feat(screener): AiNewsSentiment ScoreNode (percentile_rank + min_news_count)

stock-lab/tests/test_ai_news_node.py

@@ -0,0 +1,57 @@
+import datetime as dt
+import pandas as pd
+import pytest
+from app.screener.nodes.ai_news import AiNewsSentiment
+
+
+class FakeCtx:
+    def __init__(self, df=None):
+        self.news_sentiment = df
+        self.asof = dt.date(2026, 5, 13)
+
+
+def test_compute_empty_context():
+    out = AiNewsSentiment().compute(FakeCtx(None), {"min_news_count": 1})
+    assert out.empty
+
+
+def test_compute_with_data_percentile_ranks():
+    df = pd.DataFrame([
+        {"ticker": "A", "score_raw": -5.0, "news_count": 3},
+        {"ticker": "B", "score_raw":  0.0, "news_count": 3},
+        {"ticker": "C", "score_raw":  8.0, "news_count": 3},
+    ])
+    out = AiNewsSentiment().compute(FakeCtx(df), {"min_news_count": 1})
+    assert len(out) == 3
+    # percentile rank: A (lowest) < B < C (highest)
+    assert out.loc["A"] < out.loc["B"] < out.loc["C"]
+    # all within [0, 100]
+    assert (out >= 0).all() and (out <= 100).all()
+
+
+def test_compute_filters_by_min_news_count():
+    df = pd.DataFrame([
+        {"ticker": "A", "score_raw": -5.0, "news_count": 0},  # 필터됨
+        {"ticker": "B", "score_raw":  0.0, "news_count": 2},
+        {"ticker": "C", "score_raw":  8.0, "news_count": 5},
+    ])
+    out = AiNewsSentiment().compute(FakeCtx(df), {"min_news_count": 1})
+    assert "A" not in out.index
+    assert "B" in out.index
+    assert "C" in out.index
+
+
+def test_compute_all_filtered_returns_empty():
+    df = pd.DataFrame([
+        {"ticker": "A", "score_raw": 5.0, "news_count": 0},
+    ])
+    out = AiNewsSentiment().compute(FakeCtx(df), {"min_news_count": 1})
+    assert out.empty
+
+
+def test_metadata():
+    n = AiNewsSentiment()
+    assert n.name == "ai_news"
+    assert "AI" in n.label or "뉴스" in n.label
+    assert n.default_params == {"min_news_count": 1}
+    assert "min_news_count" in n.param_schema["properties"]