DictMergeExperiment.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "63b0a187-8866-4376-b688-1cb5601314ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "import dis\n",
    "import faker"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "8064dbca-a7af-4160-8f6d-dfd77f550f9b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python 3.12.0\n"
     ]
    }
   ],
   "source": [
    "!python --version"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "83dc9403-ee51-4102-b608-bea7d12722a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "fake = Faker()\n",
    "fake.seed(0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "57074fdc-674f-4eb8-b34c-488cac24d951",
   "metadata": {},
   "source": [
    "## Sample Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "780b457d-a87d-4ca6-9330-314f3ad0440b",
   "metadata": {},
   "outputs": [],
   "source": [
    "N = 10**2\n",
    "small_dict_1 = {fake.uuid4(): fake.uuid4() for _ in range(N)}\n",
    "small_dict_2 = {fake.uuid4(): fake.uuid4() for _ in range(N)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "0bf83fee-334f-463b-90ce-93f96025891b",
   "metadata": {},
   "outputs": [],
   "source": [
    "N = 10**6\n",
    "big_dict_1 = {fake.uuid4(): fake.uuid4() for _ in range(N)}\n",
    "big_dict_2 = {fake.uuid4(): fake.uuid4() for _ in range(N)}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "557457a5-9335-488b-95fa-3c1ecb067cc8",
   "metadata": {},
   "source": [
    "## Definitions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "92d89e58-7266-4789-ab68-0869c1bde3c5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def merge_splat(d1, d2):\n",
    "    return {**d1, **d2}\n",
    "\n",
    "def merge_union(d1, d2):\n",
    "    return d1 | d2\n",
    "\n",
    "def merge_update(d1, d2):\n",
    "    return d1.update(d2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "21fdb311-8e25-471e-acc8-e41cc1fd6820",
   "metadata": {},
   "source": [
    "## Dissasembly"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "38fc1c81-3196-4d95-bdca-aa2dfb37efc8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  1           0 RESUME                   0\n",
      "\n",
      "  2           2 BUILD_MAP                0\n",
      "              4 LOAD_FAST                0 (d1)\n",
      "              6 DICT_UPDATE              1\n",
      "              8 LOAD_FAST                1 (d2)\n",
      "             10 DICT_UPDATE              1\n",
      "             12 RETURN_VALUE\n"
     ]
    }
   ],
   "source": [
    "dis.dis(merge_splat)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "fb9d309d-bede-4d8f-a808-ce13113640c7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  4           0 RESUME                   0\n",
      "\n",
      "  5           2 LOAD_FAST                0 (d1)\n",
      "              4 LOAD_FAST                1 (d2)\n",
      "              6 BINARY_OP                7 (|)\n",
      "             10 RETURN_VALUE\n"
     ]
    }
   ],
   "source": [
    "dis.dis(merge_union)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "7141a3c5-fe6e-49ce-961c-5755186c660c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  7           0 RESUME                   0\n",
      "\n",
      "  8           2 LOAD_FAST                0 (d1)\n",
      "              4 LOAD_ATTR                1 (NULL|self + update)\n",
      "             24 LOAD_FAST                1 (d2)\n",
      "             26 CALL                     1\n",
      "             34 RETURN_VALUE\n"
     ]
    }
   ],
   "source": [
    "dis.dis(merge_update)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43efe8af-bf80-4c30-a0a5-e516ca1da23f",
   "metadata": {},
   "source": [
    "## Performance"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "67e78c2a-ad5f-4efb-af3a-7c1d07a493cd",
   "metadata": {},
   "source": [
    "### Large Dicts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "d7f3b191-013d-4d83-9c66-517c63541e2f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "121 ms ± 2.22 ms per loop (mean ± std. dev. of 10 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 10 -r 10 merge_splat(big_dict_1, big_dict_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "fddb6b32-757d-4b75-b21a-7432b11b0cfd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "120 ms ± 1.02 ms per loop (mean ± std. dev. of 10 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 10 -r 10 merge_union(big_dict_1, big_dict_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "8bdb743e-2837-4d7b-b4cb-e07eec94f11d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "101 ms ± 1.34 ms per loop (mean ± std. dev. of 10 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 10 -r 10 merge_update(big_dict_1, big_dict_2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fec5b88a-1a75-439b-b893-17925082e3ba",
   "metadata": {},
   "source": [
    "### Small Dicts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "01dcceba-1799-4c3a-b0fb-b23ea648c587",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "8.53 µs ± 1.2 µs per loop (mean ± std. dev. of 10 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 10 -r 10 merge_splat(small_dict_1, small_dict_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "356442ec-7f29-4285-ace1-c0065ee85efb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9.75 µs ± 1.58 µs per loop (mean ± std. dev. of 10 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 10 -r 10 merge_union(small_dict_1, small_dict_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "ae565eb1-42a3-463f-96f4-9c135a714fc4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5 µs ± 854 ns per loop (mean ± std. dev. of 10 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 10 -r 10 merge_update(small_dict_1, small_dict_2)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}