"""Analysis layer: the Li et al. (2024) relationship typology, spatial joins and the derived measures the dashboard plots. Where this departs from the paper, it says so. Li et al. classify a protected area by comparing it with statistically matched counterfactual sites. No counterfactual matching is possible from the open country-level series this dashboard can reach, so the reference point here is the **African median change over the same period**. That is a descriptive benchmark, not a causal estimate, and every view that uses it is labelled accordingly. """ from __future__ import annotations import math from dataclasses import dataclass import numpy as np import pandas as pd # --- The four relationships, Li et al. 2024, Figure 3C ---------------------- SYNERGY = "Synergy" CONSERVATION_IMPAIRED = "Conservation impaired" ECONOMY_IMPAIRED = "Economy impaired" RETREAT = "Retreat" RELATIONSHIPS = [SYNERGY, ECONOMY_IMPAIRED, CONSERVATION_IMPAIRED, RETREAT] RELATIONSHIP_COLORS = { SYNERGY: "#1B9E8A", ECONOMY_IMPAIRED: "#E8B04B", CONSERVATION_IMPAIRED: "#3F7FBF", RETREAT: "#C4384B", } RELATIONSHIP_MEANING = { SYNERGY: "Natural land cover held, and human development kept pace or better.", ECONOMY_IMPAIRED: "Natural land cover held, but human development lagged.", CONSERVATION_IMPAIRED: "Human development kept pace, but natural land cover was lost.", RETREAT: "Natural land cover was lost and human development lagged.", } # Global shares reported by Li et al. (2024) for 10,143 protected areas, shown # alongside this dashboard's own counts for context. LI_GLOBAL_SHARES = { SYNERGY: 47.7, ECONOMY_IMPAIRED: 42.9, CONSERVATION_IMPAIRED: 4.8, RETREAT: 4.6, } def classify(conservation_ok: bool | None, development_ok: bool | None) -> str | None: """Map the two binary outcomes onto the paper's 2x2.""" if conservation_ok is None or development_ok is None: return None if conservation_ok and development_ok: return SYNERGY if conservation_ok and not development_ok: return ECONOMY_IMPAIRED if not conservation_ok and development_ok: return CONSERVATION_IMPAIRED return RETREAT # --------------------------------------------------------------------------- # Country panel helpers # --------------------------------------------------------------------------- def observations_only(indicators: pd.DataFrame) -> pd.DataFrame: """Drop UN median-variant projections. World Bank rows carry no 'series' column and are observations by construction; UN WPP rows after 2024 are projections and must never enter a change calculation or the relationship typology. """ if indicators.empty or "series" not in indicators.columns: return indicators return indicators[indicators["series"].fillna("Estimate") != "Projection"] def year_span(indicators: pd.DataFrame, code: str) -> tuple[int, int] | None: """First and last year an indicator actually has observations for.""" if indicators.empty: return None d = indicators[indicators["indicator"] == code] if d.empty: return None return int(d["year"].min()), int(d["year"].max()) def overlapping_span(indicators: pd.DataFrame, codes: list[str]) -> tuple[int, int] | None: """The window where every requested indicator has data. UN WPP reaches back to 1950 while most World Bank series start in 1990, so a naive min/max across the whole panel produces a period in which one of the two axes is empty and the typology silently returns nothing. """ spans = [year_span(indicators, c) for c in codes] if any(s is None for s in spans): return None lo = max(s[0] for s in spans) hi = min(s[1] for s in spans) return (lo, hi) if hi - lo >= 2 else None def to_wide(indicators: pd.DataFrame) -> pd.DataFrame: """Long World Bank frame → one row per country-year, one column per code.""" if indicators.empty: return pd.DataFrame() wide = indicators.pivot_table( index=["iso3", "country", "year"], columns="indicator", values="value" ).reset_index() wide.columns.name = None return wide def latest_values(indicators: pd.DataFrame, code: str, not_after: int | None = None) -> pd.DataFrame: """Most recent non-missing observation of one indicator per country.""" if indicators.empty: return pd.DataFrame(columns=["iso3", "country", "year", "value"]) d = indicators[indicators["indicator"] == code] if not_after is not None: d = d[d["year"] <= not_after] if d.empty: return pd.DataFrame(columns=["iso3", "country", "year", "value"]) d = d.sort_values("year").groupby("iso3", as_index=False).tail(1) return d[["iso3", "country", "year", "value"]].reset_index(drop=True) def change_between(indicators: pd.DataFrame, code: str, start: int, end: int, tolerance: int = 3) -> pd.DataFrame: """Change in one indicator between two years, per country. ``tolerance`` allows the nearest observation within N years of each endpoint, which keeps sparse series (poverty, literacy) usable. """ empty = pd.DataFrame(columns=["iso3", "country", "start_year", "end_year", "start_value", "end_value", "change", "pct_change"]) if indicators.empty: return empty d = indicators[indicators["indicator"] == code] if d.empty: return empty rows = [] for iso3, grp in d.groupby("iso3"): grp = grp.sort_values("year") first = grp[(grp["year"] >= start - tolerance) & (grp["year"] <= start + tolerance)] last = grp[(grp["year"] >= end - tolerance) & (grp["year"] <= end + tolerance)] if first.empty or last.empty: continue first = first.iloc[(first["year"] - start).abs().argsort()].iloc[0] last = last.iloc[(last["year"] - end).abs().argsort()].iloc[0] if first["year"] == last["year"]: continue change = float(last["value"]) - float(first["value"]) pct = (change / abs(float(first["value"])) * 100) if first["value"] else math.nan rows.append({ "iso3": iso3, "country": grp["country"].iloc[0], "start_year": int(first["year"]), "end_year": int(last["year"]), "start_value": float(first["value"]), "end_value": float(last["value"]), "change": change, "pct_change": pct, }) return pd.DataFrame(rows) if rows else empty def orient(change: pd.Series, good: str | None) -> pd.Series: """Make 'higher is better' true for every indicator. Under-5 mortality and poverty improve when they fall, so their change is flipped before any comparison. """ if good == "low": return -change return change @dataclass class TypologyResult: frame: pd.DataFrame conservation_code: str development_code: str conservation_reference: float development_reference: float start: int end: int @property def shares(self) -> pd.Series: if self.frame.empty: return pd.Series(dtype=float) counts = self.frame["relationship"].value_counts() return (counts / counts.sum() * 100).reindex(RELATIONSHIPS).fillna(0.0) def build_typology(indicators: pd.DataFrame, conservation_code: str, development_code: str, start: int, end: int, development_good: str | None = "high", conservation_good: str | None = "high") -> TypologyResult: """Place each country in the 2x2, using the African median as the reference. A country is 'conservation ok' when its change in the conservation indicator is at least the African median change, and 'development ok' on the same footing for the human development indicator. """ cons = change_between(indicators, conservation_code, start, end) dev = change_between(indicators, development_code, start, end) cols = ["iso3", "country", "start_year", "end_year", "start_value", "end_value", "change"] if cons.empty or dev.empty: return TypologyResult(pd.DataFrame(), conservation_code, development_code, math.nan, math.nan, start, end) merged = cons[cols].merge(dev[cols], on=["iso3", "country"], suffixes=("_cons", "_dev")) if merged.empty: return TypologyResult(pd.DataFrame(), conservation_code, development_code, math.nan, math.nan, start, end) merged["cons_oriented"] = orient(merged["change_cons"], conservation_good) merged["dev_oriented"] = orient(merged["change_dev"], development_good) cons_ref = float(merged["cons_oriented"].median()) dev_ref = float(merged["dev_oriented"].median()) merged["conservation_ok"] = merged["cons_oriented"] >= cons_ref merged["development_ok"] = merged["dev_oriented"] >= dev_ref merged["relationship"] = [ classify(c, d) for c, d in zip(merged["conservation_ok"], merged["development_ok"]) ] return TypologyResult(merged.reset_index(drop=True), conservation_code, development_code, cons_ref, dev_ref, start, end) def association(result: "TypologyResult") -> dict: """How strongly the two axes move together, beyond the median split itself. The 2x2 here is built by cutting each axis at the African median, so each margin is 50/50 *by construction* and the four shares would sit near 25% each if conservation and development change were independent. The shares are therefore not comparable in level with Li et al., whose categories come from counterfactual matching. What the table does carry is the association between the two axes: phi (the correlation of the two binary outcomes) and the odds ratio, with a Haldane correction so an empty cell does not send it to infinity. phi > 0 means countries that held their conservation indicator also tended to advance on human development — synergy and retreat outnumber the two tradeoffs. """ out = {"n": 0, "phi": math.nan, "odds_ratio": math.nan, "n11": 0, "n10": 0, "n01": 0, "n00": 0} frame = result.frame if frame.empty or "conservation_ok" not in frame: return out cons = frame["conservation_ok"].astype(bool) dev = frame["development_ok"].astype(bool) n11 = int((cons & dev).sum()) # synergy n10 = int((cons & ~dev).sum()) # economy impaired n01 = int((~cons & dev).sum()) # conservation impaired n00 = int((~cons & ~dev).sum()) # retreat out.update(n=len(frame), n11=n11, n10=n10, n01=n01, n00=n00) denominator = (n11 + n10) * (n01 + n00) * (n11 + n01) * (n10 + n00) if denominator > 0: out["phi"] = (n11 * n00 - n10 * n01) / math.sqrt(denominator) a, b, c, d = n11 + 0.5, n10 + 0.5, n01 + 0.5, n00 + 0.5 out["odds_ratio"] = (a * d) / (b * c) return out def coverage(indicators: pd.DataFrame) -> pd.DataFrame: """Per indicator: how many countries and which years actually carry data.""" if indicators.empty: return pd.DataFrame(columns=["indicator", "countries", "first", "last", "points"]) grouped = indicators.groupby("indicator").agg( countries=("iso3", "nunique"), first=("year", "min"), last=("year", "max"), points=("value", "size"), ).reset_index() return grouped.sort_values("countries", ascending=False).reset_index(drop=True) # --------------------------------------------------------------------------- # Protected areas × places # --------------------------------------------------------------------------- def attach_country_context(pas: pd.DataFrame, indicators: pd.DataFrame, codes: list[str], year: int | None = None) -> pd.DataFrame: """Join the latest country value of each requested indicator onto every PA.""" if pas.empty: return pas out = pas.copy() for code in codes: latest = latest_values(indicators, code, not_after=year) if latest.empty: out[code] = np.nan continue out = out.merge( latest[["iso3", "value"]].rename(columns={"value": code}), on="iso3", how="left" ) return out def assign_regions(pas: pd.DataFrame, boundaries: dict) -> pd.DataFrame: """Point-in-polygon assignment of each PA to an administrative region. Falls back to leaving the region blank rather than guessing when shapely is unavailable or a point sits outside every polygon (islands, coastal PAs). """ if pas.empty or not boundaries.get("features"): out = pas.copy() out["region"] = pd.NA return out try: from shapely.geometry import Point, shape from shapely.strtree import STRtree except Exception: out = pas.copy() out["region"] = pd.NA return out geometries, names, isos = [], [], [] for feature in boundaries["features"]: try: geometries.append(shape(feature["geometry"])) except Exception: continue props = feature.get("properties", {}) names.append(props.get("name") or props.get("shapeName") or "") isos.append(props.get("iso3", "")) if not geometries: out = pas.copy() out["region"] = pd.NA return out tree = STRtree(geometries) regions, region_isos = [], [] for lat, lon in zip(pas["lat"], pas["lon"]): if pd.isna(lat) or pd.isna(lon): regions.append(pd.NA) region_isos.append(pd.NA) continue point = Point(float(lon), float(lat)) hit = None for idx in tree.query(point): index = int(idx) if geometries[index].contains(point): hit = index break regions.append(names[hit] if hit is not None else pd.NA) region_isos.append(isos[hit] if hit is not None else pd.NA) out = pas.copy() out["region"] = regions out["region_iso3"] = region_isos return out def neighbour_counts(pas: pd.DataFrame, radius_km: float = 50.0) -> pd.Series: """How many other protected areas sit within ``radius_km`` of each one. A cheap proxy for how clustered the estate is; equal-angle degrees are converted with a cosine correction so the radius is roughly metric. """ if pas.empty: return pd.Series(dtype=int) lat = np.radians(pas["lat"].astype(float).to_numpy()) lon = np.radians(pas["lon"].astype(float).to_numpy()) earth_km = 6371.0 x = earth_km * np.cos(lat) * np.cos(lon) y = earth_km * np.cos(lat) * np.sin(lon) z = earth_km * np.sin(lat) pts = np.column_stack([x, y, z]) counts = np.zeros(len(pts), dtype=int) chunk = 512 for start in range(0, len(pts), chunk): block = pts[start:start + chunk] d = np.linalg.norm(block[:, None, :] - pts[None, :, :], axis=2) counts[start:start + chunk] = (d <= radius_km).sum(axis=1) - 1 return pd.Series(counts, index=pas.index) def pressure_index(pas: pd.DataFrame) -> pd.Series: """Rank-based 0–100 index of human pressure around each protected area. Components, in order of preference (UN World Population Prospects first, World Bank as the fallback when the WPP extract is not present): * population density of the country — how crowded the setting is * child dependency ratio (0–14 per 100 of 15–64) — the dependent-young burden Li et al. found bound up with the economy-impaired and retreat cases * rural population share — reliance on land around parks * protected areas within 50 km — how contested the landscape is Each component is converted to a percentile across the mapped estate and the percentiles are averaged, so the index is ordinal: it says which parks sit in busier settings, not how many people live within 10 km of a boundary. That number needs gridded population clipped to a buffer, which this dashboard does not have. """ if pas.empty: return pd.Series(dtype=float) density = "UN:54" if "UN:54" in pas.columns and pas["UN:54"].notna().any() else "EN.POP.DNST" components = [ (density, False), ("UN:83", False), ("SP.RUR.TOTL.ZS", False), ("neighbours_50km", False), ] parts = [] for column, invert in components: if column in pas.columns and pas[column].notna().any(): ranked = pas[column].rank(pct=True) parts.append(1 - ranked if invert else ranked) if not parts: return pd.Series(np.nan, index=pas.index) stacked = pd.concat(parts, axis=1) return (stacked.mean(axis=1) * 100).round(1) def pressure_components(pas: pd.DataFrame) -> list[str]: """Which columns actually fed the pressure index, for display in the UI.""" density = "UN:54" if "UN:54" in pas.columns and pas["UN:54"].notna().any() else "EN.POP.DNST" candidates = [density, "UN:83", "SP.RUR.TOTL.ZS", "neighbours_50km"] return [c for c in candidates if c in pas.columns and pas[c].notna().any()] def summarise_by_country(pas: pd.DataFrame) -> pd.DataFrame: """Estate size and protected area count per country.""" if pas.empty: return pd.DataFrame(columns=["iso3", "country", "n_pas", "area_km2"]) grouped = pas.groupby(["iso3", "country"], as_index=False).agg( n_pas=("pa_id", "count"), area_km2=("area_km2", "sum"), median_area_km2=("area_km2", "median"), ) return grouped.sort_values("n_pas", ascending=False).reset_index(drop=True) def match_effectiveness(pas: pd.DataFrame, scores: pd.DataFrame) -> tuple[pd.DataFrame, dict]: """Join uploaded effectiveness scores onto the protected area table. Matching is by id when the upload has one, then by normalised name within a country, then by normalised name alone. The report tells the user exactly how many rows matched and which did not, so a silent half-join is visible. """ report = {"uploaded": len(scores), "matched": 0, "unmatched": []} if pas.empty or scores.empty: return pas.assign(effectiveness=np.nan), report def norm(s: pd.Series) -> pd.Series: return (s.astype(str).str.lower() .str.replace(r"[^a-z0-9 ]", " ", regex=True) .str.replace(r"\b(national|park|reserve|nature|wildlife|forest|" r"game|marine|protected|area|conservancy)\b", " ", regex=True) .str.replace(r"\s+", " ", regex=True).str.strip()) left = pas.copy() left["_key"] = norm(left["name"]) right = scores.copy() right["_key"] = norm(right["name"]) merged = None if "pa_id" in right.columns and right["pa_id"].notna().any(): right["pa_id"] = right["pa_id"].astype(str) left["pa_id"] = left["pa_id"].astype(str) merged = left.merge(right[["pa_id", "score"]].dropna(subset=["pa_id"]), on="pa_id", how="left") else: merged = left.copy() merged["score"] = np.nan if "iso3" in right.columns and right["iso3"].notna().any(): by_country = right.dropna(subset=["iso3"])[["iso3", "_key", "score"]] by_country = by_country.drop_duplicates(["iso3", "_key"]) merged = merged.merge(by_country, on=["iso3", "_key"], how="left", suffixes=("", "_country")) merged["score"] = merged["score"].fillna(merged.pop("score_country")) by_name = right[["_key", "score"]].drop_duplicates("_key") merged = merged.merge(by_name, on="_key", how="left", suffixes=("", "_name")) merged["score"] = merged["score"].fillna(merged.pop("score_name")) merged = merged.rename(columns={"score": "effectiveness"}).drop(columns=["_key"]) report["matched"] = int(merged["effectiveness"].notna().sum()) matched_keys = set(norm(merged.loc[merged["effectiveness"].notna(), "name"])) report["unmatched"] = [ n for n, k in zip(scores["name"], norm(scores["name"])) if k not in matched_keys ][:40] return merged, report