add tests

.gitignore

@@ -29,7 +29,6 @@ Thumbs.db
 ./webscrapper.db-wal
 .env
 .env.example
-/tests
 ._requirements.txt
 ._dockerfile
 /logs

tests/manual_test.py

@@ -0,0 +1,29 @@
+def run_manual_test(prediction_date):
+
+    # 1. Generate today's feature rows
+    features = build_live_features(
+        as_of_date=prediction_date
+    )
+
+    # 2. Validate against model metadata
+    validate_features(features)
+
+    # 3. Run XGBoost
+    predictions = predict(features)
+
+    # 4. Rank
+    predictions = rank_predictions(predictions)
+
+    # 5. Store
+    save_predictions(predictions)
+
+    # 6. Resolve using historical future data
+    resolve_predictions(
+        as_of_date=prediction_date
+    )
+
+    # 7. Calculate metrics
+    calculate_metrics()
+
+    # 8. Check retraining condition
+    check_retrain()

tests/test_metrics.py

@@ -0,0 +1,40 @@
+from datetime import date
+import pytest
+from evaluation.metrics import (
+    precision_at_threshold, hit_rate, positive_rate,
+    average_return, binary_pr_auc, rank_deciles, calculate_metrics
+)
+
+def test_precision():
+    assert precision_at_threshold([.9,.8,.4,.2], [1,0,1,0], .5) == .5
+
+def test_rates():
+    assert hit_rate([1,0,1,0,0]) == .4
+    assert positive_rate([1,0,1,0,0]) == .4
+
+def test_average_return():
+    assert average_return([.03,.05,-.01]) == pytest.approx(.0233333333)
+
+def test_pr_auc():
+    assert binary_pr_auc([.9,.8,.2,.1], [1,1,0,0]) == pytest.approx(1.0)
+
+def test_deciles():
+    probs = list(reversed([i/100 for i in range(1,101)]))
+    deciles = rank_deciles(probs, [1]*100, [.03]*100)
+    assert len(deciles) == 10
+    assert all(d["count"] == 10 for d in deciles)
+
+def test_complete_metrics():
+    rows = [
+        {"prediction_date":date(2026,7,1),"symbol":"AAA","predicted_probability":.9,"actual_label":1,"actual_return":.05},
+        {"prediction_date":date(2026,7,1),"symbol":"BBB","predicted_probability":.4,"actual_label":0,"actual_return":-.02},
+        {"prediction_date":date(2026,7,2),"symbol":"AAA","predicted_probability":.8,"actual_label":1,"actual_return":.04},
+        {"prediction_date":date(2026,7,2),"symbol":"BBB","predicted_probability":.3,"actual_label":0,"actual_return":-.01},
+    ]
+    result = calculate_metrics(rows, threshold=.5)
+    assert result.prediction_days == 2
+    assert result.resolved_predictions == 4
+    assert result.precision == 1.0
+    assert result.hit_rate == .5
+    assert result.average_return == pytest.approx(.015)
+    assert len(result.deciles) == 10

tests/test_resolver.py

@@ -0,0 +1,76 @@
+from datetime import date
+
+# from evaluation.resolver import resolve_prediction_rows
+
+from jobs import resolver
+
+
+def test_positive_prediction():
+    result = resolver.resolve_prediction_rows(
+        prediction_date=date(2026, 8, 3),
+        symbol="ABC",
+        future_rows=[
+            {"date": date(2026, 8, 4), "open": 100.0, "close": 101.0},
+            {"date": date(2026, 8, 5), "open": 101.0, "close": 102.0},
+            {"date": date(2026, 8, 6), "open": 102.0, "close": 103.0},
+            {"date": date(2026, 8, 7), "open": 103.0, "close": 104.0},
+            {"date": date(2026, 8, 10), "open": 104.0, "close": 104.0},
+        ],
+    )
+
+    assert result is not None
+    assert result.entry_date == date(2026, 8, 4)
+    assert result.entry_open == 100.0
+    assert result.max_close == 104.0
+    assert result.actual_return == 0.04
+    assert result.actual_label == 1
+
+
+def test_exact_three_percent_is_positive():
+    result = resolver.resolve_prediction_rows(
+        prediction_date=date(2026, 8, 3),
+        symbol="ABC",
+        future_rows=[
+            {"date": date(2026, 8, 4), "open": 100.0, "close": 103.0},
+            {"date": date(2026, 8, 5), "open": 103.0, "close": 101.0},
+            {"date": date(2026, 8, 6), "open": 101.0, "close": 100.0},
+            {"date": date(2026, 8, 7), "open": 100.0, "close": 99.0},
+            {"date": date(2026, 8, 10), "open": 99.0, "close": 98.0},
+        ],
+    )
+
+    assert result is not None
+    assert result.actual_return == 0.03
+    assert result.actual_label == 1
+
+
+def test_below_three_percent_is_negative():
+    result = resolver.resolve_prediction_rows(
+        prediction_date=date(2026, 8, 3),
+        symbol="ABC",
+        future_rows=[
+            {"date": date(2026, 8, 4), "open": 100.0, "close": 102.99},
+            {"date": date(2026, 8, 5), "open": 102.0, "close": 102.5},
+            {"date": date(2026, 8, 6), "open": 102.0, "close": 101.0},
+            {"date": date(2026, 8, 7), "open": 101.0, "close": 100.0},
+            {"date": date(2026, 8, 10), "open": 100.0, "close": 99.0},
+        ],
+    )
+
+    assert result is not None
+    assert result.actual_return < 0.03
+    assert result.actual_label == 0
+
+
+def test_incomplete_window_stays_unresolved():
+    result = resolver.resolve_prediction_rows(
+        prediction_date=date(2026, 8, 3),
+        symbol="ABC",
+        future_rows=[
+            {"date": date(2026, 8, 4), "open": 100.0, "close": 105.0},
+            {"date": date(2026, 8, 5), "open": 105.0, "close": 105.0},
+            {"date": date(2026, 8, 6), "open": 105.0, "close": 105.0},
+        ],
+    )
+
+    assert result is None

tests/test_retrain_trigger.py

@@ -0,0 +1,27 @@
+import pytest
+from evaluation.retrain_trigger import (
+    calculate_deterioration, evaluate_retrain_trigger
+)
+
+def test_15_percent_deterioration_triggers():
+    result = evaluate_retrain_trigger(0.60, 0.51)
+    assert result.should_flag is True
+    assert result.deterioration == pytest.approx(0.15)
+
+def test_less_than_15_percent_deterioration_does_not_trigger():
+    result = evaluate_retrain_trigger(0.60, 0.52)
+    assert result.should_flag is False
+    assert result.deterioration == pytest.approx(0.1333333333)
+
+def test_improvement_does_not_trigger():
+    result = evaluate_retrain_trigger(0.60, 0.65)
+    assert result.should_flag is False
+    assert result.deterioration < 0
+
+def test_no_metric_does_not_trigger():
+    result = evaluate_retrain_trigger(0.60, None)
+    assert result.should_flag is False
+    assert result.deterioration is None
+
+def test_deterioration_formula():
+    assert calculate_deterioration(0.50, 0.425) == pytest.approx(0.15)