{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 682,
   "id": "2aa43754",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 743,
   "id": "304eb3b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "node_labels = {0: 'Law, Politics',\n",
    "               1: 'Geography & Environment',\n",
    "               2: 'Computing',\n",
    "               3: 'Dentistry, Ophthalmology, Dermatology',\n",
    "               4: 'Oncology',\n",
    "5: 'Electrical & Electronic Engineering',\n",
    "6: 'Physics',\n",
    "7: 'Cardiology',\n",
    "8: 'Ecology & Zoology',\n",
    "9: 'Psychology',\n",
    "10: 'Information Engineering',\n",
    "11: 'Chemistry & Materials',\n",
    "12: 'Geology',\n",
    "13: 'History & Literature & Philosophy',\n",
    "14: 'Mechanic Engineering',\n",
    "15: 'Mathematics',\n",
    "16: 'Animal',\n",
    "17: 'Molecular & Cell Biology',\n",
    "18: 'Infectious Diseases',\n",
    "19: 'Linguistics',\n",
    "20: 'Nursing',\n",
    "21: 'Agriculture',\n",
    "22: 'Rehabilitation & Sports',\n",
    "23: 'Sociology & Culture',\n",
    "24: 'Economics',\n",
    "25: 'Education'}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "473eba17",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from io import StringIO\n",
    "\n",
    "data = \"\"\"cluster,inner_citations,outer_citations,total_citations,inner_pct\n",
    "0,711800,548049,1259849,56.498834384120634\n",
    "1,2825306,4350637,7175943,39.37191251379784\n",
    "2,545215,1038813,1584028,34.41953046284535\n",
    "3,3032857,2105357,5138214,59.02550964206629\n",
    "4,8835127,7723805,16558932,53.355657236831455\n",
    "5,4895488,3669681,8565169,57.15576657039691\n",
    "6,12930483,7209477,20139960,64.20312155535562\n",
    "7,11827200,10544479,22371679,52.86684115215492\n",
    "8,5666184,4822988,10489172,54.019363968862365\n",
    "9,7727996,5622399,13350395,57.88589775808132\n",
    "10,20884,181174,202058,10.33564620059587\n",
    "11,42393393,17034051,59427444,71.33638963169946\n",
    "12,10201614,5963339,16164953,63.109456612710225\n",
    "13,175760,216233,391993,44.83753536415191\n",
    "14,10137104,7893760,18030864,56.22084443651729\n",
    "15,3357277,2073105,5430382,61.82395639938406\n",
    "16,1788271,2342619,4130890,43.290211068317\n",
    "17,32475251,23904513,56379764,57.600899145303266\n",
    "18,1828191,3769129,5597320,32.66189890876348\n",
    "19,372329,422513,794842,46.84314618502797\n",
    "20,5412666,6430978,11843644,45.70101904447652\n",
    "21,5092710,6579800,11672510,43.62994762908749\n",
    "22,3578910,3525015,7103925,50.379332552075084\n",
    "23,915814,1025574,1941388,47.17315652512532\n",
    "24,4814264,1825075,6639339,72.5111942619589\n",
    "25,1303886,980294,2284180,57.08332968505109\n",
    "\"\"\"\n",
    "\n",
    "node_stats_df = pd.read_csv(StringIO(data))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b06e642c",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = \"\"\"source,target,weight\n",
    "1,0,66149\n",
    "9,0,71487\n",
    "13,0,23908\n",
    "23,0,138078\n",
    "24,0,146312\n",
    "0,1,120324\n",
    "8,1,408321\n",
    "12,1,800313\n",
    "14,1,562147\n",
    "23,1,218507\n",
    "24,1,699784\n",
    "5,2,402426\n",
    "17,2,108435\n",
    "24,2,97128\n",
    "4,3,299181\n",
    "7,3,428572\n",
    "17,3,622684\n",
    "7,4,1994114\n",
    "17,4,3630339\n",
    "20,4,666158\n",
    "2,5,498139\n",
    "6,5,525336\n",
    "10,5,22793\n",
    "14,5,618541\n",
    "15,5,499998\n",
    "10,6,22375\n",
    "11,6,3025458\n",
    "15,6,597620\n",
    "17,6,1345166\n",
    "3,7,423672\n",
    "4,7,1963211\n",
    "17,7,3720848\n",
    "18,7,699751\n",
    "20,7,1762585\n",
    "22,7,927212\n",
    "12,8,727240\n",
    "17,8,1993749\n",
    "21,8,699519\n",
    "0,9,73416\n",
    "7,9,672196\n",
    "17,9,1869135\n",
    "19,9,170920\n",
    "20,9,1119340\n",
    "22,9,413857\n",
    "23,9,166780\n",
    "25,9,236031\n",
    "5,10,18378\n",
    "6,10,14412\n",
    "11,10,51329\n",
    "14,10,60540\n",
    "6,11,4299903\n",
    "8,11,652449\n",
    "10,11,41463\n",
    "12,11,1167841\n",
    "14,11,2781998\n",
    "17,11,4779059\n",
    "21,11,1271460\n",
    "1,12,768398\n",
    "8,12,1012860\n",
    "10,12,29281\n",
    "11,12,1294923\n",
    "13,12,25792\n",
    "0,13,20819\n",
    "8,13,21134\n",
    "9,13,24415\n",
    "12,13,24099\n",
    "23,13,47977\n",
    "1,14,500750\n",
    "2,14,85965\n",
    "5,14,841689\n",
    "6,14,984505\n",
    "10,14,80114\n",
    "11,14,3330667\n",
    "15,14,342352\n",
    "5,15,331958\n",
    "6,15,772570\n",
    "8,16,275029\n",
    "17,16,933612\n",
    "18,16,370272\n",
    "21,16,269749\n",
    "3,17,657476\n",
    "4,17,3800112\n",
    "6,17,1079789\n",
    "7,17,4784463\n",
    "8,17,2025234\n",
    "9,17,1780143\n",
    "11,17,2987257\n",
    "16,17,557236\n",
    "18,17,1455812\n",
    "20,17,1001315\n",
    "21,17,1524990\n",
    "22,17,1117967\n",
    "4,18,301010\n",
    "7,18,740642\n",
    "16,18,207663\n",
    "17,18,1233237\n",
    "20,18,544621\n",
    "9,19,195756\n",
    "25,19,56815\n",
    "4,20,653182\n",
    "7,20,1799023\n",
    "9,20,1121270\n",
    "17,20,756893\n",
    "18,20,562629\n",
    "22,20,459085\n",
    "23,20,125828\n",
    "8,21,951619\n",
    "11,21,1261571\n",
    "16,21,322731\n",
    "17,21,2391614\n",
    "18,21,312984\n",
    "7,22,995276\n",
    "17,22,887859\n",
    "20,22,470379\n",
    "0,23,170152\n",
    "1,23,142231\n",
    "9,23,177747\n",
    "13,23,52370\n",
    "20,23,123757\n",
    "24,23,138902\n",
    "0,24,160567\n",
    "1,24,424907\n",
    "2,24,93550\n",
    "23,24,165142\n",
    "25,24,145669\n",
    "9,25,296731\n",
    "19,25,65181\n",
    "23,25,115073\n",
    "24,25,157661\n",
    "\"\"\"\n",
    "\n",
    "edge_df = pd.read_csv(StringIO(data))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 686,
   "id": "db344533",
   "metadata": {},
   "outputs": [],
   "source": [
    "node_stats_df['color'] = (node_stats_df['inner_citations']-node_stats_df['inner_citations'].min())/(node_stats_df['inner_citations'].max()-node_stats_df['inner_citations'].min())\n",
    "edge_df['normalized_weight'] = (edge_df['weight']-edge_df['weight'].min())/(edge_df['weight'].max()-edge_df['weight'].min())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 943,
   "id": "c0f35011",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8d5d54bbb62a4a2a89f7e245f1de533a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Figure(fig_margin={'top': 60, 'bottom': 60, 'left': 60, 'right': 60}, layout=Layout(height='1200px', width='12…"
      ]
     },
     "execution_count": 943,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from bqplot import Graph, ColorScale, Figure\n",
    "import ipywidgets as widgets\n",
    "import numpy as np\n",
    "\n",
    "# 转换节点和边数据\n",
    "node_data = []\n",
    "for _, row in node_stats_df.iterrows():\n",
    "    r = np.sqrt(row.total_citations)*0.005\n",
    "    label_text = node_labels[row.cluster]\n",
    "    label_loc = 'center'\n",
    "    if r < 15 or len(label_text) > 25:\n",
    "        label_loc = 'outside'\n",
    "    node_data.append({\n",
    "        'label': label_text,\n",
    "        'label_display': label_loc,\n",
    "        'shape': 'circle',\n",
    "        'color': row.color,\n",
    "        'shape_attrs': {'r': r},\n",
    "    })\n",
    "\n",
    "link_data = []\n",
    "for _, row in edge_df.iterrows():    \n",
    "    link_data.append({\n",
    "        'source': row.source,\n",
    "        'target': row.target,\n",
    "        'value': row.normalized_weight,\n",
    "    })\n",
    "\n",
    "# 创建颜色比例尺\n",
    "node_color_scale = ColorScale(min=node_stats_df.color.min(), \n",
    "                             max=node_stats_df.color.max(),\n",
    "                             colors=['#ffeda0', '#f03b20'])\n",
    "link_color_scale = ColorScale(min=edge_df.normalized_weight.min(), \n",
    "                             mid=edge_df.normalized_weight.mean(),\n",
    "                             max=edge_df.normalized_weight.max(),\n",
    "                             colors=['#f7fbff', '#6baed6', '#08306b'])\n",
    "\n",
    "# 创建图形标记\n",
    "graph = Graph(\n",
    "    node_data=node_data,\n",
    "    link_data=link_data,\n",
    "    static=False,\n",
    "    directed=True,\n",
    "    link_type='arc',\n",
    "    scales={\n",
    "        'color': node_color_scale,\n",
    "        'link_color': link_color_scale\n",
    "    },\n",
    "    charge=-1500,\n",
    ")\n",
    "\n",
    "# 创建图形并添加图例\n",
    "figure = Figure(\n",
    "    marks=[graph],\n",
    "    layout=widgets.Layout(width='1200px', height='1200px'),\n",
    ")\n",
    "\n",
    "figure"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0980d0e6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<div style=\"width: 16%; padding: 15px; background: white; border-radius: 6px; box-shadow: 0 2px 4px rgba(0,0,0,0.1);\">\n",
       "    <h7 style=\"margin-top: 0; margin-bottom: -0px; color: #333;\">Node Size: Total Citations</h7>\n",
       "    \n",
       "    <div style=\"margin-bottom: -0px;\">\n",
       "        <div style=\"display: flex; align-items: flex-end; height: 100px; margin-top: 0px;\">\n",
       "            <div style=\"display: flex; flex-direction: column; align-items: center; margin: 0 8px;\"><div style=\"width: 4.495086206069913px; height: 4.495086206069913px; border-radius: 50%; background: #ffeda0; border: 1.75px solid #0b0b0b;\"></div><span style=\"margin-top: 8px; font-size: 12px; color: #333\">50514</span></div><div style=\"display: flex; flex-direction: column; align-items: center; margin: 0 8px;\"><div style=\"width: 22.643614076261304px; height: 22.643614076261304px; border-radius: 50%; background: #ffeda0; border: 1.75px solid #0b0b0b;\"></div><span style=\"margin-top: 8px; font-size: 12px; color: #333\">1281833</span></div><div style=\"display: flex; flex-direction: column; align-items: center; margin: 0 8px;\"><div style=\"width: 40.792141946452695px; height: 40.792141946452695px; border-radius: 50%; background: #ffeda0; border: 1.75px solid #0b0b0b;\"></div><span style=\"margin-top: 8px; font-size: 12px; color: #333\">4159997</span></div><div style=\"display: flex; flex-direction: column; align-items: center; margin: 0 8px;\"><div style=\"width: 58.94066981664409px; height: 58.94066981664409px; border-radius: 50%; background: #ffeda0; border: 1.75px solid #0b0b0b;\"></div><span style=\"margin-top: 8px; font-size: 12px; color: #333\">8685006</span></div><div style=\"display: flex; flex-direction: column; align-items: center; margin: 0 8px;\"><div style=\"width: 77.08919768683548px; height: 77.08919768683548px; border-radius: 50%; background: #ffeda0; border: 1.75px solid #0b0b0b;\"></div><span style=\"margin-top: 8px; font-size: 12px; color: #333\">14856861</span></div>\n",
       "        </div>\n",
       "    </div>\n",
       "    \n",
       "    <h7 style=\"margin-bottom: 5px; color: #333;\">Node Color: Intradisciplinary Citations</h7>\n",
       "    <div style=\"height: 10px; width: 100%; background: linear-gradient(to right, #ffeda0, #f03b20); border-radius: 4px;\"></div>\n",
       "    <div style=\"margin-bottom: -0px; display: flex; justify-content: space-between; font-size: 12px; color: #333\">\n",
       "        <span>20884</span>\n",
       "        <span>10614011</span>\n",
       "        <span>21207138</span>\n",
       "        <span>31800266</span>\n",
       "        <span>42393393</span>\n",
       "    </div>\n",
       "\n",
       "    <h7 style=\"margin-bottom: 5px; color: #333;\">Edge Weight: Interdisciplinary Citations</h7>\n",
       "    <div style=\"height: 10px; width: 100%; background: linear-gradient(to right, #f7fbff, #6baed6, #08306b); border-radius: 4px;\"></div>\n",
       "    <div style=\"margin-bottom: -10px; display: flex; justify-content: space-between;\">\n",
       "        <span style=\"font-size: 12px; color: #333;\">14412</span>\n",
       "        <span style=\"font-size: 12px; color: #333;\">1206925</span>\n",
       "        <span style=\"font-size: 12px; color: #333;\">2399438</span>\n",
       "        <span style=\"font-size: 12px; color: #333;\">3591950</span>\n",
       "        <span style=\"font-size: 12px; color: #333;\">4784463</span>\n",
       "    </div>\n",
       "</div>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from IPython.display import display, HTML\n",
    "import numpy as np\n",
    "\n",
    "# 计算实际显示参数\n",
    "# 节点大小参数\n",
    "node_sizes = np.sqrt(node_stats_df['total_citations']) * 0.005\n",
    "min_size, max_size = node_sizes.min(), node_sizes.max()\n",
    "size_legend_values = np.linspace(min_size, max_size, 5)\n",
    "size_labels = [f\"{(s/0.01)**2:.0f}\" for s in size_legend_values]\n",
    "\n",
    "# 节点颜色参数\n",
    "inner_citations_min = node_stats_df['inner_citations'].min()\n",
    "inner_citations_max = node_stats_df['inner_citations'].max()\n",
    "\n",
    "# 边颜色参数\n",
    "edge_min = edge_df['weight'].min()\n",
    "edge_max = edge_df['weight'].max()\n",
    "\n",
    "legend_html = f\"\"\"\n",
    "<div style=\"width: 14%; padding: 15px; background: white; border-radius: 6px; box-shadow: 0 2px 4px rgba(0,0,0,0.1);\">\n",
    "    <h7 style=\"color: #333;\">Node Size: Total Citations</h7>\n",
    "    \n",
    "    <div>\n",
    "        <div style=\"display: flex; align-items: flex-end; height: 100px;\">\n",
    "            {''.join([f'<div style=\"display: flex; flex-direction: column; align-items: center; margin: 0 8px;\">'\n",
    "                     f'<div style=\"width: {s*2}px; height: {s*2}px; border-radius: 50%; '\n",
    "                     f'background: #ffeda0; border: 1.75px solid #0b0b0b;\"></div>'\n",
    "                     f'<span style=\"margin-top: 8px; font-size: 12px; color: #333\">{label}</span></div>'\n",
    "                     for s, label in zip(size_legend_values, size_labels)])}\n",
    "        </div>\n",
    "    </div>\n",
    "    \n",
    "    <h7 style=\"margin-bottom: 5px; color: #333;\">Node Color: Intradisciplinary Citations</h7>\n",
    "    <div style=\"height: 10px; width: 100%; background: linear-gradient(to right, #ffeda0, #f03b20); border-radius: 4px;\"></div>\n",
    "    <div style=\"margin-bottom: -0px; display: flex; justify-content: space-between; font-size: 12px; color: #333\">\n",
    "        <span>{inner_citations_min}</span>\n",
    "        <span>{inner_citations_min+(inner_citations_max-inner_citations_min)/4:.0f}</span>\n",
    "        <span>{inner_citations_min+(inner_citations_max-inner_citations_min)/2:.0f}</span>\n",
    "        <span>{inner_citations_min+(inner_citations_max-inner_citations_min)*3/4:.0f}</span>\n",
    "        <span>{inner_citations_max}</span>\n",
    "    </div>\n",
    "\n",
    "    <h7 style=\"margin-bottom: 5px; color: #333;\">Edge Weight: Interdisciplinary Citations</h7>\n",
    "    <div style=\"height: 10px; width: 100%; background: linear-gradient(to right, #f7fbff, #6baed6, #08306b); border-radius: 4px;\"></div>\n",
    "    <div style=\"margin-bottom: -10px; display: flex; justify-content: space-between;\">\n",
    "        <span style=\"font-size: 12px; color: #333;\">{edge_min}</span>\n",
    "        <span style=\"font-size: 12px; color: #333;\">{edge_min+(edge_max-edge_min)/4:.0f}</span>\n",
    "        <span style=\"font-size: 12px; color: #333;\">{edge_min+(edge_max-edge_min)/2:.0f}</span>\n",
    "        <span style=\"font-size: 12px; color: #333;\">{edge_min+(edge_max-edge_min)*3/4:.0f}</span>\n",
    "        <span style=\"font-size: 12px; color: #333;\">{edge_max}</span>\n",
    "    </div>\n",
    "</div>\n",
    "\"\"\"\n",
    "\n",
    "display(HTML(legend_html))"
   ]
  }
 ],
 "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": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}