0.845326 0.033948 \n", + "604901 0.994352 0.005008 \n", + "605363 0.004642 0.991251 \n", + "605364 0.003798 0.989563 \n", + "609722 0.846481 0.047709 \n", + "\n", + "[73 rows x 13 columns]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "preds[(preds['prediction'] != preds['man_prediction']) & (preds['prediction'] != 'N')]" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "80706fb7-b386-492e-908d-ef55b09ac5e4", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "6142" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(BE_preds[BE_preds['Wappenklassifizierung'].isin(['A', 'B', 'C'])])" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "caa5fef5-16d2-4d94-822c-ed93495cdb21", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "8447" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(BE_preds[BE_preds['hs. Katalog'] == 1])" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "d064f1c3-49a9-4483-a663-2dd71a9ccf54", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "4315\n", + "1686\n", + "141\n" + ] + } + ], + "source": [ + "print(len(BE_preds[BE_preds['Farbklassifizierung'] == 'red']))\n", + "print(len(BE_preds[BE_preds['Farbklassifizierung'] == 'yellow']))\n", + "print(len(BE_preds[BE_preds['Farbklassifizierung'] == 'blue']))" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "65021f88-83d0-47dd-bca6-f09f342af87e", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['identifier', 'filename', 'prediction', 'man_prediction', 'p_A', 'p_B',\n", + " 'p_C', 'p_N', 'color', 'man_color', 'p_blue', 'p_red', 'p_yellow'],\n", + " dtype='object')" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "preds.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "f4a20ea8-5ac2-4b37-a257-1e53c33b7dca", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "4345\n", + "1699\n", + "141\n" + ] + } + ], + "source": [ + "print(len(preds[preds['man_color'] == 'red']))\n", + "print(len(preds[preds['man_color'] == 'yellow']))\n", + "print(len(preds[preds['man_color'] == 'blue']))" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "53d45c76-cfe8-4cdf-a5e1-62e9a155a3b4", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "BE_certain = BE_preds[(BE_preds['Wappenklassifizierung'].isin(['A', 'B', 'C'])) | (BE_preds['hs. Katalog'] == 1)]" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "36a89221-c074-4f5f-8f0d-c20daa38ccdc", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "23376 French\n", + "23383 French\n", + "23384 French\n", + "23385 French\n", + "23386 French\n", + " ... \n", + "22638 NaN\n", + "22639 NaN\n", + "22650 French\n", + "22651 Latin\n", + "23439 Ancient Greek (to 1453)\n", + "Name: Sprache, Length: 9591, dtype: object" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "BE_certain['Sprache']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c3c059e9-bab0-4154-85e4-9bdfb2f1659a", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.10" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/Notebooks/String_matching.ipynb b/Notebooks/String_matching.ipynb index b3aa06c..9dbef55 100644 --- a/Notebooks/String_matching.ipynb +++ b/Notebooks/String_matching.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 72, + "execution_count": 1, "id": "7a3837ac-cced-4e01-bf57-265e40729692", "metadata": { "tags": [] @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "id": "29ca0dc8-cae7-4f12-bd60-fd74ea6ae5ac", "metadata": { "tags": [] @@ -36,7 +36,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "id": "c1e1c42a-962f-40bc-bb17-b62e8089feb7", "metadata": { "tags": [] @@ -48,7 +48,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 4, "id": "50d15898-4687-46b7-b7e0-528d7cf9aec0", "metadata": { "tags": [] @@ -70,7 +70,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "id": "990dfeee-1141-4acb-8a3d-a7af0573f5be", "metadata": { "tags": [] @@ -85,7 +85,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "id": "bcd301fe-cb80-4b1c-b65f-465fce5ed915", "metadata": { "tags": [] @@ -104,7 +104,7 @@ " 0.0102726686745882]], dtype=object)" ] }, - "execution_count": 8, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -115,7 +115,7 @@ }, { "cell_type": "code", - "execution_count": 1189, + "execution_count": 14, "id": "c0f4a42a-7e21-41e8-833c-2dd2f9d1985e", "metadata": { "tags": [] @@ -125,7 +125,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "1\n" + "6\n" ] }, { @@ -162,36 +162,124 @@ " </thead>\n", " <tbody>\n", " <tr>\n", - " <th>4652</th>\n", + " <th>192</th>\n", + " <td>14.376</td>\n", + " <td>58</td>\n", + " <td>Theologia</td>\n", + " <td>Concilia, & quæ ad eamdem Rem pertinentia</td>\n", + " <td>Folio</td>\n", + " <td>34</td>\n", + " <td>14.376_058_01</td>\n", + " <td>64 Piccolomini (æneæ Sylvij) Fasciculus expetendarum ac fugiendarum rerum, Seu comment. de Concilij Basiliensis gestis; insunt præterea huic operi aliquot epistolæ, libelli, tractatus, & opuscula quæ, si futurum Concilium celebrari contigerit, summopere tanquam¬ cognitu digna & necessaria ad optimis expostulabunt. omnia ab Orthuio Gratio edita. Coloniæ. 1535. n. 168.</td>\n", + " <td>Piccolomini aeneae Sylvij Fasciculus expetendarum ac fugiendarum rerum Seu comment de Concilij Basiliensis gestis insunt praeterea huic operi aliquot epistolae libelli tractatus & opuscula quae si futurum Concilium celebrari contigerit summopere tanquam cognitu digna & necessaria ad optimis expostulabunt omnia ab Orthuio Gratio edita Coloniae 1535 n 168</td>\n", + " </tr>\n", + " <tr>\n", + " <th>193</th>\n", + " <td>14.376</td>\n", + " <td>58</td>\n", + " <td>Theologia</td>\n", + " <td>Concilia, & quæ ad eamdem Rem pertinentia</td>\n", + " <td>Folio</td>\n", + " <td>34</td>\n", + " <td>14.376_058_02</td>\n", + " <td>65.......... Idem Fasciculus ab innumeris mendis expurgat. vna cum appendice, seu tomo 2.° scriptorum veterum qui Ecclesiæ Rom. abusus ac errores detegunt & damnant, necessitatemque reformationis vrgent. opera & Studio Edwardi Brown. 2 Vol. Lond. 1690. Rich. Chiswel. n. 169.</td>\n", + " <td>Idem Fasciculus ab innumeris mendis expurgat vna cum appendice seu tomo 2° scriptorum veterum qui Ecclesiae Rom abusus ac errores detegunt & damnant necessitatemque reformationis vrgent opera & Studio Edwardi Brown 2 Vol Lond 1690 Rich Chiswel n 169</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4585</th>\n", " <td>14.377</td>\n", - " <td>231</td>\n", + " <td>221</td>\n", " <td>Philologia</td>\n", - " <td>Epistolographi Gallici, & Italici</td>\n", + " <td>Epistolographi Græci & Latini</td>\n", " <td>Octavo und kleiner</td>\n", - " <td>627</td>\n", - " <td>14.377_231_03</td>\n", - " <td>Lettres edifiantes & curieuses des Missionaires Iesuites. 12.° 21 Vol. Paris. 1717. & Ann. Suivantes n. 1622.</td>\n", - " <td>Lettres edifiantes & curieuses des Missionaires Iesuites 12° 21 Vol Paris 1717 & Ann Suivantes n 1622</td>\n", + " <td>617</td>\n", + " <td>14.377_221_00</td>\n", + " <td>Fasciculus Latinarum Epistolarum Ludovici Molinæi cum interpretatione gallicâ. 12.° Eleutheropoli. 1676. n. 1589.</td>\n", + " <td>Fasciculus Latinarum Epistolarum Ludovici Molinaei cum interpretatione gallica 12° Eleutheropoli 1676 n 1589</td>\n", + " </tr>\n", + " <tr>\n", + " <th>5137</th>\n", + " <td>14.377</td>\n", + " <td>319</td>\n", + " <td>Chronologia</td>\n", + " <td>Chronologia Technica & Historica</td>\n", + " <td>Folio</td>\n", + " <td>711</td>\n", + " <td>14.377_319_00</td>\n", + " <td>1170 Fasciculus Temporum. editio antiqua, sine Loco & Venetijs 1480 XLVIII.R.19 anno. n. 2160. et S. A. n. 2324. XLVIII.R.18</td>\n", + " <td>Fasciculus Temporum editio antiqua sine Loco & Venetijs 1480 XLVIIIR19 anno n 2160 et S A n 2324 XLVIIIR18</td>\n", + " </tr>\n", + " <tr>\n", + " <th>5179</th>\n", + " <td>14.377</td>\n", + " <td>327</td>\n", + " <td>Chronologia</td>\n", + " <td>Chronographi, Seu Chronica, & Historiæ Universales</td>\n", + " <td>Folio</td>\n", + " <td>719</td>\n", + " <td>14.377_327_03</td>\n", + " <td>1192 Chronica qua dicitur Fasciculus temporum per quemdam Carthusiensem edita, nunc emendata cum additionibus ad hæc usque tempora. Venetiis. 1480. Erhardus Ratdolt.</td>\n", + " <td>Chronica qua dicitur Fasciculus temporum per quemdam Carthusiensem edita nunc emendata cum additionibus ad haec usque tempora Venetiis 1480 Erhardus Ratdolt</td>\n", + " </tr>\n", + " <tr>\n", + " <th>8487</th>\n", + " <td>14.378</td>\n", + " <td>448</td>\n", + " <td>Paralipomena Historica</td>\n", + " <td>De Academiis, Universitatibus, Scholis, Colleg. &c</td>\n", + " <td>Quarto</td>\n", + " <td>1280</td>\n", + " <td>14.378_448_02</td>\n", + " <td>Omeisij (Magni Dan.) Academiæ Altdorfinæ Gloria, Sive Orationum Fasciculus, Vniversitatis Noricæ Ortus & Progressus, omniumque ipsius Professorum Vitæ & Scripta; accedunt I. Pauli Felwingeri additamenta quædam. Altdorfi. 1683. Meyerus. n. 1600. Fasti Consolari dell'Academia Fiorentina da Salvino Salvini. in Firenze. 1717. Tartini. n. 2151 Dissertationes Ioannis Melchioris Schwimmer de¬ Academicis omnium Facultatum Professoribus. Ienæ. 1671. Mullerus. n. 2152.</td>\n", + " <td>Omeisij Magni Dan Academiae Altdorfinae Gloria Sive Orationum Fasciculus Vniversitatis Noricae Ortus & Progressus omniumque ipsius Professorum Vitae & Scripta accedunt I Pauli Felwingeri additamenta quaedam Altdorfi 1683 Meyerus n 1600 Fasti Consolari dell'Academia Fiorentina da Salvino Salvini in Firenze 1717 Tartini n 2151 Dissertationes Ioannis Melchioris Schwimmer de Academicis omnium Facultatum Professoribus Ienae 1671 Mullerus n 2152</td>\n", " </tr>\n", " </tbody>\n", "</table>\n", "</div>" ], "text/plain": [ - " volume page number category subcategory \n", - "4652 14.377 231 Philologia Epistolographi Gallici, & Italici \\\n", + " volume page number category \n", + "192 14.376 58 Theologia \\\n", + "193 14.376 58 Theologia \n", + "4585 14.377 221 Philologia \n", + "5137 14.377 319 Chronologia \n", + "5179 14.377 327 Chronologia \n", + "8487 14.378 448 Paralipomena Historica \n", "\n", - " format handwritten page number entry_ID \n", - "4652 Octavo und kleiner 627 14.377_231_03 \\\n", + " subcategory format \n", + "192 Concilia, & quæ ad eamdem Rem pertinentia Folio \\\n", + "193 Concilia, & quæ ad eamdem Rem pertinentia Folio \n", + "4585 Epistolographi Græci & Latini Octavo und kleiner \n", + "5137 Chronologia Technica & Historica Folio \n", + "5179 Chronographi, Seu Chronica, & Historiæ Universales Folio \n", + "8487 De Academiis, Universitatibus, Scholis, Colleg. &c Quarto \n", "\n", - " entry \n", - "4652 Lettres edifiantes & curieuses des Missionaires Iesuites. 12.° 21 Vol. Paris. 1717. & Ann. Suivantes n. 1622. \\\n", + " handwritten page number entry_ID \n", + "192 34 14.376_058_01 \\\n", + "193 34 14.376_058_02 \n", + "4585 617 14.377_221_00 \n", + "5137 711 14.377_319_00 \n", + "5179 719 14.377_327_03 \n", + "8487 1280 14.378_448_02 \n", + "\n", + " entry \n", + "192 64 Piccolomini (æneæ Sylvij) Fasciculus expetendarum ac fugiendarum rerum, Seu comment. de Concilij Basiliensis gestis; insunt præterea huic operi aliquot epistolæ, libelli, tractatus, & opuscula quæ, si futurum Concilium celebrari contigerit, summopere tanquam¬ cognitu digna & necessaria ad optimis expostulabunt. omnia ab Orthuio Gratio edita. Coloniæ. 1535. n. 168. \\\n", + "193 65.......... Idem Fasciculus ab innumeris mendis expurgat. vna cum appendice, seu tomo 2.° scriptorum veterum qui Ecclesiæ Rom. abusus ac errores detegunt & damnant, necessitatemque reformationis vrgent. opera & Studio Edwardi Brown. 2 Vol. Lond. 1690. Rich. Chiswel. n. 169. \n", + "4585 Fasciculus Latinarum Epistolarum Ludovici Molinæi cum interpretatione gallicâ. 12.° Eleutheropoli. 1676. n. 1589. \n", + "5137 1170 Fasciculus Temporum. editio antiqua, sine Loco & Venetijs 1480 XLVIII.R.19 anno. n. 2160. et S. A. n. 2324. XLVIII.R.18 \n", + "5179 1192 Chronica qua dicitur Fasciculus temporum per quemdam Carthusiensem edita, nunc emendata cum additionibus ad hæc usque tempora. Venetiis. 1480. Erhardus Ratdolt. \n", + "8487 Omeisij (Magni Dan.) Academiæ Altdorfinæ Gloria, Sive Orationum Fasciculus, Vniversitatis Noricæ Ortus & Progressus, omniumque ipsius Professorum Vitæ & Scripta; accedunt I. Pauli Felwingeri additamenta quædam. Altdorfi. 1683. Meyerus. n. 1600. Fasti Consolari dell'Academia Fiorentina da Salvino Salvini. in Firenze. 1717. Tartini. n. 2151 Dissertationes Ioannis Melchioris Schwimmer de¬ Academicis omnium Facultatum Professoribus. Ienæ. 1671. Mullerus. n. 2152. \n", "\n", - " cleaned entry \n", - "4652 Lettres edifiantes & curieuses des Missionaires Iesuites 12° 21 Vol Paris 1717 & Ann Suivantes n 1622 " + " cleaned entry \n", + "192 Piccolomini aeneae Sylvij Fasciculus expetendarum ac fugiendarum rerum Seu comment de Concilij Basiliensis gestis insunt praeterea huic operi aliquot epistolae libelli tractatus & opuscula quae si futurum Concilium celebrari contigerit summopere tanquam cognitu digna & necessaria ad optimis expostulabunt omnia ab Orthuio Gratio edita Coloniae 1535 n 168 \n", + "193 Idem Fasciculus ab innumeris mendis expurgat vna cum appendice seu tomo 2° scriptorum veterum qui Ecclesiae Rom abusus ac errores detegunt & damnant necessitatemque reformationis vrgent opera & Studio Edwardi Brown 2 Vol Lond 1690 Rich Chiswel n 169 \n", + "4585 Fasciculus Latinarum Epistolarum Ludovici Molinaei cum interpretatione gallica 12° Eleutheropoli 1676 n 1589 \n", + "5137 Fasciculus Temporum editio antiqua sine Loco & Venetijs 1480 XLVIIIR19 anno n 2160 et S A n 2324 XLVIIIR18 \n", + "5179 Chronica qua dicitur Fasciculus temporum per quemdam Carthusiensem edita nunc emendata cum additionibus ad haec usque tempora Venetiis 1480 Erhardus Ratdolt \n", + "8487 Omeisij Magni Dan Academiae Altdorfinae Gloria Sive Orationum Fasciculus Vniversitatis Noricae Ortus & Progressus omniumque ipsius Professorum Vitae & Scripta accedunt I Pauli Felwingeri additamenta quaedam Altdorfi 1683 Meyerus n 1600 Fasti Consolari dell'Academia Fiorentina da Salvino Salvini in Firenze 1717 Tartini n 2151 Dissertationes Ioannis Melchioris Schwimmer de Academicis omnium Facultatum Professoribus Ienae 1671 Mullerus n 2152 " ] }, - "execution_count": 1189, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -200,14 +288,14 @@ "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, 'edifiantes'), '')\n", + "info = search_in_entry(search_in_entry(entry_df, ''), 'Fasciculus')\n", "print(len(info))\n", "info" ] }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "id": "c4394718-cfd3-459e-8923-3ef255a41012", "metadata": { "tags": [] @@ -228,7 +316,7 @@ "Name: 2857, dtype: object" ] }, - "execution_count": 10, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -239,7 +327,7 @@ }, { "cell_type": "code", - "execution_count": 1176, + "execution_count": 9, "id": "20facf5d-d609-498e-9907-7ebdffc09e15", "metadata": { "tags": [] @@ -291,7 +379,7 @@ "Name: 14220, dtype: object" ] }, - "execution_count": 1176, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -3621,8 +3709,1092 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, + "id": "6a3910b6-8488-4af0-bab6-a04af623a786", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "tmp = pd.read_excel('../Daten/Vorhersagen/WIP_final_BE_3.xlsx', index_col=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 1261, "id": "12fcd3ad-222e-4afe-baea-7be69b3ae5cc", + "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>dup_title</th>\n", + " <th>copy_from</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>23376</th>\n", + " <td>*28.A.79.(Vol.1)</td>\n", + " <td>Z222907107</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23383</th>\n", + " <td>*28.A.79.(Vol.10)</td>\n", + " <td>Z222908100</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23384</th>\n", + " <td>*28.A.79.(Vol.12)</td>\n", + " <td>Z222908306</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23385</th>\n", + " <td>*28.A.79.(Vol.13)</td>\n", + " <td>Z222908409</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23386</th>\n", + " <td>*28.A.79.(Vol.14)</td>\n", + " <td>Z222908501</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</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>22638</th>\n", + " <td>Ink 9.D.5</td>\n", + " <td>+Z35095803</td>\n", + " <td>Thesaurus Cornu copiae et Horti Adonidis <griech.> Mit lat. und griech. Brief an Guarinus Favorinus von Angelus Politianus bzw. von Scipione Fortiguerra. Mit griech. Gedichten von Angelus Politianus, Aristobulos Apostolides, Scipione Fortiguerra und Aldus Manutius. Mit lat. Brief an die Gelehrten hrsg. von Aldus Manutius unter Mitarbeit von Urbanus Bolzanius</td>\n", + " <td>NaN</td>\n", + " <td>Manuzio, Aldo Pio; Bolzanio, Urbano 1443-1524; Manuzio, Aldo Pio 1450-1515</td>\n", + " <td>1496.0</td>\n", + " <td>NaN</td>\n", + " <td>Aug. 1496; [1496.08]</td>\n", + " <td>Venedig</td>\n", + " <td>Venedig</td>\n", + " <td>...</td>\n", + " <td>423</td>\n", + " <td>Grammatica</td>\n", + " <td>Tractatus Grammatici generalis cum Lexicographis</td>\n", + " <td>Folio</td>\n", + " <td>375</td>\n", + " <td>14.376_423_03</td>\n", + " <td>755 Thesaurus Cornucopiæ ac Horti Adonidis græcè. Venetiis 1496. Aldus. n. 2179</td>\n", + " <td>https://iiif.onb.ac.at/images/DOD/51202/00000423.jp2/full/full/0/native.jpg</td>\n", + " <td>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22639</th>\n", + " <td>Ink 9.F.22</td>\n", + " <td>+Z96101306</td>\n", + " <td>Comoediae ; Francesco Petrarca: Vita Terentii</td>\n", + " <td>Terentius Afer, Publius v195-v159</td>\n", + " <td>Zarotto, Antonio</td>\n", + " <td>1476.0</td>\n", + " <td>NaN</td>\n", + " <td>23. Feb. 1476; [1476.02.23]</td>\n", + " <td>Mailand</td>\n", + " <td>Mailand</td>\n", + " <td>...</td>\n", + " <td>31</td>\n", + " <td>Poëtica</td>\n", + " <td>Poëtæ Latini Antiqui</td>\n", + " <td>Folio</td>\n", + " <td>439</td>\n", + " <td>14.377_031_11</td>\n", + " <td>857....... Ejusdem Comoediæ. Mediolani. 1476. An. Za. n. 2336.</td>\n", + " <td>https://iiif.onb.ac.at/images/DOD/51184/00000031.jp2/full/full/0/native.jpg</td>\n", + " <td>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22650</th>\n", + " <td>SA.71.E.58</td>\n", + " <td>Z252861302</td>\n", + " <td>Dialogue sur la musique des anciens</td>\n", + " <td>Chateauneuf, Francois abbe de</td>\n", + " <td>NaN</td>\n", + " <td>1725.0</td>\n", + " <td>NaN</td>\n", + " <td>1725</td>\n", + " <td>Paris</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>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22651</th>\n", + " <td>SA.71.F.74</td>\n", + " <td>Z252867808</td>\n", + " <td>Friderici Adolfi Lampe De Cymbalis Veterum Libri Tres</td>\n", + " <td>Ember, Paul</td>\n", + " <td>Hase, Cornelius <<von>>; Röell, Herman Alexander</td>\n", + " <td>1703.0</td>\n", + " <td>NaN</td>\n", + " <td>1703</td>\n", + " <td>Trajecti Ad Rhenum</td>\n", + " <td>Utrecht</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>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23439</th>\n", + " <td>SA.73.B.48</td>\n", + " <td>Z25920770X</td>\n", + " <td>Claudii Ptolomaei harmonicorum libri tres. Ex Codd. Mss. Undecim, nunc primum graece editus. Johannes Wallis ... recensuit, ed. (etc.)</td>\n", + " <td>Ptolemaeus, Claudius</td>\n", + " <td>Wallis, Johannes</td>\n", + " <td>1682.0</td>\n", + " <td>NaN</td>\n", + " <td>1682</td>\n", + " <td>Oxford</td>\n", + " <td>Oxford</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>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>9591 rows × 35 columns</p>\n", + "</div>" + ], + "text/plain": [ + " Signatur Barcode \n", + "23376 *28.A.79.(Vol.1) Z222907107 \\\n", + "23383 *28.A.79.(Vol.10) Z222908100 \n", + "23384 *28.A.79.(Vol.12) Z222908306 \n", + "23385 *28.A.79.(Vol.13) Z222908409 \n", + "23386 *28.A.79.(Vol.14) Z222908501 \n", + "... ... ... \n", + "22638 Ink 9.D.5 +Z35095803 \n", + "22639 Ink 9.F.22 +Z96101306 \n", + "22650 SA.71.E.58 Z252861302 \n", + "22651 SA.71.F.74 Z252867808 \n", + "23439 SA.73.B.48 Z25920770X \n", + "\n", + " Titel \n", + "23376 Histoire des ouvrages des scavans \\\n", + "23383 Histoire des ouvrages des scavans \n", + "23384 Histoire des ouvrages des scavans \n", + "23385 Histoire des ouvrages des scavans \n", + "23386 Histoire des ouvrages des scavans \n", + "... ... \n", + "22638 Thesaurus Cornu copiae et Horti Adonidis <griech.> Mit lat. und griech. Brief an Guarinus Favorinus von Angelus Politianus bzw. von Scipione Fortiguerra. Mit griech. Gedichten von Angelus Politianus, Aristobulos Apostolides, Scipione Fortiguerra und Aldus Manutius. Mit lat. Brief an die Gelehrten hrsg. von Aldus Manutius unter Mitarbeit von Urbanus Bolzanius \n", + "22639 Comoediae ; Francesco Petrarca: Vita Terentii \n", + "22650 Dialogue sur la musique des anciens \n", + "22651 Friderici Adolfi Lampe De Cymbalis Veterum Libri Tres \n", + "23439 Claudii Ptolomaei harmonicorum libri tres. Ex Codd. Mss. Undecim, nunc primum graece editus. Johannes Wallis ... recensuit, ed. (etc.) \n", + "\n", + " Autor \n", + "23376 Basnage de Beauval, Henri \\\n", + "23383 Basnage de Beauval, Henri \n", + "23384 Basnage de Beauval, Henri \n", + "23385 Basnage de Beauval, Henri \n", + "23386 Basnage de Beauval, Henri \n", + "... ... \n", + "22638 NaN \n", + "22639 Terentius Afer, Publius v195-v159 \n", + "22650 Chateauneuf, Francois abbe de \n", + "22651 Ember, Paul \n", + "23439 Ptolemaeus, Claudius \n", + "\n", + " Mitwirkender \n", + "23376 NaN \\\n", + "23383 NaN \n", + "23384 NaN \n", + "23385 NaN \n", + "23386 NaN \n", + "... ... \n", + "22638 Manuzio, Aldo Pio; Bolzanio, Urbano 1443-1524; Manuzio, Aldo Pio 1450-1515 \n", + "22639 Zarotto, Antonio \n", + "22650 NaN \n", + "22651 Hase, Cornelius <<von>>; Röell, Herman Alexander \n", + "23439 Wallis, Johannes \n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "23376 1687.0 1709.0 \\\n", + "23383 1687.0 1709.0 \n", + "23384 1687.0 1709.0 \n", + "23385 1687.0 1709.0 \n", + "23386 1687.0 1709.0 \n", + "... ... ... \n", + "22638 1496.0 NaN \n", + "22639 1476.0 NaN \n", + "22650 1725.0 NaN \n", + "22651 1703.0 NaN \n", + "23439 1682.0 NaN \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "23376 1687-1709 Rotterdam \\\n", + "23383 1687-1709 Rotterdam \n", + "23384 1687-1709 Rotterdam \n", + "23385 1687-1709 Rotterdam \n", + "23386 1687-1709 Rotterdam \n", + "... ... ... \n", + "22638 Aug. 1496; [1496.08] Venedig \n", + "22639 23. Feb. 1476; [1476.02.23] Mailand \n", + "22650 1725 Paris \n", + "22651 1703 Trajecti Ad Rhenum \n", + "23439 1682 Oxford \n", + "\n", + " Veröffentlichungsort (normiert) ... hs. Katalogseite Digitalisat \n", + "23376 Rotterdam ... NaN \\\n", + "23383 Rotterdam ... NaN \n", + "23384 Rotterdam ... NaN \n", + "23385 Rotterdam ... NaN \n", + "23386 Rotterdam ... NaN \n", + "... ... ... ... \n", + "22638 Venedig ... 423 \n", + "22639 Mailand ... 31 \n", + "22650 Paris ... NaN \n", + "22651 Utrecht ... NaN \n", + "23439 Oxford ... NaN \n", + "\n", + " Wissensklasse Wissensunterklasse \n", + "23376 NaN NaN \\\n", + "23383 NaN NaN \n", + "23384 NaN NaN \n", + "23385 NaN NaN \n", + "23386 NaN NaN \n", + "... ... ... \n", + "22638 Grammatica Tractatus Grammatici generalis cum Lexicographis \n", + "22639 Poëtica Poëtæ Latini Antiqui \n", + "22650 NaN NaN \n", + "22651 NaN NaN \n", + "23439 NaN NaN \n", + "\n", + " Formatangabe hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "23376 NaN NaN NaN \\\n", + "23383 NaN NaN NaN \n", + "23384 NaN NaN NaN \n", + "23385 NaN NaN NaN \n", + "23386 NaN NaN NaN \n", + "... ... ... ... \n", + "22638 Folio 375 14.376_423_03 \n", + "22639 Folio 439 14.377_031_11 \n", + "22650 NaN NaN NaN \n", + "22651 NaN NaN NaN \n", + "23439 NaN NaN NaN \n", + "\n", + " hs. Katalogeintrag \n", + "23376 NaN \\\n", + "23383 NaN \n", + "23384 NaN \n", + "23385 NaN \n", + "23386 NaN \n", + "... ... \n", + "22638 755 Thesaurus Cornucopiæ ac Horti Adonidis græcè. Venetiis 1496. Aldus. n. 2179 \n", + "22639 857....... Ejusdem Comoediæ. Mediolani. 1476. An. Za. n. 2336. \n", + "22650 NaN \n", + "22651 NaN \n", + "23439 NaN \n", + "\n", + " hs. Katalog Image URL \n", + "23376 NaN \\\n", + "23383 NaN \n", + "23384 NaN \n", + "23385 NaN \n", + "23386 NaN \n", + "... ... \n", + "22638 https://iiif.onb.ac.at/images/DOD/51202/00000423.jp2/full/full/0/native.jpg \n", + "22639 https://iiif.onb.ac.at/images/DOD/51184/00000031.jp2/full/full/0/native.jpg \n", + "22650 NaN \n", + "22651 NaN \n", + "23439 NaN \n", + "\n", + " dup_title copy_from \n", + "23376 True -1 \n", + "23383 True -1 \n", + "23384 True -1 \n", + "23385 True -1 \n", + "23386 True -1 \n", + "... ... ... \n", + "22638 False -1 \n", + "22639 False -1 \n", + "22650 False -1 \n", + "22651 False -1 \n", + "23439 False -1 \n", + "\n", + "[9591 rows x 35 columns]" + ] + }, + "execution_count": 1261, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "comp_BE_no_dup[comp_BE_no_dup['Wappenklassifizierung'].isin(['A', 'B', 'C']) | (comp_BE_no_dup['hs. Katalog'] == 1)]" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "f58126a0-fd9e-40d7-a224-60522655fd2c", + "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>dup_title</th>\n", + " <th>copy_from</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>23633</th>\n", + " <td>Ink 3.E.3</td>\n", + " <td>NaN</td>\n", + " <td>Fasciculus temporum</td>\n", + " <td>Rolewinck, Werner</td>\n", + " <td>NaN</td>\n", + " <td>1474.0</td>\n", + " <td>NaN</td>\n", + " <td>[not before 1474]</td>\n", + " <td>[Cologne]</td>\n", + " <td>Köln</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>1 rows × 35 columns</p>\n", + "</div>" + ], + "text/plain": [ + " Signatur Barcode Titel Autor Mitwirkender \n", + "23633 Ink 3.E.3 NaN Fasciculus temporum Rolewinck, Werner NaN \\\n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "23633 1474.0 NaN \\\n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "23633 [not before 1474] [Cologne] \\\n", + "\n", + " Veröffentlichungsort (normiert) ... hs. Katalogseite Digitalisat \n", + "23633 Köln ... NaN \\\n", + "\n", + " Wissensklasse Wissensunterklasse Formatangabe \n", + "23633 NaN NaN NaN \\\n", + "\n", + " hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "23633 NaN NaN \\\n", + "\n", + " hs. Katalogeintrag hs. Katalog Image URL dup_title copy_from \n", + "23633 NaN NaN True -1 \n", + "\n", + "[1 rows x 35 columns]" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "comp_BE_no_dup[comp_BE_no_dup['Signatur'].str.contains('Ink 3.E.3')]" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "e260aa23-0d34-4290-8db1-9aec69b8f591", + "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>dup_title</th>\n", + " <th>copy_from</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>23376</th>\n", + " <td>*28.A.79.(Vol.1)</td>\n", + " <td>Z222907107</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23383</th>\n", + " <td>*28.A.79.(Vol.10)</td>\n", + " <td>Z222908100</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23384</th>\n", + " <td>*28.A.79.(Vol.12)</td>\n", + " <td>Z222908306</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23385</th>\n", + " <td>*28.A.79.(Vol.13)</td>\n", + " <td>Z222908409</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23386</th>\n", + " <td>*28.A.79.(Vol.14)</td>\n", + " <td>Z222908501</td>\n", + " <td>Histoire des ouvrages des scavans</td>\n", + " <td>Basnage de Beauval, Henri</td>\n", + " <td>NaN</td>\n", + " <td>1687.0</td>\n", + " <td>1709.0</td>\n", + " <td>1687-1709</td>\n", + " <td>Rotterdam</td>\n", + " <td>Rotterdam</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>True</td>\n", + " <td>-1</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>23636</th>\n", + " <td>Ink 9.F.4</td>\n", + " <td>NaN</td>\n", + " <td>Opera</td>\n", + " <td>Sallustius Crispus, Gaius</td>\n", + " <td>NaN</td>\n", + " <td>1481.0</td>\n", + " <td>NaN</td>\n", + " <td>23 Dec. 1481</td>\n", + " <td>Venice</td>\n", + " <td>Venedig</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>True</td>\n", + " <td>-3</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22640</th>\n", + " <td>Ink 9.F.5</td>\n", + " <td>1460328-10</td>\n", + " <td>Biblia ; Interpretationes Hebraicorum nominum</td>\n", + " <td>NaN</td>\n", + " <td>Wild, Leonhard</td>\n", + " <td>1481.0</td>\n", + " <td>NaN</td>\n", + " <td>1481</td>\n", + " <td>Venedig</td>\n", + " <td>Venedig</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>True</td>\n", + " <td>-3</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22650</th>\n", + " <td>SA.71.E.58</td>\n", + " <td>Z252861302</td>\n", + " <td>Dialogue sur la musique des anciens</td>\n", + " <td>Chateauneuf, Francois abbe de</td>\n", + " <td>NaN</td>\n", + " <td>1725.0</td>\n", + " <td>NaN</td>\n", + " <td>1725</td>\n", + " <td>Paris</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>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22651</th>\n", + " <td>SA.71.F.74</td>\n", + " <td>Z252867808</td>\n", + " <td>Friderici Adolfi Lampe De Cymbalis Veterum Libri Tres</td>\n", + " <td>Ember, Paul</td>\n", + " <td>Hase, Cornelius <<von>>; Röell, Herman Alexander</td>\n", + " <td>1703.0</td>\n", + " <td>NaN</td>\n", + " <td>1703</td>\n", + " <td>Trajecti Ad Rhenum</td>\n", + " <td>Utrecht</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>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23439</th>\n", + " <td>SA.73.B.48</td>\n", + " <td>Z25920770X</td>\n", + " <td>Claudii Ptolomaei harmonicorum libri tres. Ex Codd. Mss. Undecim, nunc primum graece editus. Johannes Wallis ... recensuit, ed. (etc.)</td>\n", + " <td>Ptolemaeus, Claudius</td>\n", + " <td>Wallis, Johannes</td>\n", + " <td>1682.0</td>\n", + " <td>NaN</td>\n", + " <td>1682</td>\n", + " <td>Oxford</td>\n", + " <td>Oxford</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>False</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>22861 rows × 35 columns</p>\n", + "</div>" + ], + "text/plain": [ + " Signatur Barcode \n", + "23376 *28.A.79.(Vol.1) Z222907107 \\\n", + "23383 *28.A.79.(Vol.10) Z222908100 \n", + "23384 *28.A.79.(Vol.12) Z222908306 \n", + "23385 *28.A.79.(Vol.13) Z222908409 \n", + "23386 *28.A.79.(Vol.14) Z222908501 \n", + "... ... ... \n", + "23636 Ink 9.F.4 NaN \n", + "22640 Ink 9.F.5 1460328-10 \n", + "22650 SA.71.E.58 Z252861302 \n", + "22651 SA.71.F.74 Z252867808 \n", + "23439 SA.73.B.48 Z25920770X \n", + "\n", + " Titel \n", + "23376 Histoire des ouvrages des scavans \\\n", + "23383 Histoire des ouvrages des scavans \n", + "23384 Histoire des ouvrages des scavans \n", + "23385 Histoire des ouvrages des scavans \n", + "23386 Histoire des ouvrages des scavans \n", + "... ... \n", + "23636 Opera \n", + "22640 Biblia ; Interpretationes Hebraicorum nominum \n", + "22650 Dialogue sur la musique des anciens \n", + "22651 Friderici Adolfi Lampe De Cymbalis Veterum Libri Tres \n", + "23439 Claudii Ptolomaei harmonicorum libri tres. Ex Codd. Mss. Undecim, nunc primum graece editus. Johannes Wallis ... recensuit, ed. (etc.) \n", + "\n", + " Autor \n", + "23376 Basnage de Beauval, Henri \\\n", + "23383 Basnage de Beauval, Henri \n", + "23384 Basnage de Beauval, Henri \n", + "23385 Basnage de Beauval, Henri \n", + "23386 Basnage de Beauval, Henri \n", + "... ... \n", + "23636 Sallustius Crispus, Gaius \n", + "22640 NaN \n", + "22650 Chateauneuf, Francois abbe de \n", + "22651 Ember, Paul \n", + "23439 Ptolemaeus, Claudius \n", + "\n", + " Mitwirkender \n", + "23376 NaN \\\n", + "23383 NaN \n", + "23384 NaN \n", + "23385 NaN \n", + "23386 NaN \n", + "... ... \n", + "23636 NaN \n", + "22640 Wild, Leonhard \n", + "22650 NaN \n", + "22651 Hase, Cornelius <<von>>; Röell, Herman Alexander \n", + "23439 Wallis, Johannes \n", + "\n", + " Anfang Veröffentlichungsdatum Ende Veröffentlichungsdatum \n", + "23376 1687.0 1709.0 \\\n", + "23383 1687.0 1709.0 \n", + "23384 1687.0 1709.0 \n", + "23385 1687.0 1709.0 \n", + "23386 1687.0 1709.0 \n", + "... ... ... \n", + "23636 1481.0 NaN \n", + "22640 1481.0 NaN \n", + "22650 1725.0 NaN \n", + "22651 1703.0 NaN \n", + "23439 1682.0 NaN \n", + "\n", + " Veröffentlichungsdatum Veröffentlichungsort \n", + "23376 1687-1709 Rotterdam \\\n", + "23383 1687-1709 Rotterdam \n", + "23384 1687-1709 Rotterdam \n", + "23385 1687-1709 Rotterdam \n", + "23386 1687-1709 Rotterdam \n", + "... ... ... \n", + "23636 23 Dec. 1481 Venice \n", + "22640 1481 Venedig \n", + "22650 1725 Paris \n", + "22651 1703 Trajecti Ad Rhenum \n", + "23439 1682 Oxford \n", + "\n", + " Veröffentlichungsort (normiert) ... hs. Katalogseite Digitalisat \n", + "23376 Rotterdam ... NaN \\\n", + "23383 Rotterdam ... NaN \n", + "23384 Rotterdam ... NaN \n", + "23385 Rotterdam ... NaN \n", + "23386 Rotterdam ... NaN \n", + "... ... ... ... \n", + "23636 Venedig ... NaN \n", + "22640 Venedig ... NaN \n", + "22650 Paris ... NaN \n", + "22651 Utrecht ... NaN \n", + "23439 Oxford ... NaN \n", + "\n", + " Wissensklasse Wissensunterklasse Formatangabe \n", + "23376 NaN NaN NaN \\\n", + "23383 NaN NaN NaN \n", + "23384 NaN NaN NaN \n", + "23385 NaN NaN NaN \n", + "23386 NaN NaN NaN \n", + "... ... ... ... \n", + "23636 NaN NaN NaN \n", + "22640 NaN NaN NaN \n", + "22650 NaN NaN NaN \n", + "22651 NaN NaN NaN \n", + "23439 NaN NaN NaN \n", + "\n", + " hs. Katalogseite Handschrift hs. Katalogeintrag ID \n", + "23376 NaN NaN \\\n", + "23383 NaN NaN \n", + "23384 NaN NaN \n", + "23385 NaN NaN \n", + "23386 NaN NaN \n", + "... ... ... \n", + "23636 NaN NaN \n", + "22640 NaN NaN \n", + "22650 NaN NaN \n", + "22651 NaN NaN \n", + "23439 NaN NaN \n", + "\n", + " hs. Katalogeintrag hs. Katalog Image URL dup_title copy_from \n", + "23376 NaN NaN True -1 \n", + "23383 NaN NaN True -1 \n", + "23384 NaN NaN True -1 \n", + "23385 NaN NaN True -1 \n", + "23386 NaN NaN True -1 \n", + "... ... ... ... ... \n", + "23636 NaN NaN True -3 \n", + "22640 NaN NaN True -3 \n", + "22650 NaN NaN False -1 \n", + "22651 NaN NaN False -1 \n", + "23439 NaN NaN False -1 \n", + "\n", + "[22861 rows x 35 columns]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "comp_BE_no_dup" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "38688d20-39e4-4f79-a509-c145c24eeace", "metadata": {}, "outputs": [], "source": [] -- GitLab