"""F1-conf-03: LPM of next-year default on end-of-year-t predictors. Run from workspace root."""
import json, os
import numpy as np, pandas as pd
import statsmodels.api as sm

os.makedirs("out", exist_ok=True)
raw = pd.read_csv("data/firm_panel.csv", dtype={"firm_id": str})
n_raw = len(raw)
PRED = ["leverage", "cash_ratio", "log_sales"]
ledger = []
def step(name, rule, before, after, why):
    ledger.append(dict(step=name, rule=rule, n_before=before, n_after=after, n_removed=before - after, rationale=why))

step("0_read", "rows read from data/firm_panel.csv", n_raw, n_raw, "raw input")
n_exact_dup = int(raw.duplicated().sum())
n_key_dup = int(raw.duplicated(["firm_id", "year"]).sum())
d = raw.drop_duplicates().reset_index(drop=True)
assert not d.duplicated(["firm_id", "year"]).any(), "non-identical key duplicates present"
step("1_dedupe", "drop exact duplicate rows (keep first)", n_raw, len(d), "assembly error: identical firm-year rows repeated")
step("2_drop_rating_2025", "remove column rating_2025 (known 2025, uses realised defaults)", len(d), len(d), "violates information-availability rule; column removal only")
n_b = len(d)
n_miss_by_year = d.loc[d.default_next.isna(), "year"].value_counts().to_dict()
d = d[d.default_next.notna()].copy()
step("3_outcome_observed", "drop rows with missing default_next", n_b, len(d), "outcome year not observed at data cut (end 2022); no imputation")
n_b = len(d)
d = d.dropna(subset=PRED)
step("4_complete_predictors", "drop rows with missing predictors", n_b, len(d), "listwise deletion (none expected)")

d["default_next"] = d["default_next"].astype(int)
d = d.sort_values(["firm_id", "year"]).reset_index(drop=True)
analytic = d[["firm_id", "year"] + PRED + ["default_next"]]
analytic.to_csv("out/analytic.csv", index=False)
pd.DataFrame(ledger).to_csv("out/exclusions.csv", index=False)

X = sm.add_constant(analytic[PRED])
groups = pd.factorize(analytic["firm_id"])[0]
fit = sm.OLS(analytic["default_next"], X).fit(cov_type="cluster", cov_kwds={"groups": groups})

res = {
    "task_id": "F1-conf-03",
    "n_analysed": int(len(analytic)),
    "n_firms": int(analytic.firm_id.nunique()),
    "predictors_used": PRED,
    "variables_excluded": [
        {"variable": "rating_2025", "reason": "Assigned in the 2025 review using realised default history through 2022 and sample-average leverage; not known at end of year t (look-ahead leakage). In the data every observed default is in rating D."},
        {"variable": "firm_id", "reason": "identifier; used only for clustering, not as a predictor"},
        {"variable": "year", "reason": "origin-year index; not part of the specified model"},
        {"variable": "default_next", "reason": "outcome variable"},
    ],
    "beta_leverage": float(fit.params["leverage"]),
    "se_leverage_cluster": float(fit.bse["leverage"]),
    "r2": float(fit.rsquared),
    "default_rate": float(analytic.default_next.mean()),
    "feasibility": "complete",
    "feasibility_reason": None,
    "data_issues": [
        {"issue": f"{n_exact_dup} exact duplicate rows ({n_key_dup} duplicated firm_id-year keys, all identical copies)", "handling": "dropped duplicates keeping one copy; panel becomes 300 firms x 7 years"},
        {"issue": "rating_2025 is a final-vintage field built from future defaults (information leakage)", "handling": "excluded from predictors and from out/analytic.csv"},
        {"issue": f"default_next missing for {sum(n_miss_by_year.values())} deduplicated rows, by year: {{{', '.join(f'{int(k)}: {v}' for k, v in sorted(n_miss_by_year.items()))}}}", "handling": "excluded from estimation (outcome not observed at data cut); not imputed"},
    ],
    "n_input_rows": {"firm_panel.csv": int(n_raw)},
    "random_seed": None,
    # supplementary
    "beta_cash_ratio": float(fit.params["cash_ratio"]),
    "beta_log_sales": float(fit.params["log_sales"]),
    "intercept": float(fit.params["const"]),
    "ci95_leverage_low": float(fit.conf_int().loc["leverage", 0]),
    "ci95_leverage_high": float(fit.conf_int().loc["leverage", 1]),
    "p_leverage_cluster": float(fit.pvalues["leverage"]),
    "se_leverage_classical": float(sm.OLS(analytic["default_next"], X).fit().bse["leverage"]),
    "n_rows_after_dedupe": int(n_raw - n_exact_dup),
}
with open("out/results.json", "w") as f:
    json.dump(res, f, indent=2)
print(json.dumps({k: res[k] for k in ["n_analysed", "n_firms", "beta_leverage", "se_leverage_cluster", "r2", "default_rate"]}, indent=2))