nsw-2016-storm-impact/notebooks/10_profile_clustering.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "\n",
    "from dtaidistance import dtw\n",
    "from dtaidistance import dtw_visualisation as dtwvis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import data\n",
    "def df_from_csv(csv, index_col, data_folder='../data/interim'):\n",
    "    print('Importing {}'.format(csv))\n",
    "    return pd.read_csv(os.path.join(data_folder,csv), index_col=index_col)\n",
    "\n",
    "df_profiles = df_from_csv('profiles.csv', index_col=[0, 1, 2])\n",
    "\n",
    "print('Done!')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use dtaidistance package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p1 = df_profiles.dropna(subset=['z']).xs(['AVOCAn0003','prestorm'],level=['site_id','profile_type']).z.values\n",
    "p2 = df_profiles.dropna(subset=['z']).xs(['AVOCAn0004','prestorm'],level=['site_id','profile_type']).z.values\n",
    "path = dtw.warping_path(p1,p2)\n",
    "dtwvis.plot_warping(p1,p2,path)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use kshape package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "profiles = df_profiles.dropna(subset=['z'])\\\n",
    "            .xs(['prestorm'],level=['profile_type'])\\\n",
    "            .groupby('site_id').z\\\n",
    "            .apply(list).tolist()\n",
    "\n",
    "\n",
    "# profiles = [x[-50:] for x in profiles]\n",
    "# print(min(len(x) for x in profiles))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from kshape.core import kshape, zscore\n",
    "\n",
    "time_series = [[1,2,3,4], [0,1,2,3], [0,1,2,3], [1,2,2,3]]\n",
    "cluster_num = 4\n",
    "clusters = kshape(zscore(profiles, axis=1), cluster_num)\n",
    "# print(clusters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cluster_no = 0\n",
    "\n",
    "# Plot shape of all clusters\n",
    "plt.figure(0)\n",
    "for n,cluster in enumerate(clusters):\n",
    "    plt.plot(cluster[0],label=n)\n",
    "plt.legend()\n",
    "\n",
    "plt.figure(1)\n",
    "# Plot all profiles in partiuclar cluster\n",
    "for profile_no in clusters[cluster_no][1]:\n",
    "    plt.plot(profiles[profile_no])\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = [1,2,3,4,5,6]\n",
    "a[-1:]"
   ]
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.6.6"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}