update create_blacklist_from_qdf function signature to accept metrics as a vector

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

@@ -1,4 +1,4 @@
-use pyo3::prelude::*;
+use pyo3::{prelude::*, types::PyDict};
 use pyo3_polars::{PyDataFrame, PySeries};
 
 /// Python wrapper for [`crate::utils::qdf`] module.
@@ -7,6 +7,7 @@ use pyo3_polars::{PyDataFrame, PySeries};
 pub fn utils(_py: Python, m: &PyModule) -> PyResult<()> {
     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(())
 }
 
@@ -33,3 +34,29 @@ pub fn get_bdates_series_default_opt(
             .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

@@ -56,3 +56,5 @@ class utils:
     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::pivots::{pivot_dataframe_by_ticker, pivot_wide_dataframe_to_qdf};
-use crate::utils::qdf::reduce_df::*;
+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>>,
+    agg_weights_map: &HashMap<String, (WeightValue, f64)>,
-    data_dfw: DataFrame,
+    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 = weight_signs[0] * weight_signs[1];
-        let wgt_series = Series::new(agg_targ.into(), vec![wgt; data_dfw.height()]);
+        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>> {
+) -> Result<HashMap<String, HashMap<String, (WeightValue, f64)>>, Box<dyn std::error::Error>> {
-    let _agg_xcats_for_cid = agg_xcats_for_cid(cids.clone(), xcats.clone());
+    // 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
+    // Determine if each weight option has non-empty values.
-    let weights = weights.unwrap_or(vec![1.0 / agg_targ.len() as f64; agg_targ.len()]);
+    let weights_provided = weights.as_ref().map_or(false, |v| !v.is_empty());
-    let signs = signs.unwrap_or(vec![1.0; agg_targ.len()]);
+    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
+    // Enforce that only one of weights or weight_xcats is specified.
-    check_weights_signs_lengths(
+    if weights_provided && weight_xcats_provided {
-        weights.clone(),
+        return Err("Only one of `weights` and `weight_xcats` may be specified.".into());
-        signs.clone(),
+    }
-        _agg_xcats_for_cid,
-        agg_targ.len(),
-    )?;
 
-    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 {
+            // Format the ticker
-                true => format!("{}_{}", agg_o, agg_t),
+            let ticker = if agg_xcats_for_cid {
-                false => format!("{}_{}", agg_t, agg_o),
+                format!("{}_{}", agg_o, agg_t)
+            } else {
+                format!("{}_{}", agg_t, agg_o)
             };
-            let weight_signs = vec![weights[i], signs[i]];
+            // Build the tuple (WeightValue, f64)
-            agg_t_map.insert(ticker, weight_signs);
+            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>,
+    weights_vec: &[WeightValue],
-    signs_vec: Vec<f64>,
+    signs_vec: &[f64],
-    _agg_xcats_for_cid: bool,
+    agg_xcats_for_cid: bool,
     agg_targ_len: usize,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    // for vx, vname in ...
+    // For diagnostics, decide what to call the dimension
-    let agg_targ = match _agg_xcats_for_cid {
+    let agg_targ = if agg_xcats_for_cid { "xcats" } else { "cids" };
-        true => "xcats",
+
-        false => "cids",
+    // 1) Check numeric weights for zeroes.
-    };
+    for (i, weight) in weights_vec.iter().enumerate() {
-    for (vx, vname) in vec![
+        if let WeightValue::F64(val) = weight {
-        (weights_vec.clone(), "weights"),
+            if *val == 0.0 {
-        (signs_vec.clone(), "signs"),
+                return Err(format!("The weight at index {} is 0.0", i).into());
-    ] {
-        for (i, v) in vx.iter().enumerate() {
-            if *v == 0.0 {
-                return Err(format!("The {} at index {} is 0.0", vname, i).into());
             }
         }
-        if vx.len() != agg_targ_len {
+    }
-            return Err(format!(
+    // 2) Ensure the weights vector is the expected length.
-                "The length of {} ({}) does not match the length of {} ({})",
+    if weights_vec.len() != agg_targ_len {
-                vname,
+        return Err(format!(
-                vx.len(),
+            "The length of weights ({}) does not match the length of {} ({})",
-                agg_targ,
+            weights_vec.len(),
-                agg_targ_len
+            agg_targ,
-            )
+            agg_targ_len
-            .into());
+        )
+        .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/qdf/blacklist.rs

@@ -0,0 +1,307 @@
+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 super::get_unique_metrics;
+
+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,
+    )?;
+
+    let null_mask = get_nan_mask(df, metrics)?;
+
+    let df = df.filter(&null_mask)?.clone();
+
+    let df = df
+        .clone()
+        .lazy()
+        // .filter(&null_mask)
+        // .filter(
+        //     col(metric.as_str())
+        //         .is_null()
+        //         .or(col(metric.as_str()).is_nan()),
+        // )
+        .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)
+}
+
+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_cids = get_unique_cids(&new_df)?;
-    let u_xcats: Vec<String> = get_unique_xcats(&new_df)?;
+    let u_xcats = get_unique_xcats(&new_df)?;
-    let u_tickers: Vec<String> = _get_unique_strs_from_str_column_object(&ticker_col)?;
+    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();