Add offline workflow and coverage tests

tests/test_schema_failures.py

@@ -0,0 +1,98 @@
+"""Malformed parquet/input tests for phase boundary contracts."""
+
+from __future__ import annotations
+
+import pandas as pd
+import pytest
+
+from pipeline.alpha.compute import compute_alpha
+from pipeline.combo.combine import combine_alphas
+from pipeline.derived.compute import validate_derived_frame
+from pipeline.portfolio.construct import construct_positions
+from pipeline.portfolio.simulator import ReferenceSimulator
+from tests.helpers import make_generated_daily_bars
+
+
+def test_alpha_compute_rejects_daily_data_without_close():
+    daily = make_generated_daily_bars().drop(columns=["close"])
+
+    with pytest.raises(KeyError, match="close"):
+        compute_alpha(daily, "bad", "reversal", lookback=3)
+
+
+def test_alpha_feature_path_rejects_duplicate_symbol_dates(tmp_path):
+    daily = make_generated_daily_bars()
+    feature = pd.DataFrame({
+        "symbol_id": ["sh600000", "sh600000"],
+        "date": ["2024-01-02 09:30:00", "2024-01-02 15:00:00"],
+        "toy_feature": [1.0, 2.0],
+    })
+    feature_path = tmp_path / "duplicate_feature_keys.pq"
+    feature.to_parquet(feature_path, index=False)
+
+    with pytest.raises(ValueError, match="duplicate symbol_id,date"):
+        compute_alpha(
+            daily,
+            "bad_features",
+            "reversal",
+            lookback=3,
+            feature_paths=[str(feature_path)],
+        )
+
+
+def test_derived_validation_rejects_bool_value_columns():
+    derived = pd.DataFrame({
+        "symbol_id": ["sh600000"],
+        "date": [pd.Timestamp("2024-01-02")],
+        "is_good": [True],
+    })
+
+    with pytest.raises(ValueError, match="numeric"):
+        validate_derived_frame(derived)
+
+
+def test_combo_combine_rejects_missing_weight_column(tmp_path):
+    bad_alpha = pd.DataFrame({
+        "symbol_id": ["sh600000"],
+        "date": [pd.Timestamp("2024-01-02")],
+        "alpha_name": ["bad"],
+    })
+    bad_alpha_path = tmp_path / "bad_alpha.pq"
+    bad_alpha.to_parquet(bad_alpha_path, index=False)
+
+    with pytest.raises(KeyError, match="weight"):
+        combine_alphas([str(bad_alpha_path)], "bad_combo")
+
+
+def test_portfolio_build_rejects_weights_without_symbol_id():
+    daily = make_generated_daily_bars()
+    bad_weights = pd.DataFrame({
+        "date": [pd.Timestamp("2024-01-02")],
+        "combo_name": ["bad"],
+        "weight": [1.0],
+    })
+
+    with pytest.raises(KeyError, match="symbol_id"):
+        construct_positions(
+            bad_weights,
+            daily,
+            booksize=1_000_000.0,
+            portfolio_name="bad_portfolio",
+        )
+
+
+def test_portfolio_simulate_rejects_positions_without_position_shares():
+    daily = make_generated_daily_bars()
+    bad_positions = pd.DataFrame({
+        "symbol_id": ["sh600000"],
+        "date": [pd.Timestamp("2024-01-02")],
+        "portfolio_name": ["bad"],
+        "target_weight": [1.0],
+        "target_value": [1000.0],
+        "target_shares": [100.0],
+        "position_value": [1000.0],
+        "price": [10.0],
+    })
+
+    with pytest.raises(KeyError, match="position_shares"):
+        ReferenceSimulator().run(bad_positions, daily)