Add lazy polars I/O and duplicate KL/constraint checks for giant.analysis

load_predicted_local now reads predict parquet via a lazy polars scan with
column projection pushed into the reader, instead of materializing the
whole file as a pandas DataFrame. Also adds marginal_table_pl and
constraint_report_pl, polars-native duplicates that read straight from a
predict parquet path/LazyFrame and stay lazy per (group, dim) pair, so
peak memory is one column slice rather than the whole SampleCollection.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/test_analysis.py

@@ -12,10 +12,12 @@ from giant.analysis import (
     RAW_TARGET_NAMES,
     SampleCollection,
     constraint_report,
+    constraint_report_pl,
     correlation_matrices,
     direction_alignment,
     load_predicted_local,
     marginal_table,
+    marginal_table_pl,
     plot_constraint_violations,
     plot_correlation_matrices,
     plot_direction_alignment,
@@ -241,3 +243,56 @@ def test_load_predicted_local_rejects_mismatched_schema_version(tmp_path):
     )
     with pytest.raises(ValueError, match="schema version"):
         load_predicted_local(path)
+
+
+def _predicted_local_path(tmp_path, n=200, seed=0):
+    path = tmp_path / "predicted_local.parquet"
+    _write_predicted_local_parquet(
+        path,
+        n=n,
+        rng=np.random.default_rng(seed),
+        metadata={
+            PREDICT_COORD_METADATA_KEY: "local",
+            PREDICT_SCHEMA_VERSION_KEY: PREDICT_SCHEMA_VERSION,
+        },
+    )
+    return path
+
+
+@pytest.mark.parametrize("group_by", [None, "pdg", "material", "energy"])
+def test_marginal_table_pl_matches_numpy_version(tmp_path, group_by):
+    path = _predicted_local_path(tmp_path)
+    collection = load_predicted_local(path)
+
+    expected = marginal_table(collection, group_by=group_by).sort_values(["group", "dim"])
+    actual = marginal_table_pl(path, group_by=group_by).sort(["group", "dim"]).to_pandas()
+
+    assert list(expected["group"]) == list(actual["group"])
+    assert list(expected["n"]) == list(actual["n"])
+    for col in ["real_mean", "gen_mean", "real_std", "gen_std", "kl_real_gen"]:
+        np.testing.assert_allclose(
+            expected[col].to_numpy(), actual[col].to_numpy(), atol=1e-4, rtol=1e-4,
+        )
+
+
+def test_marginal_table_pl_rejects_missing_metadata(tmp_path):
+    path = tmp_path / "no_metadata.parquet"
+    _write_predicted_local_parquet(path, metadata=None)
+    with pytest.raises(ValueError, match="no '.*' parquet metadata"):
+        marginal_table_pl(path)
+
+
+def test_constraint_report_pl_matches_numpy_version(tmp_path):
+    path = _predicted_local_path(tmp_path)
+    collection = load_predicted_local(path)
+
+    expected = constraint_report(collection)
+    actual = constraint_report_pl(path).to_pandas()
+
+    assert list(expected["check"]) == list(actual["check"])
+    np.testing.assert_allclose(
+        expected["violation_rate"].to_numpy(), actual["violation_rate"].to_numpy(), atol=1e-6,
+    )
+    np.testing.assert_allclose(
+        expected["mean_abs_error"].to_numpy(), actual["mean_abs_error"].to_numpy(), atol=1e-4,
+    )