add notebook with some benchmarks

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": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>bdates</th>\n",
+       "      <th>0</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2000-01-03</td>\n",
+       "      <td>2000-01-03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2000-01-10</td>\n",
+       "      <td>2000-01-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2000-01-17</td>\n",
+       "      <td>2000-01-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2000-01-24</td>\n",
+       "      <td>2000-01-24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2000-01-31</td>\n",
+       "      <td>2000-01-31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1056</th>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1057</th>\n",
+       "      <td>2020-04-06</td>\n",
+       "      <td>2020-04-06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1058</th>\n",
+       "      <td>2020-04-13</td>\n",
+       "      <td>2020-04-13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1059</th>\n",
+       "      <td>2020-04-20</td>\n",
+       "      <td>2020-04-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1060</th>\n",
+       "      <td>2020-04-27</td>\n",
+       "      <td>2020-04-27</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1061 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "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
+}

src/_py/utils.rs

@@ -5,18 +5,31 @@ use pyo3_polars::{PyDataFrame, PySeries};
 #[allow(deprecated)]
 #[pymodule]
 pub fn utils(_py: Python, m: &PyModule) -> PyResult<()> {
-    m.add_function(wrap_pyfunction!(get_bdates_series_default, m)?)?;
+    m.add_function(wrap_pyfunction!(get_bdates_series_default_pl, m)?)?;
+    m.add_function(wrap_pyfunction!(get_bdates_series_default_opt, m)?)?;
     Ok(())
 }
 
 #[pyfunction]
-pub fn get_bdates_series_default(
+pub fn get_bdates_series_default_pl(
     start_date: String,
     end_date: String,
     freq: Option<String>,
 ) -> PyResult<PySeries> {
     Ok(PySeries(
-        crate::utils::dateutils::get_bdates_series_default(start_date, end_date, freq)
+        crate::utils::dateutils::get_bdates_series_default_pl(start_date, end_date, freq)
+            .map_err(|e| PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{}", e)))?,
+    ))
+}
+
+#[pyfunction]
+pub fn get_bdates_series_default_opt(
+    start_date: String,
+    end_date: String,
+    freq: Option<String>,
+) -> PyResult<PySeries> {
+    Ok(PySeries(
+        crate::utils::dateutils::get_bdates_series_default_opt(start_date, end_date, freq)
             .map_err(|e| PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{}", e)))?,
     ))
 }

src/msyrs.pyi

@@ -51,6 +51,8 @@ class panel:
     def linear_composite(*args, **kwargs) -> DataFrame: ...
 
 class utils:
-    __all__ = ["get_bdates_series_default"]
+    __all__ = ["get_bdates_series_default", "get_bdates_series_default_opt"]
     @staticmethod
-    def get_bdates_series_default(*args, **kwargs) -> Series: ...
+    def get_bdates_series_default_pl(*args, **kwargs) -> Series: ...
+    @staticmethod
+    def get_bdates_series_default_opt(*args, **kwargs) -> Series: ...

src/utils/dateutils.rs

@@ -1,4 +1,4 @@
-use crate::utils::bdates::get_bdates_list_with_freq;
+use crate::utils::bdates;
 use crate::utils::bdates::BDateFreq;
 use chrono::NaiveDate;
 use chrono::{Datelike, Weekday};
@@ -36,25 +36,110 @@ pub fn get_min_max_real_dates(
     }
 }
 
-pub fn get_bdates_series_default(
+/// Get the business dates between two dates.
+pub fn get_bdates_list(
+    start_date: String,
+    end_date: String,
+) -> Result<Vec<NaiveDate>, Box<dyn Error>> {
+    let start_date = NaiveDate::parse_from_str(&start_date, "%Y-%m-%d")?;
+    let end_date = NaiveDate::parse_from_str(&end_date, "%Y-%m-%d")?;
+
+    let mut business_days = Vec::new();
+    let mut current_date = start_date;
+    while current_date <= end_date {
+        // Check if the current date is a business day (not Saturday or Sunday)
+        if current_date.weekday() != Weekday::Sat && current_date.weekday() != Weekday::Sun {
+            business_days.push(current_date);
+        }
+        current_date = current_date.succ_opt().ok_or(format!(
+            "Failed to get the next day for : {:?}",
+            current_date
+        ))?;
+    }
+    Ok(business_days)
+}
+
+fn compute_group_key(d: NaiveDate, freq: BDateFreq) -> String {
+    match freq {
+        // For Daily, each date is its own group.
+        BDateFreq::Daily => format!("{}", d),
+        // For weekly grouping, we use ISO week information.
+        BDateFreq::WeeklyMonday | BDateFreq::WeeklyFriday => {
+            let iso = d.iso_week();
+            format!("{}-W{:02}", iso.year(), iso.week())
+        }
+        // Group by Year-Month.
+        BDateFreq::MonthStart | BDateFreq::MonthEnd => {
+            format!("{}-M{:02}", d.year(), d.month())
+        }
+        // Group by Year-Quarter.
+        BDateFreq::QuarterStart | BDateFreq::QuarterEnd => {
+            let quarter = (d.month() - 1) / 3 + 1;
+            format!("{}-Q{}", d.year(), quarter)
+        }
+        // Group by Year.
+        BDateFreq::YearStart | BDateFreq::YearEnd => format!("{}", d.year()),
+    }
+}
+pub fn get_bdates_series_default_opt(
     start_date: String,
     end_date: String,
     freq: Option<String>,
 ) -> Result<Series, Box<dyn Error>> {
     let freq = freq.unwrap_or_else(|| "D".to_string());
     let freq = BDateFreq::from_str(&freq)?;
-    get_bdates_series(start_date, end_date, freq)
+    let series = Series::new(
+        "bdates".into(),
+        bdates::get_bdates_list_with_freq(&start_date, &end_date, freq)?,
+    );
+    Ok(series)
+}
+
+pub fn get_bdates_series_default_pl(
+    start_date: String,
+    end_date: String,
+    freq: Option<String>,
+) -> Result<Series, Box<dyn Error>> {
+    let freq = freq.unwrap_or_else(|| "D".to_string());
+    let freq = BDateFreq::from_str(&freq)?;
+    get_bdates_series_pl(start_date, end_date, freq)
 }
 
 /// Get the business dates between two dates as a Series.
-pub fn get_bdates_series(
+pub fn get_bdates_series_pl(
     start_date: String,
     end_date: String,
     freq: BDateFreq,
 ) -> Result<Series, Box<dyn Error>> {
-    let bdates_list = get_bdates_list_with_freq(&start_date, &end_date, freq)?;
-    let bdates_series = Series::new("bdates".into(), bdates_list);
-    Ok(bdates_series)
+    let business_days = get_bdates_list(start_date, end_date)?;
+    let group_keys: Vec<String> = business_days
+        .iter()
+        .map(|&d| compute_group_key(d, freq))
+        .collect();
+
+    let df = DataFrame::new(vec![
+        Column::new("bdates".into(), business_days),
+        Column::new("group".into(), group_keys),
+    ])?;
+    let gb = df.lazy().group_by(["group"]);
+    let aggx = match freq.agg_type() {
+        bdates::AggregationType::Start => gb.agg([col("bdates").first()]),
+        bdates::AggregationType::End => gb.agg([col("bdates").last()]),
+    };
+    let result = aggx.collect()?;
+    let result = result
+        .column("bdates")?
+        .as_series()
+        .ok_or("Column 'bdates' not found")?
+        .clone();
+    let result = result.sort(SortOptions {
+        descending: false,
+        nulls_last: false,
+        multithreaded: false,
+        maintain_order: false,
+    })?;
+
+    Ok(result)
 }
 
 /// Get the business dates from a date column in a DataFrame.