liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
"""Empty battle DataFrame must not crash Bradley-Terry LogisticRegression."""
|
|
import pandas as pd
|
|
|
|
from bradley_terry import compute_bradley_terry_leaderboard, compute_mle_elo
|
|
|
|
|
|
def test_compute_mle_elo_empty_battles():
|
|
df = pd.DataFrame(columns=["model_a", "model_b", "winner"])
|
|
ratings = compute_mle_elo(df)
|
|
assert isinstance(ratings, pd.Series)
|
|
assert len(ratings) == 0
|
|
|
|
|
|
def test_compute_bradley_terry_leaderboard_empty():
|
|
df = pd.DataFrame(columns=["model_a", "model_b", "winner"])
|
|
board = compute_bradley_terry_leaderboard(df)
|
|
assert isinstance(board, pd.DataFrame)
|
|
assert len(board) == 0
|
|
|
|
|
|
def test_nonempty_still_rates():
|
|
df = pd.DataFrame(
|
|
[
|
|
{"model_a": "A", "model_b": "B", "winner": "model_a"},
|
|
{"model_a": "A", "model_b": "B", "winner": "model_a"},
|
|
{"model_a": "B", "model_b": "C", "winner": "model_b"},
|
|
{"model_a": "A", "model_b": "C", "winner": "model_a"},
|
|
]
|
|
)
|
|
ratings = compute_mle_elo(df)
|
|
assert set(ratings.index) >= {"A", "B", "C"}
|
|
assert ratings["A"] > ratings["C"]
|