Performance of np.array for parsing list of strings

float_string_performance.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "float_strings = [str(k) for k in range(1000)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "150 µs ± 2.99 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "np.array(float_strings, dtype=float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "_cnv_flt = {\n",
    "    \"{\": lambda v: str(v),\n",
    "    \"N\": lambda v: np.nan,\n",
    "    \"n\": lambda v: np.nan,\n",
    "    \" \": lambda v: float(v),\n",
    "    \"-\": lambda v: np.nan if (len(v) == 1) else float(v),\n",
    "}\n",
    "for ch in \"+0123456789\":\n",
    "    _cnv_flt[ch] = lambda v: float(v)\n",
    "\n",
    "def _parse_float_column(values):\n",
    "    return np.array(values, dtype=np.float)\n",
    "    fvalues = [_cnv_flt[vv[0]](vv.strip()) for vv in values]\n",
    "    return np.array(fvalues, np.float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "148 µs ± 1.89 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "_parse_float_column(float_strings)"
   ]
  },
  {
   "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": "3.8.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}