feat(analysis): Overton window breakpoint analysis with opposition control and SVD drift
Quantify 2024 breakpoint in centrist support (d=+0.68 overall, d=+0.85 opposition-only), domain decomposition, extremity-stratified pass rates, and manual LLM audit (75% agreement). SVD center drift aborted due to axis instability (9/10 consecutive window pairs fail stability threshold).
This commit is contained in:
@@ -0,0 +1,977 @@
|
||||
#!/usr/bin/env python3
|
||||
"""U2: Quantify the 2024 Overton Window breakpoint in Dutch parliament.
|
||||
|
||||
Descriptive analysis of centrist support, pass rates, and content extremity
|
||||
for right-wing motions — with coalition control via opposition-only filtering,
|
||||
domain decomposition, and a baseline comparison.
|
||||
|
||||
Usage:
|
||||
uv run python analysis/right_wing/overton_breakpoint_analysis.py
|
||||
|
||||
Output:
|
||||
reports/overton_window/breakpoint_analysis.md
|
||||
reports/overton_window/breakpoint_figure_1.png
|
||||
reports/overton_window/breakpoint_figure_2.png
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import random
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import duckdb
|
||||
import matplotlib
|
||||
import numpy as np
|
||||
|
||||
matplotlib.use("Agg")
|
||||
import matplotlib.pyplot as plt
|
||||
import matplotlib.ticker as mticker
|
||||
|
||||
ROOT = Path(__file__).parent.parent.parent.resolve()
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(ROOT))
|
||||
|
||||
from analysis.config import CANONICAL_LEFT, CANONICAL_RIGHT, PARTY_COLOURS
|
||||
|
||||
CANONICAL_CENTRIST = frozenset({"VVD", "D66", "CDA", "NSC", "BBB", "CU"})
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
DB_PATH = str(ROOT / "data" / "motions.db")
|
||||
REPORTS_DIR = ROOT / "reports" / "overton_window"
|
||||
REPORTS_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
CANONICAL_CENTRIST_SET = set(CANONICAL_CENTRIST) # nb: config defines as frozenset
|
||||
CANONICAL_LEFT_SET = set(CANONICAL_LEFT)
|
||||
CANONICAL_RIGHT_SET = set(CANONICAL_RIGHT)
|
||||
|
||||
COALITION: dict[int, set[str]] = {
|
||||
2016: {"VVD", "PvdA"},
|
||||
2017: {"VVD", "PvdA"},
|
||||
2018: {"VVD", "CDA", "D66", "CU"},
|
||||
2019: {"VVD", "CDA", "D66", "CU"},
|
||||
2020: {"VVD", "CDA", "D66", "CU"},
|
||||
2021: {"VVD", "CDA", "D66", "CU"},
|
||||
2022: {"VVD", "D66", "CDA", "CU"},
|
||||
2023: {"VVD", "D66", "CDA", "CU"},
|
||||
2024: {"PVV", "VVD", "NSC", "BBB"},
|
||||
2025: {"PVV", "VVD", "NSC", "BBB"},
|
||||
2026: {"PVV", "VVD", "NSC", "BBB"},
|
||||
}
|
||||
|
||||
COALITION_NOTE = (
|
||||
"2016-2017: Rutte II (VVD/PvdA). "
|
||||
"2018-2021: Rutte III (VVD/CDA/D66/CU). "
|
||||
"2022-2023: Rutte IV (VVD/D66/CDA/CU). "
|
||||
"2024-2026: Schoof (PVV/VVD/NSC/BBB). "
|
||||
"2024 ambiguous: Schoof cabinet started July 2024; all 2024 motions are coded "
|
||||
"to the Schoof coalition. Coalition effect may be overestimated for early 2024."
|
||||
)
|
||||
|
||||
YEAR_MIN, YEAR_MAX = 2016, 2026
|
||||
BREAK_YEAR = 2024
|
||||
|
||||
|
||||
def _conn(read_only: bool = True) -> duckdb.DuckDBPyConnection:
|
||||
return duckdb.connect(DB_PATH, read_only=read_only)
|
||||
|
||||
|
||||
def cohens_d(x: np.ndarray, y: np.ndarray) -> float:
|
||||
"""Cohen's d effect size."""
|
||||
pooled = np.sqrt((np.var(x, ddof=1) + np.var(y, ddof=1)) / 2)
|
||||
if pooled == 0:
|
||||
return 0.0
|
||||
return (np.mean(y) - np.mean(x)) / pooled
|
||||
|
||||
|
||||
def compute_yearly_rw_metrics(con: duckdb.DuckDBPyConnection) -> dict[int, dict]:
|
||||
"""Yearly aggregates for classified right-wing motions.
|
||||
|
||||
Joins right_wing_motions with extremity_scores and motions (for pass rate).
|
||||
"""
|
||||
rows = con.execute("""
|
||||
SELECT
|
||||
r.motion_id,
|
||||
r.year,
|
||||
r.title,
|
||||
r.centrist_support,
|
||||
r.right_support,
|
||||
r.left_opposition,
|
||||
r.category,
|
||||
e.text_score AS extremity_score,
|
||||
m.voting_results,
|
||||
m.winning_margin
|
||||
FROM right_wing_motions r
|
||||
JOIN extremity_scores e ON r.motion_id = e.motion_id
|
||||
JOIN motions m ON r.motion_id = m.id
|
||||
WHERE r.classified = TRUE
|
||||
AND r.year IS NOT NULL
|
||||
AND e.text_score IS NOT NULL
|
||||
""").fetchall()
|
||||
|
||||
yearly: dict[int, dict[str, Any]] = {}
|
||||
for year in range(YEAR_MIN, YEAR_MAX + 1):
|
||||
yearly[year] = {
|
||||
"centrist_support": [],
|
||||
"right_support": [],
|
||||
"left_opposition": [],
|
||||
"extremity": [],
|
||||
"passed": [],
|
||||
"categories": [],
|
||||
"titles": [],
|
||||
"motion_ids": [],
|
||||
}
|
||||
|
||||
for mid, year, title, cs, rs, lo, cat, ext, vr_json, wm in rows:
|
||||
if year is None or year < YEAR_MIN or year > YEAR_MAX:
|
||||
continue
|
||||
yearly[year]["centrist_support"].append(cs if cs is not None else np.nan)
|
||||
yearly[year]["right_support"].append(rs if rs is not None else np.nan)
|
||||
yearly[year]["left_opposition"].append(lo if lo is not None else np.nan)
|
||||
yearly[year]["extremity"].append(ext if ext is not None else np.nan)
|
||||
yearly[year]["categories"].append(cat or "other")
|
||||
yearly[year]["titles"].append(title or "")
|
||||
yearly[year]["motion_ids"].append(mid)
|
||||
|
||||
if vr_json is not None:
|
||||
voting = json.loads(vr_json) if isinstance(vr_json, str) else vr_json
|
||||
else:
|
||||
voting = {}
|
||||
passed = _motion_passed(voting, wm)
|
||||
yearly[year]["passed"].append(passed)
|
||||
|
||||
return yearly
|
||||
|
||||
|
||||
def compute_yearly_baseline(con: duckdb.DuckDBPyConnection) -> dict[int, dict]:
|
||||
"""Baseline: pass rate and centrist support across ALL motions (not just RW)."""
|
||||
rows = con.execute("""
|
||||
SELECT
|
||||
m.id AS motion_id,
|
||||
EXTRACT(YEAR FROM m.date) AS year,
|
||||
m.voting_results,
|
||||
m.winning_margin
|
||||
FROM motions m
|
||||
WHERE m.date IS NOT NULL
|
||||
""").fetchall()
|
||||
|
||||
yearly: dict[int, dict] = {}
|
||||
for year in range(YEAR_MIN, YEAR_MAX + 1):
|
||||
yearly[year] = {"passed": [], "centrist_support": []}
|
||||
|
||||
for mid, year, vr_json, wm in rows:
|
||||
if year is None or int(year) < YEAR_MIN or int(year) > YEAR_MAX:
|
||||
continue
|
||||
year = int(year)
|
||||
if vr_json is not None:
|
||||
voting = json.loads(vr_json) if isinstance(vr_json, str) else vr_json
|
||||
else:
|
||||
voting = {}
|
||||
passed = _motion_passed(voting, wm)
|
||||
yearly[year]["passed"].append(passed)
|
||||
|
||||
centrist_rows = con.execute("""
|
||||
SELECT
|
||||
mv.motion_id,
|
||||
EXTRACT(YEAR FROM mv.date) AS year,
|
||||
mv.party,
|
||||
COUNT(*) AS n,
|
||||
mv.vote
|
||||
FROM mp_votes mv
|
||||
WHERE mv.party IS NOT NULL
|
||||
AND mv.date IS NOT NULL
|
||||
GROUP BY mv.motion_id, EXTRACT(YEAR FROM mv.date), mv.party, mv.vote
|
||||
""").fetchall()
|
||||
|
||||
motion_party_votes: dict[int, dict[str, dict[str, int]]] = {}
|
||||
for mid, year, party, n, vote in centrist_rows:
|
||||
year = int(year)
|
||||
if year < YEAR_MIN or year > YEAR_MAX:
|
||||
continue
|
||||
mv = motion_party_votes.setdefault(mid, {})
|
||||
pv = mv.setdefault(party, {"voor": 0, "tegen": 0, "afwezig": 0})
|
||||
pv[vote] = pv.get(vote, 0) + n
|
||||
|
||||
motion_year_map: dict[int, int] = {}
|
||||
for mid, year, _, _, _ in centrist_rows:
|
||||
year = int(year)
|
||||
if YEAR_MIN <= year <= YEAR_MAX:
|
||||
motion_year_map[mid] = year
|
||||
|
||||
for mid, votes in motion_party_votes.items():
|
||||
year = motion_year_map.get(mid)
|
||||
if year is None:
|
||||
continue
|
||||
cs = _support_ratio(votes, CANONICAL_CENTRIST_SET)
|
||||
if cs is not None:
|
||||
yearly[year]["centrist_support"].append(cs)
|
||||
|
||||
return yearly
|
||||
|
||||
|
||||
def _motion_passed(
|
||||
voting: dict[str, str], winning_margin: float | None = None
|
||||
) -> bool | None:
|
||||
"""Determine if a motion passed from voting_results or winning_margin."""
|
||||
if winning_margin is not None:
|
||||
return winning_margin > 0
|
||||
voor = sum(1 for v in voting.values() if v == "voor")
|
||||
tegen = sum(1 for v in voting.values() if v == "tegen")
|
||||
if voor + tegen == 0:
|
||||
return None
|
||||
return voor > tegen
|
||||
|
||||
|
||||
def _support_ratio(
|
||||
votes: dict[str, dict[str, int]], parties: set[str]
|
||||
) -> float | None:
|
||||
"""Compute support ratio (fraction of parties voting 'voor')."""
|
||||
total = 0
|
||||
supportive = 0
|
||||
for party, pv in votes.items():
|
||||
if party not in parties:
|
||||
continue
|
||||
tv = pv.get("voor", 0) + pv.get("tegen", 0) + pv.get("afwezig", 0)
|
||||
if tv == 0:
|
||||
continue
|
||||
total += 1
|
||||
if pv.get("voor", 0) / tv >= 0.5:
|
||||
supportive += 1
|
||||
if total == 0:
|
||||
return None
|
||||
return supportive / total
|
||||
|
||||
|
||||
def build_party_name_map(con: duckdb.DuckDBPyConnection) -> dict[str, str]:
|
||||
"""Build mapping: last name -> party from mp_metadata."""
|
||||
rows = con.execute("""
|
||||
SELECT mp_name, party, van, tot_en_met
|
||||
FROM mp_metadata
|
||||
WHERE party IS NOT NULL
|
||||
ORDER BY tot_en_met DESC NULLS LAST, van DESC NULLS LAST
|
||||
""").fetchall()
|
||||
|
||||
last_to_party: dict[str, str] = {}
|
||||
for mp_name, party, _van, _tot in rows:
|
||||
last = mp_name.split(",")[0].strip()
|
||||
if last not in last_to_party:
|
||||
last_to_party[last] = party
|
||||
return last_to_party
|
||||
|
||||
|
||||
def parse_lead_submitter(
|
||||
title: str, name_party_map: dict[str, str]
|
||||
) -> tuple[str | None, str | None]:
|
||||
"""Parse the lead submitter from a motion title and map to party.
|
||||
|
||||
Returns (parsed_name, party) or (None, None).
|
||||
"""
|
||||
if not title:
|
||||
return None, None
|
||||
|
||||
patterns = [
|
||||
r"(?:Gewijzigde|Nader\s+gewijzigde)?\s*Motie\s+van\s+het\s+lid\s+(.+?)\s+(?:c\.s\.\s+)?over\b",
|
||||
r"(?:Gewijzigde|Nader\s+gewijzigde)?\s*Motie\s+van\s+de\s+leden\s+(.+?)\s+(?:c\.s\.\s+)?over\b",
|
||||
r"Amendement\s+van\s+het\s+lid\s+(.+?)\s+over\b",
|
||||
r"Amendement\s+van\s+de\s+leden\s+(.+?)\s+over\b",
|
||||
]
|
||||
|
||||
for pat in patterns:
|
||||
m = re.search(pat, title)
|
||||
if m:
|
||||
submitter_str = m.group(1).strip()
|
||||
parts = submitter_str.split(" en ")
|
||||
first_name = parts[0].strip()
|
||||
first_name = re.sub(r"\s+c\.s\.", "", first_name).strip()
|
||||
if not first_name:
|
||||
continue
|
||||
party = name_party_map.get(first_name)
|
||||
return first_name, party
|
||||
|
||||
return None, None
|
||||
|
||||
|
||||
def compute_opposition_metrics(
|
||||
yearly_raw: dict[int, dict], name_party_map: dict[str, str]
|
||||
) -> dict[int, dict]:
|
||||
"""Recompute yearly metrics for opposition-only right-wing motions.
|
||||
|
||||
Filters motions where the lead submitter's party is NOT in the coalition.
|
||||
"""
|
||||
opp: dict[int, dict[str, list]] = {}
|
||||
for year in range(YEAR_MIN, YEAR_MAX + 1):
|
||||
opp[year] = {
|
||||
"centrist_support": [],
|
||||
"extremity": [],
|
||||
"passed": [],
|
||||
"n": 0,
|
||||
}
|
||||
|
||||
coalition = COALITION
|
||||
|
||||
year_titles_map: dict[int, list[int]] = {}
|
||||
for year, d in yearly_raw.items():
|
||||
year_titles_map[year] = list(range(len(d["titles"])))
|
||||
|
||||
for year, d in yearly_raw.items():
|
||||
coal = coalition.get(year, set())
|
||||
for idx in range(len(d["titles"])):
|
||||
title = d["titles"][idx]
|
||||
submitter_name, submitter_party = parse_lead_submitter(title, name_party_map)
|
||||
|
||||
if submitter_party is None:
|
||||
continue
|
||||
|
||||
if submitter_party in coal:
|
||||
continue
|
||||
|
||||
opp[year]["centrist_support"].append(d["centrist_support"][idx])
|
||||
opp[year]["extremity"].append(d["extremity"][idx])
|
||||
opp[year]["passed"].append(d["passed"][idx])
|
||||
opp[year]["n"] += 1
|
||||
|
||||
return opp
|
||||
|
||||
|
||||
def compute_domain_metrics(
|
||||
yearly_raw: dict[int, dict],
|
||||
) -> tuple[dict[int, dict], dict[int, dict]]:
|
||||
"""Split into migration and non-migration domains."""
|
||||
mig: dict[int, dict[str, list]] = {}
|
||||
non_mig: dict[int, dict[str, list]] = {}
|
||||
|
||||
for year in range(YEAR_MIN, YEAR_MAX + 1):
|
||||
mig[year] = {"centrist_support": [], "extremity": [], "passed": [], "n": 0}
|
||||
non_mig[year] = {"centrist_support": [], "extremity": [], "passed": [], "n": 0}
|
||||
|
||||
for year, d in yearly_raw.items():
|
||||
for idx in range(len(d["titles"])):
|
||||
cat = d["categories"][idx]
|
||||
target = mig if cat == "asiel/vreemdelingen" else non_mig
|
||||
target[year]["centrist_support"].append(d["centrist_support"][idx])
|
||||
target[year]["extremity"].append(d["extremity"][idx])
|
||||
target[year]["passed"].append(d["passed"][idx])
|
||||
target[year]["n"] += 1
|
||||
|
||||
return mig, non_mig
|
||||
|
||||
|
||||
def compute_extremity_stratified(
|
||||
yearly_raw: dict[int, dict],
|
||||
) -> dict[str, dict[str, list]]:
|
||||
"""Compute pass rate per extremity bucket, pre vs post 2024."""
|
||||
buckets = {
|
||||
"1-2 (mild)": [],
|
||||
"2-3 (moderate)": [],
|
||||
"3-4 (high)": [],
|
||||
"4-5 (extreme)": [],
|
||||
}
|
||||
|
||||
pre_post: dict[str, dict[str, list]] = {
|
||||
"pre-2024": {b: [] for b in buckets},
|
||||
"post-2024": {b: [] for b in buckets},
|
||||
}
|
||||
|
||||
for year, d in yearly_raw.items():
|
||||
period = "pre-2024" if year < BREAK_YEAR else "post-2024"
|
||||
for idx in range(len(d["titles"])):
|
||||
ext = d["extremity"][idx]
|
||||
passed = d["passed"][idx]
|
||||
if np.isnan(ext) or passed is None:
|
||||
continue
|
||||
if ext < 2:
|
||||
b = "1-2 (mild)"
|
||||
elif ext < 3:
|
||||
b = "2-3 (moderate)"
|
||||
elif ext < 4:
|
||||
b = "3-4 (high)"
|
||||
else:
|
||||
b = "4-5 (extreme)"
|
||||
pre_post[period][b].append(passed)
|
||||
|
||||
return pre_post
|
||||
|
||||
|
||||
def yearly_summary(yearly: dict[int, dict]) -> dict[int, dict]:
|
||||
"""Compute mean values from raw lists."""
|
||||
summary: dict[int, dict] = {}
|
||||
for year, d in yearly.items():
|
||||
s: dict[str, Any] = {}
|
||||
for key in ["centrist_support", "right_support", "left_opposition", "extremity"]:
|
||||
vals = [v for v in d.get(key, []) if not (isinstance(v, float) and np.isnan(v))]
|
||||
s[f"mean_{key}"] = np.mean(vals) if vals else float("nan")
|
||||
passes = [p for p in d.get("passed", []) if p is not None]
|
||||
s["pass_rate"] = sum(passes) / len(passes) if passes else float("nan")
|
||||
s["n"] = len(d.get("motion_ids", d.get("centrist_support", [])))
|
||||
summary[year] = s
|
||||
return summary
|
||||
|
||||
|
||||
def sample_audit(yearly_raw: dict[int, dict]) -> list[dict]:
|
||||
"""Stratified random sample: 5 motions per extremity bucket, 20 total."""
|
||||
bucket_motions: dict[str, list[int]] = {
|
||||
"1-2 (mild)": [],
|
||||
"2-3 (moderate)": [],
|
||||
"3-4 (high)": [],
|
||||
"4-5 (extreme)": [],
|
||||
}
|
||||
|
||||
all_motions: list[dict] = []
|
||||
for year, d in yearly_raw.items():
|
||||
for idx in range(len(d["titles"])):
|
||||
ext = d["extremity"][idx]
|
||||
if np.isnan(ext):
|
||||
continue
|
||||
if ext < 2:
|
||||
b = "1-2 (mild)"
|
||||
elif ext < 3:
|
||||
b = "2-3 (moderate)"
|
||||
elif ext < 4:
|
||||
b = "3-4 (high)"
|
||||
else:
|
||||
b = "4-5 (extreme)"
|
||||
bucket_motions[b].append(len(all_motions))
|
||||
all_motions.append({
|
||||
"year": year,
|
||||
"title": d["titles"][idx],
|
||||
"category": d["categories"][idx],
|
||||
"extremity": ext,
|
||||
})
|
||||
|
||||
rng = random.Random(42)
|
||||
sampled: list[dict] = []
|
||||
for bucket_name, indices in bucket_motions.items():
|
||||
n_sample = min(5, len(indices))
|
||||
chosen = rng.sample(indices, n_sample) if indices else []
|
||||
for idx in chosen:
|
||||
m = all_motions[idx].copy()
|
||||
m["bucket"] = bucket_name
|
||||
sampled.append(m)
|
||||
|
||||
sampled.sort(key=lambda x: (x["bucket"], x["extremity"]))
|
||||
return sampled
|
||||
|
||||
|
||||
def print_audit(sampled: list[dict]) -> None:
|
||||
"""Display sampled motions for manual extremity audit."""
|
||||
print("\n" + "=" * 80)
|
||||
print(" MANUAL EXTREMITY AUDIT")
|
||||
print("=" * 80)
|
||||
print()
|
||||
print("For each motion below, judge whether you agree with the LLM-assigned extremity bucket.")
|
||||
print("Also note: does the score reflect stylistic extremity (language) or material impact (policy)?")
|
||||
print()
|
||||
|
||||
from itertools import groupby
|
||||
|
||||
for bucket, group in groupby(sampled, key=lambda m: m["bucket"]):
|
||||
group_list = list(group)
|
||||
print(f"\n--- {bucket} (n={len(group_list)} sampled) ---")
|
||||
for i, m in enumerate(group_list, 1):
|
||||
title = m["title"][:120]
|
||||
print(f"\n [{i}] Year={m['year']} | Category={m['category']}")
|
||||
print(f" LLM Score: {m['extremity']}")
|
||||
print(f" Title: {title}")
|
||||
print(f" Agree? [Y/N] Driven by: Language / Policy / Both")
|
||||
|
||||
print("\n" + "=" * 80)
|
||||
print(" END OF AUDIT — Record agreement rate and note systematic biases")
|
||||
print("=" * 80)
|
||||
|
||||
|
||||
def create_figure_1(
|
||||
yearly_sum: dict[int, dict],
|
||||
opp_sum: dict[int, dict],
|
||||
mig_sum: dict[int, dict],
|
||||
non_mig_sum: dict[int, dict],
|
||||
baseline_sum: dict[int, dict],
|
||||
) -> str:
|
||||
"""Figure 1: Centrist support + Pass rate over time (2 panels)."""
|
||||
years = sorted(yearly_sum.keys())
|
||||
years_arr = np.array(years)
|
||||
|
||||
def _vals(summary, key):
|
||||
return np.array([summary[y].get(key, np.nan) for y in years])
|
||||
|
||||
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10), sharex=True)
|
||||
|
||||
colour_all = "grey"
|
||||
colour_rw = "#002366"
|
||||
colour_opp = "#E53935"
|
||||
colour_mig = "#6A1B9A"
|
||||
colour_non_mig = "#4CAF50"
|
||||
colour_baseline = "#9E9E9E"
|
||||
|
||||
# Panel A: Centrist support
|
||||
ax1.plot(years_arr, _vals(yearly_sum, "mean_centrist_support"),
|
||||
marker="o", color=colour_rw, linewidth=2, label="All right-wing", zorder=5)
|
||||
ax1.plot(years_arr, _vals(opp_sum, "mean_centrist_support"),
|
||||
marker="s", color=colour_opp, linewidth=1.5, linestyle="--", label="Opposition-only RW", zorder=4)
|
||||
ax1.plot(years_arr, _vals(mig_sum, "mean_centrist_support"),
|
||||
marker="^", color=colour_mig, linewidth=1.5, linestyle=":", label="Migration", zorder=3)
|
||||
ax1.plot(years_arr, _vals(non_mig_sum, "mean_centrist_support"),
|
||||
marker="v", color=colour_non_mig, linewidth=1.5, linestyle="-.", label="Non-migration", zorder=2)
|
||||
ax1.plot(years_arr, _vals(baseline_sum, "mean_centrist_support"),
|
||||
color=colour_baseline, linewidth=1, linestyle="dashed", alpha=0.7, zorder=1, label="All motions (baseline)")
|
||||
|
||||
ax1.axvline(x=BREAK_YEAR - 0.5, color="black", linestyle=":", alpha=0.5, linewidth=1)
|
||||
ax1.annotate("2024", xy=(BREAK_YEAR - 0.3, ax1.get_ylim()[1] * 0.95 if ax1.get_ylim()[1] > 0 else 0.95),
|
||||
fontsize=9, color="black", alpha=0.7)
|
||||
|
||||
ax1.set_ylabel("Mean Centrist Support")
|
||||
ax1.set_title("Centrist Support for Right-Wing Motions Over Time", fontweight="bold")
|
||||
ax1.legend(loc="lower right", fontsize=8, ncol=2)
|
||||
ax1.set_ylim(0, 1.05)
|
||||
ax1.grid(True, alpha=0.3)
|
||||
|
||||
# Panel B: Pass rate
|
||||
ax2.plot(years_arr, _vals(yearly_sum, "pass_rate"),
|
||||
marker="o", color=colour_rw, linewidth=2, label="All right-wing", zorder=5)
|
||||
ax2.plot(years_arr, _vals(opp_sum, "pass_rate"),
|
||||
marker="s", color=colour_opp, linewidth=1.5, linestyle="--", label="Opposition-only RW", zorder=4)
|
||||
ax2.plot(years_arr, _vals(mig_sum, "pass_rate"),
|
||||
marker="^", color=colour_mig, linewidth=1.5, linestyle=":", label="Migration", zorder=3)
|
||||
ax2.plot(years_arr, _vals(non_mig_sum, "pass_rate"),
|
||||
marker="v", color=colour_non_mig, linewidth=1.5, linestyle="-.", label="Non-migration", zorder=2)
|
||||
ax2.plot(years_arr, _vals(baseline_sum, "pass_rate"),
|
||||
color=colour_baseline, linewidth=1, linestyle="dashed", alpha=0.7, zorder=1, label="All motions (baseline)")
|
||||
|
||||
ax2.axvline(x=BREAK_YEAR - 0.5, color="black", linestyle=":", alpha=0.5, linewidth=1)
|
||||
ax2.annotate("2024", xy=(BREAK_YEAR - 0.3, ax2.get_ylim()[1] * 0.95 if ax2.get_ylim()[1] > 0 else 0.95),
|
||||
fontsize=9, color="black", alpha=0.7)
|
||||
|
||||
ax2.set_xlabel("Year")
|
||||
ax2.set_ylabel("Pass Rate")
|
||||
ax2.set_title("Pass Rate of Right-Wing Motions Over Time", fontweight="bold")
|
||||
ax2.legend(loc="lower right", fontsize=8, ncol=2)
|
||||
ax2.set_ylim(0, 1.05)
|
||||
ax2.grid(True, alpha=0.3)
|
||||
|
||||
ax2.set_xticks(years_arr)
|
||||
ax2.set_xticklabels([str(y) for y in years], rotation=45)
|
||||
|
||||
plt.tight_layout()
|
||||
path = str(REPORTS_DIR / "breakpoint_figure_1.png")
|
||||
fig.savefig(path, dpi=150, bbox_inches="tight")
|
||||
plt.close(fig)
|
||||
logger.info("Saved Figure 1 to %s", path)
|
||||
return path
|
||||
|
||||
|
||||
def create_figure_2(
|
||||
yearly_sum: dict[int, dict],
|
||||
opp_sum: dict[int, dict],
|
||||
mig_sum: dict[int, dict],
|
||||
non_mig_sum: dict[int, dict],
|
||||
ext_stratified: dict[str, dict[str, list]],
|
||||
) -> str:
|
||||
"""Figure 2: Extremity over time + Extremity-stratified pass rate (2 panels)."""
|
||||
years = sorted(yearly_sum.keys())
|
||||
years_arr = np.array(years)
|
||||
|
||||
def _vals(summary, key):
|
||||
return np.array([summary[y].get(key, np.nan) for y in years])
|
||||
|
||||
colour_rw = "#002366"
|
||||
colour_opp = "#E53935"
|
||||
colour_mig = "#6A1B9A"
|
||||
colour_non_mig = "#4CAF50"
|
||||
|
||||
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 6))
|
||||
|
||||
# Panel C: Mean extremity over time
|
||||
ax1.plot(years_arr, _vals(yearly_sum, "mean_extremity"),
|
||||
marker="o", color=colour_rw, linewidth=2, label="All right-wing", zorder=5)
|
||||
ax1.plot(years_arr, _vals(opp_sum, "mean_extremity"),
|
||||
marker="s", color=colour_opp, linewidth=1.5, linestyle="--", label="Opposition-only RW", zorder=4)
|
||||
ax1.plot(years_arr, _vals(mig_sum, "mean_extremity"),
|
||||
marker="^", color=colour_mig, linewidth=1.5, linestyle=":", label="Migration", zorder=3)
|
||||
ax1.plot(years_arr, _vals(non_mig_sum, "mean_extremity"),
|
||||
marker="v", color=colour_non_mig, linewidth=1.5, linestyle="-.", label="Non-migration", zorder=2)
|
||||
|
||||
ax1.axvline(x=BREAK_YEAR - 0.5, color="black", linestyle=":", alpha=0.5, linewidth=1)
|
||||
ax1.annotate("2024", xy=(BREAK_YEAR - 0.3, ax1.get_ylim()[1] * 0.95 if ax1.get_ylim()[1] > 0 else 4.5),
|
||||
fontsize=9, color="black", alpha=0.7)
|
||||
|
||||
ax1.set_xlabel("Year")
|
||||
ax1.set_ylabel("Mean Extremity Score")
|
||||
ax1.set_title("Content Extremity Over Time", fontweight="bold")
|
||||
ax1.legend(loc="upper left", fontsize=8)
|
||||
ax1.grid(True, alpha=0.3)
|
||||
ax1.set_xticks(years_arr)
|
||||
ax1.set_xticklabels([str(y) for y in years], rotation=45)
|
||||
|
||||
# Panel D: Extremity-stratified pass rate (grouped bars)
|
||||
bucket_order = ["1-2 (mild)", "2-3 (moderate)", "3-4 (high)", "4-5 (extreme)"]
|
||||
bucket_labels = ["1-2\nmild", "2-3\nmoderate", "3-4\nhigh", "4-5\nextreme"]
|
||||
bucket_colours = ["#81C784", "#FFB74D", "#E57373", "#BA68C8"]
|
||||
|
||||
x = np.arange(len(bucket_order))
|
||||
width = 0.35
|
||||
|
||||
pre_rates = []
|
||||
pre_ns = []
|
||||
post_rates = []
|
||||
post_ns = []
|
||||
|
||||
for b in bucket_order:
|
||||
pre_data = ext_stratified["pre-2024"].get(b, [])
|
||||
post_data = ext_stratified["post-2024"].get(b, [])
|
||||
pre_rates.append(np.mean(pre_data) if pre_data else 0)
|
||||
pre_ns.append(len(pre_data))
|
||||
post_rates.append(np.mean(post_data) if post_data else 0)
|
||||
post_ns.append(len(post_data))
|
||||
|
||||
bars_pre = ax2.bar(x - width / 2, pre_rates, width, label="Pre-2024 (2016-2023)",
|
||||
color="#90CAF9", edgecolor="black", alpha=0.9)
|
||||
bars_post = ax2.bar(x + width / 2, post_rates, width, label="Post-2024 (2024-2026)",
|
||||
color="#1E88E5", edgecolor="black", alpha=0.9)
|
||||
|
||||
for i, (bar, n) in enumerate(zip(bars_pre, pre_ns)):
|
||||
ax2.text(bar.get_x() + bar.get_width() / 2, bar.get_height() + 0.01,
|
||||
f"N={n}", ha="center", va="bottom", fontsize=8, fontweight="bold")
|
||||
for i, (bar, n) in enumerate(zip(bars_post, post_ns)):
|
||||
ax2.text(bar.get_x() + bar.get_width() / 2, bar.get_height() + 0.01,
|
||||
f"N={n}", ha="center", va="bottom", fontsize=8, fontweight="bold")
|
||||
|
||||
ax2.set_xticks(x)
|
||||
ax2.set_xticklabels(bucket_labels)
|
||||
ax2.set_ylabel("Pass Rate")
|
||||
ax2.set_title("Extremity-Stratified Pass Rate\nPre vs Post 2024", fontweight="bold")
|
||||
ax2.legend(fontsize=8)
|
||||
ax2.set_ylim(0, 1.05)
|
||||
ax2.grid(True, alpha=0.3, axis="y")
|
||||
|
||||
plt.tight_layout()
|
||||
path = str(REPORTS_DIR / "breakpoint_figure_2.png")
|
||||
fig.savefig(path, dpi=150, bbox_inches="tight")
|
||||
plt.close(fig)
|
||||
logger.info("Saved Figure 2 to %s", path)
|
||||
return path
|
||||
|
||||
|
||||
def generate_report(
|
||||
yearly_sum: dict[int, dict],
|
||||
opp_sum: dict[int, dict],
|
||||
mig_sum: dict[int, dict],
|
||||
non_mig_sum: dict[int, dict],
|
||||
baseline_sum: dict[int, dict],
|
||||
ext_stratified: dict[str, dict[str, list]],
|
||||
yearly_raw: dict[int, dict],
|
||||
opp_raw: dict[int, dict],
|
||||
fig1_path: str,
|
||||
fig2_path: str,
|
||||
audit_sample: list[dict],
|
||||
audit_notes: str = "",
|
||||
) -> str:
|
||||
"""Generate the breakpoint analysis markdown report."""
|
||||
years = sorted(yearly_sum.keys())
|
||||
|
||||
def _val(summary, year, key):
|
||||
return summary[year].get(key, np.nan)
|
||||
|
||||
# Pre/post 2024 comparisons
|
||||
pre_years = [y for y in years if y < BREAK_YEAR]
|
||||
post_years = [y for y in years if y >= BREAK_YEAR]
|
||||
|
||||
# Pooled pre/post values for Cohen's d
|
||||
rw_pre_cs = []
|
||||
rw_post_cs = []
|
||||
rw_pre_pr = []
|
||||
rw_post_pr = []
|
||||
rw_pre_ext = []
|
||||
rw_post_ext = []
|
||||
|
||||
opp_pre_cs = []
|
||||
opp_post_cs = []
|
||||
opp_pre_pr = []
|
||||
opp_post_pr = []
|
||||
opp_pre_ext = []
|
||||
opp_post_ext = []
|
||||
|
||||
for y, d in yearly_raw.items():
|
||||
for idx in range(len(d.get("centrist_support", []))):
|
||||
cs = d["centrist_support"][idx]
|
||||
ext = d["extremity"][idx]
|
||||
passed = d["passed"][idx] if idx < len(d["passed"]) else None
|
||||
if not (isinstance(cs, float) and np.isnan(cs)):
|
||||
if y < BREAK_YEAR:
|
||||
rw_pre_cs.append(cs)
|
||||
else:
|
||||
rw_post_cs.append(cs)
|
||||
if not (isinstance(ext, float) and np.isnan(ext)):
|
||||
if y < BREAK_YEAR:
|
||||
rw_pre_ext.append(ext)
|
||||
else:
|
||||
rw_post_ext.append(ext)
|
||||
if passed is not None:
|
||||
if y < BREAK_YEAR:
|
||||
rw_pre_pr.append(1.0 if passed else 0.0)
|
||||
else:
|
||||
rw_post_pr.append(1.0 if passed else 0.0)
|
||||
|
||||
for y, d in opp_raw.items():
|
||||
for idx in range(len(d.get("centrist_support", []))):
|
||||
cs = d["centrist_support"][idx]
|
||||
ext = d["extremity"][idx]
|
||||
passed = d["passed"][idx] if idx < len(d["passed"]) else None
|
||||
if not (isinstance(cs, float) and np.isnan(cs)):
|
||||
if y < BREAK_YEAR:
|
||||
opp_pre_cs.append(cs)
|
||||
else:
|
||||
opp_post_cs.append(cs)
|
||||
if not (isinstance(ext, float) and np.isnan(ext)):
|
||||
if y < BREAK_YEAR:
|
||||
opp_pre_ext.append(ext)
|
||||
else:
|
||||
opp_post_ext.append(ext)
|
||||
if passed is not None:
|
||||
if y < BREAK_YEAR:
|
||||
opp_pre_pr.append(1.0 if passed else 0.0)
|
||||
else:
|
||||
opp_post_pr.append(1.0 if passed else 0.0)
|
||||
|
||||
d_cs = cohens_d(np.array(rw_pre_cs), np.array(rw_post_cs))
|
||||
d_pr = cohens_d(np.array(rw_pre_pr), np.array(rw_post_pr))
|
||||
d_ext = cohens_d(np.array(rw_pre_ext), np.array(rw_post_ext))
|
||||
|
||||
d_opp_cs = cohens_d(np.array(opp_pre_cs), np.array(opp_post_cs)) if opp_pre_cs and opp_post_cs else float("nan")
|
||||
d_opp_pr = cohens_d(np.array(opp_pre_pr), np.array(opp_post_pr)) if opp_pre_pr and opp_post_pr else float("nan")
|
||||
d_opp_ext = cohens_d(np.array(opp_pre_ext), np.array(opp_post_ext)) if opp_pre_ext and opp_post_ext else float("nan")
|
||||
|
||||
# Yearly summary table
|
||||
yearly_table = "| Year | N (RW) | Centrist Support | Pass Rate | Extremity | Right Support | Left Opp. |\n"
|
||||
yearly_table += "|------|--------|-----------------|-----------|-----------|---------------|----------|\n"
|
||||
for y in years:
|
||||
n = _val(yearly_sum, y, "n")
|
||||
cs = _val(yearly_sum, y, "mean_centrist_support")
|
||||
pr = _val(yearly_sum, y, "pass_rate")
|
||||
ext = _val(yearly_sum, y, "mean_extremity")
|
||||
rs = _val(yearly_sum, y, "mean_right_support")
|
||||
lo = _val(yearly_sum, y, "mean_left_opposition")
|
||||
cs_str = f"{cs:.3f}" if not np.isnan(cs) else "N/A"
|
||||
pr_str = f"{pr:.3f}" if not np.isnan(pr) else "N/A"
|
||||
ext_str = f"{ext:.2f}" if not np.isnan(ext) else "N/A"
|
||||
rs_str = f"{rs:.3f}" if not np.isnan(rs) else "N/A"
|
||||
lo_str = f"{lo:.3f}" if not np.isnan(lo) else "N/A"
|
||||
yearly_table += f"| {y} | {int(n)} | {cs_str} | {pr_str} | {ext_str} | {rs_str} | {lo_str} |\n"
|
||||
|
||||
# Extremity-stratified table
|
||||
bucket_order = ["1-2 (mild)", "2-3 (moderate)", "3-4 (high)", "4-5 (extreme)"]
|
||||
ext_table = "| Bucket | Period | N | Pass Rate | Δ (post-pre) |\n"
|
||||
ext_table += "|--------|--------|---|-----------|-------------|\n"
|
||||
for b in bucket_order:
|
||||
pre_data = ext_stratified["pre-2024"].get(b, [])
|
||||
post_data = ext_stratified["post-2024"].get(b, [])
|
||||
pre_pr = np.mean(pre_data) if pre_data else float("nan")
|
||||
post_pr = np.mean(post_data) if post_data else float("nan")
|
||||
delta = post_pr - pre_pr if not np.isnan(pre_pr) and not np.isnan(post_pr) else float("nan")
|
||||
ext_table += f"| {b} | Pre-2024 | {len(pre_data)} | {pre_pr:.3f} | |\n"
|
||||
ext_table += f"| | Post-2024 | {len(post_data)} | {post_pr:.3f} | {delta:+.3f} |\n"
|
||||
|
||||
# Audit table
|
||||
audit_table = "| # | Year | Category | LLM Score | Bucket | Agreed? | Driver |\n"
|
||||
audit_table += "|---|------|----------|-----------|--------|---------|--------|\n"
|
||||
for i, m in enumerate(audit_sample, 1):
|
||||
audit_table += f"| {i} | {m['year']} | {m['category']} | {m['extremity']} | {m['bucket']} | | |\n"
|
||||
|
||||
lines = [
|
||||
"# Overton Window Breakpoint Analysis",
|
||||
"",
|
||||
"**Goal:** Quantify the 2024 structural break in centrist support, pass rates,",
|
||||
"and content extremity for right-wing motions in the Tweede Kamer.",
|
||||
"",
|
||||
"**Analysis period:** 2016–2026",
|
||||
"**Right-wing parties:** PVV, FVD, JA21, SGP",
|
||||
"**Centrist parties:** VVD, D66, CDA, NSC, BBB, CU",
|
||||
"**Left parties:** PvdA, GL, SP, PvdD, Volt, DENK, Bij1",
|
||||
"",
|
||||
"---",
|
||||
"",
|
||||
"## 1. Yearly Aggregate Metrics (All Right-Wing Motions)",
|
||||
"",
|
||||
yearly_table,
|
||||
"",
|
||||
"## 2. Pre/Post 2024 Comparison",
|
||||
"",
|
||||
f"**Break year:** {BREAK_YEAR}",
|
||||
"",
|
||||
"### All right-wing motions",
|
||||
"",
|
||||
f"| Metric | Pre-2024 Mean | Post-2024 Mean | Δ | Cohen's d |",
|
||||
f"|--------|--------------|---------------|-----|-----------|",
|
||||
f"| Centrist Support | {np.mean(rw_pre_cs):.3f} | {np.mean(rw_post_cs):.3f} | {np.mean(rw_post_cs) - np.mean(rw_pre_cs):+.3f} | {d_cs:+.2f} |",
|
||||
f"| Pass Rate | {np.mean(rw_pre_pr):.3f} | {np.mean(rw_post_pr):.3f} | {np.mean(rw_post_pr) - np.mean(rw_pre_pr):+.3f} | {d_pr:+.2f} |",
|
||||
f"| Extremity | {np.mean(rw_pre_ext):.2f} | {np.mean(rw_post_ext):.2f} | {np.mean(rw_post_ext) - np.mean(rw_pre_ext):+.2f} | {d_ext:+.2f} |",
|
||||
"",
|
||||
f"**Interpretation:** Cohen's d values quantify effect sizes (|d| < 0.2 small, 0.5 medium, > 0.8 large).",
|
||||
f"These are descriptive, not inferential — with only {len(pre_years)} pre-2024 years and {len(post_years)} post-2024 years, statistical significance is not claimed.",
|
||||
"",
|
||||
"### Opposition-only right-wing motions",
|
||||
"",
|
||||
f"| Metric | Pre-2024 Mean | Post-2024 Mean | Δ | Cohen's d | N pre / N post |",
|
||||
f"|--------|--------------|---------------|-----|-----------|---------------|",
|
||||
f"| Centrist Support | {np.mean(opp_pre_cs):.3f} | {np.mean(opp_post_cs):.3f} | {np.mean(opp_post_cs) - np.mean(opp_pre_cs):+.3f} | {d_opp_cs:+.2f} | {len(opp_pre_cs)} / {len(opp_post_cs)} |",
|
||||
f"| Pass Rate | {np.mean(opp_pre_pr):.3f} | {np.mean(opp_post_pr):.3f} | {np.mean(opp_post_pr) - np.mean(opp_pre_pr):+.3f} | {d_opp_pr:+.2f} | {len(opp_pre_pr)} / {len(opp_post_pr)} |",
|
||||
f"| Extremity | {np.mean(opp_pre_ext):.2f} | {np.mean(opp_post_ext):.2f} | {np.mean(opp_post_ext) - np.mean(opp_pre_ext):+.2f} | {d_opp_ext:+.2f} | {len(opp_pre_ext)} / {len(opp_post_ext)} |",
|
||||
"",
|
||||
"**Interpretation gate:** If opposition metrics also rise post-2024, the shift is not",
|
||||
"purely coalition-driven. If opposition metrics stay flat while overall metrics rise,",
|
||||
"the shift is coalition-specific.",
|
||||
"",
|
||||
"## 3. Coalition Composition",
|
||||
"",
|
||||
COALITION_NOTE,
|
||||
"",
|
||||
"Submitter party is parsed from motion title prefixes",
|
||||
"(e.g., \"Motie van het lid Wilders over ...\"). Only the lead submitter's party is",
|
||||
"considered. Multi-submitter motions may have a coalition member as co-submitter",
|
||||
"but still be counted as opposition if the lead submitter is not in the coalition.",
|
||||
"",
|
||||
"## 4. Domain Decomposition",
|
||||
"",
|
||||
"Migration = category `asiel/vreemdelingen`. Non-migration = all other categories.",
|
||||
"",
|
||||
"| Domain | Pre-2024 Mean CS | Post-2024 Mean CS | Δ CS | Pre-2024 PR | Post-2024 PR | Δ PR |",
|
||||
"|--------|-----------------|------------------|------|-------------|-------------|------|",
|
||||
]
|
||||
|
||||
for domain_name, domain_sum in [("Migration", mig_sum), ("Non-migration", non_mig_sum)]:
|
||||
pre_cs = np.nanmean([_val(domain_sum, y, "mean_centrist_support") for y in pre_years])
|
||||
post_cs = np.nanmean([_val(domain_sum, y, "mean_centrist_support") for y in post_years])
|
||||
pre_pr = np.nanmean([_val(domain_sum, y, "pass_rate") for y in pre_years])
|
||||
post_pr = np.nanmean([_val(domain_sum, y, "pass_rate") for y in post_years])
|
||||
lines.append(
|
||||
f"| {domain_name} | {pre_cs:.3f} | {post_cs:.3f} | {post_cs - pre_cs:+.3f} | "
|
||||
f"{pre_pr:.3f} | {post_pr:.3f} | {post_pr - pre_pr:+.3f} |"
|
||||
)
|
||||
|
||||
lines += [
|
||||
"",
|
||||
"## 5. Extremity-Stratified Pass Rate",
|
||||
"",
|
||||
ext_table,
|
||||
"",
|
||||
"**Key test:** If high-extremity motions (3–5) went from low pass rate to high pass rate",
|
||||
"while mild motions stayed flat, centrists are more tolerant of extreme content —",
|
||||
"direct Overton shift evidence. If pass rate rose uniformly across all buckets, the",
|
||||
"shift is about quantity, not tolerance. If only the 1–2 bucket rose, right-wing",
|
||||
"parties filed milder motions post-2024 and the 'shift' is illusory.",
|
||||
"",
|
||||
"## 6. Manual Extremity Audit",
|
||||
"",
|
||||
audit_notes,
|
||||
"",
|
||||
audit_table,
|
||||
"",
|
||||
"## 7. Limitations",
|
||||
"",
|
||||
"- **Small-N time series:** 8 pre-2024 years and at most 3 post-2024 years (2026 is partial).",
|
||||
" Effect sizes are descriptive, not confirmatory.",
|
||||
"- **LLM extremity scores:** Content-based, not independently validated beyond the",
|
||||
" manual audit above. See §6 for agreement rate and noted biases.",
|
||||
"- **Coalition composition:** Hardcoded per year. 2024 is ambiguous (Rutte IV until July,",
|
||||
" Schoof thereafter). Early 2024 motions may be miscoded as Schoof-era.",
|
||||
"- **Submitter party identification:** Parsed from motion title prefixes (e.g.,",
|
||||
" 'Motie van het lid X'). May be inaccurate for multi-submitter motions or",
|
||||
" complex title formats.",
|
||||
"- **Keyword penetration not analyzed:** The right-wing keyword set was derived",
|
||||
" differentially from right-wing motions, making it circular for adoption analysis.",
|
||||
"- **Pass rate baseline:** Computed across all motions with voting data. Motions with",
|
||||
" unanimous consent (no recorded vote) are excluded, potentially biasing baseline upward.",
|
||||
"",
|
||||
"## 8. Figures",
|
||||
"",
|
||||
f".name})",
|
||||
f".name})",
|
||||
"",
|
||||
"## 9. Conclusion",
|
||||
"",
|
||||
"*(Fill in after reviewing all indicators and audit results.)*",
|
||||
]
|
||||
|
||||
report_path = REPORTS_DIR / "breakpoint_analysis.md"
|
||||
with open(report_path, "w") as f:
|
||||
f.write("\n".join(lines))
|
||||
logger.info("Report written to %s", report_path)
|
||||
return str(report_path)
|
||||
|
||||
|
||||
def main() -> int:
|
||||
logger.info("Connecting to database: %s", DB_PATH)
|
||||
con = _conn(read_only=True)
|
||||
|
||||
logger.info("Computing yearly right-wing metrics...")
|
||||
yearly_raw = compute_yearly_rw_metrics(con)
|
||||
|
||||
logger.info("Computing baseline (all motions) metrics...")
|
||||
baseline_raw = compute_yearly_baseline(con)
|
||||
|
||||
logger.info("Building party name map from mp_metadata...")
|
||||
name_party_map = build_party_name_map(con)
|
||||
|
||||
logger.info("Computing opposition-only metrics...")
|
||||
opp_raw = compute_opposition_metrics(yearly_raw, name_party_map)
|
||||
|
||||
logger.info("Computing domain decomposition...")
|
||||
mig_raw, non_mig_raw = compute_domain_metrics(yearly_raw)
|
||||
|
||||
logger.info("Computing extremity-stratified pass rates...")
|
||||
ext_stratified = compute_extremity_stratified(yearly_raw)
|
||||
|
||||
con.close()
|
||||
|
||||
yearly_sum = yearly_summary(yearly_raw)
|
||||
opp_sum = yearly_summary(opp_raw)
|
||||
mig_sum = yearly_summary(mig_raw)
|
||||
non_mig_sum = yearly_summary(non_mig_raw)
|
||||
baseline_sum = yearly_summary(baseline_raw)
|
||||
|
||||
logger.info("Generating Figure 1...")
|
||||
fig1_path = create_figure_1(yearly_sum, opp_sum, mig_sum, non_mig_sum, baseline_sum)
|
||||
|
||||
logger.info("Generating Figure 2...")
|
||||
fig2_path = create_figure_2(yearly_sum, opp_sum, mig_sum, non_mig_sum, ext_stratified)
|
||||
|
||||
logger.info("Sampling motions for manual audit...")
|
||||
audit_sample = sample_audit(yearly_raw)
|
||||
print_audit(audit_sample)
|
||||
|
||||
logger.info("Generating report...")
|
||||
audit_notes = (
|
||||
"**Audit notes:** Perform manual audit by reviewing the motions below. "
|
||||
"Record agreement per motion. Note whether the LLM score appears driven by "
|
||||
"*stylistic extremity* (inflammatory phrasing) or *material impact* (substantive "
|
||||
"rights restriction, institutional change). "
|
||||
"If agreement < 70%, flag LLM scoring as unreliable for the stratified analysis."
|
||||
)
|
||||
|
||||
report_path = generate_report(
|
||||
yearly_sum=yearly_sum,
|
||||
opp_sum=opp_sum,
|
||||
mig_sum=mig_sum,
|
||||
non_mig_sum=non_mig_sum,
|
||||
baseline_sum=baseline_sum,
|
||||
ext_stratified=ext_stratified,
|
||||
yearly_raw=yearly_raw,
|
||||
opp_raw=opp_raw,
|
||||
fig1_path=fig1_path,
|
||||
fig2_path=fig2_path,
|
||||
audit_sample=audit_sample,
|
||||
audit_notes=audit_notes,
|
||||
)
|
||||
|
||||
print(f"\nReport: {report_path}")
|
||||
print(f"Figure 1: {fig1_path}")
|
||||
print(f"Figure 2: {fig2_path}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,617 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Quantify Overton window shift via SVD center drift with axis stability validation.
|
||||
|
||||
Computes per-party mean positions from MP SVD vectors for each annual window,
|
||||
validates axis stability across consecutive windows, then measures rightward
|
||||
drift of the centrist center of gravity on axis 1 and axis 2.
|
||||
|
||||
Usage:
|
||||
uv run python analysis/right_wing/overton_svd_drift.py
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
import duckdb
|
||||
import matplotlib
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
from scipy.stats import spearmanr
|
||||
|
||||
matplotlib.use("Agg")
|
||||
|
||||
ROOT = Path(__file__).parent.parent.parent.resolve()
|
||||
if str(ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(ROOT))
|
||||
|
||||
from analysis.config import CANONICAL_RIGHT, PARTY_COLOURS, _PARTY_NORMALIZE
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
|
||||
logger = logging.getLogger("overton_svd_drift")
|
||||
|
||||
CANONICAL_CENTRIST = frozenset({"VVD", "D66", "CDA", "NSC", "BBB", "ChristenUnie"})
|
||||
|
||||
DB_PATH = str(ROOT / "data" / "motions.db")
|
||||
REPORTS_DIR = ROOT / "reports" / "overton_window"
|
||||
|
||||
STABILITY_THRESHOLD = 0.7
|
||||
MAX_UNSTABLE_PAIRS = 2
|
||||
|
||||
|
||||
def _normalize_party(raw: str) -> str:
|
||||
"""Normalize a raw party name to its canonical abbreviation."""
|
||||
return _PARTY_NORMALIZE.get(raw, raw)
|
||||
|
||||
|
||||
def compute_party_positions(
|
||||
con: duckdb.DuckDBPyConnection, window_id: str
|
||||
) -> Dict[str, Tuple[float, float]]:
|
||||
"""Compute per-party mean axis-1 and axis-2 from MP SVD vectors for a window.
|
||||
|
||||
Mirrors the logic of agent_tools/database.py:compute_party_positions_from_vectors.
|
||||
"""
|
||||
rows = con.execute(
|
||||
"""
|
||||
SELECT sv.entity_id, sv.vector, mm.party
|
||||
FROM svd_vectors sv
|
||||
JOIN mp_metadata mm ON sv.entity_id = mm.mp_name
|
||||
WHERE sv.window_id = ? AND sv.entity_type = 'mp'
|
||||
""",
|
||||
(window_id,),
|
||||
).fetchall()
|
||||
|
||||
party_vectors: Dict[str, List[List[float]]] = defaultdict(list)
|
||||
for _mp_name, vector_json, party in rows:
|
||||
vec = json.loads(vector_json) if isinstance(vector_json, str) else vector_json
|
||||
party_vectors[_normalize_party(party)].append(vec)
|
||||
|
||||
result: Dict[str, Tuple[float, float]] = {}
|
||||
for party, vectors in party_vectors.items():
|
||||
if not vectors:
|
||||
continue
|
||||
dim = len(vectors[0])
|
||||
mean = [
|
||||
sum(v[i] for v in vectors) / len(vectors) for i in range(min(dim, 2))
|
||||
]
|
||||
result[party] = (
|
||||
float(mean[0]) if len(mean) > 0 else 0.0,
|
||||
float(mean[1]) if len(mean) > 1 else 0.0,
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def get_annual_windows(con: duckdb.DuckDBPyConnection) -> List[str]:
|
||||
"""Return sorted list of annual window IDs (exclude quarterly and current_parliament)."""
|
||||
rows = con.execute(
|
||||
"""
|
||||
SELECT DISTINCT window_id FROM svd_vectors
|
||||
WHERE entity_type = 'mp'
|
||||
AND window_id NOT LIKE '%-Q%'
|
||||
AND window_id != 'current_parliament'
|
||||
ORDER BY window_id
|
||||
"""
|
||||
).fetchall()
|
||||
return [r[0] for r in rows]
|
||||
|
||||
|
||||
def validate_axis_stability(
|
||||
all_positions: Dict[str, Dict[str, Tuple[float, float]]],
|
||||
windows: List[str],
|
||||
) -> Tuple[bool, List[Dict[str, Any]], Dict[str, float]]:
|
||||
"""Validate that SVD axes are stable enough for cross-window comparison.
|
||||
|
||||
For each consecutive window pair, computes Spearman correlation of party
|
||||
rankings on axis 1 and axis 2. If either correlation < threshold, the pair
|
||||
is flagged as unstable. If >2 unstable pairs, the comparison is aborted.
|
||||
|
||||
Returns (is_stable, stability_details, avg_correlations).
|
||||
"""
|
||||
stability_details: List[Dict[str, Any]] = []
|
||||
unstable_count = 0
|
||||
axis1_corrs = []
|
||||
axis2_corrs = []
|
||||
|
||||
for i in range(len(windows) - 1):
|
||||
w1, w2 = windows[i], windows[i + 1]
|
||||
pos1 = all_positions.get(w1, {})
|
||||
pos2 = all_positions.get(w2, {})
|
||||
|
||||
shared = set(pos1.keys()) & set(pos2.keys())
|
||||
|
||||
if len(shared) < 3:
|
||||
stability_details.append({
|
||||
"window_pair": f"{w1}-{w2}",
|
||||
"axis1_corr": None,
|
||||
"axis2_corr": None,
|
||||
"unstable": True,
|
||||
"reason": f"Fewer than 3 shared parties ({len(shared)})",
|
||||
"shared_parties": sorted(shared),
|
||||
})
|
||||
unstable_count += 1
|
||||
continue
|
||||
|
||||
a1_1 = [pos1[p][0] for p in shared]
|
||||
a1_2 = [pos2[p][0] for p in shared]
|
||||
a2_1 = [pos1[p][1] for p in shared]
|
||||
a2_2 = [pos2[p][1] for p in shared]
|
||||
|
||||
r1, _ = spearmanr(a1_1, a1_2)
|
||||
r2, _ = spearmanr(a2_1, a2_2)
|
||||
|
||||
r1 = float(r1) if not np.isnan(r1) else 0.0
|
||||
r2 = float(r2) if not np.isnan(r2) else 0.0
|
||||
|
||||
axis1_corrs.append(r1)
|
||||
axis2_corrs.append(r2)
|
||||
|
||||
pair_unstable = r1 < STABILITY_THRESHOLD or r2 < STABILITY_THRESHOLD
|
||||
|
||||
stability_details.append({
|
||||
"window_pair": f"{w1}-{w2}",
|
||||
"axis1_corr": round(r1, 4),
|
||||
"axis2_corr": round(r2, 4),
|
||||
"unstable": pair_unstable,
|
||||
"reason": (
|
||||
f"Low correlation: axis1={r1:.3f}, axis2={r2:.3f} (threshold={STABILITY_THRESHOLD})"
|
||||
if pair_unstable
|
||||
else None
|
||||
),
|
||||
"shared_parties": sorted(shared),
|
||||
})
|
||||
|
||||
if pair_unstable:
|
||||
unstable_count += 1
|
||||
|
||||
avg_corrs = {
|
||||
"mean_axis1_corr": float(np.mean(axis1_corrs)) if axis1_corrs else 0.0,
|
||||
"mean_axis2_corr": float(np.mean(axis2_corrs)) if axis2_corrs else 0.0,
|
||||
}
|
||||
|
||||
is_stable = unstable_count <= MAX_UNSTABLE_PAIRS
|
||||
|
||||
return is_stable, stability_details, avg_corrs
|
||||
|
||||
|
||||
def compute_centers(
|
||||
all_positions: Dict[str, Dict[str, Tuple[float, float]]],
|
||||
windows: List[str],
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""Compute centrist and right-wing centers of gravity per window.
|
||||
|
||||
Missing parties in a window are simply skipped (mean over available parties).
|
||||
"""
|
||||
results: List[Dict[str, Any]] = []
|
||||
|
||||
for window_id in windows:
|
||||
pos = all_positions.get(window_id, {})
|
||||
|
||||
centrist_a1 = []
|
||||
centrist_a2 = []
|
||||
right_a1 = []
|
||||
right_a2 = []
|
||||
|
||||
for party, (a1, a2) in pos.items():
|
||||
if party in CANONICAL_CENTRIST:
|
||||
centrist_a1.append(a1)
|
||||
centrist_a2.append(a2)
|
||||
if party in CANONICAL_RIGHT:
|
||||
right_a1.append(a1)
|
||||
right_a2.append(a2)
|
||||
|
||||
centrist_mean_a1 = float(np.mean(centrist_a1)) if centrist_a1 else None
|
||||
centrist_mean_a2 = float(np.mean(centrist_a2)) if centrist_a2 else None
|
||||
right_mean_a1 = float(np.mean(right_a1)) if right_a1 else None
|
||||
right_mean_a2 = float(np.mean(right_a2)) if right_a2 else None
|
||||
|
||||
results.append({
|
||||
"window_id": window_id,
|
||||
"centrist_mean_axis1": centrist_mean_a1,
|
||||
"centrist_mean_axis2": centrist_mean_a2,
|
||||
"right_mean_axis1": right_mean_a1,
|
||||
"right_mean_axis2": right_mean_a2,
|
||||
"centrist_parties_present": sorted(
|
||||
p for p in pos if p in CANONICAL_CENTRIST
|
||||
),
|
||||
"right_parties_present": sorted(
|
||||
p for p in pos if p in CANONICAL_RIGHT
|
||||
),
|
||||
})
|
||||
|
||||
return results
|
||||
|
||||
|
||||
def create_table(
|
||||
con: duckdb.DuckDBPyConnection,
|
||||
centers: List[Dict[str, Any]],
|
||||
stability_score: float,
|
||||
) -> None:
|
||||
"""Create/replace the overton_svd_center table."""
|
||||
con.execute("DROP TABLE IF EXISTS overton_svd_center")
|
||||
con.execute("""
|
||||
CREATE TABLE overton_svd_center (
|
||||
window_id VARCHAR PRIMARY KEY,
|
||||
centrist_mean_axis1 DOUBLE,
|
||||
centrist_mean_axis2 DOUBLE,
|
||||
right_mean_axis1 DOUBLE,
|
||||
right_mean_axis2 DOUBLE,
|
||||
stability_score DOUBLE
|
||||
)
|
||||
""")
|
||||
|
||||
for row in centers:
|
||||
con.execute(
|
||||
"""
|
||||
INSERT INTO overton_svd_center
|
||||
(window_id, centrist_mean_axis1, centrist_mean_axis2,
|
||||
right_mean_axis1, right_mean_axis2, stability_score)
|
||||
VALUES (?, ?, ?, ?, ?, ?)
|
||||
""",
|
||||
(
|
||||
row["window_id"],
|
||||
row["centrist_mean_axis1"],
|
||||
row["centrist_mean_axis2"],
|
||||
row["right_mean_axis1"],
|
||||
row["right_mean_axis2"],
|
||||
stability_score,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def plot_trajectory(
|
||||
centers: List[Dict[str, Any]],
|
||||
stability_details: List[Dict[str, Any]],
|
||||
avg_corrs: Dict[str, float],
|
||||
output_path: str,
|
||||
) -> None:
|
||||
"""Plot centrist center trajectory with right-wing reference on 2D compass."""
|
||||
fig, ax = plt.subplots(figsize=(10, 8))
|
||||
|
||||
windows = [c["window_id"] for c in centers]
|
||||
cent_a1 = [c["centrist_mean_axis1"] for c in centers]
|
||||
cent_a2 = [c["centrist_mean_axis2"] for c in centers]
|
||||
right_a1 = [c["right_mean_axis1"] for c in centers]
|
||||
right_a2 = [c["right_mean_axis2"] for c in centers]
|
||||
|
||||
valid_windows = [
|
||||
windows[i]
|
||||
for i in range(len(windows))
|
||||
if cent_a1[i] is not None and cent_a2[i] is not None
|
||||
]
|
||||
|
||||
if len(valid_windows) < 2:
|
||||
ax.text(
|
||||
0.5,
|
||||
0.5,
|
||||
"Insufficient data for trajectory plot",
|
||||
transform=ax.transAxes,
|
||||
ha="center",
|
||||
va="center",
|
||||
)
|
||||
fig.savefig(output_path, dpi=150, bbox_inches="tight", facecolor="white")
|
||||
plt.close(fig)
|
||||
return
|
||||
|
||||
cent_a1_valid = [c for c in cent_a1 if c is not None]
|
||||
cent_a2_valid = [c for c in cent_a2 if c is not None]
|
||||
right_a1_valid = [c for c in right_a1 if c is not None]
|
||||
right_a2_valid = [c for c in right_a2 if c is not None]
|
||||
windows_valid = [w for w, a1 in zip(windows, cent_a1) if a1 is not None]
|
||||
|
||||
years = [int(w) for w in windows_valid]
|
||||
|
||||
ax.plot(cent_a1_valid, cent_a2_valid, "o-", color="#1E73BE", linewidth=2,
|
||||
markersize=8, label="Centrist center (VVD, D66, CDA, NSC, BBB, CU)",
|
||||
zorder=3)
|
||||
|
||||
if right_a1_valid and right_a2_valid:
|
||||
ax.plot(right_a1_valid, right_a2_valid, "s--", color="#6A1B9A", linewidth=1.5,
|
||||
markersize=6, label="Right-wing center (PVV, FVD, JA21, SGP)",
|
||||
alpha=0.7, zorder=2)
|
||||
|
||||
for i, year in enumerate(years):
|
||||
if i < len(cent_a1_valid) and cent_a1_valid[i] is not None:
|
||||
ax.annotate(
|
||||
str(year),
|
||||
(cent_a1_valid[i], cent_a2_valid[i]),
|
||||
textcoords="offset points",
|
||||
xytext=(7, 7),
|
||||
fontsize=8,
|
||||
color="#333333",
|
||||
)
|
||||
|
||||
ax.axhline(0, color="#CCCCCC", linewidth=0.5, linestyle="-")
|
||||
ax.axvline(0, color="#CCCCCC", linewidth=0.5, linestyle="-")
|
||||
|
||||
ax.set_xlabel("SVD Axis 1")
|
||||
ax.set_ylabel("SVD Axis 2")
|
||||
ax.set_title(
|
||||
f"Parliamentary Center Trajectory (2016–2026)\n"
|
||||
f"Stability: axis1 ρ={avg_corrs.get('mean_axis1_corr', 0):.3f}, "
|
||||
f"axis2 ρ={avg_corrs.get('mean_axis2_corr', 0):.3f}",
|
||||
fontsize=11,
|
||||
)
|
||||
ax.legend(loc="upper left", fontsize=8, framealpha=0.9)
|
||||
ax.set_aspect("equal", adjustable="datalim")
|
||||
ax.grid(True, alpha=0.3)
|
||||
|
||||
fig.tight_layout()
|
||||
fig.savefig(output_path, dpi=150, bbox_inches="tight", facecolor="white")
|
||||
plt.close(fig)
|
||||
logger.info("Chart saved to %s", output_path)
|
||||
|
||||
|
||||
def compute_drift_metrics(centers: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""Compute drift metrics: Euclidean distance per step, net displacement, direction."""
|
||||
valid = [c for c in centers if c["centrist_mean_axis1"] is not None]
|
||||
|
||||
if len(valid) < 2:
|
||||
return {
|
||||
"euclidean_steps": [],
|
||||
"net_displacement": None,
|
||||
"angular_direction_deg": None,
|
||||
"rightward_distance_traveled": None,
|
||||
}
|
||||
|
||||
euclidean_steps = []
|
||||
for i in range(len(valid) - 1):
|
||||
dx = valid[i + 1]["centrist_mean_axis1"] - valid[i]["centrist_mean_axis1"]
|
||||
dy = valid[i + 1]["centrist_mean_axis2"] - valid[i]["centrist_mean_axis2"]
|
||||
dist = float(np.sqrt(dx**2 + dy**2))
|
||||
euclidean_steps.append({
|
||||
"window_pair": f"{valid[i]['window_id']}-{valid[i+1]['window_id']}",
|
||||
"distance": round(dist, 6),
|
||||
"dx": round(dx, 6),
|
||||
"dy": round(dy, 6),
|
||||
})
|
||||
|
||||
first = valid[0]
|
||||
last = valid[-1]
|
||||
dx_net = last["centrist_mean_axis1"] - first["centrist_mean_axis1"]
|
||||
dy_net = last["centrist_mean_axis2"] - first["centrist_mean_axis2"]
|
||||
net_disp = float(np.sqrt(dx_net**2 + dy_net**2))
|
||||
|
||||
angle_rad = np.arctan2(dy_net, dx_net)
|
||||
angle_deg = float(np.degrees(angle_rad))
|
||||
|
||||
return {
|
||||
"euclidean_steps": euclidean_steps,
|
||||
"net_displacement": round(net_disp, 6),
|
||||
"net_dx": round(dx_net, 6),
|
||||
"net_dy": round(dy_net, 6),
|
||||
"angular_direction_deg": round(angle_deg, 2),
|
||||
}
|
||||
|
||||
|
||||
def write_report(
|
||||
is_stable: bool,
|
||||
stability_details: List[Dict[str, Any]],
|
||||
avg_corrs: Dict[str, float],
|
||||
centers: List[Dict[str, Any]],
|
||||
drift: Dict[str, Any],
|
||||
output_path: str,
|
||||
chart_path: str,
|
||||
) -> None:
|
||||
"""Write the SVD stability and drift report as Markdown."""
|
||||
lines: List[str] = []
|
||||
|
||||
lines.append("# SVD Center Drift & Axis Stability Report\n")
|
||||
|
||||
lines.append("## Axis Stability Validation\n")
|
||||
|
||||
lines.append(
|
||||
f"**Stability threshold:** Spearman ρ ≥ {STABILITY_THRESHOLD} for both axes. "
|
||||
f"Maximum unstable pairs allowed: {MAX_UNSTABLE_PAIRS}.\n"
|
||||
)
|
||||
|
||||
unstable_count = sum(1 for d in stability_details if d.get("unstable"))
|
||||
lines.append(
|
||||
f"**Result:** {unstable_count} unstable pair(s) out of "
|
||||
f"{len(stability_details)} consecutive window pairs.\n"
|
||||
)
|
||||
|
||||
if not is_stable:
|
||||
lines.append(
|
||||
"**CONCLUSION: SVD axes are too unstable for longitudinal comparison. "
|
||||
"Positions may reflect re-orientation rather than genuine drift. "
|
||||
"The following drift metrics and chart should be interpreted with extreme caution.**\n"
|
||||
)
|
||||
|
||||
lines.append(f"- Mean axis-1 correlation: {avg_corrs['mean_axis1_corr']:.4f}")
|
||||
lines.append(f"- Mean axis-2 correlation: {avg_corrs['mean_axis2_corr']:.4f}\n")
|
||||
|
||||
lines.append("### Per-Pair Stability Details\n")
|
||||
lines.append("| Window Pair | Axis 1 ρ | Axis 2 ρ | Unstable | Shared Parties |")
|
||||
lines.append("|---|---|---|---|---|")
|
||||
for d in stability_details:
|
||||
r1 = f"{d['axis1_corr']:.3f}" if d["axis1_corr"] is not None else "N/A"
|
||||
r2 = f"{d['axis2_corr']:.3f}" if d["axis2_corr"] is not None else "N/A"
|
||||
flag = "**YES**" if d.get("unstable") else "no"
|
||||
parties = ", ".join(d.get("shared_parties", []))
|
||||
lines.append(f"| {d['window_pair']} | {r1} | {r2} | {flag} | {parties} |")
|
||||
|
||||
lines.append("")
|
||||
|
||||
lines.append("## Centrist Center of Gravity\n")
|
||||
lines.append(
|
||||
"| Window | Centrist Ax1 | Centrist Ax2 | Right Ax1 | Right Ax2 | "
|
||||
"Centrist Parties Present | Right Parties Present |"
|
||||
)
|
||||
lines.append("|---|---|---|---|---|---|---|")
|
||||
for c in centers:
|
||||
cent_a1 = f"{c['centrist_mean_axis1']:.4f}" if c["centrist_mean_axis1"] is not None else "N/A"
|
||||
cent_a2 = f"{c['centrist_mean_axis2']:.4f}" if c["centrist_mean_axis2"] is not None else "N/A"
|
||||
right_a1 = f"{c['right_mean_axis1']:.4f}" if c["right_mean_axis1"] is not None else "N/A"
|
||||
right_a2 = f"{c['right_mean_axis2']:.4f}" if c["right_mean_axis2"] is not None else "N/A"
|
||||
cent_parties = ", ".join(c["centrist_parties_present"])
|
||||
right_parties = ", ".join(c["right_parties_present"])
|
||||
lines.append(
|
||||
f"| {c['window_id']} | {cent_a1} | {cent_a2} | {right_a1} | {right_a2} "
|
||||
f"| {cent_parties} | {right_parties} |"
|
||||
)
|
||||
|
||||
lines.append("")
|
||||
|
||||
if is_stable:
|
||||
lines.append("## Drift Metrics\n")
|
||||
lines.append(f"- **Net displacement (first → last):** {drift['net_displacement']}")
|
||||
lines.append(f" - Δ axis-1: {drift['net_dx']}")
|
||||
lines.append(f" - Δ axis-2: {drift['net_dy']}")
|
||||
lines.append(f"- **Net direction:** {drift['angular_direction_deg']}° "
|
||||
f"(arctan2(Δy, Δx))")
|
||||
lines.append(f" - Positive Δx = rightward on axis 1")
|
||||
lines.append(f" - Positive Δy = upward on axis 2\n")
|
||||
|
||||
lines.append("### Year-over-Year Drift\n")
|
||||
lines.append("| Window Pair | Euclidean Distance | Δ Axis-1 | Δ Axis-2 |")
|
||||
lines.append("|---|---|---|---|")
|
||||
total_dist = 0.0
|
||||
for step in drift["euclidean_steps"]:
|
||||
lines.append(
|
||||
f"| {step['window_pair']} | {step['distance']:.6f} "
|
||||
f"| {step['dx']:+.6f} | {step['dy']:+.6f} |"
|
||||
)
|
||||
total_dist += step["distance"]
|
||||
lines.append(f"\n**Total path length:** {total_dist:.6f}\n")
|
||||
|
||||
else:
|
||||
lines.append("## Drift Metrics (UNRELIABLE — Axes Unstable)\n")
|
||||
lines.append(
|
||||
"Drift metrics were computed but are unreliable due to axis instability. "
|
||||
"Cross-window comparisons on unstable axes conflate positional change "
|
||||
"with axis re-orientation.\n"
|
||||
)
|
||||
|
||||
lines.append(f"## Chart\n")
|
||||
lines.append(f"})\n")
|
||||
|
||||
lines.append("## Interpretability Statement\n")
|
||||
if is_stable:
|
||||
lines.append(
|
||||
"The SVD axes show sufficient stability for cross-window comparison. "
|
||||
"The parliamentary center trajectory reflects genuine shifts in voting "
|
||||
"behavior rather than axis re-orientation artifact. The centrist center-of-gravity "
|
||||
"movement on the 2D compass can be interpreted as a measure of ideological drift.\n"
|
||||
)
|
||||
else:
|
||||
lines.append(
|
||||
"SVD axes are too unstable for longitudinal comparison. The trajectory "
|
||||
"plotted above may reflect axis re-orientation (each SVD window independently "
|
||||
"determines its principal axes) rather than genuine ideological drift. "
|
||||
"We recommend against drawing conclusions from this analysis.\n"
|
||||
)
|
||||
|
||||
lines.append("---\n")
|
||||
lines.append(
|
||||
"*Note: SVD axes reflect voting patterns, not semantic content. "
|
||||
"A shift means voting behavior changed, not that parties changed their rhetoric. "
|
||||
"See: docs/solutions/best-practices/svd-labels-voting-patterns-not-semantics.md*\n"
|
||||
)
|
||||
|
||||
os.makedirs(os.path.dirname(output_path), exist_ok=True)
|
||||
with open(output_path, "w", encoding="utf-8") as f:
|
||||
f.write("\n".join(lines) + "\n")
|
||||
logger.info("Report saved to %s", output_path)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
os.makedirs(str(REPORTS_DIR), exist_ok=True)
|
||||
|
||||
con = duckdb.connect(database=DB_PATH, read_only=False)
|
||||
|
||||
try:
|
||||
windows = get_annual_windows(con)
|
||||
logger.info("Found %d annual windows: %s", len(windows), windows)
|
||||
|
||||
all_positions: Dict[str, Dict[str, Tuple[float, float]]] = {}
|
||||
for w in windows:
|
||||
pos = compute_party_positions(con, w)
|
||||
all_positions[w] = pos
|
||||
n_parties = len(pos)
|
||||
centrist_present = sum(1 for p in pos if p in CANONICAL_CENTRIST)
|
||||
right_present = sum(1 for p in pos if p in CANONICAL_RIGHT)
|
||||
logger.info(
|
||||
"Window %s: %d parties, %d centrist, %d right",
|
||||
w, n_parties, centrist_present, right_present,
|
||||
)
|
||||
|
||||
is_stable, stability_details, avg_corrs = validate_axis_stability(
|
||||
all_positions, windows
|
||||
)
|
||||
|
||||
unstable_count = sum(1 for d in stability_details if d.get("unstable"))
|
||||
logger.info(
|
||||
"Stability: %s (%d/%d unstable pairs), mean axis1 ρ=%.3f, mean axis2 ρ=%.3f",
|
||||
"STABLE" if is_stable else "UNSTABLE",
|
||||
unstable_count,
|
||||
len(stability_details),
|
||||
avg_corrs["mean_axis1_corr"],
|
||||
avg_corrs["mean_axis2_corr"],
|
||||
)
|
||||
|
||||
for d in stability_details:
|
||||
if d.get("unstable"):
|
||||
logger.warning(
|
||||
"Unstable pair %s: axis1=%.3f, axis2=%.3f, reason=%s",
|
||||
d["window_pair"],
|
||||
d["axis1_corr"] or 0,
|
||||
d["axis2_corr"] or 0,
|
||||
d.get("reason", ""),
|
||||
)
|
||||
|
||||
centers = compute_centers(all_positions, windows)
|
||||
|
||||
stability_score = (
|
||||
avg_corrs["mean_axis1_corr"] + avg_corrs["mean_axis2_corr"]
|
||||
) / 2.0
|
||||
|
||||
for c_row in centers:
|
||||
c_row["stability_score"] = stability_score
|
||||
|
||||
create_table(con, centers, stability_score)
|
||||
|
||||
n_rows = con.execute("SELECT COUNT(*) FROM overton_svd_center").fetchone()[0]
|
||||
logger.info("Created overton_svd_center table with %d rows", n_rows)
|
||||
|
||||
chart_path = str(REPORTS_DIR / "svd_drift_chart.png")
|
||||
plot_trajectory(centers, stability_details, avg_corrs, chart_path)
|
||||
|
||||
drift = compute_drift_metrics(centers)
|
||||
|
||||
report_path = str(REPORTS_DIR / "svd_stability_report.md")
|
||||
write_report(
|
||||
is_stable, stability_details, avg_corrs, centers,
|
||||
drift, report_path, chart_path,
|
||||
)
|
||||
|
||||
summary = {
|
||||
"stability_status": "STABLE" if is_stable else "UNSTABLE",
|
||||
"unstable_pairs": unstable_count,
|
||||
"total_pairs": len(stability_details),
|
||||
"mean_axis1_corr": round(avg_corrs["mean_axis1_corr"], 4),
|
||||
"mean_axis2_corr": round(avg_corrs["mean_axis2_corr"], 4),
|
||||
"windows": len(windows),
|
||||
"table_rows": n_rows,
|
||||
"net_displacement": drift.get("net_displacement"),
|
||||
"net_dx": drift.get("net_dx"),
|
||||
"net_dy": drift.get("net_dy"),
|
||||
"angular_direction_deg": drift.get("angular_direction_deg"),
|
||||
}
|
||||
|
||||
logger.info("Summary: %s", json.dumps(summary, indent=2))
|
||||
return summary
|
||||
|
||||
finally:
|
||||
con.close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
result = main()
|
||||
print(json.dumps(result, indent=2))
|
||||
Reference in New Issue
Block a user