| 1 | """Tests for hype_risk scoring model.""" |
| 2 | |
| 3 | import json |
| 4 | import sys |
| 5 | from pathlib import Path |
| 6 | |
| 7 | sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "scripts")) |
| 8 | from hype_risk import classify_repo, extract_week, score_hype_risk # noqa: E402 |
| 9 | |
| 10 | |
| 11 | class TestClassifyRepo: |
| 12 | """Test individual repo classification paths.""" |
| 13 | |
| 14 | def test_no_press_correlation(self): |
| 15 | """Not press_correlated → risk = 'none'.""" |
| 16 | result = classify_repo("org/repo", press_correlated=False) |
| 17 | assert result["hype_risk"] == "none" |
| 18 | assert result["label"] == "No press signal" |
| 19 | assert result["press_correlated"] is False |
| 20 | |
| 21 | def test_press_correlated_no_previous_data(self): |
| 22 | """Press correlated but no previous data → risk = 'medium'.""" |
| 23 | result = classify_repo( |
| 24 | "org/repo", |
| 25 | press_correlated=True, |
| 26 | current_stars=1000, |
| 27 | current_stars_gained=200, |
| 28 | previous_stars=None, |
| 29 | previous_stars_gained=None, |
| 30 | ) |
| 31 | assert result["hype_risk"] == "medium" |
| 32 | assert result["press_correlated"] is True |
| 33 | assert result["confidence"] < 0.6 |
| 34 | |
| 35 | def test_organic_growth_before_press(self): |
| 36 | """Stars already growing before press → risk = 'very_low'.""" |
| 37 | result = classify_repo( |
| 38 | "org/repo", |
| 39 | press_correlated=True, |
| 40 | current_stars=2000, |
| 41 | current_stars_gained=100, |
| 42 | previous_stars=1900, |
| 43 | previous_stars_gained=80, # Already had strong growth |
| 44 | ) |
| 45 | assert result["hype_risk"] == "very_low" |
| 46 | assert result["label"] == "Organic growth" |
| 47 | assert result["stars_trend"] == "organic" |
| 48 | |
| 49 | def test_sustained_growth_after_press(self): |
| 50 | """Stars spike after article and sustain → risk = 'low'.""" |
| 51 | result = classify_repo( |
| 52 | "org/repo", |
| 53 | press_correlated=True, |
| 54 | current_stars=5000, |
| 55 | current_stars_gained=500, |
| 56 | previous_stars=4500, |
| 57 | previous_stars_gained=100, # Small growth before, big growth now |
| 58 | ) |
| 59 | assert result["hype_risk"] == "low" |
| 60 | assert result["label"] == "Press-validated, community-sustained" |
| 61 | assert result["stars_trend"] == "sustained" |
| 62 | |
| 63 | def test_decaying_growth_after_press(self): |
| 64 | """Stars spiked but now fading → risk = 'high'.""" |
| 65 | result = classify_repo( |
| 66 | "org/repo", |
| 67 | press_correlated=True, |
| 68 | current_stars=5000, |
| 69 | current_stars_gained=50, # Much lower than previous |
| 70 | previous_stars=4950, |
| 71 | previous_stars_gained=500, # Big spike last week |
| 72 | ) |
| 73 | assert result["hype_risk"] == "high" |
| 74 | assert result["label"] == "Press-driven hype, fading" |
| 75 | assert result["stars_trend"] == "decaying" |
| 76 | |
| 77 | def test_press_correlated_no_activity_spike(self): |
| 78 | """Press coverage but no GitHub activity spike → risk = 'medium'.""" |
| 79 | result = classify_repo( |
| 80 | "org/repo", |
| 81 | press_correlated=True, |
| 82 | current_stars=100, |
| 83 | current_stars_gained=0, |
| 84 | previous_stars=100, |
| 85 | previous_stars_gained=0, |
| 86 | ) |
| 87 | assert result["hype_risk"] == "medium" |
| 88 | assert result["label"] == "Announced but unbuilt" |
| 89 | |
| 90 | def test_assessment_has_all_fields(self): |
| 91 | """Every assessment should have all required fields.""" |
| 92 | result = classify_repo("org/repo", press_correlated=False) |
| 93 | assert "repo" in result |
| 94 | assert "hype_risk" in result |
| 95 | assert "label" in result |
| 96 | assert "press_correlated" in result |
| 97 | assert "stars_trend" in result |
| 98 | assert "confidence" in result |
| 99 | assert "reasoning" in result |
| 100 | |
| 101 | |
| 102 | class TestScoreHypeRisk: |
| 103 | """Test the batch scoring function.""" |
| 104 | |
| 105 | def test_empty_correlations(self): |
| 106 | result = score_hype_risk({"correlations": []}, None, None) |
| 107 | assert result == [] |
| 108 | |
| 109 | def test_scores_correlated_repos(self): |
| 110 | correlations = { |
| 111 | "correlations": [ |
| 112 | {"repo": "org/alpha", "press_correlated": True}, |
| 113 | {"repo": "org/beta", "press_correlated": False}, |
| 114 | ] |
| 115 | } |
| 116 | raw_data = [ |
| 117 | {"full_name": "org/alpha", "stars": 1000, "stars_gained": 200}, |
| 118 | {"full_name": "org/beta", "stars": 500, "stars_gained": 10}, |
| 119 | ] |
| 120 | result = score_hype_risk(correlations, raw_data, None) |
| 121 | assert len(result) == 2 |
| 122 | |
| 123 | alpha = next(a for a in result if a["repo"] == "org/alpha") |
| 124 | beta = next(a for a in result if a["repo"] == "org/beta") |
| 125 | |
| 126 | assert alpha["hype_risk"] == "medium" # correlated, no previous |
| 127 | assert beta["hype_risk"] == "none" # not correlated |
| 128 | |
| 129 | def test_with_previous_data(self): |
| 130 | correlations = { |
| 131 | "correlations": [ |
| 132 | {"repo": "org/sustained", "press_correlated": True}, |
| 133 | ] |
| 134 | } |
| 135 | raw_data = [ |
| 136 | {"full_name": "org/sustained", "stars": 3000, "stars_gained": 400}, |
| 137 | ] |
| 138 | previous_data = [ |
| 139 | {"full_name": "org/sustained", "stars": 2600, "stars_gained": 50}, |
| 140 | ] |
| 141 | result = score_hype_risk(correlations, raw_data, previous_data) |
| 142 | sustained = next(a for a in result if a["repo"] == "org/sustained") |
| 143 | assert sustained["hype_risk"] == "low" |
| 144 | |
| 145 | def test_raw_data_wrapped_in_dict(self): |
| 146 | """Raw data may be wrapped in a dict with 'repos' key.""" |
| 147 | correlations = {"correlations": [{"repo": "x/y", "press_correlated": False}]} |
| 148 | raw_data = {"repos": [{"full_name": "x/y", "stars": 10, "stars_gained": 1}]} |
| 149 | result = score_hype_risk(correlations, raw_data, None) |
| 150 | assert len(result) == 1 |
| 151 | assert result[0]["hype_risk"] == "none" |
| 152 | |
| 153 | |
| 154 | class TestExtractWeek: |
| 155 | def test_simple_week(self): |
| 156 | assert extract_week("data/raw/ai-ml/2026-W21.json") == "2026-W21" |
| 157 | |
| 158 | def test_correlations_suffix(self): |
| 159 | assert extract_week("data/analyzed/ai-ml/2026-W21-correlations.json") == "2026-W21" |
| 160 | |
| 161 | def test_none_path(self): |
| 162 | assert extract_week(None) == "unknown" |
| 163 | |
| 164 | |
| 165 | class TestCLI: |
| 166 | """Test CLI main function.""" |
| 167 | |
| 168 | def test_main_with_files(self, tmp_path): |
| 169 | from hype_risk import main |
| 170 | |
| 171 | corr_file = tmp_path / "correlations.json" |
| 172 | raw_file = tmp_path / "2026-W21.json" |
| 173 | out_file = tmp_path / "output.json" |
| 174 | |
| 175 | corr_file.write_text( |
| 176 | json.dumps({"correlations": [{"repo": "org/repo", "press_correlated": True}]}) |
| 177 | ) |
| 178 | raw_file.write_text( |
| 179 | json.dumps([{"full_name": "org/repo", "stars": 500, "stars_gained": 100}]) |
| 180 | ) |
| 181 | |
| 182 | main( |
| 183 | [ |
| 184 | "--correlations", |
| 185 | str(corr_file), |
| 186 | "--raw", |
| 187 | str(raw_file), |
| 188 | "--output", |
| 189 | str(out_file), |
| 190 | ] |
| 191 | ) |
| 192 | |
| 193 | output = json.loads(out_file.read_text()) |
| 194 | assert output["week"] == "2026-W21" |
| 195 | assert len(output["assessments"]) == 1 |
| 196 | assert output["assessments"][0]["repo"] == "org/repo" |