refactor: rename apply_blacklist_lazy to apply_blacklist and update documentation

Optimizing `bdates` utils

.gitattributes

@@ -0,0 +1 @@
+notebooks/** linguist-vendored

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
+}

scripts/unix/build.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+# Exit immediately if a command exits with a non-zero status
+set -e
+
+# Run "maturin --help". If it fails, print an error message and exit.
+if ! maturin --help > /dev/null 2>&1; then
+    echo "Failed to run maturin --help" >&2
+    exit 1
+fi
+
+# Delete any existing build directory and create a new one.
+rm -rf ./build
+mkdir -p ./build
+
+# Copy ./src/msyrs.pyi to ./msyrs.pyi.
+cp ./src/msyrs.pyi ./msyrs.pyi
+
+# Build using maturin.
+maturin build --release --sdist --out ./build/
+
+# Get the first wheel file found in the build directory.
+whl_file=$(ls ./build/*.whl 2>/dev/null | head -n 1)
+if [ -z "$whl_file" ]; then
+    echo "No wheel file found in ./build" >&2
+    exit 1
+fi
+
+# Rename the wheel file from .whl to .zip.
+base_name="${whl_file%.whl}"
+mv "$whl_file" "${base_name}.zip"
+
+# Delete the temporary .pyi file.
+rm ./msyrs.pyi

scripts/unix/install.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+set -e
+
+# Ensure maturin is installed. For example, you can install it via:
+# pip install maturin
+
+# Run "maturin --help". If it fails, print an error message and exit.
+if ! maturin --help > /dev/null 2>&1; then
+    echo "Failed to run maturin --help" >&2
+    exit 1
+fi
+
+# Copy ./src/msyrs.pyi to the current directory as msyrs.pyi
+cp ./src/msyrs.pyi ./msyrs.pyi
+
+# Run maturin develop in release mode.
+maturin develop --release
+
+# Delete the temporary msyrs.pyi file.
+rm ./msyrs.pyi

src/_py/panel.rs

@@ -68,7 +68,7 @@ pub fn get_period_indices_hv(dfw: PyDataFrame, est_freq: &str) -> PyResult<Vec<u
     cids,
     weights = None,
     signs = None,
-    weight_xcats = None,
+    weight_xcat = None,
     normalize_weights = false,
     start = None,
     end = None,
@@ -84,7 +84,7 @@ pub fn linear_composite(
     cids: Vec<String>,
     weights: Option<Vec<f64>>,
     signs: Option<Vec<f64>>,
-    weight_xcats: Option<Vec<String>>,
+    weight_xcat: Option<String>,
     normalize_weights: bool,
     start: Option<String>,
     end: Option<String>,
@@ -101,7 +101,7 @@ pub fn linear_composite(
             cids,
             weights,
             signs,
-            weight_xcats,
+            weight_xcat,
             normalize_weights,
             start,
             end,

src/_py/utils.rs

@@ -1,22 +1,62 @@
-use pyo3::prelude::*;
+use pyo3::{prelude::*, types::PyDict};
 use pyo3_polars::{PyDataFrame, PySeries};
 
 /// Python wrapper for [`crate::utils::qdf`] module.
 #[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)?)?;
+    m.add_function(wrap_pyfunction!(create_blacklist_from_qdf, 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)))?,
+    ))
+}
+
+#[allow(deprecated)]
+#[pyfunction(signature = (df, group_by_cid=None, blacklist_name=None, metrics=None))]
+pub fn create_blacklist_from_qdf(
+    df: PyDataFrame,
+    group_by_cid: Option<bool>,
+    blacklist_name: Option<String>,
+    metrics: Option<Vec<String>>,
+) -> PyResult<PyObject> {
+    let result = crate::utils::qdf::blacklist::create_blacklist_from_qdf(
+        &df.into(),
+        group_by_cid,
+        blacklist_name,
+        metrics,
+    )
+    .map_err(|e| PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{}", e)))?;
+    Python::with_gil(|py| {
+        let dict = PyDict::new(py);
+        // for (key, (start_date, end_date)) in result {
+        //     dict.set_item(key, (start_date, end_date))
+        for (key, dates) in result {
+            dict.set_item(key, dates).map_err(|e| PyErr::from(e))?;
+        }
+        Ok(dict.into())
+    })
+}

src/download/jpmaqsdownload.rs

@@ -58,7 +58,7 @@ fn all_jpmaq_expressions(expressions: Vec<String>) -> bool {
 ///
 /// Example Usage:
 ///
-/// ```rust
+/// ```ignore
 /// use msyrs::download::jpmaqsdownload::JPMaQSDownloadGetIndicatorArgs;
 /// use msyrs::download::jpmaqsdownload::JPMaQSDownload;
 ///
@@ -102,7 +102,7 @@ impl Default for JPMaQSDownloadGetIndicatorArgs {
 /// Struct for downloading data from the JPMaQS data from JPMorgan DataQuery API.
 ///
 /// ## Example Usage
-/// ```rust
+/// ```ignore
 /// use msyrs::download::jpmaqsdownload::JPMaQSDownload;
 /// use msyrs::download::jpmaqsdownload::JPMaQSDownloadGetIndicatorArgs;
 /// use polars::prelude::*;
@@ -277,7 +277,7 @@ impl JPMaQSDownload {
     ///  
     /// Usage:
     ///
-    /// ```rust
+    /// ```ignore
     /// use msyrs::download::jpmaqsdownload::JPMaQSDownload;
     /// use msyrs::download::jpmaqsdownload::JPMaQSDownloadGetIndicatorArgs;
     /// let mut jpamqs_download = JPMaQSDownload::default();

src/msyrs.pyi

@@ -51,6 +51,10 @@ 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: ...
+    @staticmethod
+    def create_blacklist_from_qdf(*args, **kwargs) -> dict: ...

src/panel/historic_vol.rs

@@ -1,6 +1,6 @@
 use crate::utils::dateutils::{get_bdates_from_col, get_min_max_real_dates};
 use crate::utils::qdf::pivots::*;
-use crate::utils::qdf::reduce_df::*;
+use crate::utils::qdf::reduce_dataframe;
 use chrono::NaiveDate;
 use ndarray::{s, Array, Array1, Zip};
 use polars::prelude::*;

src/panel/linear_composite.rs

@@ -1,6 +1,6 @@
 use crate::utils::qdf::check_quantamental_dataframe;
-use crate::utils::qdf::pivots::*;
-use crate::utils::qdf::reduce_df::*;
+use crate::utils::qdf::pivots::{pivot_dataframe_by_ticker, pivot_wide_dataframe_to_qdf};
+use crate::utils::qdf::reduce_df::reduce_dataframe;
 use polars::prelude::*;
 use std::collections::HashMap;
 const TOLERANCE: f64 = 1e-8;
@@ -108,14 +108,42 @@ fn _form_agg_nan_mask_series(nan_mask_dfw: &DataFrame) -> Result<Series, PolarsE
     Ok(combined.into_series())
 }
 
+/// Form the weights DataFrame
 fn _form_agg_weights_dfw(
-    agg_weights_map: &HashMap<String, Vec<f64>>,
-    data_dfw: DataFrame,
+    agg_weights_map: &HashMap<String, (WeightValue, f64)>,
+    dfw: &DataFrame,
 ) -> Result<DataFrame, PolarsError> {
     let mut weights_dfw = DataFrame::new(vec![])?;
     for (agg_targ, weight_signs) in agg_weights_map.iter() {
-        let wgt = weight_signs[0] * weight_signs[1];
-        let wgt_series = Series::new(agg_targ.into(), vec![wgt; data_dfw.height()]);
+        // let wgt = weight_signs[0] * weight_signs[1];
+        let wgt_series = match &weight_signs.0 {
+            WeightValue::F64(val) => {
+                let wgt = val * weight_signs.1;
+                Series::new(agg_targ.into(), vec![wgt; dfw.height()])
+            }
+            WeightValue::Str(vstr) => {
+                // vstr column from data_dfw, else raise wieght specification error
+                if !dfw.get_column_names().contains(&&PlSmallStr::from(vstr)) {
+                    return Err(PolarsError::ComputeError(
+                        format!(
+                            "The column {} does not exist in the DataFrame. {:?}",
+                            vstr, agg_weights_map
+                        )
+                        .into(),
+                    ));
+                }
+                let vstr_series = dfw.column(vstr)?;
+                let multiplied_series = vstr_series * weight_signs.1;
+                let mut multiplied_series =
+                    multiplied_series.as_series().cloned().ok_or_else(|| {
+                        PolarsError::ComputeError(
+                            "Failed to convert multiplied_series to Series".into(),
+                        )
+                    })?;
+                multiplied_series.rename(agg_targ.into());
+                multiplied_series
+            }
+        };
         weights_dfw.with_column(wgt_series)?;
     }
     Ok(weights_dfw)
@@ -143,14 +171,14 @@ fn perform_single_group_agg(
     dfw: &DataFrame,
     agg_on: &String,
     agg_targs: &Vec<String>,
-    agg_weights_map: &HashMap<String, Vec<f64>>,
+    agg_weights_map: &HashMap<String, (WeightValue, f64)>,
     normalize_weights: bool,
     complete: bool,
 ) -> Result<Column, PolarsError> {
     let data_dfw = _form_agg_data_dfw(dfw, agg_targs)?;
     let nan_mask_dfw = _form_agg_nan_mask_dfw(&data_dfw)?;
     let nan_mask_series = _form_agg_nan_mask_series(&nan_mask_dfw)?;
-    let weights_dfw = _form_agg_weights_dfw(agg_weights_map, data_dfw.clone())?;
+    let weights_dfw = _form_agg_weights_dfw(agg_weights_map, dfw)?;
     let weights_dfw = match normalize_weights {
         true => normalize_weights_with_nan_mask(weights_dfw, nan_mask_dfw)?,
         false => weights_dfw,
@@ -192,7 +220,7 @@ fn perform_single_group_agg(
 fn perform_multiplication(
     dfw: &DataFrame,
     mult_targets: &HashMap<String, Vec<String>>,
-    weights_map: &HashMap<String, HashMap<String, Vec<f64>>>,
+    weights_map: &HashMap<String, HashMap<String, (WeightValue, f64)>>,
     complete: bool,
     normalize_weights: bool,
 ) -> Result<DataFrame, PolarsError> {
@@ -200,6 +228,7 @@ fn perform_multiplication(
     // let mut new_dfw = DataFrame::new(vec![real_date])?;
     let mut new_dfw = DataFrame::new(vec![])?;
     assert!(!mult_targets.is_empty(), "agg_targs is empty");
+
     for (agg_on, agg_targs) in mult_targets.iter() {
         // perform_single_group_agg
         let cols_len = new_dfw.get_column_names().len();
@@ -288,76 +317,122 @@ fn get_mul_targets(
     Ok(mul_targets)
 }
 
+/// Builds a map of the shape:
+/// `HashMap<String, HashMap<String, (WeightValue, f64)>>`
+/// where only one of `weights` or `weight_xcats` can be provided.  
+/// If neither is provided, weights default to 1.0.  
+/// Each tuple is `(WeightValue, f64) = (weight, sign)`.
 fn form_weights_and_signs_map(
     cids: Vec<String>,
     xcats: Vec<String>,
     weights: Option<Vec<f64>>,
+    weight_xcat: Option<String>,
     signs: Option<Vec<f64>>,
-) -> Result<HashMap<String, HashMap<String, Vec<f64>>>, Box<dyn std::error::Error>> {
-    let _agg_xcats_for_cid = agg_xcats_for_cid(cids.clone(), xcats.clone());
-
+) -> Result<HashMap<String, HashMap<String, (WeightValue, f64)>>, Box<dyn std::error::Error>> {
+    // For demonstration, we pretend to load or infer these from helpers:
+    let agg_xcats_for_cid = agg_xcats_for_cid(cids.clone(), xcats.clone());
     let (agg_on, agg_targ) = get_agg_on_agg_targs(cids.clone(), xcats.clone());
 
-    // if weights are None, create a vector of 1s of the same length as agg_targ
-    let weights = weights.unwrap_or(vec![1.0 / agg_targ.len() as f64; agg_targ.len()]);
-    let signs = signs.unwrap_or(vec![1.0; agg_targ.len()]);
+    // Determine if each weight option has non-empty values.
+    let weights_provided = weights.as_ref().map_or(false, |v| !v.is_empty());
+    let weight_xcats_provided = weight_xcat.as_ref().map_or(false, |v| !v.is_empty());
 
-    // check that the lengths of weights and signs match the length of agg_targ
-    check_weights_signs_lengths(
-        weights.clone(),
-        signs.clone(),
-        _agg_xcats_for_cid,
-        agg_targ.len(),
-    )?;
+    // Enforce that only one of weights or weight_xcats is specified.
+    if weights_provided && weight_xcats_provided {
+        return Err("Only one of `weights` and `weight_xcats` may be specified.".into());
+    }
 
-    let mut weights_map = HashMap::new();
+    // 1) Build the "actual_weights" vector as WeightValue.
+    let actual_weights: Vec<WeightValue> = if weights_provided {
+        weights.unwrap().into_iter().map(WeightValue::F64).collect()
+    } else if weight_xcats_provided {
+        vec![WeightValue::Str(weight_xcat.unwrap()); agg_targ.len()]
+    } else {
+        // Default to numeric 1.0 if neither is provided
+        vec![WeightValue::F64(1.0); agg_targ.len()]
+    };
+
+    // 2) Build the "signs" vector; default to 1.0 if not provided
+    let signs = signs.unwrap_or_else(|| vec![1.0; agg_targ.len()]);
+
+    // 3) Optional: check lengths & zero values (only numeric weights).
+    check_weights_signs_lengths(&actual_weights, &signs, agg_xcats_for_cid, agg_targ.len())?;
+
+    // 4) Build the final nested HashMap
+    let mut weights_map: HashMap<String, HashMap<String, (WeightValue, f64)>> = HashMap::new();
 
     for agg_o in agg_on {
         let mut agg_t_map = HashMap::new();
         for (i, agg_t) in agg_targ.iter().enumerate() {
-            let ticker = match _agg_xcats_for_cid {
-                true => format!("{}_{}", agg_o, agg_t),
-                false => format!("{}_{}", agg_t, agg_o),
+            // Format the ticker
+            let ticker = if agg_xcats_for_cid {
+                format!("{}_{}", agg_o, agg_t)
+            } else {
+                format!("{}_{}", agg_t, agg_o)
             };
-            let weight_signs = vec![weights[i], signs[i]];
-            agg_t_map.insert(ticker, weight_signs);
+            // Build the tuple (WeightValue, f64)
+            let weight_sign_tuple = match &actual_weights[i] {
+                WeightValue::F64(val) => (WeightValue::F64(*val).clone(), signs[i]),
+                WeightValue::Str(vstr) => {
+                    let new_str = format!("{}_{}", agg_t, vstr);
+                    (WeightValue::Str(new_str), signs[i])
+                }
+            };
+            agg_t_map.insert(ticker, weight_sign_tuple);
         }
         weights_map.insert(agg_o.clone(), agg_t_map);
     }
+
     Ok(weights_map)
 }
-
+/// Checks that the given slices have the expected length and that:
+/// - numeric weights are non-zero,
+/// - signs are non-zero.
 fn check_weights_signs_lengths(
-    weights_vec: Vec<f64>,
-    signs_vec: Vec<f64>,
-    _agg_xcats_for_cid: bool,
+    weights_vec: &[WeightValue],
+    signs_vec: &[f64],
+    agg_xcats_for_cid: bool,
     agg_targ_len: usize,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    // for vx, vname in ...
-    let agg_targ = match _agg_xcats_for_cid {
-        true => "xcats",
-        false => "cids",
-    };
-    for (vx, vname) in vec![
-        (weights_vec.clone(), "weights"),
-        (signs_vec.clone(), "signs"),
-    ] {
-        for (i, v) in vx.iter().enumerate() {
-            if *v == 0.0 {
-                return Err(format!("The {} at index {} is 0.0", vname, i).into());
+    // For diagnostics, decide what to call the dimension
+    let agg_targ = if agg_xcats_for_cid { "xcats" } else { "cids" };
+
+    // 1) Check numeric weights for zeroes.
+    for (i, weight) in weights_vec.iter().enumerate() {
+        if let WeightValue::F64(val) = weight {
+            if *val == 0.0 {
+                return Err(format!("The weight at index {} is 0.0", i).into());
             }
         }
-        if vx.len() != agg_targ_len {
-            return Err(format!(
-                "The length of {} ({}) does not match the length of {} ({})",
-                vname,
-                vx.len(),
-                agg_targ,
-                agg_targ_len
-            )
-            .into());
+    }
+    // 2) Ensure the weights vector is the expected length.
+    if weights_vec.len() != agg_targ_len {
+        return Err(format!(
+            "The length of weights ({}) does not match the length of {} ({})",
+            weights_vec.len(),
+            agg_targ,
+            agg_targ_len
+        )
+        .into());
+    }
+
+    // 3) Check signs for zero.
+    for (i, sign) in signs_vec.iter().enumerate() {
+        if *sign == 0.0 {
+            return Err(format!("The sign at index {} is 0.0", i).into());
         }
     }
+    // 4) Ensure the signs vector is the expected length.
+    if signs_vec.len() != agg_targ_len {
+        return Err(format!(
+            "The length of signs ({}) does not match the length of {} ({})",
+            signs_vec.len(),
+            agg_targ,
+            agg_targ_len
+        )
+        .into());
+    }
+
     Ok(())
 }
 fn rename_result_dfw_cols(
@@ -393,6 +468,36 @@ fn agg_xcats_for_cid(cids: Vec<String>, xcats: Vec<String>) -> bool {
     xcats.len() > 1
 }
 
+/// Represents a weight value that can be a string, (float, or integer).
+#[derive(Debug, Clone, PartialEq)]
+pub enum WeightValue {
+    Str(String),
+    F64(f64),
+}
+impl From<String> for WeightValue {
+    fn from(s: String) -> Self {
+        WeightValue::Str(s)
+    }
+}
+
+impl<'a> From<&'a str> for WeightValue {
+    fn from(s: &'a str) -> Self {
+        WeightValue::Str(s.to_string())
+    }
+}
+
+impl From<f64> for WeightValue {
+    fn from(f: f64) -> Self {
+        WeightValue::F64(f)
+    }
+}
+
+impl From<i32> for WeightValue {
+    fn from(i: i32) -> Self {
+        WeightValue::F64(i as f64)
+    }
+}
+
 /// Weighted linear combinations of cross sections or categories
 /// # Arguments
 /// * `df` - QDF DataFrame
@@ -417,7 +522,7 @@ pub fn linear_composite(
     cids: Vec<String>,
     weights: Option<Vec<f64>>,
     signs: Option<Vec<f64>>,
-    weight_xcats: Option<Vec<String>>,
+    weight_xcat: Option<String>,
     normalize_weights: bool,
     start: Option<String>,
     end: Option<String>,
@@ -429,10 +534,28 @@ pub fn linear_composite(
 ) -> Result<DataFrame, Box<dyn std::error::Error>> {
     // Check if the DataFrame is a Quantamental DataFrame
     check_quantamental_dataframe(df)?;
+
+    if agg_xcats_for_cid(cids.clone(), xcats.clone()) {
+        if weight_xcat.is_some() {
+            return Err(
+                format!(
+                    "Using xcats as weights is not supported when aggregating cids for a single xcat. {:?} {:?}",
+                    cids, xcats
+                )
+                .into(),
+            );
+        }
+    }
+
+    let mut rxcats = xcats.clone();
+    if weight_xcat.is_some() {
+        rxcats.extend(vec![weight_xcat.clone().unwrap()]);
+    }
+
     let rdf = reduce_dataframe(
         df.clone(),
         Some(cids.clone()),
-        Some(xcats.clone()),
+        Some(rxcats.clone()),
         Some(vec!["value".to_string()]),
         start.clone(),
         end.clone(),
@@ -443,10 +566,11 @@ pub fn linear_composite(
     let new_xcat = new_xcat.unwrap_or_else(|| "COMPOSITE".to_string());
     let new_cid = new_cid.unwrap_or_else(|| "GLB".to_string());
 
-    let dfw = pivot_dataframe_by_ticker(rdf.clone(), Some("value".to_string())).unwrap();
+    let dfw = pivot_dataframe_by_ticker(rdf, Some("value".to_string())).unwrap();
 
     let mul_targets = get_mul_targets(cids.clone(), xcats.clone())?;
-    let weights_map = form_weights_and_signs_map(cids.clone(), xcats.clone(), weights, signs)?;
+    let weights_map =
+        form_weights_and_signs_map(cids.clone(), xcats.clone(), weights, weight_xcat, signs)?;
 
     for (ticker, targets) in mul_targets.iter() {
         println!("ticker: {}, targets: {:?}", ticker, targets);

src/utils/dateutils.rs

@@ -1,3 +1,5 @@
+use crate::utils::bdates;
+use crate::utils::bdates::BDateFreq;
 use chrono::NaiveDate;
 use chrono::{Datelike, Weekday};
 use polars::prelude::*;
@@ -57,61 +59,6 @@ pub fn get_bdates_list(
     Ok(business_days)
 }
 
-#[derive(Debug, Clone, Copy)]
-pub enum BDateFreq {
-    Daily,
-    WeeklyMonday,
-    MonthStart,
-    QuarterStart,
-    YearStart,
-    MonthEnd,
-    QuarterEnd,
-    WeeklyFriday,
-    YearEnd,
-}
-
-impl BDateFreq {
-    pub fn from_string(freq: String) -> Result<Self, Box<dyn Error>> {
-        // use `from_str` to convert the string to a BDateFreq enum
-        Self::from_str(&freq)
-    }
-    pub fn from_str(freq: &str) -> Result<Self, Box<dyn Error>> {
-        match freq {
-            "D" => Ok(BDateFreq::Daily),
-            "W" => Ok(BDateFreq::WeeklyMonday),
-            "M" => Ok(BDateFreq::MonthStart),
-            "Q" => Ok(BDateFreq::QuarterStart),
-            "A" => Ok(BDateFreq::YearStart),
-            "ME" => Ok(BDateFreq::MonthEnd),
-            "QE" => Ok(BDateFreq::QuarterEnd),
-            "WF" => Ok(BDateFreq::WeeklyFriday),
-            "YE" => Ok(BDateFreq::YearEnd),
-            _ => Err("Invalid frequency specified".into()),
-        }
-    }
-
-    pub fn agg_type(&self) -> AggregationType {
-        match self {
-            BDateFreq::Daily
-            | BDateFreq::WeeklyMonday
-            | BDateFreq::MonthStart
-            | BDateFreq::QuarterStart
-            | BDateFreq::YearStart => AggregationType::Start,
-            BDateFreq::WeeklyFriday
-            | BDateFreq::MonthEnd
-            | BDateFreq::QuarterEnd
-            | BDateFreq::YearEnd => AggregationType::End,
-        }
-    }
-}
-
-#[derive(Debug, Clone, Copy)]
-pub enum AggregationType {
-    Start, // Indicates picking the first date in a group.
-    End,   // Indicates picking the last date in a group.
-}
-
-// Map a BDateFreq to an AggregationType.
 fn compute_group_key(d: NaiveDate, freq: BDateFreq) -> String {
     match freq {
         // For Daily, each date is its own group.
@@ -134,19 +81,32 @@ fn compute_group_key(d: NaiveDate, freq: BDateFreq) -> String {
         BDateFreq::YearStart | BDateFreq::YearEnd => format!("{}", d.year()),
     }
 }
-
-pub fn get_bdates_series_default(
+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,
@@ -163,8 +123,8 @@ pub fn get_bdates_series(
     ])?;
     let gb = df.lazy().group_by(["group"]);
     let aggx = match freq.agg_type() {
-        AggregationType::Start => gb.agg([col("bdates").first()]),
-        AggregationType::End => gb.agg([col("bdates").last()]),
+        bdates::AggregationType::Start => gb.agg([col("bdates").first()]),
+        bdates::AggregationType::End => gb.agg([col("bdates").last()]),
     };
     let result = aggx.collect()?;
     let result = result

src/utils/mod.rs

@@ -1,3 +1,4 @@
-pub mod qdf;
+pub mod bdates;
+pub mod dateutils;
 pub mod misc;
-pub mod dateutils;
+pub mod qdf;

src/utils/qdf/blacklist.rs

@@ -0,0 +1,373 @@
+use crate::utils::bdates::{get_bdates_list_with_freq, BDateFreq};
+use crate::utils::dateutils::get_min_max_real_dates;
+use crate::utils::misc::get_cid;
+use crate::utils::qdf::core::check_quantamental_dataframe;
+use chrono::NaiveDate;
+use polars::prelude::*;
+use std::collections::{BTreeMap, HashMap};
+use std::error::Error;
+
+use crate::utils::qdf::get_unique_metrics;
+
+// struct Blacklist which is a wrapper around hashmap and btreemap
+#[derive(Debug, Clone)]
+pub struct Blacklist {
+    pub blacklist: BTreeMap<String, (String, String)>,
+}
+
+// impl hashmap into
+impl Blacklist {
+    pub fn into_hashmap(self) -> HashMap<String, (String, String)> {
+        self.blacklist.into_iter().collect()
+    }
+}
+
+/// Apply a blacklist to a Quantamental DataFrame.
+///
+/// * `blacklist` is a map from any “ticker‑like” key to a tuple of
+///   `(start_date, end_date)` in **inclusive** `"YYYY‑MM‑DD"` format.
+/// * `metrics` – if `None`, every metric from `get_unique_metrics(df)`
+///   is used.
+/// * `group_by_cid = Some(false)` is not implemented yet.
+pub fn apply_blacklist(
+    df: &mut DataFrame,
+    blacklist: &BTreeMap<String, (String, String)>,
+    metrics: Option<Vec<String>>,
+    group_by_cid: Option<bool>,
+) -> Result<DataFrame, Box<dyn std::error::Error>> {
+    check_quantamental_dataframe(df)?;
+    // dataframe is like:
+    // | cid | xcat | real_date | metric1 | metric2 |
+    // |-----|------|-----------|---------|---------|
+    // | A   | B    | 2023-01-01| 1.0     | 2.0     |
+    // | A   | B    | 2023-01-02| 1.0     | 2.0     |
+    // | A   | C    | 2023-01-01| 1.0     | 2.0     |
+    // | A   | C    | 2023-01-02| 1.0     | 2.0     |
+    // | D   | E    | 2023-01-01| 1.0     | 2.0     |
+    // | D   | E    | 2023-01-02| 1.0     | 2.0     |
+
+    // (real date column is Naive date)
+
+    // blacklist is like:
+    // {'A_B_1': ('2023-01-02', '2023-01-03'),
+    //  'A_B_2': ('2023-01-04', '2023-01-05'),
+    //  'A_C_1': ('2023-01-02', '2023-01-03'), }
+
+    // get_cid('A_B_1') = 'A'
+    // get_cid('A_B_2') = 'A'
+    // get_cid('D_E_1') = 'D'
+
+    Ok(df.clone())
+}
+/// Create a blacklist from a Quantamental DataFrame.
+/// The blacklist is a mapping of tickers to date ranges where the specified metrics are null or NaN.
+/// # Arguments:
+/// * `df` - The Quantamental DataFrame.
+/// * `group_by_cid` - If true, group the blacklist by `cid`. Defaults to true.
+/// * `blacklist_name` - The name of the blacklist. Defaults to "BLACKLIST".
+/// * `metrics` - The metrics to check for null or NaN values. If None, all metrics are used.
+pub fn create_blacklist_from_qdf(
+    df: &DataFrame,
+    group_by_cid: Option<bool>,
+    blacklist_name: Option<String>,
+    metrics: Option<Vec<String>>,
+) -> Result<BTreeMap<String, (String, String)>, Box<dyn Error>> {
+    check_quantamental_dataframe(df)?;
+    let metrics = metrics.unwrap_or_else(|| get_unique_metrics(df).unwrap());
+    let blacklist_name = blacklist_name.unwrap_or_else(|| "BLACKLIST".into());
+    let group_by_cid = group_by_cid.unwrap_or(true);
+
+    let (min_date, max_date) = get_min_max_real_dates(df, "real_date".into())?;
+    let min_date_str = min_date.format("%Y-%m-%d").to_string();
+    let max_date_str = max_date.format("%Y-%m-%d").to_string();
+    // let all_bdates = get_bdates_series_default_opt(min_date_str, max_date_str, None)?;
+    let all_bdates = get_bdates_list_with_freq(
+        min_date_str.clone().as_str(),
+        max_date_str.clone().as_str(),
+        BDateFreq::Daily,
+    )?;
+
+    // if none of the metrics are null or NaN, return an empty blacklist
+    if !metrics.iter().any(|metric| {
+        df.column(metric)
+            .map(|col| col.is_null().any())
+            .unwrap_or(false)
+    }) {
+        return Ok(BTreeMap::new());
+    }
+
+    // let null_mask = get_nan_mask(df, metrics)?;
+    // let df = df.filter(&null_mask)?.clone();
+
+    let df = df
+        .clone()
+        .lazy()
+        .with_columns([
+            (cols(metrics.clone()).is_null().or(cols(metrics).is_nan())).alias("null_mask")
+        ])
+        .filter(col("null_mask"))
+        // if is now empty, return an empty blacklist
+        .sort(
+            ["cid", "xcat"],
+            SortMultipleOptions::default().with_maintain_order(true),
+        )
+        .group_by([col("cid"), col("xcat")])
+        // .agg([col("real_date").sort(SortOptions::default())])
+        .agg([col("real_date")
+            .dt()
+            .strftime("%Y-%m-%d")
+            .sort(SortOptions::default())])
+        .select([
+            concat_str([col("cid"), col("xcat")], "_", true).alias("ticker"),
+            col("real_date").alias("real_dates"),
+        ])
+        .collect()?;
+
+    // assert!(0 == 1, "{:?}", df);
+
+    let ticker_vec = df
+        .column("ticker")?
+        .str()?
+        .into_iter()
+        .filter_map(|opt| opt.map(|s| s.to_string()))
+        .collect::<Vec<String>>();
+
+    let rdt = get_vec_of_vec_of_dates_from_df(df)?;
+
+    let mut blk: HashMap<String, Vec<String>> = HashMap::new();
+    for (tkr, dates) in ticker_vec.iter().zip(rdt.iter()) {
+        if group_by_cid {
+            let _cid = get_cid(tkr.clone())?;
+            if blk.contains_key(&_cid) {
+                blk.get_mut(&_cid).unwrap().extend(dates.iter().cloned());
+            } else {
+                blk.insert(_cid, dates.clone());
+            }
+        } else {
+            blk.insert(tkr.to_string(), dates.clone());
+        }
+    }
+    for (_key, vals) in blk.iter_mut() {
+        // order is important - dedup depends on the vec being sorted
+        vals.sort();
+        vals.dedup();
+    }
+
+    let all_bdates_strs = all_bdates
+        .iter()
+        .map(|date| date.format("%Y-%m-%d").to_string())
+        .collect::<Vec<String>>();
+
+    let mut blacklist: HashMap<String, (String, String)> = HashMap::new();
+    for (tkr, dates) in blk.iter() {
+        let date_ranges = convert_dates_list_to_date_ranges(dates.clone(), all_bdates_strs.clone());
+        for (rng_idx, (start_date, end_date)) in date_ranges.iter() {
+            let range_key = format!("{}_{}_{}", tkr, blacklist_name.clone(), rng_idx);
+            blacklist.insert(range_key, (start_date.clone(), end_date.clone()));
+        }
+    }
+    // Ok(blacklist)
+
+    let mut btree_map: BTreeMap<String, (String, String)> = BTreeMap::new();
+    for (key, (start_date, end_date)) in blacklist.iter() {
+        btree_map.insert(key.clone(), (start_date.clone(), end_date.clone()));
+    }
+
+    Ok(btree_map)
+}
+
+/// Get a mask of NaN values for the specified metrics in the DataFrame.
+#[allow(dead_code)]
+fn get_nan_mask(
+    df: &DataFrame,
+    metrics: Vec<String>,
+) -> Result<ChunkedArray<BooleanType>, Box<dyn Error>> {
+    let null_masks: Vec<ChunkedArray<BooleanType>> = metrics
+        .iter()
+        .map(|metric| {
+            let null_mask = df.column(metric.as_str())?.is_null();
+            let nan_mask = df.column(metric.as_str())?.is_nan()?;
+            Ok(null_mask | nan_mask)
+        })
+        .collect::<Result<_, Box<dyn Error>>>()?;
+    let null_mask = null_masks
+        .into_iter()
+        .reduce(|acc, mask| acc | mask)
+        .unwrap_or_else(|| BooleanChunked::full_null("null_mask".into(), df.height()));
+    Ok(null_mask)
+}
+
+fn convert_dates_list_to_date_ranges(
+    blacklist: Vec<String>,
+    all_bdates_strs: Vec<String>,
+) -> HashMap<String, (String, String)> {
+    // Step 1: Map every date in all_bdates_strs to its index
+    let mut all_map: HashMap<String, usize> = HashMap::new();
+    for (i, d) in all_bdates_strs.iter().enumerate() {
+        all_map.insert(d.clone(), i);
+    }
+
+    // Step 2: Convert each blacklisted date into its index, if it exists
+    let mut blacklisted_indices: Vec<usize> = Vec::new();
+    for dt in blacklist {
+        if let Some(&idx) = all_map.get(&dt) {
+            blacklisted_indices.push(idx);
+        }
+    }
+
+    // Step 3: Sort the blacklisted indices
+    blacklisted_indices.sort_unstable();
+
+    // Step 4: Traverse and group consecutive indices into ranges
+    let mut result: HashMap<i64, (String, String)> = HashMap::new();
+    let mut string_result: HashMap<String, (String, String)> = HashMap::new();
+
+    if blacklisted_indices.is_empty() {
+        return string_result;
+    }
+
+    let mut range_idx: i64 = 0;
+    let mut start_idx = blacklisted_indices[0];
+    let mut end_idx = start_idx;
+
+    for &cur_idx in blacklisted_indices.iter().skip(1) {
+        if cur_idx == end_idx + 1 {
+            // We are still in a contiguous run
+            end_idx = cur_idx;
+        } else {
+            // We hit a break in contiguity, so store the last range
+            result.insert(
+                range_idx,
+                (
+                    all_bdates_strs[start_idx].clone(),
+                    all_bdates_strs[end_idx].clone(),
+                ),
+            );
+            range_idx += 1;
+
+            // Start a new range
+            start_idx = cur_idx;
+            end_idx = cur_idx;
+        }
+    }
+
+    // Don't forget to store the final range after the loop
+    result.insert(
+        range_idx,
+        (
+            all_bdates_strs[start_idx].clone(),
+            all_bdates_strs[end_idx].clone(),
+        ),
+    );
+
+    let max_digits = result.keys().max().unwrap_or(&-1).to_string().len();
+    for (key, (start_date, end_date)) in result.iter() {
+        let new_key = format!("{:0width$}", key, width = max_digits);
+        string_result.insert(new_key, (start_date.clone(), end_date.clone()));
+    }
+
+    string_result
+}
+
+fn get_vec_of_vec_of_dates_from_df(df: DataFrame) -> Result<Vec<Vec<String>>, Box<dyn Error>> {
+    let rdt = df
+        .column("real_dates")?
+        // .clone()
+        .as_series()
+        .unwrap()
+        .list()?
+        .into_iter()
+        .filter_map(|opt| opt)
+        .collect::<Vec<Series>>()
+        .iter()
+        .map(|s| {
+            s.str()
+                .unwrap()
+                .into_iter()
+                .filter_map(|opt| opt.map(|s| s.to_string()))
+                .collect::<Vec<String>>()
+        })
+        .collect::<Vec<Vec<String>>>();
+    Ok(rdt)
+}
+
+#[allow(dead_code)]
+fn get_vec_of_vec_of_naivedates_from_df(
+    df: DataFrame,
+) -> Result<Vec<Vec<NaiveDate>>, Box<dyn Error>> {
+    let rdt = df
+        .column("real_dates")?
+        // .clone()
+        .as_series()
+        .unwrap()
+        .list()?
+        .into_iter()
+        .filter_map(|opt| opt)
+        .collect::<Vec<Series>>()
+        .iter()
+        .map(|s| {
+            s.date()
+                .unwrap()
+                .into_iter()
+                .filter_map(|opt| opt.and_then(|date| NaiveDate::from_num_days_from_ce_opt(date)))
+                .collect::<Vec<NaiveDate>>()
+        })
+        .collect::<Vec<Vec<NaiveDate>>>();
+    Ok(rdt)
+}
+
+// fn get_vec_of_vec_of_dates_from_df(df: DataFrame) -> Result<Vec<Vec<String>>, Box<dyn Error>> {
+//     let real_dates_column = df.column("real_dates")?.clone();
+//     let series = real_dates_column.as_series().unwrap().clone();
+//     let rdt = series.list()?.clone();
+//     let rdt = rdt
+//         .into_iter()
+//         .filter_map(|opt| opt)
+//         .collect::<Vec<Series>>();
+//     let rdt = rdt
+//         .iter()
+//         .map(|s| {
+//             s.str()
+//                 .unwrap()
+//                 .into_iter()
+//                 .filter_map(|opt| opt.map(|s| s.to_string()))
+//                 .collect::<Vec<String>>()
+//         })
+//         .collect::<Vec<Vec<String>>>();
+//     Ok(rdt)
+// }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_convert_dates_list_to_date_ranges() {
+        let all_dates = vec![
+            "2023-01-01".to_string(),
+            "2023-01-02".to_string(),
+            "2023-01-03".to_string(),
+            "2023-01-04".to_string(),
+            "2023-01-05".to_string(),
+            "2023-01-06".to_string(),
+        ];
+        let blacklist = vec![
+            "2023-01-02".to_string(),
+            "2023-01-03".to_string(),
+            "2023-01-05".to_string(),
+        ];
+
+        let result = convert_dates_list_to_date_ranges(blacklist, all_dates);
+        // Expect two ranges:
+        //   range 0 => ("2023-01-02", "2023-01-03")
+        //   range 1 => ("2023-01-05", "2023-01-05")
+        assert_eq!(
+            result["0"],
+            ("2023-01-02".to_string(), "2023-01-03".to_string())
+        );
+        assert_eq!(
+            result["1"],
+            ("2023-01-05".to_string(), "2023-01-05".to_string())
+        );
+    }
+}

src/utils/qdf/core.rs

@@ -17,14 +17,15 @@ use std::error::Error;
 pub fn check_quantamental_dataframe(df: &DataFrame) -> Result<(), Box<dyn Error>> {
     let expected_cols = ["real_date", "cid", "xcat"];
     let expected_dtype = [DataType::Date, DataType::String, DataType::String];
+    let err = "Quantamental DataFrame must have at least 4 columns: 'real_date', 'cid', 'xcat' and one or more metrics.";
     for (col, dtype) in expected_cols.iter().zip(expected_dtype.iter()) {
         let col = df.column(col);
         if col.is_err() {
-            return Err(format!("Column {:?} not found", col).into());
+            return Err(format!("{} Column {:?} not found", err, col).into());
         }
         let col = col?;
         if col.dtype() != dtype {
-            return Err(format!("Column {:?} has wrong dtype", col).into());
+            return Err(format!("{} Column {:?} has wrong dtype", err, col).into());
         }
     }
     Ok(())

src/utils/qdf/mod.rs

@@ -1,11 +1,12 @@
+pub mod blacklist;
 pub mod core;
-pub mod update_df;
 pub mod load;
-pub mod reduce_df;
 pub mod pivots;
+pub mod reduce_df;
+pub mod update_df;
 
 // Re-export submodules for easier access
 pub use core::*;
-pub use update_df::*;
 pub use load::*;
 pub use reduce_df::*;
+pub use update_df::*;

src/utils/qdf/reduce_df.rs

@@ -30,12 +30,12 @@ pub fn reduce_dataframe(
     let df_size = df.shape();
     let mut new_df = df.clone();
 
-    let ticker_col: Column = get_ticker_column_for_quantamental_dataframe(&new_df)?;
+    let ticker_col = get_ticker_column_for_quantamental_dataframe(&new_df)?;
 
     // if cids is not provided, get all unique cids
-    let u_cids: Vec<String> = get_unique_cids(&new_df)?;
-    let u_xcats: Vec<String> = get_unique_xcats(&new_df)?;
-    let u_tickers: Vec<String> = _get_unique_strs_from_str_column_object(&ticker_col)?;
+    let u_cids = get_unique_cids(&new_df)?;
+    let u_xcats = get_unique_xcats(&new_df)?;
+    let u_tickers = _get_unique_strs_from_str_column_object(&ticker_col)?;
 
     let cids_vec = cids.unwrap_or_else(|| u_cids.clone());
     let specified_cids: Vec<&str> = cids_vec.iter().map(AsRef::as_ref).collect();