simulation_plots_orig.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Signaling Game Simulation Plots"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Requirements"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from typing import *\n",
    "\n",
    "import plots\n",
    "import simulations\n",
    "import utils\n",
    "\n",
    "plt.rcParams['figure.dpi'] = 300\n",
    "plt.style.use('seaborn-whitegrid')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load a simulation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/murphy/anaconda3/envs/signaling_auto_encoder/lib/python3.8/site-packages/dataclasses_json/core.py:142: RuntimeWarning: `NoneType` object value of non-optional type target_function detected when decoding Simulation.\n",
      "  warnings.warn(f\"`NoneType` object {warning}.\", RuntimeWarning)\n",
      "/Users/murphy/anaconda3/envs/signaling_auto_encoder/lib/python3.8/site-packages/dataclasses_json/core.py:142: RuntimeWarning: `NoneType` object value of non-optional type context_generator detected when decoding Simulation.\n",
      "  warnings.warn(f\"`NoneType` object {warning}.\", RuntimeWarning)\n"
     ]
    }
   ],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\"\n",
    "simulation = simulations.load_simulation(simulation_name)\n",
    "evaluations = simulation.evaluations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\n",
      "Simulation message sizes: [2]\n",
      "Number of trials per evaluation: 10\n"
     ]
    }
   ],
   "source": [
    "print(simulation.experiment_name)\n",
    "print(f\"Simulation message sizes: {list(evaluations.keys())}\")\n",
    "print(f\"Number of trials per evaluation: {len(evaluations[2])}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Available simulations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "strict_context_simulations = {\n",
    "    # O=5\n",
    "    \"Strict\\nshared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Strict\\nnon-shared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    # O=3\n",
    "    \"Strict\\nshared\\nO=3, C=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_1__shared_context_1__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Strict\\nnon-shared\\nO=3, C=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_1__shared_context_0__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "}\n",
    "\n",
    "non_strict_context_simulations = {\n",
    "    # O=5\n",
    "    \"Non-strict\\nshared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Non-Strict\\nnon-shared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Non-strict\\nshared\\nO=5, C=(15,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_15__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Non-strict\\nnon-shared\\nO=5, C=(15,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_15__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Non-strict\\nshared\\nO=5, C=(5,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_5__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Non-strict\\nnon-shared\\nO=5, C=(5,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_5__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    # O=3\n",
    "    \"Non-strict\\nshared\\nO=3, C=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_0__shared_context_1__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"Non-strict\\nnon-shared\\nO=3, C=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_0__shared_context_0__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",    \n",
    "}\n",
    "\n",
    "# Encoder input is <c, f(c)>\n",
    "\n",
    "nature_includes_fc_simulations = {\n",
    "    # O=5\n",
    "    \"F(c) input\\nStrict\\nshared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nStrict\\nnon-shared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "\n",
    "    \"F(c) input\\nNon-strict\\nshared\\nO=5\\nC=(5,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_5__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nNon-strict\\nnon-shared\\nO=5\\nC=(5,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_5__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nNon-strict\\nshared\\nO=5\\nC=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nNon-strict\\nnon-shared\\nO=5\\nC=(10,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nNon-strict\\nshared\\nO=5\\nC=(15,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_15__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nNon-strict\\nnon-shared\\nO=5\\nC=(15,5)\": \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_15__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "\n",
    "    # O=3\n",
    "    \"F(c) input\\nStrict\\nshared\\nO=3\\nC=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_1__shared_context_1__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nStrict\\nnon-shared\\nO=3\\nC=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_1__shared_context_0__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \n",
    "    \"F(c) input\\nNon-strict\\nshared\\nO=3\\nC=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_0__shared_context_1__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"F(c) input\\nNon-strict\\nnon-shared\\nO=3\\nC=(6,3)\": \"acl_ready/extremity_game_acl_4__object_size_3__strict_context_0__shared_context_0__num_objects_6__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "}\n",
    "\n",
    "# Untrained\n",
    "\n",
    "# untrained_simulations = {\n",
    "#     \"Strict, shared\\nO=5, C=(10,5)\": \"acl_ready/extremity_game_acl_untrained__object_size_5__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_0\",\n",
    "#     \"Strict, shared\\nO=3, C=(6,3)\": \"acl_ready/extremity_game_acl_untrained__object_size_3__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_0\",\n",
    "# }"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Available evaluations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "training_losses\n",
      "object_prediction_accuracy\n",
      "detected_num_clusters\n",
      "object_prediction_by_cluster_loss\n",
      "predictions_by_average_msg_loss\n",
      "predictions_by_average_msg_accuracy\n",
      "addition_compositionality_mean_message_loss\n",
      "addition_compositionality_mean_message_cluster_accuracy\n",
      "addition_compositionality_mean_prediction_loss\n",
      "addition_compositionality_mean_prediction_accuracy\n",
      "analogy_compositionality_net_message_mean_loss\n",
      "analogy_compositionality_net_message_cluster_mean_accuracy\n",
      "analogy_compositionality_net_prediction_mean_loss\n",
      "analogy_compositionality_net_prediction_mean_accuracy\n",
      "compositionality_net_message_mean_loss\n",
      "compositionality_net_message_cluster_mean_accuracy\n",
      "compositionality_net_prediction_mean_loss\n",
      "compositionality_net_prediction_mean_accuracy\n",
      "functions_from_messages\n",
      "min_max_from_messages\n",
      "dimension_from_messages\n",
      "sanity_from_messages\n",
      "object_by_context_from_messages\n",
      "object_by_decoder_context_from_messages\n",
      "context_from_messages\n",
      "decoder_context_from_messages\n"
     ]
    }
   ],
   "source": [
    "print('\\n'.join(evaluations[2][0].keys()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Helper functions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_evaluation_mean_and_err(simulation_name, evaluation_name, message_size, percents=False) -> float:\n",
    "    simulation = simulations.load_simulation(simulation_name)\n",
    "    vals = []\n",
    "    for trial in simulation.evaluations[message_size]:\n",
    "        vals.append(trial[evaluation_name])\n",
    "    if percents:\n",
    "        vals = np.array(vals) * 100\n",
    "    return np.mean(vals), np.std(vals)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_bars_for_evaluation(evaluation_name, display_names_to_simulation_names, title, y_label, width=18, msg_size=2):\n",
    "    bar_width = 1\n",
    "    num_simulation_sets = len(display_names_to_simulation_names)\n",
    "\n",
    "    fig, ax = plt.subplots(num_simulation_sets, figsize=(width,8*num_simulation_sets))\n",
    "    \n",
    "    for i, (set_name, display_name_to_simulation) in enumerate(display_names_to_simulation_names.items()):\n",
    "        for s, (display_name, file_name) in enumerate(display_name_to_simulation.items()):\n",
    "            mean, err = get_evaluation_mean_and_err(file_name, evaluation_name, msg_size)\n",
    "            ax[i].bar(s, mean, yerr=err, capsize=10, color=f\"C{i}\", label=display_name)    \n",
    "\n",
    "            ax[i].set_title(set_name)\n",
    "            ax[i].set_xticks(range(len(display_name_to_simulation)))\n",
    "            ax[i].set_xticklabels(display_name_to_simulation.keys())\n",
    "            ax[i].set_ylabel(y_label)\n",
    "\n",
    "    fig.suptitle(title, y=0.92, fontsize=15)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_bars_for_acl(evaluation_name, display_name_to_simulation, title, y_label, msg_size=2):\n",
    "    fig, ax = plt.subplots(1, figsize=(6, 4))\n",
    "    \n",
    "    for s, (display_name, file_name) in enumerate(display_name_to_simulation.items()):\n",
    "        mean, err = get_evaluation_mean_and_err(file_name, evaluation_name, msg_size)\n",
    "        ax.bar(s, mean, yerr=err, capsize=10, color=f\"C{s}\", label=display_name)    \n",
    "\n",
    "        ax.set_xticks(range(len(display_name_to_simulation)))\n",
    "        ax.set_xticklabels(display_name_to_simulation.keys())\n",
    "        ax.set_ylabel(y_label)\n",
    "\n",
    "    fig.suptitle(title, y=0.92, fontsize=15)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "def print_mean_err_for_evaluation(evaluation_name, display_names_to_simulation_names, message_size=2):\n",
    "    for name, sim_name in display_names_to_simulation_names.items():\n",
    "        mean, err = get_evaluation_mean_and_err(sim_name, evaluation_name, message_size)\n",
    "        print(f\"{name}:\\n\\tmean = {mean}\\n\\tstd = {err}\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ACL Plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Shared  | non-shared\n",
    "# Strict                \n",
    "# Non-strict 5\n",
    "# Non-strict 10\n",
    "# Non-strict 15\n",
    "\n",
    "cells = [\n",
    "    [\"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\"],\n",
    "    \n",
    "    [\"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_5__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_5__mini_batch_size_128__loss_type_cross_entropy\"],\n",
    "    \n",
    "    [\"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\", \n",
    "     \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy\"],\n",
    "    \n",
    "    [\"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_15__mini_batch_size_128__loss_type_cross_entropy\",\n",
    "    \"acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_15__mini_batch_size_128__loss_type_cross_entropy\"]\n",
    "]\n",
    "\n",
    "cells = np.array(cells)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\\begin{table}[hbt!]\n",
      "\\begin{tabular}{lcccc}\n",
      "\\toprule\n",
      "                       & \\multicolumn{2}{c}{\\textbf{Compositionality by Addition}} & \\multicolumn{2}{c}{\\textbf{Composition Network}} \\\\ \\midrule\n",
      "                       & \\textbf{Shared} & \\textbf{Non-shared} & \\textbf{Shared} & \\textbf{Non-shared} \\\\ \\midrule\n",
      "\\textbf{Strict} & \\\\ \n",
      "\\emph{10 objects} &  $9.43\\%\\pm 1.26$  & $10.38\\%\\pm 1.37$ &  $11.13\\%\\pm 1.71$  & $11.64\\%\\pm 1.09$      \\\\ % \\midrule\n",
      "\\textbf{Non-strict} & \\\\\n",
      "\\emph{5 objects} &\n",
      "\t$18.49\\%\\pm 1.19$  & $18.99\\%\\pm 1.24$ &  $38.72\\%\\pm 9.96$  & $43.30\\%\\pm 6.49$      \\\\\n",
      "%\\textbf{Non-strict} & \\\\\n",
      "\\emph{10 objects} &\n",
      "\t$8.95\\%\\pm 1.82$  & $9.36\\%\\pm 1.65$ &  $20.84\\%\\pm 4.36$  & $19.66\\%\\pm 3.91$     \\\\\n",
      "\\emph{15 objects} &\n",
      "\t$7.29\\%\\pm 1.65$  & $6.99\\%\\pm 0.96$ &  $11.02\\%\\pm 0.90$  & $11.04\\%\\pm 1.22$     \\\\ \\bottomrule\n",
      "\\end{tabular}\n",
      "\\caption{CAPTION}\\label{tab:LABEL}\n",
      "\\end{table}\n",
      "    \n",
      "\n",
      "\\begin{table}[hbt!]\n",
      "\\begin{tabular}{lcccc}\n",
      "\\toprule\n",
      "                       & \\multicolumn{2}{c}{\\textbf{Compositionality by Addition}} & \\multicolumn{2}{c}{\\textbf{Composition Network}} \\\\ \\midrule\n",
      "                       & \\textbf{Shared} & \\textbf{Non-shared} & \\textbf{Shared} & \\textbf{Non-shared} \\\\ \\midrule\n",
      "\\textbf{Strict} & \\\\ \n",
      "\\emph{10 objects} &  $2.49\\pm 0.18$  & $2.42\\pm 0.17$ &  $2.23\\pm 0.07$  & $2.22\\pm 0.05$      \\\\ % \\midrule\n",
      "\\textbf{Non-strict} & \\\\\n",
      "\\emph{5 objects} &\n",
      "\t$7.66\\pm 0.48$  & $7.55\\pm 0.50$ &  $3.62\\pm 0.56$  & $3.15\\pm 0.48$      \\\\\n",
      "%\\textbf{Non-strict} & \\\\\n",
      "\\emph{10 objects} &\n",
      "\t$4.03\\pm 0.39$  & $3.95\\pm 0.89$ &  $2.20\\pm 0.21$  & $2.16\\pm 0.14$     \\\\\n",
      "\\emph{15 objects} &\n",
      "\t$3.27\\pm 0.41$  & $3.38\\pm 0.24$ &  $2.48\\pm 0.08$  & $2.52\\pm 0.13$     \\\\ \\bottomrule\n",
      "\\end{tabular}\n",
      "\\caption{Lossess}\\label{tab:composition_mse_losses}\n",
      "\\end{table}\n",
      "    \n"
     ]
    }
   ],
   "source": [
    "def plot_table(evaluation_name, cells, caption=\"\", label=\"\", percents=False, message_size=2):\n",
    "\n",
    "    s=r\"\"\"\n",
    "\\begin{table}[]\n",
    "\\begin{tabular}{lcc}\n",
    "\\toprule\n",
    "                       & \\textbf{Shared} & \\textbf{Non-shared} \\\\ \\midrule\n",
    "\\textbf{Strict} & \\\\\n",
    "\\emph{10 objects} & \n",
    "\tXX0,0  & XX0,1      \\\\ % \\midrule\n",
    "\\textbf{Non-strict} & \\\\\n",
    "\\emph{5 objects} &\n",
    "\tXX1,0  & XX1,1      \\\\\n",
    "%\\textbf{Non-strict} & \\\\\n",
    "\\emph{10 objects} &\n",
    "\tXX2,0  & XX2,1      \\\\\n",
    "\\emph{15 objects} &\n",
    "\tXX3,0  & XX3,1      \\\\ \\bottomrule\n",
    "\\end{tabular}\n",
    "\\caption{CAPTION}\\label{tab:LABEL}\n",
    "\\end{table}\n",
    "    \"\"\"\n",
    "    \n",
    "    \n",
    "    for idxs, x in np.ndenumerate(cells):\n",
    "        mean, err = get_evaluation_mean_and_err(x, evaluation_name, message_size, percents)\n",
    "        filler = \"$\" + f\"{mean:.2f}\" \n",
    "        filler += r'\\%' if percents else ''\n",
    "        filler += r\"\\pm \" + f\"{err:.2f}\" + \"$\"\n",
    "        s = s.replace(F\"XX{idxs[0]},{idxs[1]}\", filler)\n",
    "        s = s.replace(\"LABEL\", label)\n",
    "        s = s.replace(\"CAPTION\", caption)\n",
    "\n",
    "    print(s)\n",
    "    \n",
    "    \n",
    "def plot_compositionality_table(evaluation_names, cells, caption=\"\", label=\"\", percents=False, message_size=2):\n",
    "\n",
    "    s=r\"\"\"\n",
    "\\begin{table}[hbt!]\n",
    "\\begin{tabular}{lcccc}\n",
    "\\toprule\n",
    "                       & \\multicolumn{2}{c}{\\textbf{Compositionality by Addition}} & \\multicolumn{2}{c}{\\textbf{Composition Network}} \\\\ \\midrule\n",
    "                       & \\textbf{Shared} & \\textbf{Non-shared} & \\textbf{Shared} & \\textbf{Non-shared} \\\\ \\midrule\n",
    "\\textbf{Strict} & \\\\ \n",
    "\\emph{10 objects} &  XX0,0  & XX0,1 &  YY0,0  & YY0,1      \\\\ % \\midrule\n",
    "\\textbf{Non-strict} & \\\\\n",
    "\\emph{5 objects} &\n",
    "\tXX1,0  & XX1,1 &  YY1,0  & YY1,1      \\\\\n",
    "%\\textbf{Non-strict} & \\\\\n",
    "\\emph{10 objects} &\n",
    "\tXX2,0  & XX2,1 &  YY2,0  & YY2,1     \\\\\n",
    "\\emph{15 objects} &\n",
    "\tXX3,0  & XX3,1 &  YY3,0  & YY3,1     \\\\ \\bottomrule\n",
    "\\end{tabular}\n",
    "\\caption{CAPTION}\\label{tab:LABEL}\n",
    "\\end{table}\n",
    "    \"\"\"\n",
    "    \n",
    "    \n",
    "    for idxs, x in np.ndenumerate(cells):\n",
    "        mean1, err1 = get_evaluation_mean_and_err(x, evaluation_names[0], message_size, percents)\n",
    "        mean2, err2 = get_evaluation_mean_and_err(x, evaluation_names[1], message_size, percents)\n",
    "        filler = \"$\" + f\"{mean1:.2f}\" \n",
    "        filler += r'\\%' if percents else ''\n",
    "        filler += r\"\\pm \" + f\"{err1:.2f}\" + \"$\"\n",
    "        \n",
    "        filler2 = \"$\" + f\"{mean2:.2f}\" \n",
    "        filler2 += r'\\%' if percents else ''\n",
    "        filler2 += r\"\\pm \" + f\"{err2:.2f}\" + \"$\"\n",
    "        \n",
    "        s = s.replace(F\"XX{idxs[0]},{idxs[1]}\", filler)\n",
    "        s = s.replace(F\"YY{idxs[0]},{idxs[1]}\", filler2)\n",
    "        \n",
    "        s = s.replace(\"LABEL\", label)\n",
    "        s = s.replace(\"CAPTION\", caption)\n",
    "\n",
    "    print(s)\n",
    "    \n",
    "plot_compositionality_table([\"addition_compositionality_mean_prediction_accuracy\", \n",
    "                             \"analogy_compositionality_net_prediction_mean_accuracy\"],\n",
    "                           cells,\n",
    "                           \"CAPTION\",\n",
    "                           \"LABEL\", percents=True)\n",
    "\n",
    "\n",
    "plot_compositionality_table([\"addition_compositionality_mean_prediction_loss\", \n",
    "                             \"analogy_compositionality_net_prediction_mean_loss\"],\n",
    "                           cells,\n",
    "                           \"Lossess\",\n",
    "                           \"composition_mse_losses\", percents=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_table_bars(evaluation_name, cells, title, y_label, y_min, y_max=None, percents=False, message_size=2):\n",
    "    plt.style.use('seaborn-whitegrid')\n",
    "    num_ticks = 5\n",
    "    fig, ax = plt.subplots(cells.shape[0], cells.shape[1], figsize=(7,10))\n",
    "    \n",
    "    \n",
    "    global_max = float(\"-inf\")\n",
    "    \n",
    "    for row in range(cells.shape[0]):\n",
    "        for col in range(cells.shape[1]):\n",
    "            mean, err = get_evaluation_mean_and_err(cells[row,col], evaluation_name, message_size)\n",
    "            global_max = max(global_max, mean)\n",
    "            \n",
    "            ax_ = ax[row,col]\n",
    "            ax_.bar([0], mean, yerr=err, capsize=10, color=\"cornflowerblue\")\n",
    "            ax_.set_xticks([])\n",
    "            ax_.set_xticklabels([])\n",
    "#             ax_.set_ylabel(y_label)\n",
    "    \n",
    "    y_max = y_max or global_max\n",
    "    \n",
    "    y_interval = round(\n",
    "        y_max / num_ticks, int(np.abs(np.floor(np.log10(y_max / num_ticks))))\n",
    "    )\n",
    "    y_ticks = [round(x, 1) for x in np.arange(0.0, y_max + y_interval, y_interval)]\n",
    "    y_tick_labels = [str(x) for x in y_ticks]\n",
    "    if percents:\n",
    "        y_tick_labels = [str(int(x*100)) + \"%\" for x in y_ticks]\n",
    "    \n",
    "    for _, curr_ax in np.ndenumerate(ax):\n",
    "        curr_ax.set_yticks(y_ticks)\n",
    "        curr_ax.set_yticklabels(y_tick_labels)\n",
    "\n",
    "#     fig.suptitle(title, fontsize=18, y=0.98)\n",
    "    \n",
    "    fig.text(0.31,0.9, \"Shared context\", fontsize=16, horizontalalignment='center')\n",
    "    fig.text(0.72,0.9, \"Non-shared context\", fontsize=16, horizontalalignment='center')\n",
    "    \n",
    "    fig.text(-0.02,0.8, \"Strict\", fontsize=16, horizontalalignment='center')\n",
    "    fig.text(-0.02,0.6, \"Non-strict,\\n5 objects\", fontsize=16, horizontalalignment='center')\n",
    "    fig.text(-0.02,0.4, \"Non-strict,\\n10 objects\", fontsize=16, horizontalalignment='center')\n",
    "    fig.text(-0.02,0.2, \"Non-strict,\\n15 objects\", fontsize=16, horizontalalignment='center')\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Compositionality accuracy drop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Addition network\n",
      "\t\t [[0.1186, 0.09430000000000001], [0.1176, 0.10375000000000001], [0.8187000000000001, 0.18485000000000001], [0.8299999999999998, 0.18995], [0.3079, 0.0895], [0.2791, 0.09355], [0.1222, 0.0729], [0.1264, 0.06989999999999999]]\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.02429999999999999 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.013849999999999987 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_5__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.63385 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_5__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.6400499999999998 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.2184 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.18555000000000002 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_15__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.0493 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_15__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.05650000000000002 %\n",
      "\n",
      "Min: 0.013849999999999987\n",
      "Compositionality network\n",
      "\t\t [[0.1186, 0.11080000000000001], [0.1176, 0.1234], [0.8187000000000001, 0.4016], [0.8299999999999998, 0.429], [0.3079, 0.20780000000000004], [0.2791, 0.1792], [0.1222, 0.1046], [0.1264, 0.1238]]\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.0077999999999999875 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_1__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t -0.0058 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_5__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.4171000000000001 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_5__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.40099999999999986 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.10009999999999997 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_10__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.09990000000000002 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_1__num_objects_15__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.017600000000000005 %\n",
      "\n",
      "acl_ready/extremity_game_acl_4__object_size_5__strict_context_0__shared_context_0__num_objects_15__mini_batch_size_128__loss_type_cross_entropy:\n",
      "\t 0.002600000000000019 %\n",
      "\n",
      "Min: -0.0058\n"
     ]
    }
   ],
   "source": [
    "def get_performance_drop(evaluation_names):\n",
    "    eval_means = [[get_evaluation_mean_and_err(str(simulation_name), x, message_size=2)[0] for x in evaluation_names] \n",
    "                  for simulation_name in np.nditer(cells)]\n",
    "    print(\"\\t\\t\", eval_means)\n",
    "\n",
    "    decreases = [(x[0]-x[1]) for x in eval_means]\n",
    "\n",
    "    for sim, decrease in zip(np.nditer(cells), decreases):\n",
    "        print(f\"{sim}:\\n\\t\", decrease, \"%\\n\")\n",
    "    print(\"Min:\", min(decreases))\n",
    "\n",
    "print(f\"Addition network\")\n",
    "get_performance_drop([\"object_prediction_accuracy\", \"addition_compositionality_mean_prediction_accuracy\"])\n",
    "\n",
    "print(f\"Compositionality network\")\n",
    "get_performance_drop([\"object_prediction_accuracy\", \"compositionality_net_prediction_mean_accuracy\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Compositionality Appendix Tables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\\begin{table}[]\n",
      "\\begin{tabular}{lcc}\n",
      "\\toprule\n",
      "                       & \\textbf{Shared} & \\textbf{Non-shared} \\\\ \\midrule\n",
      "\\textbf{Strict} & \\\\\n",
      "\\emph{10 objects} & \n",
      "\t$9.43\\%\\pm 1.26$  & $10.38\\%\\pm 1.37$      \\\\ % \\midrule\n",
      "\\textbf{Non-strict} & \\\\\n",
      "\\emph{5 objects} &\n",
      "\t$18.49\\%\\pm 1.19$  & $18.99\\%\\pm 1.24$      \\\\\n",
      "%\\textbf{Non-strict} & \\\\\n",
      "\\emph{10 objects} &\n",
      "\t$8.95\\%\\pm 1.82$  & $9.36\\%\\pm 1.65$      \\\\\n",
      "\\emph{15 objects} &\n",
      "\t$7.29\\%\\pm 1.65$  & $6.99\\%\\pm 0.96$      \\\\ \\bottomrule\n",
      "\\end{tabular}\n",
      "\\caption{addition_compositionality_mean_prediction_accuracy }\\label{tab:addition_compositionality_accuracy}\n",
      "\\end{table}\n",
      "    \n"
     ]
    }
   ],
   "source": [
    "plot_table(\"addition_compositionality_mean_prediction_accuracy\", cells, caption=\"addition_compositionality_mean_prediction_accuracy \", label=\"addition_compositionality_accuracy\", percents=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\\begin{table}[]\n",
      "\\begin{tabular}{lcc}\n",
      "\\toprule\n",
      "                       & \\textbf{Shared} & \\textbf{Non-shared} \\\\ \\midrule\n",
      "\\textbf{Strict} & \\\\\n",
      "\\emph{10 objects} & \n",
      "\t$11.13\\%\\pm 1.71$  & $11.64\\%\\pm 1.09$      \\\\ % \\midrule\n",
      "\\textbf{Non-strict} & \\\\\n",
      "\\emph{5 objects} &\n",
      "\t$38.72\\%\\pm 9.96$  & $43.30\\%\\pm 6.49$      \\\\\n",
      "%\\textbf{Non-strict} & \\\\\n",
      "\\emph{10 objects} &\n",
      "\t$20.84\\%\\pm 4.36$  & $19.66\\%\\pm 3.91$      \\\\\n",
      "\\emph{15 objects} &\n",
      "\t$11.02\\%\\pm 0.90$  & $11.04\\%\\pm 1.22$      \\\\ \\bottomrule\n",
      "\\end{tabular}\n",
      "\\caption{addition_compositionality_mean_prediction_accuracy }\\label{tab:addition_compositionality_accuracy}\n",
      "\\end{table}\n",
      "    \n"
     ]
    }
   ],
   "source": [
    "plot_table(\"analogy_compositionality_net_prediction_mean_accuracy\", cells, caption=\"addition_compositionality_mean_prediction_accuracy \", label=\"addition_compositionality_accuracy\", percents=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Object Prediciton Accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/murphy/anaconda3/envs/signaling_auto_encoder/lib/python3.8/site-packages/dataclasses_json/core.py:142: RuntimeWarning: `NoneType` object value of non-optional type target_function detected when decoding Simulation.\n",
      "  warnings.warn(f\"`NoneType` object {warning}.\", RuntimeWarning)\n",
      "/Users/murphy/anaconda3/envs/signaling_auto_encoder/lib/python3.8/site-packages/dataclasses_json/core.py:142: RuntimeWarning: `NoneType` object value of non-optional type context_generator detected when decoding Simulation.\n",
      "  warnings.warn(f\"`NoneType` object {warning}.\", RuntimeWarning)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2100x3000 with 8 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_table_bars(\"object_prediction_accuracy\", cells, \"Object Prediction Accuracy\", \"Accuracy\", percents=True, y_min=0, y_max=1.0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyError",
     "evalue": "'clusterization_f_score'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-21-5031c6595beb>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mplot_table\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"clusterization_f_score\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcells\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcaption\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"Message clusterization F1 scores. \"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"f1_scores\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpercents\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m<ipython-input-15-5fd26da13e12>\u001b[0m in \u001b[0;36mplot_table\u001b[0;34m(evaluation_name, cells, caption, label, percents, message_size)\u001b[0m\n\u001b[1;32m     24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     25\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0midxs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndenumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcells\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 26\u001b[0;31m         \u001b[0mmean\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0merr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_evaluation_mean_and_err\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mevaluation_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmessage_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpercents\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     27\u001b[0m         \u001b[0mfiller\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"$\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34mf\"{mean:.2f}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     28\u001b[0m         \u001b[0mfiller\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;34mr'\\%'\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mpercents\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;34m''\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-9-e7f0d21ab76a>\u001b[0m in \u001b[0;36mget_evaluation_mean_and_err\u001b[0;34m(simulation_name, evaluation_name, message_size, percents)\u001b[0m\n\u001b[1;32m      3\u001b[0m     \u001b[0mvals\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mtrial\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msimulation\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluations\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmessage_size\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m         \u001b[0mvals\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrial\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mevaluation_name\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mpercents\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m         \u001b[0mvals\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvals\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0;36m100\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'clusterization_f_score'"
     ]
    }
   ],
   "source": [
    "plot_table(\"clusterization_f_score\", cells, caption=\"Message clusterization F1 scores. \", label=\"f1_scores\", percents=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_table(\"predictions_by_average_msg_accuracy\", cells, caption=\"Object prediction accuracy using average message from each function cluster. \", label=\"average_message_accuracy\", percents=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_table_bars(\"clusterization_f_score\", cells, \"Object Prediction Accuracy\", \"Accuracy\", percents=False, y_min=0, y_max=1.0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## General prediction accuracy\n",
    "Test whether predicted object is closest to target object.\n",
    "\n",
    "Method: Take network's predicted object, find closest object in input context C (using MSE), check if closest object is the target object."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_sets = {\"Strict context\": strict_context_simulations, \n",
    "                   \"Non-strict\": non_strict_context_simulations, \n",
    "                   \"F(c) input\": nature_includes_fc_simulations,\n",
    "                  \"Untrained networks\": untrained_simulations}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"object_prediction_accuracy\", simulation_sets, \"Prediction accuracy of objects\", \"Accuracy\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predictions from M\n",
    "\n",
    "Method: a simple neural network (hidden layer size 32 * ReLU) is trained to predict the various game elements from the messages M.\n",
    "For one-hot objects (i.e. F) an accuracy measure can be used. For the other elements, which are continuous, MSE is used. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"functions_from_messages\", simulation_sets, \"M -> F\", \"Accuracy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"context_from_messages\", simulation_sets, \"M -> C\", \"MSE\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"decoder_context_from_messages\", simulation_sets, \"M -> C'\", \"MSE\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"object_by_context_from_messages\", simulation_sets, \"M -> f(c)\", \"MSE\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"object_by_decoder_context_from_messages\", simulation_sets, \"M -> f(c')\", \"MSE\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"min_max_from_messages\", simulation_sets, \"M -> min/max\", \"Accuracy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"dimension_from_messages\", simulation_sets, \"M -> Param(F)\", \"Accuracy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"sanity_from_messages\", simulation_sets, \"Sanity Check\", \"Accuracy\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training losses"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Shared vs. Non-shared"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_display_name_to_file_name = {\n",
    "    \"Shared context\": \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\",\n",
    "    \"Non-shared context\": \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\",\n",
    "} \n",
    "\n",
    "plots.plot_simulation_training_loss(simulation_display_name_to_file_name, max_epochs=5000, epoch_interval=100, label_interval=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### First 50 epochs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plots.plot_simulation_training_loss(simulation_display_name_to_file_name, max_epochs=50, epoch_interval=1, label_interval=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict context, O=5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_display_name_to_file_name = {\n",
    "    \"Strict context\": \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\",\n",
    "} \n",
    "\n",
    "plots.plot_simulation_training_loss(simulation_display_name_to_file_name, max_epochs=5000, epoch_interval=100, label_interval=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Non-strict, O=5, C=(15, 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_display_name_to_file_name = {\n",
    "    \"Non-strict context\\nO=5, C=(15,5)\": \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_0__shared_context_1__nature_includes_function_1__num_objects_15__mini_batch_size_128__num_batches_5000\",\n",
    "} \n",
    "\n",
    "plots.plot_simulation_training_loss(simulation_display_name_to_file_name, max_epochs=5000, epoch_interval=100, label_interval=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Non-strict, O=5, C=(10,5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_display_name_to_file_name = {\n",
    "    \"Non-strict context\": \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_0__shared_context_1__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\",\n",
    "} \n",
    "plots.plot_simulation_training_loss(simulation_display_name_to_file_name, max_epochs=5000, epoch_interval=100, label_interval=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Non-strict, O=5, C=(5,5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_display_name_to_file_name = {\n",
    "    \"Non-strict context\\nO=5, C=(5,5)\": \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_0__shared_context_1__nature_includes_function_1__num_objects_5__mini_batch_size_128__num_batches_5000\",\n",
    "} \n",
    "\n",
    "plots.plot_simulation_training_loss(simulation_display_name_to_file_name, max_epochs=5000, epoch_interval=100, label_interval=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clustering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Cluster-function F1-score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "sets = {\"Strict context\": strict_context_simulations, \n",
    "        \"Non-strict\": non_strict_context_simulations, \n",
    "        \"F(c) input\": nature_includes_fc_simulations,\n",
    "        \"Untrained networks\": untrained_simulations}\n",
    "plot_bars_for_evaluation(\"clusterization_f_score\", sets, \"Clusterization F1-score\", \"F1\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Prediction by cluster average message"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "plot_bars_for_evaluation(\"predictions_by_average_msg_accuracy\", \n",
    "                         sets, \n",
    "                         \"Prediction of context objects from cluster average message\", \n",
    "                         \"Accuracy\", \n",
    "                         width=12)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compositionality Tests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "compositionality_test_to_evals = {\n",
    "    \"Compositionality as addition\": {\n",
    "        \"loss_evals\": {\n",
    "            \"Perception loss (O)\": \"addition_compositionality_mean_prediction_loss\",\n",
    "            \"Production loss (M)\": \"addition_compositionality_mean_message_loss\",\n",
    "        },\n",
    "        \"accuracy_evals\": {\n",
    "            \"Perception accuracy\\n(O)\": \"addition_compositionality_mean_prediction_accuracy\",\n",
    "            \"Production accuracy\\n(M cluster)\": \"addition_compositionality_mean_message_cluster_accuracy\",\n",
    "        }\n",
    "    },\n",
    "\n",
    "    \"Compositionality as analogy\":  {       \n",
    "        \"loss_evals\": {\n",
    "            \"Perception loss (O)\": \"analogy_compositionality_net_prediction_mean_loss\",\n",
    "            \"Production loss (M)\": \"analogy_compositionality_net_message_mean_loss\"\n",
    "        },\n",
    "        \"accuracy_evals\": {\n",
    "            \"Perception accuracy (O)\": \"analogy_compositionality_net_prediction_mean_accuracy\",\n",
    "            \"Production accuracy\\n(M cluster)\": \"analogy_compositionality_net_message_cluster_mean_accuracy\"\n",
    "        }\n",
    "    },\n",
    "\n",
    "    \"Compositionality network\": { \n",
    "        \"loss_evals\": {\n",
    "            \"Perception loss (O)\": \"addition_compositionality_mean_prediction_loss\",\n",
    "            \"Production loss (M)\": \"addition_compositionality_mean_message_loss\",\n",
    "        },\n",
    "        \"accuracy_evals\": {\n",
    "            \"Perception accuracy\\n(O)\": \"addition_compositionality_mean_prediction_accuracy\",\n",
    "            \"Production accuracy\\n(M cluster)\": \"addition_compositionality_mean_message_cluster_accuracy\",\n",
    "        }\n",
    "    }\n",
    "}\n",
    "\n",
    "def plot_all_compositionality_stats(simulation_name):\n",
    "    for compo_test_name, evals in compositionality_test_to_evals.items():\n",
    "        plot_compositionality(compo_test_name, simulation_name, evals[\"loss_evals\"], evals[\"accuracy_evals\"])\n",
    "\n",
    "    \n",
    "def plot_compositionality(title, simulation_name, loss_evals, accuracy_evals, message_size=2):\n",
    "    fig, ax = plt.subplots(1,2, figsize=(10,4))\n",
    "    bar_width = 1\n",
    "\n",
    "    for i, (display_name, eval_name) in enumerate(loss_evals.items()):\n",
    "        mean, err = get_evaluation_mean_and_err(simulation_name, eval_name, message_size)\n",
    "        ax[0].bar(i, mean, yerr=err, capsize=5, color=f\"C{i}\", label=display_name)\n",
    "\n",
    "    for i, (display_name, eval_name) in enumerate(accuracy_evals.items()):\n",
    "        mean, err = get_evaluation_mean_and_err(simulation_name, eval_name, message_size)\n",
    "        ax[1].bar(i, mean, yerr=err, capsize=5, color=f\"C{i}\", label=display_name)\n",
    "\n",
    "    ax[0].set_xticks(range(len(accuracy_evals)))\n",
    "    ax[0].set_xticklabels(list(loss_evals.keys()))\n",
    "\n",
    "    ax[1].set_xticks(range(len(loss_evals)))\n",
    "    ax[1].set_xticklabels(list(accuracy_evals.keys()))\n",
    "\n",
    "    ax[0].set_ylabel(\"MSE loss\")\n",
    "    ax[1].set_ylabel(\"Accuracy\")\n",
    "    fig.suptitle(title)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Shared context, O=5, Encoder input = <c, f>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Non-shared context, O=5, Encoder input = <c, f>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'plot_all_compositionality_stats' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-22-d5e4d3707260>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0msimulation\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mplot_all_compositionality_stats\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msimulation\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'plot_all_compositionality_stats' is not defined"
     ]
    }
   ],
   "source": [
    "simulation = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Shared context, O=5, Encoder input = <c, f(c)>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_1__nature_includes_function_0__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Non-shared context, O=5, Encoder input = <c, f(c)>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation=\"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_0__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Shared context, O=3, Encoder input = <c, f>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation=\"acl_ready/extremity_game_acl_o_3__object_size_3__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Non-shared context, O=3, Encoder input = <c, f>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation=\"acl_ready/extremity_game_acl_o_3__object_size_3__strict_context_1__shared_context_0__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Shared context, O=3, Encoder input = <c, f(c)>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation=\"acl_ready/extremity_game_acl_o_3__object_size_3__strict_context_1__shared_context_1__nature_includes_function_0__num_objects_6__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, Non-shared context, O=3, Encoder input = <c, f(c)>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "simulation=\"acl_ready/extremity_game_acl_o_3__object_size_3__strict_context_1__shared_context_0__nature_includes_function_0__num_objects_6__mini_batch_size_128__num_batches_5000\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Untrained network"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation=\"acl_ready/extremity_game_acl_untrained__object_size_3__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_0\"\n",
    "plot_all_compositionality_stats(simulation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Message visualizations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def visualize_messages(simulation_name, game_number=0):\n",
    "    simulation = simulations.load_simulation(simulation_name)\n",
    "    games=simulations.load_games(simulation_name)\n",
    "    message_size = simulation.message_sizes[0]\n",
    "    games[message_size][game_number]._plot_messages_information()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Encoder input is <c, f>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, shared context, O=5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import utils\n",
    "plt.style.use('seaborn-whitegrid')\n",
    "\n",
    "simulation_name = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, non-shared context, O=5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name, 3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "### Non-strict, non-shared, O=5, C=5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_0__shared_context_0__nature_includes_function_1__num_objects_5__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name, 3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Encoder input is <c, f(c)>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Strict, shared context, O=5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_1__nature_includes_function_0__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### O=5, Non-shared context"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_0__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### O=3, Shared context"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_3__object_size_3__strict_context_1__shared_context_1__nature_includes_function_0__num_objects_6__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### O=3, Non-shared context"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_3__object_size_3__strict_context_1__shared_context_0__nature_includes_function_0__num_objects_6__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Encoder input is <c, f>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Non-shared context"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_o_5__object_size_5__strict_context_1__shared_context_0__nature_includes_function_1__num_objects_10__mini_batch_size_128__num_batches_5000\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Untrained network, O=5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_untrained__object_size_5__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_0\"\n",
    "visualize_messages(simulation_name, 6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Untrained network, O=3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulation_name = \"acl_ready/extremity_game_acl_untrained__object_size_3__strict_context_1__shared_context_1__nature_includes_function_1__num_objects_6__mini_batch_size_128__num_batches_0\"\n",
    "visualize_messages(simulation_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Categorical Perception"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from scipy import interpolate\n",
    "\n",
    "simulation_name = \"extremity_game__object_size_5__context_size_10,5__message_sizes_2__strict_context_1__shared_context_0__num_objects_10__num_batches_5000__num_trials_20\"\n",
    "simulation = simulations.load_simulation(simulation_name)\n",
    "\n",
    "target_1_accuracies = [np.array(simulation.evaluations[2][i][\"categorical_perception_target_1_accuracies\"]) for i in range(len(simulation.evaluations[2]))]\n",
    "target_2_accuracies = [np.array(simulation.evaluations[2][i][\"categorical_perception_target_2_accuracies\"]) for i in range(len(simulation.evaluations[2]))]\n",
    "\n",
    "target_1_mean_accuracies = np.mean(target_1_accuracies, axis=0)\n",
    "target_2_mean_accuracies = np.mean(target_2_accuracies, axis=0)\n",
    "\n",
    "target_1_std_accuracies = np.std(target_1_accuracies, axis=0)\n",
    "target_2_std_accuracies = np.std(target_2_accuracies, axis=0)\n",
    "\n",
    "step_size = 10\n",
    "idxs = np.arange(0,target_1_mean_accuracies.shape[0], step_size)\n",
    "x = np.arange(len(idxs))\n",
    "\n",
    "print(len(idxs))\n",
    "fig, ax = plt.subplots(1, figsize=(8, 4))\n",
    "\n",
    "_, caps_1, bars_1 = ax.errorbar(x, target_1_mean_accuracies[idxs], yerr=target_1_std_accuracies[idxs], capsize=2, marker=\".\", linestyle=\"solid\", color=\"C2\", label='$F_{-1}$', alpha=1)\n",
    "_, caps_2, bars_2 = ax.errorbar(x, target_2_mean_accuracies[idxs], yerr=target_2_std_accuracies[idxs], capsize=2, marker=\".\", linestyle=\"solid\", color=\"C3\", label='$F_{+1}$', alpha=1)\n",
    "[bar.set_alpha(0.2) for bar in bars_1 + bars_2]\n",
    "[cap.set_alpha(0.2) for cap in caps_1 + caps_2]\n",
    "\n",
    "ax.set_xlabel(\"Message shift ($t$)\")\n",
    "ax.set_ylabel(\"Object recovery accuracy\")\n",
    "len_x = len(idxs)\n",
    "\n",
    "ax.set_xticks([0, len_x//4, 4*len_x//10, len_x//2, 6*len_x//10,3*len_x//4, len_x])\n",
    "ax.set_xticklabels([-5,-2.5,\"-1\\n$M_{-1}$\",0,\"1\\n$M_{+1}$\",2.5,5])\n",
    "\n",
    "ax.legend(ncol=1, loc=\"lower right\", bbox_to_anchor=(0.97, 0.76))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}