{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.insert(0,\"..\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# print(sys.path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "from optimus import Optimus"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\argenisleon\\Anaconda3\\lib\\site-packages\\numpy\\_distributor_init.py:32: UserWarning: loaded more than 1 DLL from .libs:\n",
      "C:\\Users\\argenisleon\\Anaconda3\\lib\\site-packages\\numpy\\.libs\\libopenblas.NOIJJG62EMASZI6NYURL6JBKM4EVBGM7.gfortran-win_amd64.dll\n",
      "C:\\Users\\argenisleon\\Anaconda3\\lib\\site-packages\\numpy\\.libs\\libopenblas.PYQHXLVVQ7VESDPUVUADXEVJOBGHJPAY.gfortran-win_amd64.dll\n",
      "  stacklevel=1)\n"
     ]
    }
   ],
   "source": [
    "# op = Optimus(engine=\"dask\",verbose=True)\n",
    "op = Optimus(\"dask\", n_workers=1, threads_per_worker=8, processes=False, memory_limit=\"3G\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df = op.load.file(\"data/Meteorite_Landings.csv\")\n",
    "# df = op.load.file(\"https://bumblebee.nyc3.digitaloceanspaces.com/luisaguirre/edad-32291509-7a3f-4d48-a3a5-a224e088dde7.csv\")\n",
    "df = op.load.file(\"data/crime.csv\").cache()\n",
    "# df = op.load.file(\"data/crime.csv\")\n",
    "# df= df.to_optimus_pandas()\n",
    "\n",
    "# op.load.csv(\"data/airline-safety_csv.csv\", sep=\",\", error_bad_lines=False, header=True, null_value=\"null\",infer_schema=\"true\").ext.cache()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdf = df.compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "def case1(self, df, col_name, conditions, default):\n",
    "    \n",
    "    _when = list(conditions.keys())\n",
    "    _values = list(conditions.values())\n",
    "    _else_ = default\n",
    "\n",
    "    return np.select(_when, _values, default=_else_)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "case(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "invalid syntax (<ipython-input-4-c9364212201c>, line 3)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;36m  File \u001b[1;32m\"<ipython-input-4-c9364212201c>\"\u001b[1;36m, line \u001b[1;32m3\u001b[0m\n\u001b[1;33m    x,y for i,j in a:\u001b[0m\n\u001b[1;37m          ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m invalid syntax\n"
     ]
    }
   ],
   "source": [
    "a = [(\"cond1\", \"value1\"), (\"cond2\", \"value2\")]\n",
    "\n",
    "x,y for i,j in a:\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "class Case:\n",
    "    def __init__(self, df):\n",
    "        self.df = df\n",
    "        self._when = []\n",
    "        self._values = []\n",
    "        self._else_ = []\n",
    "        \n",
    "    def case(value):\n",
    "        return value\n",
    "\n",
    "    def when(self, expr, value):\n",
    "        self._when.append(expr)\n",
    "        self._values.append(value)\n",
    "        return self\n",
    "\n",
    "    def else_(self, value):\n",
    "        self._else_.append(value)\n",
    "        return self\n",
    "\n",
    "    def end(self):\n",
    "        return np.select(self._when, self._values, default=self._else_)\n",
    "#         return value\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for ()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# {\"when\":[cond1, cond2], \"values\":[\"Easy\",\"Medium\"], default:\"Unknown\"}\n",
    "\n",
    "\n",
    "condition = [\n",
    "    (cond1, value1)\n",
    "    \n",
    "]\n",
    "\n",
    "df.cols.case(\"name\",\n",
    "             conditions, \n",
    "             default=\"Unknown\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "#case\n",
    "cond1 = pdf['INCIDENT_NUMBER']==\"I182070945\"\n",
    "cond2 = pdf['INCIDENT_NUMBER']==\"I182070943\"\n",
    "\n",
    "pdf[\"name\"] = pdf[\"name\"].case(pdf['INCIDENT_NUMBER']).\n",
    "     .when(cond1, \"Easy\")\n",
    "     .when(cond2, \"Medium\")\n",
    "     .else_(\"Unknown\")\n",
    "     .end()\n",
    "    \n",
    "\n",
    "#if"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Easy', 'Medium', 'Unknown', ..., 'Unknown', 'Unknown', 'Unknown'],\n",
       "      dtype='<U7')"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Easy', 'Medium']\n",
      "['nknown']\n",
      "[0          True\n",
      "1         False\n",
      "2         False\n",
      "3         False\n",
      "4         False\n",
      "          ...  \n",
      "319068    False\n",
      "319069    False\n",
      "319070    False\n",
      "319071    False\n",
      "319072    False\n",
      "Name: INCIDENT_NUMBER, Length: 319073, dtype: bool, 0         False\n",
      "1          True\n",
      "2         False\n",
      "3         False\n",
      "4         False\n",
      "          ...  \n",
      "319068    False\n",
      "319069    False\n",
      "319070    False\n",
      "319071    False\n",
      "319072    False\n",
      "Name: INCIDENT_NUMBER, Length: 319073, dtype: bool]\n"
     ]
    }
   ],
   "source": [
    "print(a._value)\n",
    "print(a._else_)\n",
    "print(a._when)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wall time: 83 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "import numpy as np\n",
    "\n",
    "np.select(\n",
    "    [\n",
    "        pdf['INCIDENT_NUMBER']==\"I182070945\", \n",
    "        pdf['INCIDENT_NUMBER']==\"I182070943\"\n",
    "    ], \n",
    "    [\n",
    "        'Easy', \n",
    "        'Medium'\n",
    "    ], \n",
    "    default='Unknown'\n",
    ")"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}