This commit is contained in:
Andras Schmelczer 2026-07-12 20:30:19 +01:00
parent 6df2812a4e
commit 9e4e65fa2a
35 changed files with 1172 additions and 70 deletions

View file

@ -12,6 +12,16 @@ use crate::utils::{normalize_postcode, GridIndex, InternedColumn};
const GRID_CELL_SIZE: f32 = 0.01;
/// One observation on a listing's accruing asking-price timeline, recovered from
/// the scraper's forward-only store (finder/price_history.py). `reason` is one of
/// "listed" | "reduced" | "increased"; `date` is `YYYY-MM-DD`.
#[derive(Serialize, Clone)]
pub struct PriceHistoryPoint {
pub date: String,
pub price: i64,
pub reason: String,
}
#[derive(Serialize, Clone)]
pub struct ActualListing {
pub lat: f32,
@ -32,6 +42,10 @@ pub struct ActualListing {
pub listing_status: Option<String>,
pub listing_date_iso: Option<String>,
pub features: Vec<String>,
/// Accrued asking-price observations, oldest -> newest. Empty until the
/// scraper's forward-only store has recorded at least one run for this id.
#[serde(skip_serializing_if = "Vec::is_empty")]
pub price_history: Vec<PriceHistoryPoint>,
}
pub struct ActualListingData {
@ -54,6 +68,8 @@ pub struct ActualListingData {
pub listing_status: InternedColumn,
pub listing_date_iso: Vec<Option<String>>,
pub features: Vec<Vec<String>>,
/// Per-row accrued asking-price series (empty when absent from the parquet).
pub price_history: Vec<Vec<PriceHistoryPoint>>,
/// Row-major feature matrix aligned with PropertyData::feature_names.
///
/// Rows start from a best-effort address/postcode join to the historical property
@ -102,6 +118,7 @@ impl ActualListingData {
let listing_status_raw = extract_opt_str(&df, "Listing status")?;
let listing_date_iso = extract_opt_datetime_iso(&df, "Listing date")?;
let features = extract_str_list(&df, "Listing features")?;
let price_history = extract_price_history(&df)?;
let postcode: Vec<String> = postcode_raw.iter().map(|s| normalize_postcode(s)).collect();
@ -146,6 +163,7 @@ impl ActualListingData {
listing_status,
listing_date_iso,
features,
price_history,
filter_feature_data,
poi_filter_feature_data,
grid,
@ -172,6 +190,7 @@ impl ActualListingData {
listing_status: opt_from_interned(&self.listing_status, row),
listing_date_iso: self.listing_date_iso[row].clone(),
features: self.features[row].clone(),
price_history: self.price_history[row].clone(),
}
}
}
@ -629,6 +648,64 @@ fn extract_str_list(df: &DataFrame, name: &str) -> Result<Vec<Vec<String>>> {
Ok(out)
}
/// Extract `price_history: List<Struct{date: Utf8, price: Int64, reason: Utf8}>`.
///
/// Schema-gated: a parquet written before the column existed simply yields an
/// empty series per row (the column is dropped from serialized listings). A
/// null/empty list is likewise an empty series.
fn extract_price_history(df: &DataFrame) -> Result<Vec<Vec<PriceHistoryPoint>>> {
let row_count = df.height();
let Ok(column) = df.column("price_history") else {
return Ok(vec![Vec::new(); row_count]);
};
let list_ca = column
.list()
.context("price_history is not a list column")?;
let mut out: Vec<Vec<PriceHistoryPoint>> = Vec::with_capacity(row_count);
for row in 0..row_count {
let mut points = Vec::new();
if let Some(inner) = list_ca.get_as_series(row) {
if !inner.is_empty() {
let structs = inner
.struct_()
.context("price_history inner is not a struct")?;
let dates_s = structs
.field_by_name("date")
.context("Missing 'date' field in price_history struct")?;
let date_ca = dates_s.str().context("price_history.date is not a string")?;
let prices_s = structs
.field_by_name("price")
.context("Missing 'price' field in price_history struct")?;
let prices_i64 = prices_s
.cast(&DataType::Int64)
.context("price_history.price is not castable to Int64")?;
let price_ca = prices_i64.i64().context("price_history.price is not Int64")?;
let reasons_s = structs
.field_by_name("reason")
.context("Missing 'reason' field in price_history struct")?;
let reason_ca = reasons_s
.str()
.context("price_history.reason is not a string")?;
for idx in 0..inner.len() {
let (Some(date), Some(price), Some(reason)) =
(date_ca.get(idx), price_ca.get(idx), reason_ca.get(idx))
else {
continue;
};
points.push(PriceHistoryPoint {
date: date.to_string(),
price,
reason: reason.to_string(),
});
}
}
}
out.push(points);
}
Ok(out)
}
#[cfg(test)]
mod tests {
use super::*;
@ -663,4 +740,30 @@ mod tests {
assert!(any_listing.lon.is_finite());
assert!(!any_listing.listing_url.is_empty());
}
#[test]
fn extracts_price_history_from_parquet() {
let path = PathBuf::from("src/data/testdata/listings_price_history.parquet");
if !path.exists() {
eprintln!("price_history fixture not present; skipping");
return;
}
let data = ActualListingData::load_inner(&path, None).expect("listings load");
assert_eq!(data.price_history.len(), data.lat.len());
// Row 0: two points, listed -> reduced, oldest first.
let r0 = data.listing_at(0);
assert_eq!(r0.price_history.len(), 2);
assert_eq!(r0.price_history[0].date, "2026-07-01");
assert_eq!(r0.price_history[0].price, 500_000);
assert_eq!(r0.price_history[0].reason, "listed");
assert_eq!(r0.price_history[1].price, 480_000);
assert_eq!(r0.price_history[1].reason, "reduced");
// Row 1: a single "listed" point.
assert_eq!(data.listing_at(1).price_history.len(), 1);
// Row 2 (empty list) and row 3 (null) carry no points.
assert!(data.listing_at(2).price_history.is_empty());
assert!(data.listing_at(3).price_history.is_empty());
}
}