src/display/utils.py

from dataclasses import dataclass, make_dataclass
from src.about import EvalDimensions

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(["rank", ColumnContent, ColumnContent("Rank", "str", True, False)])
auto_eval_column_dict.append(["model_source", ColumnContent, ColumnContent("Source", "str", True, False)])
auto_eval_column_dict.append(["model_category", ColumnContent, ColumnContent("Size", "str", True, False)])
auto_eval_column_dict.append(["model", ColumnContent, ColumnContent("Model Name", "markdown", True, never_hidden=True)])
#Scores
auto_eval_column_dict.append(["average_score", ColumnContent, ColumnContent("Benchmark Score (0-10)", "number", True)])
for eval_dim in EvalDimensions:
    if eval_dim.value.metric in ["speed", "contamination_score"]:
         auto_eval_column_dict.append([eval_dim.name, ColumnContent, ColumnContent(eval_dim.value.col_name, "number", True)])
    else:
        auto_eval_column_dict.append([eval_dim.name, ColumnContent, ColumnContent(eval_dim.value.col_name, "number", False)])


# We use make dataclass to dynamically fill the scores from Tasks
AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)

## For the queue columns in the submission tab
@dataclass(frozen=True)
class EvalQueueColumn:  # Queue column
    model = ColumnContent("model", "markdown", True)
    revision = ColumnContent("revision", "str", True)
    status = ColumnContent("status", "str", True)

# Column selection
COLS = [c.name for c in fields(AutoEvalColumn) if not c.hidden]

EVAL_COLS = [c.name for c in fields(EvalQueueColumn)]
EVAL_TYPES = [c.type for c in fields(EvalQueueColumn)]

BENCHMARK_COLS = [t.value.col_name for t in EvalDimensions]