04_hybrid_linucb_param_tuning.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You need to install the package version of this path https://github.com/aldente0630/striatum/tree/dev.\n",
    "  \n",
    "```git clone -b dev --single-branch https://github.com/aldente0630/striatum.git\n",
    "cd striatum\n",
    "python setup.py install```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "import os\n",
    "import matplotlib.pyplot as plt\n",
    "from striatum.bandit import hyblinucb\n",
    "from utils.data import *\n",
    "from utils.policy import *\n",
    "plt.style.use('seaborn')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_DIR = os.path.abspath('../../Data/yahoo!_front_page_today_module_user_click_log/R6')\n",
    "DATA_FILE_NAMES = ['ydata-fp-td-clicks-v1_0.20090501.gz']\n",
    "MODEL_DIR = os.path.abspath('models')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_paths = []\n",
    "for data_file in DATA_FILE_NAMES:\n",
    "    data_paths.append(os.path.join(DATA_DIR, data_file))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "policy_learner = PolicyLearner(hyblinucb.HybLinUCB, shared_context_dimension=35, unshared_context_dimension=6, \n",
    "                               is_shared_context_first=True, seed=0, reset_freq=1000000)\n",
    "param_grid = {'alpha': [0.0, 0.2, 0.4, 0.6, 0.8, 1.0, 1.2, 1.4]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parameters: {'alpha': 0.0} | Average Reward: 5.4816% | Computation Time: 7:47:32\n",
      "Parameters: {'alpha': 0.2} | Average Reward: 6.7748% | Computation Time: 10:10:10\n",
      "Parameters: {'alpha': 0.4} | Average Reward: 6.8336% | Computation Time: 6:00:41\n",
      "Parameters: {'alpha': 0.6} | Average Reward: 6.5022% | Computation Time: 6:05:57\n",
      "Parameters: {'alpha': 0.8} | Average Reward: 6.3473% | Computation Time: 6:04:37\n",
      "Parameters: {'alpha': 1.0} | Average Reward: 6.3421% | Computation Time: 6:14:06\n",
      "Parameters: {'alpha': 1.2} | Average Reward: 6.1590% | Computation Time: 6:09:11\n",
      "Parameters: {'alpha': 1.4} | Average Reward: 5.9606% | Computation Time: 6:15:20\n"
     ]
    }
   ],
   "source": [
    "res = search_param(policy_learner, param_grid, parse_data, data_paths=data_paths, share_context=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not os.path.isdir(MODEL_DIR):\n",
    "    os.mkdir(MODEL_DIR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(os.path.join(MODEL_DIR, 'param_hybrid_linucb.pkl'), 'wb') as file:\n",
    "    pickle.dump(res, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(os.path.join(MODEL_DIR, 'param_hybrid_linucb.pkl'), 'rb') as file:\n",
    "    res = pickle.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Parameter: {'alpha': 0.4}\n",
      "Cumulative CTR: 6.8336%\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "best_param = res['param'][np.argmax(res['avg_reward'])]\n",
    "cum_ctr = np.max(res['avg_reward'])\n",
    "print('Best Parameter: {0}\\nCumulative CTR: {1:0.4%}'.format(best_param, cum_ctr))\n",
    "fig, ax = plt.subplots(figsize=(10, 6))\n",
    "_ = ax.plot(res['seq_avg_reward'][np.argmax(res['avg_reward'])], color='mediumblue', \n",
    "            label='LinUCB with Hybrid Linear Models', linewidth=1)\n",
    "ax.axhline(y=cum_ctr, color='black', linestyle='--', linewidth=1)\n",
    "ax.set_xlabel('Num. of Events')\n",
    "ax.set_ylabel('CTR')\n",
    "ax.set_ylim([0.0, 0.1])\n",
    "ax.legend(loc='best')\n",
    "_ = ax.set_title('Average Reward', fontsize=12, fontweight='bold')"
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}