src/display/utils.py

from dataclasses import dataclass, make_dataclass
from enum import Enum

import pandas as pd

from src.about import Tasks

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(["library_type_symbol", ColumnContent, ColumnContent("T", "str", True, never_hidden=True)])
auto_eval_column_dict.append(["library", ColumnContent, ColumnContent("Library", "markdown", True, never_hidden=True)])
#Scores
auto_eval_column_dict.append(["overall_risk", ColumnContent, ColumnContent("Overall Risk ⬇️", "number", True)])
for task in Tasks:
    auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
# Library information
auto_eval_column_dict.append(["library_type", ColumnContent, ColumnContent("Type", "str", False)])
auto_eval_column_dict.append(["framework", ColumnContent, ColumnContent("Framework", "str", False)])
auto_eval_column_dict.append(["version", ColumnContent, ColumnContent("Version", "str", False, False)])
auto_eval_column_dict.append(["language", ColumnContent, ColumnContent("Language", "str", False)])
auto_eval_column_dict.append(["license_name", ColumnContent, ColumnContent("License", "str", True)])
auto_eval_column_dict.append(["stars", ColumnContent, ColumnContent("GitHub ⭐", "number", False)])
auto_eval_column_dict.append(["last_update", ColumnContent, ColumnContent("Last Updated", "str", False)])
auto_eval_column_dict.append(["verified", ColumnContent, ColumnContent("Independently Verified", "bool", False)])
auto_eval_column_dict.append(["availability", ColumnContent, ColumnContent("Active Maintenance", "bool", True)])
auto_eval_column_dict.append(["report_url", ColumnContent, ColumnContent("Report", "html", True)])

# 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
    library = ColumnContent("library", "markdown", True)
    version = ColumnContent("version", "str", True)
    language = ColumnContent("language", "str", True) 
    framework = ColumnContent("framework", "str", True)
    library_type = ColumnContent("library_type", "str", True)
    status = ColumnContent("status", "str", True)

## All the library information that we might need
@dataclass
class LibraryDetails:
    name: str
    display_name: str = ""
    symbol: str = "" # emoji


class LibraryType(Enum):
    ML = LibraryDetails(name="machine learning", symbol="🟢")
    LLM = LibraryDetails(name="llm framework", symbol="🔶")
    AGENT = LibraryDetails(name="agent framework", symbol="⭕")
    VIS = LibraryDetails(name="visualization", symbol="🟦")
    GENERAL = LibraryDetails(name="general ai", symbol="🟣")
    Unknown = LibraryDetails(name="", symbol="?")

    def to_str(self, separator=" "):
        return f"{self.value.symbol}{separator}{self.value.name}"

    @staticmethod
    def from_str(type):
        if "machine learning" in type or "🟢" in type:
            return LibraryType.ML
        if "llm framework" in type or "🔶" in type:
            return LibraryType.LLM 
        if "agent framework" in type or "⭕" in type:
            return LibraryType.AGENT
        if "visualization" in type or "🟦" in type:
            return LibraryType.VIS
        if "general ai" in type or "🟣" in type:
            return LibraryType.GENERAL
        return LibraryType.Unknown

class Language(Enum):
    Python = LibraryDetails("Python")
    JavaScript = LibraryDetails("JavaScript")
    TypeScript = LibraryDetails("TypeScript") 
    Java = LibraryDetails("Java")
    CPP = LibraryDetails("C++")
    Other = LibraryDetails("Other")

class AssessmentStatus(Enum):
    Verified = LibraryDetails("Verified")
    Unverified = LibraryDetails("Unverified")
    Disputed = LibraryDetails("Disputed")

# 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)]

# Task columns for benchmarking - use the display column names from the Tasks enum
BENCHMARK_COLS = [task.value.col_name for task in Tasks]