# source: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/blob/main/src/utils_display.py
from dataclasses import dataclass
import plotly.graph_objects as go
from transformers import AutoConfig

# 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


def fields(raw_class):
    return [
        v for k, v in raw_class.__dict__.items() if k[:2] != "__" and k[-2:] != "__"
    ]


@dataclass(frozen=True)
class AutoEvalColumn:  # Auto evals column
    model_type_symbol = ColumnContent("T", "str", True)
    model = ColumnContent("Models", "markdown", True)
    ARC = ColumnContent("ARC", "number", True)
    HellaSwag = ColumnContent("HellaSwag", "number", True)
    MMLU = ColumnContent("MMLU", "number", True)
    TruthfulQA = ColumnContent("TruthfulQA", "number", True)
    Winogrande = ColumnContent("Winogrande", "number", True)
    GSM8K = ColumnContent("GSM8K", "number", True)
    dummy = ColumnContent("Models", "str", True)
    ref_model = ColumnContent("Reference Model", "str", True)


def model_hyperlink(link, model_name):
    return f'<a target="_blank" href="{link}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{model_name}</a>'


def make_clickable_names(df):
    df["Models"] = df.apply(
        lambda row: model_hyperlink(row["Links"], row["Models"]), axis=1
    )
    return df

def styled_error(error):
    return f"<p style='color: red; font-size: 20px; text-align: center;'>{error}</p>"


def styled_warning(warn):
    return f"<p style='color: orange; font-size: 20px; text-align: center;'>{warn}</p>"


def styled_message(message):
    return f"<p style='color: green; font-size: 20px; text-align: center;'>{message}</p>"


def has_no_nan_values(df, columns):
    return df[columns].notna().all(axis=1)


def has_nan_values(df, columns):
    return df[columns].isna().any(axis=1)


def is_model_on_hub(model_name: str, revision: str) -> bool:
    try:
        AutoConfig.from_pretrained(model_name, revision=revision, trust_remote_code=False)
        return True, None

    except ValueError:
        return (
            False,
            "needs to be launched with `trust_remote_code=True`. For safety reason, we do not allow these models to be automatically submitted to the leaderboard.",
        )

    except Exception as e:
        print(f"Could not get the model config from the hub.: {e}")
        return False, "was not found on hub!"

@dataclass(frozen=True)
class EvalQueueColumn:  # Queue column
    model = ColumnContent("model", "markdown", True)
    revision = ColumnContent("revision", "str", True)
    private = ColumnContent("private", "bool", True)
    precision = ColumnContent("precision", "str", True)
    weight_type = ColumnContent("weight_type", "str", "Original")
    status = ColumnContent("status", "str", True)

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