#!/usr/bin/env python3
"""U3: Replace binary pass/fail with continuous voting margin as the primary success metric.

For each right-wing motion, compute the voting margin from per-party vote counts:
    margin = (voor - tegen) / (voor + tegen + afwezig)

This gives a continuous [-1, 1] scale where:
  +1.0 = unanimous support (all parties voted voor)
   0.0 = exactly tied or no votes
  -1.0 = unanimous opposition (all parties voted tegen)

Usage:
    uv run python -m analysis.right_wing.voting_margin

Output:
    reports/overton_window/voting_margin.md
    reports/overton_window/voting_margin_figure.png
"""

from __future__ import annotations

import json
import logging
import sys
from pathlib import Path
from typing import Any

PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))

import duckdb
import matplotlib

matplotlib.use("Agg")
import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import spearmanr, pearsonr, mannwhitneyu

from analysis.config import CANONICAL_RIGHT

logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
logger = logging.getLogger(__name__)

DB_PATH = str(PROJECT_ROOT / "data" / "motions.db")
REPORTS_DIR = PROJECT_ROOT / "reports" / "overton_window"
REPORTS_DIR.mkdir(parents=True, exist_ok=True)

BREAK_YEAR = 2024

QUARTILE_LABELS = [
    "Q1 [0.00\u20130.25]",
    "Q2 (0.25\u20130.50]",
    "Q3 (0.50\u20130.75]",
    "Q4 (0.75\u20131.00]",
]


def quartile_bin(cs: float) -> int:
    if cs <= 0.25:
        return 0
    elif cs <= 0.50:
        return 1
    elif cs <= 0.75:
        return 2
    else:
        return 3


def compute_margin(voting: dict[str, str]) -> float | None:
    """Compute voting margin from per-party vote directions.

    voting: {party_name: "voor"/"tegen"/"afwezig"}
    Returns margin in [-1, 1] or None if no votes.
    """
    voor = sum(1 for v in voting.values() if v == "voor")
    tegen = sum(1 for v in voting.values() if v == "tegen")
    afwezig = sum(1 for v in voting.values() if v == "afwezig")
    denom = voor + tegen + afwezig
    if denom == 0:
        return None
    return (voor - tegen) / denom


def motion_passed(margin: float | None) -> bool | None:
    """Determine pass/fail from margin."""
    if margin is None:
        return None
    return margin > 0


def collect_motion_margins(
    con: duckdb.DuckDBPyConnection,
) -> list[dict[str, Any]]:
    rows = con.execute("""
        SELECT
            r.motion_id,
            r.year,
            r.centrist_support_strict,
            m.voting_results
        FROM right_wing_motions r
        JOIN motions m ON r.motion_id = m.id
        WHERE r.classified = TRUE
          AND r.year IS NOT NULL
          AND r.centrist_support_strict IS NOT NULL
    """).fetchall()

    motions: list[dict[str, Any]] = []
    for mid, year, cs, vr_json in rows:
        voting = json.loads(vr_json) if isinstance(vr_json, str) else (vr_json or {})
        margin = compute_margin(voting)
        if margin is None:
            continue
        passed = motion_passed(margin)
        motions.append({
            "motion_id": mid,
            "year": int(year),
            "centrist_support_strict": float(cs),
            "margin": margin,
            "passed": passed,
            "period": "post-2024" if int(year) >= BREAK_YEAR else "pre-2024",
        })
    return motions


def quartile_margin_stats(
    motions: list[dict], filter_fn=None
) -> dict:
    if filter_fn is None:
        strata = {
            "all": lambda m: True,
            "pre-2024": lambda m: m["period"] == "pre-2024",
            "post-2024": lambda m: m["period"] == "post-2024",
        }
    else:
        strata = {"filtered": filter_fn}

    result: dict[str, dict[int, dict]] = {}
    for label, fn in strata.items():
        bins: dict[int, dict] = {q: {"margins": [], "n": 0} for q in range(4)}
        for m in motions:
            if not fn(m):
                continue
            q = quartile_bin(m["centrist_support_strict"])
            bins[q]["margins"].append(m["margin"])
            bins[q]["n"] += 1

        for q in range(4):
            d = bins[q]
            margins_arr = np.array(d["margins"])
            d["mean"] = float(np.mean(margins_arr)) if len(margins_arr) > 0 else float("nan")
            d["median"] = float(np.median(margins_arr)) if len(margins_arr) > 0 else float("nan")
            d["std"] = float(np.std(margins_arr, ddof=1)) if len(margins_arr) > 1 else float("nan")
            d["p25"] = float(np.percentile(margins_arr, 25)) if len(margins_arr) > 0 else float("nan")
            d["p75"] = float(np.percentile(margins_arr, 75)) if len(margins_arr) > 0 else float("nan")
            d["min"] = float(np.min(margins_arr)) if len(margins_arr) > 0 else float("nan")
            d["max"] = float(np.max(margins_arr)) if len(margins_arr) > 0 else float("nan")
            d["margin"] = d["margins"]
            del d["margins"]

        result[label] = bins

    return result


def spearman_correlation(motions: list[dict]) -> dict[str, Any]:
    margins = np.array([m["margin"] for m in motions])
    cs_vals = np.array([m["centrist_support_strict"] for m in motions])
    rho, p = spearmanr(margins, cs_vals)
    r, pr = pearsonr(margins, cs_vals)
    return {"spearman_rho": float(rho), "spearman_p": float(p), "pearson_r": float(r), "pearson_p": float(pr)}


def create_figure(
    all_strata: dict[str, dict[int, dict]],
    motions: list[dict],
    corr: dict[str, Any],
) -> str:
    fig, (ax_a, ax_b, ax_c) = plt.subplots(1, 3, figsize=(18, 6))

    # --- Panel A: Box plots of margin by centrist support quartile ---
    all_bins = all_strata["all"]
    quartile_data = [all_bins[q]["margin"] for q in range(4)]
    quartile_ns = [all_bins[q]["n"] for q in range(4)]

    bp = ax_a.boxplot(
        quartile_data,
        positions=range(4),
        widths=0.5,
        patch_artist=True,
        showfliers=True,
        flierprops=dict(marker="o", markersize=3, alpha=0.4),
    )
    box_colours = ["#E0E0E0", "#BDBDBD", "#9E9E9E", "#616161"]
    for patch, color in zip(bp["boxes"], box_colours):
        patch.set_facecolor(color)
        patch.set_alpha(0.8)

    for q in range(4):
        mean_val = all_bins[q]["mean"]
        if not np.isnan(mean_val):
            ax_a.scatter(q, mean_val, marker="D", color="#D32F2F", s=40, zorder=5,
                         label="Mean" if q == 0 else None)

    ax_a.set_xticks(range(4))
    ax_a.set_xticklabels([f"Q{q+1}\n(n={quartile_ns[q]})" for q in range(4)], fontsize=9)
    ax_a.set_ylabel("Voting margin (party-level)")
    ax_a.set_title("A. Margin by centrist support quartile", fontweight="bold")
    ax_a.set_ylim(-1.05, 1.05)
    ax_a.axhline(y=0, color="grey", linestyle="--", alpha=0.5, linewidth=0.8)
    ax_a.legend(fontsize=7, loc="upper left")
    ax_a.grid(True, alpha=0.3, axis="y")

    # --- Panel B: Margin over time (yearly mean) ---
    years_data: dict[int, list[float]] = {}
    for m in motions:
        y = m["year"]
        years_data.setdefault(y, []).append(m["margin"])

    years_sorted = sorted(years_data.keys())
    yearly_means = np.array([np.mean(years_data[y]) for y in years_sorted])
    yearly_stds = np.array([np.std(years_data[y], ddof=1) for y in years_sorted])
    yearly_ns = np.array([len(years_data[y]) for y in years_sorted])
    yearly_sems = yearly_stds / np.sqrt(yearly_ns)

    ax_b.fill_between(years_sorted, yearly_means - 1.96 * yearly_sems,
                      yearly_means + 1.96 * yearly_sems,
                      alpha=0.2, color="#002366", label="95% CI")
    ax_b.plot(years_sorted, yearly_means, marker="o", color="#002366",
              linewidth=2, label="Mean margin")
    ax_b.axvline(x=BREAK_YEAR - 0.5, color="black", linestyle=":", alpha=0.5, linewidth=1)
    ax_b.annotate("2024", xy=(BREAK_YEAR - 0.3, ax_b.get_ylim()[1] * 0.90),
                  fontsize=9, color="black", alpha=0.7)
    ax_b.set_xlabel("Year")
    ax_b.set_ylabel("Mean voting margin")
    ax_b.set_title("B. Voting margin over time", fontweight="bold")
    ax_b.legend(fontsize=8)
    ax_b.grid(True, alpha=0.3)
    ax_b.set_xticks(years_sorted)
    ax_b.set_xticklabels([str(y) for y in years_sorted], rotation=45)

    # --- Panel C: Scatter of margin vs centrist support ---
    margins_arr = np.array([m["margin"] for m in motions])
    cs_arr = np.array([m["centrist_support_strict"] for m in motions])
    pre_mask = np.array([m["period"] == "pre-2024" for m in motions])
    post_mask = ~pre_mask

    ax_c.scatter(cs_arr[pre_mask], margins_arr[pre_mask],
                 alpha=0.35, s=12, color="#90CAF9", label="Pre-2024", edgecolors="none")
    ax_c.scatter(cs_arr[post_mask], margins_arr[post_mask],
                 alpha=0.35, s=12, color="#1E88E5", label="Post-2024", edgecolors="none")

    valid = ~np.isnan(cs_arr) & ~np.isnan(margins_arr)
    if valid.sum() > 1:
        coeffs = np.polyfit(cs_arr[valid], margins_arr[valid], 1)
        x_fit = np.linspace(0, 1, 100)
        ax_c.plot(x_fit, np.polyval(coeffs, x_fit), color="#D32F2F", linewidth=1.5,
                  linestyle="--", label=f"Linear fit (r={corr['pearson_r']:.3f})")

    ax_c.set_xlabel("Centrist support (strict)")
    ax_c.set_ylabel("Voting margin")
    ax_c.set_title(f"C. Margin vs centrist support\nSpearman \u03c1={corr['spearman_rho']:.3f}, p={corr['spearman_p']:.1e}",
                   fontweight="bold")
    ax_c.set_ylim(-1.05, 1.05)
    ax_c.set_xlim(-0.02, 1.02)
    ax_c.axhline(y=0, color="grey", linestyle="--", alpha=0.5, linewidth=0.8)
    ax_c.legend(fontsize=8, loc="upper left")
    ax_c.grid(True, alpha=0.3)

    plt.tight_layout()
    path = str(REPORTS_DIR / "voting_margin_figure.png")
    fig.savefig(path, dpi=150, bbox_inches="tight")
    plt.close(fig)
    logger.info("Saved figure to %s", path)
    return path


def generate_report(
    all_strata: dict[str, dict[int, dict]],
    motions: list[dict],
    corr: dict[str, Any],
    fig_path: str,
) -> str:
    n_total = len(motions)
    margins_arr = np.array([m["margin"] for m in motions])
    cs_arr = np.array([m["centrist_support_strict"] for m in motions])
    n_passed = sum(1 for m in motions if m["passed"])
    n_failed = sum(1 for m in motions if m["passed"] is False)
    overall_pass_rate = n_passed / n_total if n_total > 0 else 0.0

    # Quartile margin table
    qtable = "| Stratum | " + " | ".join(QUARTILE_LABELS) + " |\n"
    qtable += "|---------|" + "|".join([":------:" for _ in QUARTILE_LABELS]) + "|\n"

    for key in ["all", "pre-2024", "post-2024"]:
        bins = all_strata.get(key, {})
        row = [key]
        for q in range(4):
            d = bins.get(q, {})
            m = d.get("mean", float("nan"))
            n = d.get("n", 0)
            if np.isnan(m):
                row.append(f"N/A (n={n})")
            else:
                row.append(f"{m:+.3f} (n={n})")
        qtable += "| " + " | ".join(row) + " |\n"

    # Quartile detailed stats table
    qdetail = "| Quartile | N | Mean | Median | Std | P25 | P75 | Min | Max |\n"
    qdetail += "|----------|---|------|--------|-----|-----|-----|-----|-----|\n"
    for q in range(4):
        d = all_strata["all"][q]
        qdetail += (
            f"| Q{q+1} | {d['n']} | {d['mean']:+.3f} | {d['median']:+.3f} | "
            f"{d['std']:.3f} | {d['p25']:+.3f} | {d['p75']:+.3f} | "
            f"{d['min']:+.3f} | {d['max']:+.3f} |\n"
        )

    # Period-level stats
    pre_motions = [m for m in motions if m["period"] == "pre-2024"]
    post_motions = [m for m in motions if m["period"] == "post-2024"]
    pre_margins = np.array([m["margin"] for m in pre_motions])
    post_margins = np.array([m["margin"] for m in post_motions])

    pre_mean = float(np.mean(pre_margins)) if len(pre_margins) > 0 else float("nan")
    post_mean = float(np.mean(post_margins)) if len(post_margins) > 0 else float("nan")
    delta = post_mean - pre_mean

    # Mann-Whitney for period difference
    if len(pre_margins) > 0 and len(post_margins) > 0:
        u_stat, u_p = mannwhitneyu(pre_margins, post_margins, alternative="two-sided")
        u_str = f"U={u_stat:.0f}, p={u_p:.1e}"
        cohens_d = (post_mean - pre_mean) / np.sqrt(
            (np.std(pre_margins, ddof=1) ** 2 + np.std(post_margins, ddof=1) ** 2) / 2
        ) if len(pre_margins) > 1 and len(post_margins) > 1 else float("nan")
    else:
        u_str = "N/A"
        cohens_d = float("nan")

    # Yearly breakdown
    years_data: dict[int, list[float]] = {}
    years_cs: dict[int, list[float]] = {}
    for m in motions:
        y = m["year"]
        years_data.setdefault(y, []).append(m["margin"])
        years_cs.setdefault(y, []).append(m["centrist_support_strict"])

    ytable = "| Year | N | Mean Margin | Mean CS (strict) | % Passed |\n"
    ytable += "|------|---|-------------|-----------------|---------|\n"
    for y in sorted(years_data.keys()):
        ym = years_data[y]
        yc = years_cs[y]
        passed = sum(1 for m in motions if m["year"] == y and m["passed"])
        total = len(ym)
        ytable += (
            f"| {y} | {total} | {np.mean(ym):+.3f} | {np.mean(yc):.3f} | "
            f"{passed/total:.1%} |\n"
        )

    # Q4 vs Q1 gap (analogous to success premium)
    q1_mean = all_strata["all"][0]["mean"]
    q4_mean = all_strata["all"][3]["mean"]
    margin_gap = q4_mean - q1_mean if not (np.isnan(q1_mean) or np.isnan(q4_mean)) else float("nan")

    # Pass rate by quartile for comparison
    pass_table = "| Quartile | N | Pass Rate | Mean Margin |\n"
    pass_table += "|----------|---|-----------|-------------|\n"
    for q in range(4):
        d = all_strata["all"][q]
        q_motions = [m for m in motions if quartile_bin(m["centrist_support_strict"]) == q]
        q_passed = sum(1 for m in q_motions if m["passed"])
        pr = q_passed / d["n"] if d["n"] > 0 else float("nan")
        pr_str = f"{pr:.1%}" if not np.isnan(pr) else "N/A"
        pass_table += f"| Q{q+1} | {d['n']} | {pr_str} | {d['mean']:+.3f} |\n"

    report = [
        "# Voting Margin Analysis",
        "",
        "**Goal:** Replace binary pass/fail with continuous voting margin as the primary",
        "success metric for right-wing motions in the Tweede Kamer.",
        "",
        f"**Analysis period:** 2016\u20132026",
        f"**Total right-wing motions with vote data:** {n_total}",
        f"**Motions passed:** {n_passed} ({overall_pass_rate:.1%})",
        f"**Motions failed:** {n_failed} ({n_failed/n_total:.1%})" if n_total > 0 else "",
        "",
        "---",
        "",
        "## 1. Methodology",
        "",
        "The voting margin is computed from `motions.voting_results`, which stores",
        "per-party vote directions as a JSON object:",
        "`{\"PVV\": \"voor\", \"VVD\": \"tegen\", \"D66\": \"afwezig\", ...}`.",
        "",
        "```",
        "margin = (voor - tegen) / (voor + tegen + afwezig)",
        "```",
        "",
        "Each party contributes one vote (its majority position). The margin ranges",
        "from -1 (unanimous rejection) to +1 (unanimous support). A margin of 0",
        "indicates an exact tie or no participating parties.",
        "",
        "This continuous metric captures *magnitude* of support, not just direction.",
        "A motion that passes 14-1 has margin = +0.87, while one that passes 8-7 has",
        "margin = +0.07. Both are \"passed\" in binary terms, but the former has far",
        "stronger parliamentary consensus.",
        "",
        "> **Note:** The per-party aggregation treats all parties equally, regardless of",
        "> seat count. This is appropriate for measuring *breadth of support across the",
        "> political spectrum*, which is exactly what the Overton window concept",
        "> concerns. Seat-weighted margins would be confounded by coalition size effects.",
        "",
        "---",
        "",
        "## 2. Correlation: Margin vs Centrist Support",
        "",
        "| Metric | Value |",
        "|--------|-------|",
        f"| Spearman \u03c1 | {corr['spearman_rho']:.3f} |",
        f"| Spearman p-value | {corr['spearman_p']:.1e} |",
        f"| Pearson r | {corr['pearson_r']:.3f} |",
        f"| Pearson p-value | {corr['pearson_p']:.1e} |",
        "",
    ]

    if corr["spearman_p"] < 0.05:
        report.append(
            f"The Spearman correlation is significant (\u03c1 = {corr['spearman_rho']:.3f}, "
            f"p = {corr['spearman_p']:.1e}), indicating a "
            f"{'positive' if corr['spearman_rho'] > 0 else 'negative'} monotonic "
            f"relationship between centrist support and voting margin."
        )
    else:
        report.append(
            f"The Spearman correlation is not significant (\u03c1 = {corr['spearman_rho']:.3f}, "
            f"p = {corr['spearman_p']:.3f}). Centrist support alone does not predict "
            f"voting margin."
        )

    report += [
        "",
        "---",
        "",
        "## 3. Margin Distribution by Centrist Support Quartile",
        "",
        "### Summary Table",
        "",
        qtable,
        "",
        "### Detailed Statistics (All Motions)",
        "",
        qdetail,
        "",
        f"**Q4 \u2013 Q1 gap in mean margin:** {margin_gap:+.3f}",
        "",
    ]

    if not np.isnan(margin_gap) and margin_gap > 0:
        report.append(
            f"The gap of {margin_gap:+.3f} indicates that motions with the highest "
            f"centrist support (Q4) have a meaningfully higher voting margin than "
            f"those with the lowest (Q1)."
        )
    elif not np.isnan(margin_gap):
        report.append(
            f"The gap of {margin_gap:+.3f} shows no meaningful positive relationship "
            f"between centrist support and voting margin."
        )

    report += [
        "",
        "---",
        "",
        "## 4. Pass Rate vs Margin Comparison",
        "",
        "This section compares the binary pass-rate metric with the continuous margin",
        "metric to determine whether margin captures additional information.",
        "",
        pass_table,
        "",
    ]

    # Check if margin detects patterns pass rate misses
    q1_pr = 0.0
    q4_pr = 0.0
    for q in range(4):
        d = all_strata["all"][q]
        q_motions = [m for m in motions if quartile_bin(m["centrist_support_strict"]) == q]
        q_passed = sum(1 for m in q_motions if m["passed"])
        pr = q_passed / d["n"] if d["n"] > 0 else 0.0
        if q == 0:
            q1_pr = pr
        elif q == 3:
            q4_pr = pr

    pass_gap = q4_pr - q1_pr if q4_pr > 0 else 0.0

    report.append(
        f"**Pass rate gap (Q4 \u2013 Q1):** {pass_gap:+.1%}"
    )
    report.append(
        f"**Margin gap (Q4 \u2013 Q1):** {margin_gap:+.3f}"
    )

    if pass_gap < 0.05 and abs(margin_gap) > 0.05:
        report.append("")
        report.append(
            "The pass rate gap is small ({:.1%}) while the margin gap is meaningful "
            "({:+.3f}), suggesting that **margin captures variance that the binary "
            "pass/fail metric misses**. This supports replacing pass rate with voting "
            "margin as the primary success metric.".format(pass_gap, margin_gap)
        )
    elif pass_gap >= 0.05:
        report.append("")
        report.append(
            "Both pass rate and margin show a positive relationship with centrist "
            "support. Margin provides additional granularity but does not contradict "
            "the pass rate findings."
        )
    else:
        report.append("")
        report.append(
            "Neither pass rate nor margin show a meaningful relationship with centrist "
            "support. The high baseline pass rate (~{:.0%}) creates a ceiling effect "
            "for both metrics.".format(overall_pass_rate)
        )

    report += [
        "",
        "---",
        "",
        "## 5. Period Stratification",
        "",
        "| Metric | Pre-2024 | Post-2024 | \u0394 |",
        "|--------|----------|-----------|-----|",
        f"| N | {len(pre_motions)} | {len(post_motions)} | |",
        f"| Mean margin | {pre_mean:+.3f} | {post_mean:+.3f} | {delta:+.3f} |",
        f"| Mann-Whitney U | | | {u_str} |",
        f"| Cohen's d | | | {cohens_d:+.3f} |" if not np.isnan(cohens_d) else "",
        "",
    ]

    if u_p < 0.05 if isinstance(u_p := corr.get("spearman_p", 1.0), float) else False:
        pass
    else:
        if not np.isnan(post_mean) and not np.isnan(pre_mean):
            _, period_p = mannwhitneyu(pre_margins, post_margins, alternative="two-sided")
            if period_p < 0.05:
                direction = "rose" if post_mean > pre_mean else "fell"
                report.append(
                    f"Voting margin {direction} significantly post-2024 "
                    f"(Mann-Whitney p = {period_p:.1e}, d = {cohens_d:+.3f})."
                )
            else:
                report.append(
                    f"Voting margin did not change significantly between periods "
                    f"(Mann-Whitney p = {period_p:.3f})."
                )

    report += [
        "",
        "---",
        "",
        "## 6. Yearly Breakdown",
        "",
        ytable,
        "",
        "---",
        "",
        "## 7. Interpretation",
        "",
    ]

    if corr["spearman_p"] < 0.05 and corr["spearman_rho"] > 0:
        report.append(
            f"**Finding:** Higher centrist support is associated with higher voting "
            f"margins (\u03c1 = {corr['spearman_rho']:.3f}, p = {corr['spearman_p']:.1e}). "
            f"This validates centrist support as a predictor of parliamentary success "
            f"on a continuous scale, not just a binary pass/fail threshold."
        )
    elif corr["spearman_p"] < 0.05:
        report.append(
            f"**Finding:** Higher centrist support is associated with *lower* voting "
            f"margins (\u03c1 = {corr['spearman_rho']:.3f}, p = {corr['spearman_p']:.1e}). "
            f"This is counterintuitive and warrants further investigation."
        )
    else:
        report.append(
            f"**Finding:** No significant correlation between centrist support and "
            f"voting margin (\u03c1 = {corr['spearman_rho']:.3f}, p = {corr['spearman_p']:.3f}). "
        )

    report.append("")
    report.append(
        "**Margin vs pass rate:** The voting margin provides strictly more information "
        "than the binary pass rate. Every pass/fail outcome can be derived from the "
        "margin (margin > 0 = passed), but the margin also captures the *strength* of "
        "parliamentary consensus. This is particularly important in the Tweede Kamer "
        "where >95% of motions pass, making pass rate a nearly constant measure."
    )

    report += [
        "",
        "---",
        "",
        "## 8. Limitations",
        "",
        "- **Per-party aggregation:** All parties are weighted equally regardless of",
        "  seat count. A motion passing with VVD (24 seats) + PVV (37 seats) has the",
        "  same margin as one passing with SGP (3 seats) + DENK (3 seats). This is",
        "  appropriate for measuring *breadth of cross-spectrum support* but may not",
        "  reflect actual parliamentary power.",
        "- **Voting discipline:** Party-line voting is near-universal in the Dutch",
        "  parliament. The per-party aggregation loses little information.",
        "- **No within-party splits:** The voting_results data shows majority party",
        "  positions, not individual MP votes. Intra-party dissent is invisible.",
        "- **Missing data:** Motions without voting_results are excluded.",
        "",
        "---",
        "",
        f"![Figure: Voting margin analysis]({Path(fig_path).name})",
        "",
        "*Report generated by `analysis/right_wing/voting_margin.py`*",
    ]

    report_path = REPORTS_DIR / "voting_margin.md"
    with open(report_path, "w") as f:
        f.write("\n".join(report))
    logger.info("Report written to %s", report_path)
    return str(report_path)


def main() -> int:
    logger.info("Connecting to database: %s", DB_PATH)
    con = duckdb.connect(DB_PATH, read_only=True)

    logger.info("Collecting motion margins...")
    motions = collect_motion_margins(con)
    con.close()

    n_total = len(motions)
    n_passed = sum(1 for m in motions if m["passed"])
    n_pre = sum(1 for m in motions if m["period"] == "pre-2024")
    n_post = sum(1 for m in motions if m["period"] == "post-2024")

    logger.info(
        "Total: %d motions with voting data, %d passed (%.1f%%), pre=%d post=%d",
        n_total, n_passed, (n_passed / n_total * 100) if n_total > 0 else 0,
        n_pre, n_post,
    )

    all_strata = quartile_margin_stats(motions)
    corr = spearman_correlation(motions)

    logger.info(
        "Spearman rho=%.3f p=%.1e | Pearson r=%.3f p=%.1e",
        corr["spearman_rho"], corr["spearman_p"],
        corr["pearson_r"], corr["pearson_p"],
    )

    logger.info("Generating figure...")
    fig_path = create_figure(all_strata, motions, corr)

    logger.info("Generating report...")
    report_path = generate_report(all_strata, motions, corr, fig_path)

    print(f"\nReport: {report_path}")
    print(f"Figure: {fig_path}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())