feat: add PIT OHLCV runner and fetch support

tests/test_fetch_historical.py

@@ -0,0 +1,46 @@
+import tempfile
+import unittest
+from pathlib import Path
+from unittest import mock
+
+import pandas as pd
+
+from research import fetch_historical
+
+
+class FetchHistoricalTests(unittest.TestCase):
+    def test_fetch_all_historical_ohlcv_writes_field_specific_csvs(self):
+        dates = pd.to_datetime(["2024-01-02", "2024-01-03"])
+        raw = pd.DataFrame(
+            {
+                ("Close", "AAA"): [10.0, 11.0],
+                ("Close", "BBB"): [20.0, 21.0],
+                ("High", "AAA"): [10.5, 11.5],
+                ("High", "BBB"): [20.5, 21.5],
+                ("Low", "AAA"): [9.5, 10.5],
+                ("Low", "BBB"): [19.5, 20.5],
+                ("Volume", "AAA"): [1000.0, 1100.0],
+                ("Volume", "BBB"): [2000.0, 2100.0],
+            },
+            index=dates,
+        )
+        raw.columns = pd.MultiIndex.from_tuples(raw.columns)
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            with mock.patch.object(fetch_historical, "DATA_DIR", tmpdir):
+                with mock.patch.object(fetch_historical, "OUT_PATH", str(Path(tmpdir) / "us_pit.csv")):
+                    with mock.patch("research.fetch_historical.uh.load_sp500_history", return_value={"AAA": [[None, None]], "BBB": [[None, None]]}):
+                        with mock.patch("research.fetch_historical.uh.all_tickers_ever", return_value=["AAA", "BBB"]):
+                            with mock.patch("research.fetch_historical.yf.download", return_value=raw):
+                                panels = fetch_historical.fetch_all_historical_ohlcv(force=True)
+
+            self.assertEqual(set(panels.keys()), {"close", "high", "low", "volume"})
+            self.assertTrue((Path(tmpdir) / "us_pit.csv").exists())
+            self.assertTrue((Path(tmpdir) / "us_pit_close.csv").exists())
+            self.assertTrue((Path(tmpdir) / "us_pit_high.csv").exists())
+            self.assertTrue((Path(tmpdir) / "us_pit_low.csv").exists())
+            self.assertTrue((Path(tmpdir) / "us_pit_volume.csv").exists())
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_us_alpha_pipeline.py

@@ -1,4 +1,6 @@
 import unittest
+from pathlib import Path
+from unittest import mock
 
 import pandas as pd
 
@@ -33,9 +35,22 @@ class USAlphaPipelineTests(unittest.TestCase):
 
         equity = _equity_curve(close, weights)
 
-        self.assertEqual(float(equity.iloc[1]), 1.0)
+        self.assertEqual(float(equity.iloc[1]), 2.0)
         self.assertEqual(float(equity.iloc[2]), 2.0)
 
+    def test_summarize_equity_window_returns_nans_when_history_is_too_short(self):
+        from research.us_alpha_report import summarize_equity_window
+
+        dates = pd.date_range("2024-01-01", periods=10, freq="D")
+        equity = pd.Series([1.0 + 0.01 * i for i in range(10)], index=dates)
+
+        summary = summarize_equity_window(equity, "demo", window_years=1)
+
+        self.assertTrue(pd.isna(summary["CAGR"]))
+        self.assertTrue(pd.isna(summary["Sharpe"]))
+        self.assertTrue(pd.isna(summary["MaxDD"]))
+        self.assertTrue(pd.isna(summary["TotalRet"]))
+
     def test_run_alpha_pipeline_returns_expected_strategy_summary(self):
         from research.us_alpha_pipeline import run_alpha_pipeline
 
@@ -109,6 +124,41 @@ class USAlphaPipelineTests(unittest.TestCase):
         self.assertEqual(len(summary), 2)
         self.assertTrue(summary[["CAGR", "Sharpe", "MaxDD", "TotalRet"]].notna().all().all())
 
+    def test_run_saved_pit_alpha_pipeline_reads_saved_inputs(self):
+        from research.us_alpha_pipeline import run_saved_pit_alpha_pipeline
+
+        dates = pd.date_range("2024-01-01", periods=320, freq="D")
+        close = pd.DataFrame(
+            {
+                "AAA": [50.0 + 0.2 * i for i in range(320)],
+                "BBB": [40.0 + 0.1 * i for i in range(320)],
+            },
+            index=dates,
+        )
+        high = close + 1.0
+        low = close - 1.0
+        volume = pd.DataFrame({"AAA": [2_500_000.0] * 320, "BBB": [2_000_000.0] * 320}, index=dates)
+        etf_close = pd.DataFrame(
+            {"SPY": [300.0 + 0.8 * i for i in range(320)], "QQQ": [280.0 + 1.1 * i for i in range(320)]},
+            index=dates,
+        )
+
+        with self.subTest("saved_inputs"):
+            import tempfile
+
+            with tempfile.TemporaryDirectory() as tmpdir:
+                close.to_csv(Path(tmpdir) / "us_pit_close.csv")
+                high.to_csv(Path(tmpdir) / "us_pit_high.csv")
+                low.to_csv(Path(tmpdir) / "us_pit_low.csv")
+                volume.to_csv(Path(tmpdir) / "us_pit_volume.csv")
+                etf_close.to_csv(Path(tmpdir) / "us_etf.csv")
+
+                intervals = {"AAA": [[None, None]], "BBB": [[None, None]]}
+                with mock.patch("research.us_alpha_pipeline.uh.load_sp500_history", return_value=intervals):
+                    summary = run_saved_pit_alpha_pipeline(data_dir=tmpdir, windows=(1,), top_n=1)
+
+        self.assertEqual(set(summary["strategy"]), {"breakout_regime", "rank_blend_regime"})
+
 
 if __name__ == "__main__":
     unittest.main()