mirror of
https://github.com/Magnus167/msyrs.git
synced 2025-08-21 02:10:00 +00:00
Compare commits
No commits in common. "80603aa951baa6c65fb04e27f96eb4b2919cb123" and "ee531deb7a991c0030860c16847ae32b8441ad99" have entirely different histories.
80603aa951
...
ee531deb7a
File diff suppressed because one or more lines are too long
@ -7,45 +7,8 @@ use polars::prelude::*;
|
|||||||
use std::collections::{BTreeMap, HashMap};
|
use std::collections::{BTreeMap, HashMap};
|
||||||
use std::error::Error;
|
use std::error::Error;
|
||||||
|
|
||||||
use crate::utils::qdf::get_unique_metrics;
|
use super::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 with Lazy API.
|
|
||||||
///
|
|
||||||
/// * `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 (parity with
|
|
||||||
/// the eager version).
|
|
||||||
pub fn apply_blacklist_lazy(
|
|
||||||
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)?;
|
|
||||||
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(
|
pub fn create_blacklist_from_qdf(
|
||||||
df: &DataFrame,
|
df: &DataFrame,
|
||||||
group_by_cid: Option<bool>,
|
group_by_cid: Option<bool>,
|
||||||
@ -67,26 +30,19 @@ pub fn create_blacklist_from_qdf(
|
|||||||
BDateFreq::Daily,
|
BDateFreq::Daily,
|
||||||
)?;
|
)?;
|
||||||
|
|
||||||
// if none of the metrics are null or NaN, return an empty blacklist
|
let null_mask = get_nan_mask(df, metrics)?;
|
||||||
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.filter(&null_mask)?.clone();
|
|
||||||
|
|
||||||
let df = df
|
let df = df
|
||||||
.clone()
|
.clone()
|
||||||
.lazy()
|
.lazy()
|
||||||
.with_columns([
|
// .filter(&null_mask)
|
||||||
(cols(metrics.clone()).is_null().or(cols(metrics).is_nan())).alias("null_mask")
|
// .filter(
|
||||||
])
|
// col(metric.as_str())
|
||||||
.filter(col("null_mask"))
|
// .is_null()
|
||||||
// if is now empty, return an empty blacklist
|
// .or(col(metric.as_str()).is_nan()),
|
||||||
|
// )
|
||||||
.sort(
|
.sort(
|
||||||
["cid", "xcat"],
|
["cid", "xcat"],
|
||||||
SortMultipleOptions::default().with_maintain_order(true),
|
SortMultipleOptions::default().with_maintain_order(true),
|
||||||
@ -156,8 +112,6 @@ pub fn create_blacklist_from_qdf(
|
|||||||
Ok(btree_map)
|
Ok(btree_map)
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Get a mask of NaN values for the specified metrics in the DataFrame.
|
|
||||||
#[allow(dead_code)]
|
|
||||||
fn get_nan_mask(
|
fn get_nan_mask(
|
||||||
df: &DataFrame,
|
df: &DataFrame,
|
||||||
metrics: Vec<String>,
|
metrics: Vec<String>,
|
||||||
|
Loading…
x
Reference in New Issue
Block a user