auto-infer locations for predict_dte/pte/ldte/lpte (#68)

[okiner-3]

Summary

Closes #68. Make the locations argument optional in predict_dte, predict_pte, predict_ldte, and predict_lpte. When omitted, locations are generated automatically from the observed outcomes so users no longer need to write np.linspace(Y.min(), Y.max(), N) themselves.

Behavior

• locations=None (default) → evenly-spaced locations spanning [Y.min(), Y.max()], with the bin count derived from np.histogram_bin_edges(outcomes, bins='auto') (combines Sturges and Freedman-Diaconis rules, scaling with data size and IQR).
• For predict_pte / predict_lpte, the left endpoint is shifted just below outcomes.min() so that the smallest observation falls inside the first interval (loc[0], loc[1]].
• locations=ndarray (existing behavior) → used as-is. Fully backward compatible.
• The actual locations array used is stored on estimator.last_locations for plotting / downstream use.

Example

# Before
locations = np.linspace(Y.min(), Y.max(), 20)
dte, lo, hi = est.predict_dte(1, 0, locations)
plot(locations, dte, lo, hi, ...)

# After
dte, lo, hi = est.predict_dte(1, 0)
plot(est.last_locations, dte, lo, hi, ...)

Test plan

• Added _infer_default_locations unit tests (tests/test_utils.py).
• Added auto-locations tests for SimpleDistributionEstimator.predict_dte / predict_pte (tests/test_simple_estimator.py).
• Added auto-locations tests for SimpleLocalDistributionEstimator.predict_ldte / predict_lpte (tests/test_local_estimators.py).
• Existing 49 tests still pass; total 59 tests pass.