Add offline workflow and coverage tests

2026-06-16 17:37:16 +08:00
parent 8d908477e2
commit 31baa18ce5
16 changed files with 2104 additions and 9 deletions
@@ -413,3 +413,92 @@ def test_feature_aware_alpha_reads_joined_feature_column(tmp_path):
    assert (result["alpha_name"] == "feature_run").all()
    last = result[result["date"] == result["date"].max()]
    assert last.set_index("symbol_id")["weight"].idxmax() == "sh600519"
+
+
+def test_feature_paths_join_multiple_files_and_normalize_dates(tmp_path):
+    module_path = tmp_path / "multi_feature_alpha.py"
+    module_path.write_text(textwrap.dedent('''
+        import pandas as pd
+        from pipeline.alpha.base import BaseAlpha
+        from pipeline.alpha.registry import register_alpha
+
+        @register_alpha
+        class MultiFeatureAlpha(BaseAlpha):
+            name = "multi_feature_test_alpha"
+
+            def signal_from_data(
+                self,
+                data: pd.DataFrame,
+                close: pd.DataFrame,
+            ) -> pd.DataFrame:
+                data = data.copy()
+                data["combined_feature"] = data["toy_a"] + data["toy_b"]
+                signal = data.pivot_table(
+                    index="date",
+                    columns="symbol_id",
+                    values="combined_feature",
+                    aggfunc="first",
+                )
+                return signal.reindex(index=close.index, columns=close.columns)
+    '''))
+
+    data = _make_data(n_days=8)
+    symbol_score = {"sh600000": 1.0, "sz000001": 2.0, "sh600519": 3.0}
+
+    feature_a = data[["symbol_id", "date"]].copy()
+    feature_a["date"] = feature_a["date"] + pd.Timedelta(hours=15)
+    feature_a["toy_a"] = feature_a["symbol_id"].map(symbol_score)
+
+    feature_b = data[["symbol_id", "date"]].copy()
+    feature_b["date"] = feature_b["date"].dt.strftime("%Y-%m-%d 09:30:00")
+    feature_b["toy_b"] = feature_b["symbol_id"].map(symbol_score) * 10.0
+
+    feature_a_path = tmp_path / "toy_a.pq"
+    feature_b_path = tmp_path / "toy_b.pq"
+    feature_a.to_parquet(feature_a_path, index=False)
+    feature_b.to_parquet(feature_b_path, index=False)
+
+    load_alpha_module(str(module_path))
+    result = compute_alpha(
+        data,
+        "multi_feature_run",
+        "multi_feature_test_alpha",
+        feature_paths=[str(feature_a_path), str(feature_b_path)],
+    )
+
+    assert list(result.columns) == ALPHA_COLUMNS
+    assert (result["alpha_name"] == "multi_feature_run").all()
+    last = result[result["date"] == result["date"].max()]
+    assert last.set_index("symbol_id")["weight"].idxmax() == "sh600519"
+
+
+def test_compute_alpha_rejects_duplicate_feature_frame_columns():
+    data = _make_data()
+    duplicate_columns = pd.DataFrame(
+        [["sh600000", pd.Timestamp("2024-01-01"), 1.0, 2.0]],
+        columns=["symbol_id", "date", "toy_feature", "toy_feature"],
+    )
+
+    with pytest.raises(ValueError, match="duplicate columns"):
+        compute_alpha(
+            data,
+            "bad_features",
+            "reversal",
+            feature_frames=[duplicate_columns],
+        )
+
+
+def test_compute_alpha_rejects_feature_path_collision_with_daily_data(tmp_path):
+    data = _make_data()
+    close_collision = data[["symbol_id", "date"]].copy()
+    close_collision["close"] = 1.0
+    close_collision_path = tmp_path / "close_collision.pq"
+    close_collision.to_parquet(close_collision_path, index=False)
+
+    with pytest.raises(ValueError, match="conflict"):
+        compute_alpha(
+            data,
+            "close_collision",
+            "reversal",
+            feature_paths=[str(close_collision_path)],
+        )