diff --git a/wikidata/plot-timeline.ipynb b/wikidata/plot-timeline.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..701b71a6d297f62e9810e49eb8d5ead83f089be2
--- /dev/null
+++ b/wikidata/plot-timeline.ipynb
@@ -0,0 +1,120 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "initial_id",
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import plotly.express as px\n",
+ "\n",
+ "# Load the data\n",
+ "df = pd.read_csv(\"scholars.csv\", encoding='utf-8')\n",
+ "\n",
+ "# Initialize a list to track the last dateOfDeath in each row to manage overlaps\n",
+ "last_dates = []\n",
+ "\n",
+ "# Function to find the appropriate row for each scholar\n",
+ "def find_row(last_dates, start_date):\n",
+ " for i, last_date in enumerate(last_dates):\n",
+ " if start_date > last_date:\n",
+ " return i\n",
+ " return len(last_dates)\n",
+ "\n",
+ "# Assign rows without overlaps and sort by the earliest dateOfBirth\n",
+ "df['row'] = 0\n",
+ "for index, scholar in df.iterrows():\n",
+ " row = find_row(last_dates, scholar['dateOfBirth'])\n",
+ " if row < len(last_dates):\n",
+ " last_dates[row] = scholar['dateOfDeath']\n",
+ " else:\n",
+ " last_dates.append(scholar['dateOfDeath'])\n",
+ " df.at[index, 'row'] = row\n",
+ "\n",
+ "# Now plotting without row labels\n",
+ "fig = px.timeline(df, x_start=\"dateOfBirth\", x_end=\"dateOfDeath\", y=\"row\", text=\"fullName\", title=\"Scholars' Life Spans Timeline\")\n",
+ "\n",
+ "# Update layout\n",
+ "fig.update_layout(yaxis=dict(tickmode='array', tickvals=[], ticktext=[]))\n",
+ "fig.update_yaxes(autorange=\"reversed\") # This reverses the y-axis to match your requirement\n",
+ "\n",
+ "fig.show()\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "from datetime import datetime\n",
+ "\n",
+ "# Assuming df is your existing DataFrame\n",
+ "\n",
+ "# Convert dateOfBirth and dateOfDeath to just the year, handle NaT/NaN appropriately\n",
+ "df['Year'] = pd.to_datetime(df['dateOfBirth'], errors='coerce').dt.year.astype('Int64')\n",
+ "df['End Year'] = pd.to_datetime(df['dateOfDeath'], errors='coerce').dt.year.astype('Int64')\n",
+ "\n",
+ "# Create 'Display Date' as \"dateOfBirth - dateOfDeath\"\n",
+ "df['Display Date'] = df['Year'].astype(str).replace('<NA>','') + ' - ' + df['End Year'].astype(str).replace('<NA>','')\n",
+ "\n",
+ "# Create 'Headline' as \"fullName (dateOfBirth - dateOfDeath)\"\n",
+ "df['Headline'] = df['fullName'] + ' (' + df['Display Date'] + ')'\n",
+ "\n",
+ "# Create 'Text' column by combining occupation, fieldOfWork, employer\n",
+ "df['Text'] = df[['occupation', 'fieldOfWork']].apply(lambda x: '<br>'.join(x.dropna()), axis=1)\n",
+ "\n",
+ "# Use the image directly; assuming the URLs are already correctly formed in the 'image' column\n",
+ "df['Media'] = df['image']\n",
+ "\n",
+ "# Add a \"Group\" column with the value \"actors\" for all rows\n",
+ "df['Group'] = 'actors'\n",
+ "\n",
+ "# fix date columns\n",
+ "df['Display Date'] = df['Display Date'].fillna('') # Ensure no NaNs in Display Date\n",
+ "df['Headline'] = df['Headline'].fillna('') # Ensure no NaNs in Headline\n",
+ "df['Text'] = df['Text'].fillna('') # Ensure no NaNs in Text\n",
+ "df['Media'] = df['Media'].fillna('') # Ensure no NaNs in Media\n",
+ "\n",
+ "# Now select and order the DataFrame according to the TimelineJS template requirements\n",
+ "columns = \"Year\tMonth\tDay\tTime\tEnd Year\tEnd Month\tEnd Day\tEnd Time\tDisplay Date\tHeadline\tText\tMedia\tMedia Credit\tMedia Caption\tMedia Thumbnail\tType\tGroup\tBackground\tLink\".split(\"\\t\")\n",
+ "for col in columns:\n",
+ " if col not in df:\n",
+ " df[col] = ''\n",
+ "timeline_df = df[columns]\n",
+ "\n",
+ "timeline_df.to_excel(\"timeline_data.xlsx\", index=False)\n"
+ ],
+ "metadata": {
+ "collapsed": false
+ },
+ "id": "f774e82925504bd"
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 2
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython2",
+ "version": "2.7.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/wikidata/scholars-de.ipynb b/wikidata/scholars-de.ipynb
index 658f3070e5c404c1e6c6d80873090af05c5acca2..02784afc3ecbaf90641180c3eab54c0e7190bbeb 100644
--- a/wikidata/scholars-de.ipynb
+++ b/wikidata/scholars-de.ipynb
@@ -248,132 +248,6 @@
}
},
"id": "2d7bdaeed0f38415"
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "outputs": [
- {
- "ename": "TypeError",
- "evalue": "'>' not supported between instances of 'float' and 'str'",
- "output_type": "error",
- "traceback": [
- "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
- "\u001B[1;31mTypeError\u001B[0m Traceback (most recent call last)",
- "Cell \u001B[1;32mIn[13], line 20\u001B[0m\n\u001B[0;32m 18\u001B[0m df[\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mrow\u001B[39m\u001B[38;5;124m'\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;241m0\u001B[39m\n\u001B[0;32m 19\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m index, scholar \u001B[38;5;129;01min\u001B[39;00m df\u001B[38;5;241m.\u001B[39miterrows():\n\u001B[1;32m---> 20\u001B[0m row \u001B[38;5;241m=\u001B[39m \u001B[43mfind_row\u001B[49m\u001B[43m(\u001B[49m\u001B[43mlast_dates\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mscholar\u001B[49m\u001B[43m[\u001B[49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43mdateOfBirth\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m]\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m 21\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m row \u001B[38;5;241m<\u001B[39m \u001B[38;5;28mlen\u001B[39m(last_dates):\n\u001B[0;32m 22\u001B[0m last_dates[row] \u001B[38;5;241m=\u001B[39m scholar[\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mdateOfDeath\u001B[39m\u001B[38;5;124m'\u001B[39m]\n",
- "Cell \u001B[1;32mIn[13], line 13\u001B[0m, in \u001B[0;36mfind_row\u001B[1;34m(last_dates, start_date)\u001B[0m\n\u001B[0;32m 11\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mfind_row\u001B[39m(last_dates, start_date):\n\u001B[0;32m 12\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m i, last_date \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28menumerate\u001B[39m(last_dates):\n\u001B[1;32m---> 13\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[43mstart_date\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m>\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mlast_date\u001B[49m:\n\u001B[0;32m 14\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m i\n\u001B[0;32m 15\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(last_dates)\n",
- "\u001B[1;31mTypeError\u001B[0m: '>' not supported between instances of 'float' and 'str'"
- ]
- }
- ],
- "source": [
- "import pandas as pd\n",
- "import plotly.express as px\n",
- "\n",
- "# Load the data\n",
- "df = pd.read_csv(\"scholars.csv\", encoding='utf-8')\n",
- "\n",
- "# Initialize a list to track the last dateOfDeath in each row to manage overlaps\n",
- "last_dates = []\n",
- "\n",
- "# Function to find the appropriate row for each scholar\n",
- "def find_row(last_dates, start_date):\n",
- " for i, last_date in enumerate(last_dates):\n",
- " if start_date > last_date:\n",
- " return i\n",
- " return len(last_dates)\n",
- "\n",
- "# Assign rows without overlaps and sort by the earliest dateOfBirth\n",
- "df['row'] = 0\n",
- "for index, scholar in df.iterrows():\n",
- " row = find_row(last_dates, scholar['dateOfBirth'])\n",
- " if row < len(last_dates):\n",
- " last_dates[row] = scholar['dateOfDeath']\n",
- " else:\n",
- " last_dates.append(scholar['dateOfDeath'])\n",
- " df.at[index, 'row'] = row\n",
- "\n",
- "# Now plotting without row labels\n",
- "fig = px.timeline(df, x_start=\"dateOfBirth\", x_end=\"dateOfDeath\", y=\"row\", text=\"fullName\", title=\"Scholars' Life Spans Timeline\")\n",
- "\n",
- "# Update layout\n",
- "fig.update_layout(yaxis=dict(tickmode='array', tickvals=[], ticktext=[]))\n",
- "fig.update_yaxes(autorange=\"reversed\") # This reverses the y-axis to match your requirement\n",
- "\n",
- "fig.show()\n",
- "\n"
- ],
- "metadata": {
- "collapsed": false,
- "ExecuteTime": {
- "end_time": "2024-03-11T22:37:55.002823500Z",
- "start_time": "2024-03-11T22:37:53.483582400Z"
- }
- },
- "id": "9bdf188991f29962"
- },
- {
- "cell_type": "code",
- "execution_count": 44,
- "outputs": [],
- "source": [
- "import pandas as pd\n",
- "from datetime import datetime\n",
- "\n",
- "# Assuming df is your existing DataFrame\n",
- "\n",
- "# Convert dateOfBirth and dateOfDeath to just the year, handle NaT/NaN appropriately\n",
- "df['Year'] = pd.to_datetime(df['dateOfBirth'], errors='coerce').dt.year.astype('Int64')\n",
- "df['End Year'] = pd.to_datetime(df['dateOfDeath'], errors='coerce').dt.year.astype('Int64')\n",
- "\n",
- "# Create 'Display Date' as \"dateOfBirth - dateOfDeath\"\n",
- "df['Display Date'] = df['Year'].astype(str).replace('<NA>','') + ' - ' + df['End Year'].astype(str).replace('<NA>','')\n",
- "\n",
- "# Create 'Headline' as \"fullName (dateOfBirth - dateOfDeath)\"\n",
- "df['Headline'] = df['fullName'] + ' (' + df['Display Date'] + ')'\n",
- "\n",
- "# Create 'Text' column by combining occupation, fieldOfWork, employer\n",
- "df['Text'] = df[['occupation', 'fieldOfWork']].apply(lambda x: '<br>'.join(x.dropna()), axis=1)\n",
- "\n",
- "# Use the image directly; assuming the URLs are already correctly formed in the 'image' column\n",
- "df['Media'] = df['image']\n",
- "\n",
- "# Add a \"Group\" column with the value \"actors\" for all rows\n",
- "df['Group'] = 'actors'\n",
- "\n",
- "# fix date columns\n",
- "df['Display Date'] = df['Display Date'].fillna('') # Ensure no NaNs in Display Date\n",
- "df['Headline'] = df['Headline'].fillna('') # Ensure no NaNs in Headline\n",
- "df['Text'] = df['Text'].fillna('') # Ensure no NaNs in Text\n",
- "df['Media'] = df['Media'].fillna('') # Ensure no NaNs in Media\n",
- "\n",
- "# Now select and order the DataFrame according to the TimelineJS template requirements\n",
- "columns = \"Year\tMonth\tDay\tTime\tEnd Year\tEnd Month\tEnd Day\tEnd Time\tDisplay Date\tHeadline\tText\tMedia\tMedia Credit\tMedia Caption\tMedia Thumbnail\tType\tGroup\tBackground\tLink\".split(\"\\t\")\n",
- "for col in columns:\n",
- " if col not in df:\n",
- " df[col] = ''\n",
- "timeline_df = df[columns]\n",
- "\n",
- "timeline_df.to_excel(\"timeline_data.xlsx\", index=False)\n"
- ],
- "metadata": {
- "collapsed": false,
- "ExecuteTime": {
- "end_time": "2024-03-06T15:08:24.294712700Z",
- "start_time": "2024-03-06T15:08:24.250520100Z"
- }
- },
- "id": "b8058de7fa9212b"
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "outputs": [],
- "source": [],
- "metadata": {
- "collapsed": false
- },
- "id": "f4b14ea7d4941e57"
}
],
"metadata": {