Build 1kk string with 10 chars each using numba builder.

gistfile1.txt

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fletcher._numba_compat import NumbaString, NumbaStringArray\n",
    "from fletcher._algorithms import _startswith\n",
    "import fletcher as fr\n",
    "import numba\n",
    "import pyarrow as pa"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from random import choice\n",
    "from string import ascii_letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "char_arr = np.zeros((10 ** 7,), dtype=np.uint8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(len(char_arr)):\n",
    "    char_arr[i] = ord(choice(ascii_letters))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([100, 109, 103, 104,  81,  70, 118,  78,  71, 105], dtype=uint8)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "char_arr[10:20]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "@numba.njit(nogil=True)\n",
    "def build_strs(arr):\n",
    "    sb = fr._numba_compat.NumbaStringArrayBuilder(10 ** 6, 10 ** 7)\n",
    "    for i in range(0, 10 ** 6, 10):\n",
    "        for j in range(0, 10):\n",
    "            sb.put_byte(arr[i + j])\n",
    "        sb.finish_string()\n",
    "    sb.finish()\n",
    "    return NumbaStringArray(sb.missing, sb.offsets, sb.data, 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "39.1 ms ± 211 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit build_strs(char_arr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "s_arr =  build_strs(char_arr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([100, 109, 103, 104,  81,  70, 118,  78,  71, 105], dtype=int32)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s_arr.decode(1)"
   ]
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}