|
| 1 | +import warnings |
| 2 | +from pathlib import Path |
| 3 | + |
| 4 | +import pandas as pd |
| 5 | +from fast_langdetect import detect_language |
| 6 | +from huggingface_hub import snapshot_download |
| 7 | + |
| 8 | + |
| 9 | +def _extract_instruction_text(turn: dict) -> str: |
| 10 | + """Extract plain instruction text from a conversation first turn. |
| 11 | +
|
| 12 | + Handles both the 100k schema (content is a plain string) and the 140k |
| 13 | + schema (content is an array of {type, text, ...} objects). |
| 14 | + """ |
| 15 | + content = turn["content"] |
| 16 | + if isinstance(content, str): |
| 17 | + return content |
| 18 | + return " ".join(block["text"] for block in content if block.get("type") == "text") |
| 19 | + |
| 20 | + |
| 21 | +KNOWN_ARENAS = ["LMArena-100k", "LMArena-140k", "ComparIA"] |
| 22 | + |
| 23 | + |
| 24 | +def _load_arena_dataframe( |
| 25 | + arena: str, comparia_revision: str | None = None |
| 26 | +) -> pd.DataFrame: |
| 27 | + assert arena in KNOWN_ARENAS |
| 28 | + if "LMArena" in arena: |
| 29 | + size = arena.split("-")[1] # "100k" or "140k" |
| 30 | + path = snapshot_download( |
| 31 | + repo_id=f"lmarena-ai/arena-human-preference-{size}", |
| 32 | + repo_type="dataset", |
| 33 | + allow_patterns="*parquet", |
| 34 | + force_download=False, |
| 35 | + ) |
| 36 | + parquet_files = sorted((Path(path) / "data").glob("*.parquet")) |
| 37 | + df = pd.concat([pd.read_parquet(f) for f in parquet_files], ignore_index=True) |
| 38 | + |
| 39 | + if "tstamp" in df.columns: |
| 40 | + # 100k: tstamp is a unix timestamp in seconds |
| 41 | + df["date"] = pd.to_datetime(df["tstamp"], unit="s") |
| 42 | + else: |
| 43 | + # 140k: timestamp is already a datetime |
| 44 | + df["tstamp"] = df["timestamp"].astype("int64") // 10**9 |
| 45 | + df["date"] = df["timestamp"] |
| 46 | + |
| 47 | + if "question_id" not in df.columns: |
| 48 | + df["question_id"] = df["id"] |
| 49 | + |
| 50 | + # 140k uses "both_bad" instead of "tie (bothbad)" |
| 51 | + df["winner"] = df["winner"].replace("both_bad", "tie (bothbad)") |
| 52 | + |
| 53 | + df["benchmark"] = arena |
| 54 | + |
| 55 | + else: |
| 56 | + path = snapshot_download( |
| 57 | + repo_id="ministere-culture/comparia-votes", |
| 58 | + repo_type="dataset", |
| 59 | + allow_patterns="*", |
| 60 | + revision=comparia_revision, |
| 61 | + force_download=False, |
| 62 | + ) |
| 63 | + |
| 64 | + df = pd.read_parquet(Path(path) / "votes.parquet") |
| 65 | + |
| 66 | + # unify schema |
| 67 | + df["tstamp"] = df["timestamp"] |
| 68 | + df["model_a"] = df["model_a_name"] |
| 69 | + df["model_b"] = df["model_b_name"] |
| 70 | + |
| 71 | + def get_winner( |
| 72 | + chosen_model_name: str, |
| 73 | + model_a: str, |
| 74 | + model_b: str, |
| 75 | + both_equal: bool, |
| 76 | + **kwargs, |
| 77 | + ): |
| 78 | + if both_equal: |
| 79 | + return "tie" |
| 80 | + else: |
| 81 | + if chosen_model_name is None or isinstance(chosen_model_name, float): |
| 82 | + return None |
| 83 | + if chosen_model_name not in [model_a, model_b]: |
| 84 | + warnings.warn( |
| 85 | + f"Chosen model {chosen_model_name!r} not in model_a={model_a!r} or model_b={model_b!r}; skipping." |
| 86 | + ) |
| 87 | + return None |
| 88 | + return "model_a" if chosen_model_name == model_a else "model_b" |
| 89 | + |
| 90 | + df["winner"] = df.apply(lambda row: get_winner(**row), axis=1) |
| 91 | + |
| 92 | + # filter battles without winner annotated |
| 93 | + df = df[~df.winner.isna()] |
| 94 | + df["benchmark"] = "ComparIA" |
| 95 | + df["question_id"] = df["id"] |
| 96 | + |
| 97 | + df["lang"] = df["conversation_a"].apply( |
| 98 | + lambda conv: detect_language(_extract_instruction_text(conv[0])).lower() |
| 99 | + ) |
| 100 | + |
| 101 | + cols = [ |
| 102 | + "question_id", |
| 103 | + "tstamp", |
| 104 | + "model_a", |
| 105 | + "model_b", |
| 106 | + "winner", |
| 107 | + "conversation_a", |
| 108 | + "conversation_b", |
| 109 | + "benchmark", |
| 110 | + "lang", |
| 111 | + ] |
| 112 | + df = df.loc[:, cols] |
| 113 | + |
| 114 | + # keep only one turn conversation for now as they are easier to evaluate |
| 115 | + df["turns"] = df.apply(lambda row: len(row["conversation_a"]) - 1, axis=1) |
| 116 | + n_before = len(df) |
| 117 | + df = df.loc[df.turns == 1] |
| 118 | + n_dropped = n_before - len(df) |
| 119 | + if n_dropped > 0: |
| 120 | + print( |
| 121 | + f"[{arena}] Dropped {n_dropped}/{n_before} multi-turn battles (keeping single-turn only)." |
| 122 | + ) |
| 123 | + |
| 124 | + return df |
| 125 | + |
| 126 | + |
| 127 | +def load_arena_dataframe( |
| 128 | + arena: str | None, |
| 129 | + comparia_revision: str = "7a40bce496c1f2aa3be4001da85a49cb4743042b", |
| 130 | +) -> pd.DataFrame: |
| 131 | + """Load battles from one or all arenas. |
| 132 | +
|
| 133 | + :param arena: one of "LMArena-100k", "LMArena-140k", "ComparIA", "LMArena" |
| 134 | + (concatenation of both LMArena variants), or None (all arenas). |
| 135 | + :param comparia_revision: pinned revision for the ComparIA dataset. |
| 136 | + :return: dataframe containing battles for the arena(s) selected. |
| 137 | + """ |
| 138 | + if arena is None: |
| 139 | + arenas = KNOWN_ARENAS |
| 140 | + elif arena == "LMArena": |
| 141 | + arenas = ["LMArena-100k", "LMArena-140k"] |
| 142 | + else: |
| 143 | + return _load_arena_dataframe(arena, comparia_revision) |
| 144 | + return pd.concat( |
| 145 | + [_load_arena_dataframe(a, comparia_revision) for a in arenas], |
| 146 | + ignore_index=True, |
| 147 | + ) |
| 148 | + |
| 149 | + |
| 150 | +def main(): |
| 151 | + for arena in KNOWN_ARENAS: |
| 152 | + print(f"Loading {arena}") |
| 153 | + df = _load_arena_dataframe(arena) |
| 154 | + n_battles = len(df) |
| 155 | + n_models = len(set(df["model_a"]) | set(df["model_b"])) |
| 156 | + n_languages = df["lang"].nunique() |
| 157 | + print( |
| 158 | + f"{arena}: {n_battles} battles, {n_models} models, {n_languages} languages" |
| 159 | + ) |
| 160 | + |
| 161 | + |
| 162 | +if __name__ == "__main__": |
| 163 | + main() |
0 commit comments