Experiment 3 Toy Example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "from comchoice.aggregate import divisiveness, win_rate, copeland, borda\n",
    "from helpers import using_preflib\n",
    "import argparse\n",
    "import math\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.ticker as mtick\n",
    "import pandas as pd\n",
    "import random\n",
    "import seaborn as sns"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# This is a Toy Example for Experiment 3\n",
    "We copied the function `get_manipulation()` from `run_manipulation.py` in order to generate the data for this example. The parameters are defined below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_manipulation(\n",
    "    agents_initial_size=100,\n",
    "    n_alternatives=10,\n",
    "    max_agents=1000,\n",
    "    method_name=\"copeland\",\n",
    "    starting_issue=10,\n",
    "    step=10,\n",
    "    _type=\"UM10\"\n",
    "):\n",
    "    i = 1\n",
    "    method_kws = dict() if method_name == \"copeland\" else dict(score=\"weighted\")\n",
    "    method = copeland if method_name == \"copeland\" else borda\n",
    "\n",
    "    output_divisiveness = []\n",
    "\n",
    "    data = using_preflib(\n",
    "        number_proposals=n_alternatives,\n",
    "        number_individuals=agents_initial_size,\n",
    "        type_=_type\n",
    "    )\n",
    "\n",
    "    alternatives = data[0]\n",
    "    data = [\">\".join(map(str, x)) for x in data]\n",
    "\n",
    "    df = pd.DataFrame(data, columns=[\"ballot\"])\n",
    "    df[\"voter\"] = range(df.shape[0])\n",
    "\n",
    "    voter = agents_initial_size * 1\n",
    "\n",
    "    df_dv = divisiveness(\n",
    "        df,\n",
    "        dtype=\"ballot\",\n",
    "        convert_pairwise_kws=dict(),\n",
    "        method=method,\n",
    "        method_kws=method_kws\n",
    "    )\n",
    "\n",
    "    df_dv[\"size\"] = agents_initial_size\n",
    "    df_dv[\"iteration\"] = 0\n",
    "\n",
    "    alternative_id_manipulate = starting_issue - 1\n",
    "\n",
    "    alternative_id = df_dv[\"alternative\"].unique()[alternative_id_manipulate]\n",
    "    df_dv[\"custom_id\"] = range(1, df_dv.shape[0] + 1)\n",
    "    df_dv[\"alternative_of_interest\"] = df_dv[\"alternative\"] == alternative_id\n",
    "\n",
    "    rank = method(df)\n",
    "    custom_id = df_dv[[\"custom_id\", \"alternative\"]]\n",
    "\n",
    "    output_divisiveness.append(df_dv)\n",
    "\n",
    "    rank = rank[rank[\"alternative\"].astype(str) != str(alternative_id)]\n",
    "    alternatives_rmv = list(rank[\"alternative\"])\n",
    "\n",
    "    while i <= max_agents:\n",
    "        # If i is odd\n",
    "        if i % 2 == 1:\n",
    "            ballot = \">\".join(map(str, [alternative_id] + alternatives_rmv))\n",
    "            df2 = pd.DataFrame({\"ballot\": [ballot], \"voter\": [voter]})\n",
    "            df = pd.concat([df, df2], ignore_index=True)\n",
    "        else:\n",
    "            ballot = \">\".join(map(str, alternatives_rmv + [alternative_id]))\n",
    "            df2 = pd.DataFrame({\"ballot\": [ballot], \"voter\": [voter]})\n",
    "            df = pd.concat([df, df2], ignore_index=True)\n",
    "\n",
    "        if i % step == 0 and i > 1:\n",
    "\n",
    "            df_dv = divisiveness(\n",
    "                df,\n",
    "                dtype=\"ballot\",\n",
    "                convert_pairwise_kws=dict(),\n",
    "                method=method,\n",
    "                method_kws=method_kws\n",
    "            )\n",
    "            df_dv[\"size\"] = voter\n",
    "            df_dv[\"alternative_of_interest\"] = df_dv[\"alternative\"] == alternative_id\n",
    "            df_dv = pd.merge(df_dv, custom_id, on=\"alternative\")\n",
    "            df_dv[\"iteration\"] = i\n",
    "\n",
    "            output_divisiveness.append(df_dv)\n",
    "\n",
    "        voter += 1\n",
    "        i += 1\n",
    "\n",
    "    df_manipulation = pd.concat(output_divisiveness)\n",
    "    df_manipulation[\"starting_id\"] = starting_issue\n",
    "    df_manipulation[\"type\"] = _type\n",
    "\n",
    "    return df_manipulation"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here, we define the parameters to initialize the heuristic. It should be noted that we create 3 profiles, for 5 issues. In this case, the heuristic is initialized with Copeland."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 20/20 [00:01<00:00, 18.33it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 18.46it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 17.80it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 15.39it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 15.63it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 14.95it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 14.15it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 13.42it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 12.75it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 12.31it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 11.29it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 19.76it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 18.70it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 17.81it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 15.95it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 15.70it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 14.81it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 14.18it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 13.52it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 12.69it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 11.41it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 11.67it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 19.28it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 18.59it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 17.63it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 16.61it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 15.47it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 14.90it/s]\n",
      "100%|██████████| 20/20 [00:01<00:00, 12.24it/s]\n",
      "100%|██████████| 20/20 [00:02<00:00,  8.13it/s]\n",
      "100%|██████████| 20/20 [00:02<00:00,  9.08it/s]\n",
      "100%|██████████| 20/20 [00:02<00:00,  9.99it/s]\n",
      "100%|██████████| 20/20 [00:02<00:00,  9.67it/s]\n"
     ]
    },
    {
     "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>alternative</th>\n",
       "      <th>value</th>\n",
       "      <th>rank</th>\n",
       "      <th>size</th>\n",
       "      <th>iteration</th>\n",
       "      <th>custom_id</th>\n",
       "      <th>alternative_of_interest</th>\n",
       "      <th>starting_id</th>\n",
       "      <th>type</th>\n",
       "      <th>percentage</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>IC</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>IC</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>IC</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>IC</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>True</td>\n",
       "      <td>5</td>\n",
       "      <td>IC</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  alternative  value  rank  size  iteration  custom_id  \\\n",
       "0           0    1.0     1   100          0          1   \n",
       "1           1    1.0     1   100          0          2   \n",
       "2           3    1.0     1   100          0          3   \n",
       "3           4    1.0     1   100          0          4   \n",
       "4           2    1.0     1   100          0          5   \n",
       "\n",
       "   alternative_of_interest  starting_id type  percentage  \n",
       "0                    False            5   IC         0.0  \n",
       "1                    False            5   IC         0.0  \n",
       "2                    False            5   IC         0.0  \n",
       "3                    False            5   IC         0.0  \n",
       "4                     True            5   IC         0.0  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n_iterations = 3 # Number of profiles to generate\n",
    "_type = \"IC\" # Method to run. Options are \"IC\", \"UM10\", \"UM50\"\n",
    "max_agents = 100 # Exit condition. Max number of agents to be added.\n",
    "n_alternatives = 5 # Number of issues.\n",
    "starting_issue = 5 # Issue in which we want to manipulate its ranking of divisiveness\n",
    "step = 10 # Number of agents to be added before calculating divisiveness\n",
    "\n",
    "output = []\n",
    "for iteration in range(n_iterations):\n",
    "    dd = get_manipulation(\n",
    "        _type=_type,\n",
    "        max_agents=max_agents,\n",
    "        n_alternatives=n_alternatives,\n",
    "        starting_issue=starting_issue,\n",
    "        step=step\n",
    "    )\n",
    "\n",
    "    output.append(dd)\n",
    "\n",
    "df = pd.concat(output, ignore_index=True)\n",
    "df[\"percentage\"] = (df[\"size\"] - 100) / 100\n",
    "df.head()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, we visualize the results as similar to the figure 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 700x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set(font_scale=2, style=\"white\")\n",
    "fig, ax = plt.subplots(figsize=(7, 7))\n",
    "palette = {c:\"red\" if c==starting_issue else \"grey\" for c in df.custom_id.unique()}\n",
    "\n",
    "g = sns.lineplot(\n",
    "    x=\"percentage\",\n",
    "    y=\"rank\",\n",
    "    palette=palette,\n",
    "    hue=\"custom_id\",\n",
    "    lw=3,\n",
    "    data=df,\n",
    "    legend=False,\n",
    "    ax=ax\n",
    ")\n",
    "\n",
    "ax.xaxis.set_major_formatter(mtick.PercentFormatter(xmax=1))\n",
    "ax.set_xlabel(\"New agents (%)\")\n",
    "ax.set_ylabel(\"Issue ranking\")\n",
    "# ax.set_title(f\"{voting.title()}, {n_alternatives} issues, {method}\")\n",
    "ax.invert_yaxis()\n",
    "sns.despine()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.8"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "369f2c481f4da34e4445cda3fffd2e751bd1c4d706f27375911949ba6bb62e1c"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}