added fig s12 code

jupyter_notebooks/0_Scraping_model_metadata.ipynb

@@ -246,7 +246,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "id": "3f95b4ba-5742-4268-b2e8-de9145faf495",
    "metadata": {
     "execution": {
@@ -257,7 +257,15 @@
      "shell.execute_reply.started": "2025-02-08T19:37:58.117369Z"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Failed to fetch data: HTTP 500\n"
+     ]
+    }
+   ],
    "source": [
     "get_model_metadata()"
    ]

jupyter_notebooks/SuppM_Figure_S12_asset_types.ipynb

@@ -0,0 +1,84 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0d18a6a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from matplotlib.ticker import FuncFormatter\n",
+    "from pathlib import Path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "98d25755",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "current_dir = Path.cwd()\n",
+    "\n",
+    "def sortByFrequency_model_types_csv(csv_path, output_svg_path):\n",
+    "    hatch_pattern = '\\\\\\\\\\\\\\\\\\\\\\\\'  # Hatch pattern for the bars\n",
+    "\n",
+    "    # Read the CSV file\n",
+    "    df = pd.read_csv(csv_path)\n",
+    "\n",
+    "    if 'type' not in df.columns:\n",
+    "        return \"The CSV file does not contain a 'type' column.\"\n",
+    "\n",
+    "    # Count the occurrences of each model type\n",
+    "    type_counts = df['type'].value_counts().reset_index()\n",
+    "    type_counts.columns = ['Type', 'Count']\n",
+    "    total = type_counts['Count'].sum()\n",
+    "    type_counts['Percentage'] = (type_counts['Count'] / total * 100).round(2)\n",
+    "\n",
+    "    # Sort the data in ascending order\n",
+    "    type_counts = type_counts.sort_values(by='Count', ascending=True)\n",
+    "\n",
+    "    # Plotting\n",
+    "    plt.figure(figsize=(10, 3.5))\n",
+    "    bars = plt.barh(type_counts['Type'], type_counts['Count'], color='white', hatch=hatch_pattern, edgecolor='coral')\n",
+    "    plt.xlabel('Counts', fontweight='bold')\n",
+    "    plt.ylabel('Asset Type', fontweight='bold')\n",
+    "\n",
+    "    ax = plt.gca()\n",
+    "\n",
+    "    # Hide all axis spines\n",
+    "    for spine in ax.spines.values():\n",
+    "        spine.set_visible(False)\n",
+    "\n",
+    "    # Keep ticks visible\n",
+    "    ax.xaxis.set_ticks_position('bottom')\n",
+    "    ax.yaxis.set_ticks_position('left')\n",
+    "\n",
+    "    # Bold tick labels\n",
+    "    for label in ax.get_xticklabels() + ax.get_yticklabels():\n",
+    "        label.set_fontweight('bold')\n",
+    "\n",
+    "    # Format x-axis ticks: 25000 → 25 k\n",
+    "    ax.xaxis.set_major_formatter(FuncFormatter(lambda x, _: f'{int(x/1000)} k' if x >= 1000 else f'{int(x)}'))\n",
+    "\n",
+    "    # Add percentage labels to the bars\n",
+    "    for bar, percentage in zip(bars, type_counts['Percentage']):\n",
+    "        plt.text(bar.get_width() + 5, bar.get_y() + bar.get_height()/2,\n",
+    "                 f'  {percentage}%', va='center', color='blueviolet', fontweight='bold')\n",
+    "\n",
+    "    plt.tight_layout()\n",
+    "    plt.savefig(out_file, format='svg')\n",
+    "    plt.show()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}