File size: 2,295 Bytes
737fa2d f19f8d1 737fa2d f19f8d1 ba9a086 f19f8d1 ac176c3 d8484e3 35eacb4 8711098 f19f8d1 18d2712 bd4573d 18d2712 d8484e3 a127e54 737fa2d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
from dataclasses import dataclass, make_dataclass
from enum import Enum
import pandas as pd
def fields(raw_class):
return [v for k, v in raw_class.__dict__.items() if k[:2] != "__" and k[-2:] != "__"]
# These classes are for user facing column names,
# to avoid having to change them all around the code
# when a modif is needed
@dataclass
class ColumnContent:
name: str
type: str
displayed_by_default: bool
hidden: bool = False
never_hidden: bool = False
## Leaderboard columns
auto_eval_column_dict = []
# Init
auto_eval_column_dict.append(
["method_name", ColumnContent, ColumnContent("Method", "markdown", True, never_hidden=True)]
)
auto_eval_column_dict.append(["model_name", ColumnContent, ColumnContent("Base Model", "markdown", True)])
# Scores
auto_eval_column_dict.append(["score", ColumnContent, ColumnContent("Score", "number", True)])
auto_eval_column_dict.append(["full_pass_count", ColumnContent, ColumnContent("Repaired", "number", True)])
auto_eval_column_dict.append(["fast_pass_count", ColumnContent, ColumnContent("Repaired (Fast)", "number", False)])
auto_eval_column_dict.append(["with_hint", ColumnContent, ColumnContent("Hint", "str", True)])
auto_eval_column_dict.append(["attempts", ColumnContent, ColumnContent("Number of Attempts", "number", False)])
auto_eval_column_dict.append(
["full_pass_count_crash", ColumnContent, ColumnContent("Repaired (Crash)", "number", True)]
)
auto_eval_column_dict.append(
["full_pass_count_miscompilation", ColumnContent, ColumnContent("Repaired (Miscompilation)", "number", True)]
)
auto_eval_column_dict.append(["full_pass_count_hang", ColumnContent, ColumnContent("Repaired (Hang)", "number", True)])
auto_eval_column_dict.append(
["build_success_rate", ColumnContent, ColumnContent("Build Success Rate (%)", "number", False)]
)
auto_eval_column_dict.append(["mttr", ColumnContent, ColumnContent("MTTR (min)", "number", True)])
auto_eval_column_dict.append(["sample_count", ColumnContent, ColumnContent("Average Sample Count", "number", False)])
# We use make dataclass to dynamically fill the scores from Tasks
AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
# Column selection
COLS = [c.name for c in fields(AutoEvalColumn) if not c.hidden]
|