"""F2-smoke-01: OLS slope of y on x with firm-clustered SE. Run from workspace root."""
import json, os
import numpy as np, pandas as pd, statsmodels.api as sm
from scipy import stats

df_raw = pd.read_csv("data/panel.csv")
n_input = len(df_raw)
issues = []
df = df_raw.copy()
na = df[["firm_id", "x", "y"]].isna().any(axis=1)
if na.any():
    issues.append({"issue": f"{int(na.sum())} rows with missing values", "handling": "dropped"})
    df = df[~na]
dup = df.duplicated()
if dup.any():
    issues.append({"issue": f"{int(dup.sum())} exact duplicate rows", "handling": "kept (cannot distinguish from genuine repeats); flagged"})
nonfinite = ~np.isfinite(df[["x", "y"]]).all(axis=1)
if nonfinite.any():
    issues.append({"issue": f"{int(nonfinite.sum())} non-finite values", "handling": "dropped"})
    df = df[~nonfinite]

X = sm.add_constant(df["x"].to_numpy())
y = df["y"].to_numpy()
g = df["firm_id"].to_numpy()
ols = sm.OLS(y, X).fit()
cl = sm.OLS(y, X).fit(cov_type="cluster", cov_kwds={"groups": g, "use_correction": True})
G = int(pd.Series(g).nunique())
beta, alpha = float(ols.params[1]), float(ols.params[0])
se_cl = float(cl.bse[1])
tcrit = float(stats.t.ppf(0.975, G - 1))  # t with G-1 df for clustered inference

res = {
    "task_id": "F2-smoke-01",
    "beta_hat": beta,
    "alpha_hat": alpha,
    "se_ols": float(ols.bse[1]),
    "se_cluster": se_cl,
    "beta_ci_low": beta - tcrit * se_cl,
    "beta_ci_high": beta + tcrit * se_cl,
    "n_analysed": int(len(df)),
    "n_clusters": G,
    "feasibility": "complete",
    "feasibility_reason": None,
    "data_issues": issues,
    "n_input_rows": {"panel.csv": int(n_input)},
    "random_seed": None,
    # supplementary diagnostics
    "se_cluster_ratio_to_ols": se_cl / float(ols.bse[1]),
    "t_crit_df": G - 1,
    "t_crit": tcrit,
    "cluster_sizes_min_max": [int(pd.Series(g).value_counts().min()), int(pd.Series(g).value_counts().max())],
}
os.makedirs("out", exist_ok=True)
with open("out/results.json", "w") as f:
    json.dump(res, f, indent=2)
print(json.dumps(res, indent=2))