magnus167/msyrs
1
0
Fork 0
mirror of https://github.com/Magnus167/msyrs.git synced 2025-11-19 20:06:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: magnus167:rawdf
Branches Tags
magnus167:main magnus167:rawdf
..
compare: magnus167:5c3862c297d2a1cd582310fc355045206ac2143f
Branches Tags
magnus167:main magnus167:rawdf

6 Commits
rawdf ... 5c3862c297

Author SHA1 Message Date
Palash Tyagi
5c3862c297 refactor: reorganize module exports for clarity 2025-04-14 00:25:23 +01:00
Palash Tyagi
3559a90ad2 adding blacklist ability 2025-04-14 00:25:09 +01:00
Palash Tyagi
b7368a366e add weight_xcat capability 2025-04-14 00:24:26 +01:00
Palash Tyagi
24a4176e17 fix: correct import statement for reduce_dataframe in historic_vol.rs 2025-04-14 00:24:02 +01:00
Palash Tyagi
165e1c19e4 updating linear composite binding 2025-04-14 00:22:59 +01:00
Palash Tyagi
fefe849394 updating notebook 2025-04-14 00:22:38 +01:00
12 changed files with 393 additions and 664 deletions
Expand all files Collapse all files

260
notebooks/funcwise/linear_composites.ipynb
View File

File diff suppressed because one or more lines are too long

6
src/_py/panel.rs
View File

@@ -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,

281
src/core/dateseries.rs
View File

@@ -1,281 +0,0 @@
//! # DateSeries and BDateSeries Implementations
//!
//! This module provides two date-handling types using the [`chrono`](https://docs.rs/chrono) crate:
//!
//! - [`DateSeries`]: Stores any set of calendar dates and allows adding/subtracting *calendar days*.
//! - [`BDateSeries`]: Stores only Monday–Friday business days and interprets add/sub as *business day* shifts,
//! skipping weekends (e.g., adding 1 to Friday goes to Monday).
//!
//! Both types also provide a [`from_iso8601_range`](#method.from_iso8601_range) constructor
//! that builds a date series (or business‑date series) from a start/end string (YYYY‑MM‑DD).
use chrono::{Datelike, Duration, NaiveDate, ParseResult};
use std::ops::{Add, Sub};
/// Determines if the date is Saturday or Sunday.
fn is_weekend(date: NaiveDate) -> bool {
matches!(date.weekday(), chrono::Weekday::Sat | chrono::Weekday::Sun)
}
/// A `DateSeries` stores a list of [`NaiveDate`] values and shifts by **calendar days**.
///
/// ## Example Usage
///
/// ```
/// use chrono::NaiveDate;
/// use msyrs::core::dateseries::DateSeries;
///
/// // Create from explicit dates
/// let ds = DateSeries::new(vec![
/// NaiveDate::from_ymd_opt(2023, 7, 14).unwrap(), // a Friday
/// NaiveDate::from_ymd_opt(2023, 7, 15).unwrap(), // a Saturday
/// ]);
///
/// // Shift forward by 5 calendar days
/// let ds_plus = ds + 5;
/// // 2023-07-14 + 5 => 2023-07-19 (Wednesday)
/// // 2023-07-15 + 5 => 2023-07-20 (Thursday)
///
/// assert_eq!(ds_plus.data()[0], NaiveDate::from_ymd_opt(2023, 7, 19).unwrap());
/// assert_eq!(ds_plus.data()[1], NaiveDate::from_ymd_opt(2023, 7, 20).unwrap());
/// ```
///
#[derive(Debug, Clone)]
pub struct DateSeries {
data: Vec<NaiveDate>,
}
impl DateSeries {
/// Creates a new `DateSeries` from a vector of [`NaiveDate`] values.
///
/// # Panics
/// - Does not panic on invalid weekend or anything; this type accepts all valid dates.
pub fn new(data: Vec<NaiveDate>) -> Self {
Self { data }
}
/// Constructs a `DateSeries` by parsing an ISO‑8601 start/end string (YYYY‑MM‑DD)
/// and including **every calendar date** from start to end (inclusive).
///
/// # Errors
/// - Returns a [`chrono::ParseError`](chrono::ParseError) if parsing fails.
/// - Panics if `start` > `end` chronologically.
///
/// # Examples
///
/// ```
/// use msyrs::core::dateseries::DateSeries;
/// # fn main() -> Result<(), chrono::ParseError> {
/// let ds = DateSeries::from_iso8601_range("2023-07-14", "2023-07-16")?;
/// assert_eq!(ds.data().len(), 3);
/// # Ok(())
/// # }
/// ```
pub fn from_iso8601_range(start: &str, end: &str) -> ParseResult<Self> {
let start_date = NaiveDate::parse_from_str(start, "%Y-%m-%d")?;
let end_date = NaiveDate::parse_from_str(end, "%Y-%m-%d")?;
assert!(
start_date <= end_date,
"start date cannot be after end date"
);
let mut dates = Vec::new();
let mut current = start_date;
while current <= end_date {
dates.push(current);
current = current
.checked_add_signed(Duration::days(1))
.expect("Date overflow in from_iso8601_range");
}
Ok(Self::new(dates))
}
/// Returns a reference to the underlying slice of dates.
pub fn data(&self) -> &[NaiveDate] {
&self.data
}
/// Internal helper applying a function to each date.
fn apply<F>(&self, op: F) -> Self
where
F: Fn(NaiveDate) -> NaiveDate,
{
let new_data = self.data.iter().map(|&date| op(date)).collect();
Self { data: new_data }
}
}
/// Implements adding calendar days to each `NaiveDate`.
///
/// If the shifted date goes out of chrono's valid range, it panics.
impl Add<i64> for DateSeries {
type Output = Self;
fn add(self, rhs: i64) -> Self::Output {
self.apply(|date| {
date.checked_add_signed(Duration::days(rhs))
.expect("Overflow in date addition")
})
}
}
/// Implements subtracting calendar days from each `NaiveDate`.
///
/// If the shifted date goes out of chrono's valid range, it panics.
impl Sub<i64> for DateSeries {
type Output = Self;
fn sub(self, rhs: i64) -> Self::Output {
self.apply(|date| {
date.checked_sub_signed(Duration::days(rhs))
.expect("Overflow in date subtraction")
})
}
}
/// A “Business Date Series” for Monday–Friday only.
///
/// 1. The constructor disallows weekend dates (panics if any date is Sat/Sun).
/// 2. Adding or subtracting an `i64` interprets that integer as *business days*, skipping weekends.
/// For example, adding 1 to a Friday yields the following Monday.
///
/// ## Example Usage
///
/// ```
/// use chrono::NaiveDate;
/// use msyrs::core::dateseries::BDateSeries;
///
/// // Friday
/// let friday = NaiveDate::from_ymd_opt(2023, 7, 14).unwrap();
/// let mut bds = BDateSeries::new(vec![friday]);
///
/// // Adding 1 “business day” => next Monday, 2023-07-17
/// bds = bds + 1;
/// assert_eq!(bds.data()[0], NaiveDate::from_ymd_opt(2023, 7, 17).unwrap());
/// ```
#[derive(Debug, Clone)]
pub struct BDateSeries {
data: Vec<NaiveDate>,
}
impl BDateSeries {
/// Creates a new `BDateSeries`, panicking if any of the supplied dates is on Saturday/Sunday.
pub fn new(data: Vec<NaiveDate>) -> Self {
for &d in &data {
if is_weekend(d) {
panic!("BDateSeries cannot contain weekend dates: {}", d);
}
}
Self { data }
}
/// Constructs a `BDateSeries` by parsing an ISO‑8601 start/end string (YYYY‑MM‑DD).
///
/// Only Monday–Friday dates within `[start, end]` are included in the series.
///
/// # Errors
/// - Returns a [`chrono::ParseError`](chrono::ParseError) if parsing fails.
/// - Panics if `start` > `end` chronologically.
///
/// # Examples
///
/// ```
/// use msyrs::core::dateseries::BDateSeries;
/// # fn main() -> Result<(), chrono::ParseError> {
/// let bds = BDateSeries::from_iso8601_range("2023-07-14", "2023-07-18")?;
/// // 2023-07-14 (Friday), 2023-07-15 (Saturday) => skipped,
/// // 2023-07-16 (Sunday) => skipped,
/// // 2023-07-17 (Monday), 2023-07-18 (Tuesday)
/// // so total 3 valid business days
/// assert_eq!(bds.data().len(), 3);
/// # Ok(())
/// # }
/// ```
pub fn from_iso8601_range(start: &str, end: &str) -> ParseResult<Self> {
let start_date = NaiveDate::parse_from_str(start, "%Y-%m-%d")?;
let end_date = NaiveDate::parse_from_str(end, "%Y-%m-%d")?;
assert!(
start_date <= end_date,
"start date cannot be after end date"
);
let mut dates = Vec::new();
let mut current = start_date;
while current <= end_date {
if !is_weekend(current) {
dates.push(current);
}
current = current
.checked_add_signed(Duration::days(1))
.expect("Date overflow in from_iso8601_range");
}
Ok(Self::new(dates))
}
/// Returns a reference to the underlying slice of dates.
pub fn data(&self) -> &[NaiveDate] {
&self.data
}
/// Internal helper that tries to shift a date forward or backward by one day at a time,
/// skipping weekends, for a total of `delta` business days.
fn shift_business_days(date: NaiveDate, delta: i64) -> NaiveDate {
if delta == 0 {
return date;
}
let step = if delta > 0 { 1 } else { -1 };
let abs_delta = delta.abs();
let mut new_date = date;
for _ in 0..abs_delta {
// Move by 1 day in the correct direction
new_date = new_date
.checked_add_signed(Duration::days(step))
.expect("Overflow in BDateSeries add/sub");
// If we land on weekend, keep moving until Monday..Friday
while is_weekend(new_date) {
new_date = new_date
.checked_add_signed(Duration::days(step))
.expect("Overflow in BDateSeries skipping weekend");
}
}
new_date
}
/// Internal helper to apply a shift of `delta` business days to each date.
fn apply(&self, delta: i64) -> Self {
let new_data = self
.data
.iter()
.map(|&date| Self::shift_business_days(date, delta))
.collect();
Self { data: new_data }
}
}
/// Implement *business day* addition for `BDateSeries`.
///
/// # Panics
/// - If the resulting date(s) overflow `NaiveDate` range.
/// - `BDateSeries` is guaranteed to remain Monday..Friday after the shift.
impl Add<i64> for BDateSeries {
type Output = Self;
fn add(self, rhs: i64) -> Self::Output {
self.apply(rhs)
}
}
/// Implement *business day* subtraction for `BDateSeries`.
///
/// # Panics
/// - If the resulting date(s) overflow `NaiveDate`.
/// - `BDateSeries` is guaranteed to remain Monday..Friday after the shift.
impl Sub<i64> for BDateSeries {
type Output = Self;
fn sub(self, rhs: i64) -> Self::Output {
self.apply(-rhs)
}
}

0
src/core/df.rs
View File

3
src/core/mod.rs
View File

@@ -1,3 +0,0 @@
pub mod df;
pub mod xseries;
pub mod dateseries;

223
src/core/xseries.rs
View File

@@ -1,223 +0,0 @@
use std::ops::{Add, Div, Mul, Sub};
//
// 1) Define a float series: FSeries
//
#[derive(Debug, Clone)]
pub struct FSeries {
data: Vec<f64>,
}
impl FSeries {
/// Create a new FSeries from a vector of f64 values.
pub fn new(data: Vec<f64>) -> Self {
Self { data }
}
pub fn len(&self) -> usize {
self.data.len()
}
/// Element‑wise helper applying an operation between two FSeries.
pub fn apply<F>(&self, other: &Self, op: F) -> Self
where
F: Fn(f64, f64) -> f64,
{
assert!(
self.len() == other.len(),
"FSeries must have the same length to apply operations."
);
let data = self
.data
.iter()
.zip(other.data.iter())
.map(|(&a, &b)| op(a, b))
.collect();
FSeries { data }
}
/// Access to the underlying data
pub fn data(&self) -> &[f64] {
&self.data
}
}
// Macros for float series arithmetic (element‑wise)
macro_rules! impl_fseries_bin_op {
($trait:ident, $method:ident, $op:tt) => {
impl $trait for FSeries {
type Output = Self;
fn $method(self, rhs: Self) -> Self::Output {
self.apply(&rhs, |a, b| a $op b)
}
}
};
}
impl_fseries_bin_op!(Add, add, +);
impl_fseries_bin_op!(Sub, sub, -);
impl_fseries_bin_op!(Mul, mul, *);
impl_fseries_bin_op!(Div, div, /);
macro_rules! impl_fseries_scalar_op {
($trait:ident, $method:ident, $op:tt) => {
impl $trait<f64> for FSeries {
type Output = Self;
fn $method(mut self, scalar: f64) -> Self::Output {
for x in self.data.iter_mut() {
*x = *x $op scalar;
}
self
}
}
};
}
impl_fseries_scalar_op!(Add, add, +);
impl_fseries_scalar_op!(Sub, sub, -);
impl_fseries_scalar_op!(Mul, mul, *);
impl_fseries_scalar_op!(Div, div, /);
//
// 2) Define an integer series: ISeries
//
#[derive(Debug, Clone)]
pub struct ISeries {
data: Vec<i64>,
}
impl ISeries {
/// Create an ISeries from a vector of i64 values.
pub fn new(data: Vec<i64>) -> Self {
Self { data }
}
pub fn len(&self) -> usize {
self.data.len()
}
pub fn data(&self) -> &[i64] {
&self.data
}
/// Element‑wise helper for integer series.
pub fn apply<F>(&self, other: &Self, op: F) -> Self
where
F: Fn(i64, i64) -> i64,
{
assert!(
self.len() == other.len(),
"ISeries must have the same length to apply operations."
);
let data = self
.data
.iter()
.zip(other.data.iter())
.map(|(&a, &b)| op(a, b))
.collect();
ISeries { data }
}
}
// Macros for integer series arithmetic (element‑wise)
macro_rules! impl_iseries_bin_op {
($trait:ident, $method:ident, $op:tt) => {
impl $trait for ISeries {
type Output = Self;
fn $method(self, rhs: Self) -> Self::Output {
self.apply(&rhs, |a, b| a $op b)
}
}
};
}
impl_iseries_bin_op!(Add, add, +);
impl_iseries_bin_op!(Sub, sub, -);
impl_iseries_bin_op!(Mul, mul, *);
impl_iseries_bin_op!(Div, div, /); // integer division (floor trunc)
// Optional scalar operations (for i64)
macro_rules! impl_iseries_scalar_op {
($trait:ident, $method:ident, $op:tt) => {
impl $trait<i64> for ISeries {
type Output = Self;
fn $method(mut self, scalar: i64) -> Self::Output {
for x in self.data.iter_mut() {
*x = *x $op scalar;
}
self
}
}
};
}
impl_iseries_scalar_op!(Add, add, +);
impl_iseries_scalar_op!(Sub, sub, -);
impl_iseries_scalar_op!(Mul, mul, *);
impl_iseries_scalar_op!(Div, div, /); // floor/trunc division by scalar
/// A boolean series: BSeries
///
#[derive(Debug, Clone)]
pub struct BSeries {
data: Vec<bool>,
}
impl BSeries {
pub fn new(data: Vec<bool>) -> Self {
Self { data }
}
pub fn len(&self) -> usize {
self.data.len()
}
pub fn data(&self) -> &[bool] {
&self.data
}
}
/// Convert an FSeries to ISeries by truncation (floor cast).
impl From<FSeries> for ISeries {
fn from(fseries: FSeries) -> Self {
let data = fseries
.data
.into_iter()
.map(|val| val as i64) // trunc cast
.collect();
ISeries::new(data)
}
}
/// Implement conversion from ISeries to FSeries by casting to f64.
impl From<ISeries> for FSeries {
fn from(iseries: ISeries) -> Self {
let data = iseries.data.into_iter().map(|val| val as f64).collect();
FSeries::new(data)
}
}
/// Convert an ISeries to BSeries by checking if each value is non-zero.
impl From<ISeries> for BSeries {
fn from(iseries: ISeries) -> Self {
let data = iseries.data.into_iter().map(|val| val != 0).collect();
BSeries::new(data)
}
}
impl From<BSeries> for ISeries {
fn from(bseries: BSeries) -> Self {
let data = bseries
.data
.into_iter()
.map(|val| if val { 1 } else { 0 })
.collect();
ISeries::new(data)
}
}

6
src/download/jpmaqsdownload.rs
View File

@@ -102,7 +102,7 @@ impl Default for JPMaQSDownloadGetIndicatorArgs {
/// Struct for downloading data from the JPMaQS data from JPMorgan DataQuery API.
///
/// ## Example Usage
/// ```ignore
/// ```rust
/// use msyrs::download::jpmaqsdownload::JPMaQSDownload;
/// use msyrs::download::jpmaqsdownload::JPMaQSDownloadGetIndicatorArgs;
/// use polars::prelude::*;
@@ -140,7 +140,7 @@ impl Default for JPMaQSDownloadGetIndicatorArgs {
/// Ok(_) => println!("Saved indicators to disk"),
/// Err(e) => println!("Error saving indicators: {:?}", e),
/// }
/// ```
///
#[derive(Debug, Clone)]
pub struct JPMaQSDownload {
requester: DQRequester,
@@ -277,7 +277,7 @@ impl JPMaQSDownload {
///
/// Usage:
///
/// ```ignore
/// ```rust
/// use msyrs::download::jpmaqsdownload::JPMaQSDownload;
/// use msyrs::download::jpmaqsdownload::JPMaQSDownloadGetIndicatorArgs;
/// let mut jpamqs_download = JPMaQSDownload::default();

4
src/lib.rs
View File

@@ -1,5 +1,4 @@
// #![doc = include_str!("../README.md")]
// uncomment the above line to include the README.md file in the documentation
//! # msyrs
//!
@@ -19,9 +18,6 @@
/// Documentation and type-stubs for the `msyrs` Python API.
pub mod _py;
/// Implementation for the `core` module.
pub mod core;
/// Implementation for the `download` module.
pub mod download;

2
src/panel/historic_vol.rs
View File

@@ -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::*;

228
src/panel/linear_composite.rs
View File

@@ -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 {
}
// 2) Ensure the weights vector is the expected length.
if weights_vec.len() != agg_targ_len {
return Err(format!(
"The length of {} ({}) does not match the length of {} ({})",
vname,
vx.len(),
"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);

27
src/utils/qdf/blacklist.rs Normal file
View File

@@ -0,0 +1,27 @@
use crate::utils::dateutils::{get_bdates_series_default_opt, get_min_max_real_dates};
use crate::utils::qdf::core::*;
use chrono::{Duration, NaiveDate};
use polars::prelude::*;
use std::collections::HashMap;
use std::error::Error;
use super::pivots::pivot_dataframe_by_ticker;
/// The required columns for a Quantamental DataFrame.
const QDF_INDEX_COLUMNS: [&str; 3] = ["real_date", "cid", "xcat"];
pub fn create_blacklist_from_qdf(
df: &DataFrame,
metric: Option<String>,
start: Option<String>,
end: Option<String>,
) -> Result<HashMap<String, Vec<String>>, Box<dyn Error>> {
// Verify that the DataFrame follows the Quantamental structure.
check_quantamental_dataframe(df)?;
let mut blacklist: HashMap<String, Vec<String>> = HashMap::new();
// Use the provided metric or default to "value".
let metric = metric.unwrap_or_else(|| "value".into());
Ok(blacklist)
}

7
src/utils/qdf/mod.rs
View File

@@ -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::*;