From cfbd54be7a85da626262558d2eeb1c2d95f1356e Mon Sep 17 00:00:00 2001 From: Palash Tyagi <23239946+Magnus167@users.noreply.github.com> Date: Sun, 13 Apr 2025 11:16:03 +0100 Subject: [PATCH] add notebook with some benchmarks --- notebooks/funcwise/bdate_range_util.ipynb | 360 ++++++++++++++++++++++ 1 file changed, 360 insertions(+) create mode 100644 notebooks/funcwise/bdate_range_util.ipynb diff --git a/notebooks/funcwise/bdate_range_util.ipynb b/notebooks/funcwise/bdate_range_util.ipynb new file mode 100644 index 0000000..d1a6a0a --- /dev/null +++ b/notebooks/funcwise/bdate_range_util.ipynb @@ -0,0 +1,360 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# ! uv pip install E:\\Work\\ruzt\\msyrs --upgrade" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Import Python packages\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import macrosynergy\n", + "import pandas as pd\n", + "import numpy as np\n", + "import polars as pl\n", + "import os\n", + "import time\n", + "\n", + "from macrosynergy.panel import view_timelines\n", + "from macrosynergy.management.types import QuantamentalDataFrame\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Import Python bindings - `msyrs`\n" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "import msyrs" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
bdates0
02000-01-032000-01-03
12000-01-102000-01-10
22000-01-172000-01-17
32000-01-242000-01-24
42000-01-312000-01-31
.........
10562020-03-302020-03-30
10572020-04-062020-04-06
10582020-04-132020-04-13
10592020-04-202020-04-20
10602020-04-272020-04-27
\n", + "

1061 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " bdates 0\n", + "0 2000-01-03 2000-01-03\n", + "1 2000-01-10 2000-01-10\n", + "2 2000-01-17 2000-01-17\n", + "3 2000-01-24 2000-01-24\n", + "4 2000-01-31 2000-01-31\n", + "... ... ...\n", + "1056 2020-03-30 2020-03-30\n", + "1057 2020-04-06 2020-04-06\n", + "1058 2020-04-13 2020-04-13\n", + "1059 2020-04-20 2020-04-20\n", + "1060 2020-04-27 2020-04-27\n", + "\n", + "[1061 rows x 2 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x = msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq='W').to_pandas()\n", + "y = pd.Series(pd.bdate_range(start='2000-01-01', end='2020-05-01', freq='W-MON'))\n", + "\n", + "pd.concat([x, y], axis=1)\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Results for M\t & \tBMS\t are exactly the same\n", + "Results for Q\t & \tBQS\t are exactly the same\n", + "Results for W\t & \tW-MON\t are exactly the same\n", + "Results for WF\t & \tW-FRI\t are exactly the same\n" + ] + } + ], + "source": [ + "for rs_freq, pd_freq in [('M', 'BMS'), ('Q', 'BQS'), ('W', 'W-MON'), ('WF', 'W-FRI')]:\n", + "\n", + "\n", + " x = msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq=rs_freq).to_pandas()\n", + " y = pd.Series(pd.bdate_range(start='2000-01-01', end='2020-05-01', freq=pd_freq))\n", + "\n", + " e = x == y\n", + " res = e.all()\n", + " non_matching_df = pd.concat([x[~e], y[~e]], axis=1)\n", + " assert res, f\"Results for {rs_freq}\\t and \\t{pd_freq}\\t are not the same\\n{non_matching_df}\"\n", + " print(f\"Results for {rs_freq}\\t & \\t{pd_freq}\\t are exactly the same\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "23.5 μs ± 1.02 μs per loop (mean ± std. dev. of 7 runs, 10,000 loops each)\n", + "67.4 μs ± 979 ns per loop (mean ± std. dev. of 7 runs, 10,000 loops each)\n", + "1.97 ms ± 57.3 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", + "4.65 ms ± 170 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "28.3 ms ± 898 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", + "93.8 ms ± 2.02 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n" + ] + } + ], + "source": [ + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq='D')\n", + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='1971-01-01', end_date='2040-05-01', freq='D')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='2000-01-01', end_date='2020-05-01', freq='D')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='1971-01-01', end_date='2040-05-01', freq='D')\n", + "%timeit pd.bdate_range(start='2000-01-01', end='2020-05-01', freq='B')\n", + "%timeit pd.bdate_range(start='1971-01-01', end='2040-05-01', freq='B')" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "7.95 μs ± 146 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "17.9 μs ± 108 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "1.73 ms ± 20.8 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", + "4 ms ± 69.3 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "5.69 ms ± 139 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "19.1 ms ± 268 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n" + ] + } + ], + "source": [ + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq='WF')\n", + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='1971-01-01', end_date='2040-05-01', freq='WF')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='2000-01-01', end_date='2020-05-01', freq='WF')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='1971-01-01', end_date='2040-05-01', freq='WF')\n", + "%timeit pd.bdate_range(start='2000-01-01', end='2020-05-01', freq='W-FRI')\n", + "%timeit pd.bdate_range(start='1971-01-01', end='2040-05-01', freq='W-FRI')" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "6.9 μs ± 126 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "13.1 μs ± 93.3 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "1.73 ms ± 29.3 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", + "4.2 ms ± 81.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "931 μs ± 14.2 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", + "3.05 ms ± 47.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n" + ] + } + ], + "source": [ + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq='ME')\n", + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='1971-01-01', end_date='2040-05-01', freq='ME')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='2000-01-01', end_date='2020-05-01', freq='ME')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='1971-01-01', end_date='2040-05-01', freq='ME')\n", + "%timeit pd.bdate_range(start='2000-01-01', end='2020-05-01', freq='BME')\n", + "%timeit pd.bdate_range(start='1971-01-01', end='2040-05-01', freq='BME')" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "3.65 μs ± 69.1 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "4.78 μs ± 38.7 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "1.73 ms ± 122 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", + "4.16 ms ± 286 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "340 μs ± 11.3 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", + "1.1 ms ± 11.5 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n" + ] + } + ], + "source": [ + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq='Q')\n", + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='1971-01-01', end_date='2040-05-01', freq='Q')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='2000-01-01', end_date='2020-05-01', freq='Q')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='1971-01-01', end_date='2040-05-01', freq='Q')\n", + "%timeit pd.bdate_range(start='2000-01-01', end='2020-05-01', freq='BQS')\n", + "%timeit pd.bdate_range(start='1971-01-01', end='2040-05-01', freq='BQS')" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "3.21 μs ± 83.4 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "3.66 μs ± 198 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n", + "2.67 ms ± 459 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "3.71 ms ± 143 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", + "98.7 μs ± 1.47 μs per loop (mean ± std. dev. of 7 runs, 10,000 loops each)\n", + "289 μs ± 15.3 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n" + ] + } + ], + "source": [ + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='2000-01-01', end_date='2020-05-01', freq='YE')\n", + "%timeit msyrs.utils.get_bdates_series_default_opt(start_date='1971-01-01', end_date='2040-05-01', freq='YE')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='2000-01-01', end_date='2020-05-01', freq='YE')\n", + "%timeit msyrs.utils.get_bdates_series_default_pl(start_date='1971-01-01', end_date='2040-05-01', freq='YE')\n", + "%timeit pd.bdate_range(start='2000-01-01', end='2020-05-01', freq='BYE')\n", + "%timeit pd.bdate_range(start='1971-01-01', end='2040-05-01', freq='BYE')" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": ".venv", + "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": "3.12.4" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}