gist4.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_label_times(logs, prediction_date, churn_days):\n",
    "    \"\"\"\n",
    "    Make labels for an entire series of transactions. \n",
    "    \n",
    "    Params\n",
    "    --------\n",
    "        transactions (dataframe): table of customer transactions\n",
    "        prediction_date (str): time at which predictions are made. Either \"MS\" for the first of the month\n",
    "                               or \"SMS\" for the first and fifteenth of each month \n",
    "        churn_days (int): integer number of days without an active membership required for a churn. A churn is\n",
    "                          defined by exceeding this number of days without an active membership.\n",
    "        lead_time (int): number of periods in advance to make predictions for. Defaults to 1 (preditions for one offset)\n",
    "        prediction_window(int): number of periods over which to consider churn. Defaults to 1.\n",
    "    Return\n",
    "    --------\n",
    "        label_times (dataframe): a table with customer ids, cutoff times, binary label, regression label, \n",
    "                                 and date of churn. This table can then be used for feature engineering.\n",
    "    \"\"\"\n",
    "    \n",
    "    label_times = []\n",
    "    logs = logs.sort_values(['actor_account_id'])\n",
    "    \n",
    "    # Iterate through each customer and find labels\n",
    "    for customer_id, logins in logs.groupby('actor_account_id'):\n",
    "        lt_cust = label_customer(customer_id, logins, prediction_date, churn_days, \n",
    "                                                   )\n",
    "        \n",
    "        label_times.append(lt_cust)\n",
    "        \n",
    "    # Concatenate into a single dataframe\n",
    "    return pd.concat(label_times)"
   ]
  }
 ],
 "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": "3.6.5"
  },
  "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
}