diff --git a/Daten/Vorhersagen/BE_final.xlsx b/Daten/Vorhersagen/BE_final.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..d9db3718bfecc713720c8615353b068e2a5eb420
Binary files /dev/null and b/Daten/Vorhersagen/BE_final.xlsx differ
diff --git a/Daten/Vorhersagen/Complete_BE.xlsx b/Daten/Vorhersagen/Complete_BE.xlsx
deleted file mode 100644
index 3b9acd1d3aaf0e3ac2b33f7fe96155a45ace5e38..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/Complete_BE.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/Complete_BE_Years.xlsx b/Daten/Vorhersagen/Complete_BE_Years.xlsx
deleted file mode 100644
index c8878cbf852d9de05ae899f25836c6e04acd2113..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/Complete_BE_Years.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/Complete_BE_Years_Places.xlsx b/Daten/Vorhersagen/Complete_BE_Years_Places.xlsx
deleted file mode 100644
index 53d6ad84f33f4ad36672f82cab2b9131433d1bf5..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/Complete_BE_Years_Places.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/WIP_complete_BE.xlsx b/Daten/Vorhersagen/WIP_complete_BE.xlsx
deleted file mode 100644
index 2fccd99211ca209864bddc055f445ba5f50ad799..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/WIP_complete_BE.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/WIP_final_BE.xlsx b/Daten/Vorhersagen/WIP_final_BE.xlsx
deleted file mode 100644
index b3e7112058821332c99f6a681a7d29eeaf5ddff7..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/WIP_final_BE.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/WIP_final_BE_2.xlsx b/Daten/Vorhersagen/WIP_final_BE_2.xlsx
deleted file mode 100644
index e8c2c9b921daf437aeefea071a327fd37fbc9a2c..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/WIP_final_BE_2.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/WIP_final_BE_3.xlsx b/Daten/Vorhersagen/WIP_final_BE_3.xlsx
deleted file mode 100644
index 1052487927814fa10aae0202113c456fd09eed02..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/WIP_final_BE_3.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/WIP_final_BE_4.xlsx b/Daten/Vorhersagen/WIP_final_BE_4.xlsx
deleted file mode 100644
index 5f52703952a91115560bb9f3a53243529d2541b8..0000000000000000000000000000000000000000
Binary files a/Daten/Vorhersagen/WIP_final_BE_4.xlsx and /dev/null differ
diff --git a/Daten/Vorhersagen/hw_entries_final.xlsx b/Daten/Vorhersagen/hw_entries_final.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..b07c247e7079769424f0c292b1783a82d7b9382b
Binary files /dev/null and b/Daten/Vorhersagen/hw_entries_final.xlsx differ
diff --git a/Notebooks/XML_Aufbereitung.ipynb b/Notebooks/XML_Aufbereitung.ipynb
index d3a2c7e13250cc9822f9756641a3fe90be643968..d49832591909af3da576b62201533ab4df1278c1 100644
--- a/Notebooks/XML_Aufbereitung.ipynb
+++ b/Notebooks/XML_Aufbereitung.ipynb
@@ -2596,6 +2596,287 @@
"print(repl)"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 295,
+ "id": "10e58748-acb8-48c7-b4c7-a1953f2a70a4",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "final_BE_df = BE_df.drop(['dup_title', 'copy_from'], axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 306,
+ "id": "ee4e5056-d53d-4288-ba06-41af7e6cd3d4",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "final_BE_df.to_excel('../Daten/Vorhersagen/BE_final.xlsx')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 311,
+ "id": "32fc7d42-2093-4a54-9003-00b4a03e9558",
+ "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>volume</th>\n",
+ " <th>page number</th>\n",
+ " <th>category</th>\n",
+ " <th>subcategory</th>\n",
+ " <th>format</th>\n",
+ " <th>handwritten page number</th>\n",
+ " <th>entry_ID</th>\n",
+ " <th>entry</th>\n",
+ " <th>AC numbers</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>14.376</td>\n",
+ " <td>25</td>\n",
+ " <td>Theologia</td>\n",
+ " <td>Textus & Versiones Sacræ Scripturæ</td>\n",
+ " <td>Folio</td>\n",
+ " <td>1</td>\n",
+ " <td>14.376_025_00</td>\n",
+ " <td>1 Biblia Sacra Polyglotta curis Cardinalis Xim...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>14.376</td>\n",
+ " <td>25</td>\n",
+ " <td>Theologia</td>\n",
+ " <td>Textus & Versiones Sacræ Scripturæ</td>\n",
+ " <td>Folio</td>\n",
+ " <td>1</td>\n",
+ " <td>14.376_025_01</td>\n",
+ " <td>2 Biblia Sacra Polyglotta Philippi II. Regis C...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>14.376</td>\n",
+ " <td>25</td>\n",
+ " <td>Theologia</td>\n",
+ " <td>Textus & Versiones Sacræ Scripturæ</td>\n",
+ " <td>Folio</td>\n",
+ " <td>1</td>\n",
+ " <td>14.376_025_02</td>\n",
+ " <td>3 Biblia Sacra Polyglotta Studio & curâ Briani...</td>\n",
+ " <td>[(AC09762517, sicher)]</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>14.376</td>\n",
+ " <td>25</td>\n",
+ " <td>Theologia</td>\n",
+ " <td>Textus & Versiones Sacræ Scripturæ</td>\n",
+ " <td>Folio</td>\n",
+ " <td>1</td>\n",
+ " <td>14.376_025_03</td>\n",
+ " <td>4 Biblia Sacra Latina Moguntina dicta, prima o...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>14.376</td>\n",
+ " <td>25</td>\n",
+ " <td>Theologia</td>\n",
+ " <td>Textus & Versiones Sacræ Scripturæ</td>\n",
+ " <td>Folio</td>\n",
+ " <td>1</td>\n",
+ " <td>14.376_025_04</td>\n",
+ " <td>5 Biblia Sacra Latina Moguntina, editio altera...</td>\n",
+ " <td>[(AC07081950, sicher)]</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",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9398</th>\n",
+ " <td>14.378</td>\n",
+ " <td>582</td>\n",
+ " <td>Imaginum Delineatarum Collectio</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1402</td>\n",
+ " <td>14.378_582_00</td>\n",
+ " <td>CCCXXXI Vn Portefeüilles contenant des Dessein...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9399</th>\n",
+ " <td>14.378</td>\n",
+ " <td>582</td>\n",
+ " <td>Imaginum Delineatarum Collectio</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1402</td>\n",
+ " <td>14.378_582_01</td>\n",
+ " <td>CCCXXXII Vn Recueil des Portraits peints en m...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9400</th>\n",
+ " <td>14.378</td>\n",
+ " <td>582</td>\n",
+ " <td>Imaginum Delineatarum Collectio</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1402</td>\n",
+ " <td>14.378_582_02</td>\n",
+ " <td>CCCXXXIII Dix Vol. de Plantes peintes en mini...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9401</th>\n",
+ " <td>14.378</td>\n",
+ " <td>582</td>\n",
+ " <td>Imaginum Delineatarum Collectio</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1402</td>\n",
+ " <td>14.378_582_03</td>\n",
+ " <td>CCCXXXIV Cinq Vol. d'Oiseaux peints en Miniat...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9402</th>\n",
+ " <td>14.378</td>\n",
+ " <td>582</td>\n",
+ " <td>Imaginum Delineatarum Collectio</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1402</td>\n",
+ " <td>14.378_582_04</td>\n",
+ " <td>CCCXXXV Divers Portraits, Ceremonies, Marches ...</td>\n",
+ " <td>-1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>9403 rows × 9 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " volume page number category \n",
+ "0 14.376 25 Theologia \\\n",
+ "1 14.376 25 Theologia \n",
+ "2 14.376 25 Theologia \n",
+ "3 14.376 25 Theologia \n",
+ "4 14.376 25 Theologia \n",
+ "... ... ... ... \n",
+ "9398 14.378 582 Imaginum Delineatarum Collectio \n",
+ "9399 14.378 582 Imaginum Delineatarum Collectio \n",
+ "9400 14.378 582 Imaginum Delineatarum Collectio \n",
+ "9401 14.378 582 Imaginum Delineatarum Collectio \n",
+ "9402 14.378 582 Imaginum Delineatarum Collectio \n",
+ "\n",
+ " subcategory format handwritten page number \n",
+ "0 Textus & Versiones Sacræ Scripturæ Folio 1 \\\n",
+ "1 Textus & Versiones Sacræ Scripturæ Folio 1 \n",
+ "2 Textus & Versiones Sacræ Scripturæ Folio 1 \n",
+ "3 Textus & Versiones Sacræ Scripturæ Folio 1 \n",
+ "4 Textus & Versiones Sacræ Scripturæ Folio 1 \n",
+ "... ... ... ... \n",
+ "9398 NaN NaN 1402 \n",
+ "9399 NaN NaN 1402 \n",
+ "9400 NaN NaN 1402 \n",
+ "9401 NaN NaN 1402 \n",
+ "9402 NaN NaN 1402 \n",
+ "\n",
+ " entry_ID entry \n",
+ "0 14.376_025_00 1 Biblia Sacra Polyglotta curis Cardinalis Xim... \\\n",
+ "1 14.376_025_01 2 Biblia Sacra Polyglotta Philippi II. Regis C... \n",
+ "2 14.376_025_02 3 Biblia Sacra Polyglotta Studio & curâ Briani... \n",
+ "3 14.376_025_03 4 Biblia Sacra Latina Moguntina dicta, prima o... \n",
+ "4 14.376_025_04 5 Biblia Sacra Latina Moguntina, editio altera... \n",
+ "... ... ... \n",
+ "9398 14.378_582_00 CCCXXXI Vn Portefeüilles contenant des Dessein... \n",
+ "9399 14.378_582_01 CCCXXXII Vn Recueil des Portraits peints en m... \n",
+ "9400 14.378_582_02 CCCXXXIII Dix Vol. de Plantes peintes en mini... \n",
+ "9401 14.378_582_03 CCCXXXIV Cinq Vol. d'Oiseaux peints en Miniat... \n",
+ "9402 14.378_582_04 CCCXXXV Divers Portraits, Ceremonies, Marches ... \n",
+ "\n",
+ " AC numbers \n",
+ "0 -1 \n",
+ "1 -1 \n",
+ "2 [(AC09762517, sicher)] \n",
+ "3 -1 \n",
+ "4 [(AC07081950, sicher)] \n",
+ "... ... \n",
+ "9398 -1 \n",
+ "9399 -1 \n",
+ "9400 -1 \n",
+ "9401 -1 \n",
+ "9402 -1 \n",
+ "\n",
+ "[9403 rows x 9 columns]"
+ ]
+ },
+ "execution_count": 311,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "final_entry_df = entry_df.drop(['AC number', 'AC cert', 'AC comb', 'AC comb set len'], axis=1)\n",
+ "final_entry_df.rename(columns={'AC comb set': 'AC numbers'}, inplace=True)\n",
+ "final_entry_df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 312,
+ "id": "83c0b002-6cf5-4677-8b84-a39d8815daa1",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "final_entry_df.to_excel('../Daten/Vorhersagen/hw_entries_final.xlsx')"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 253,