src/data_utils.py

import pandas as pd
from pathlib import Path

def get_dataframe_category(data_prefix: str = "open/"):
    from src.data_loader import get_category_dataframe
    return get_category_dataframe(processed=False, data_prefix=data_prefix)

def get_dataframe_language(data_prefix: str = "open/"):
    from src.data_loader import get_language_dataframe
    return get_language_dataframe(processed=False, data_prefix=data_prefix)

import json

def get_length_category_df(selected_category, data_prefix: str = "open/"):
    """
    Loads length_data.json and returns a DataFrame for the selected category.
    Columns: Model Name, {Category} Min, {Category} Max, {Category} Med,  {Category} Med Resp
    """
    abs_path = Path(__file__).parent
    json_path = abs_path / "data" / data_prefix / "length_data.json"
    with open(json_path, "r", encoding="utf-8") as f:
        data = json.load(f)
    rows = []
    for model_name, stats in data.items():
        cat = stats.get(selected_category, {})
        row = {
            "Model Name": model_name,
            f"Min Len. ({selected_category})": cat.get("Min", None),
            f"Max Len. ({selected_category}))": cat.get("Max", None),
            f"Med. Len. ({selected_category})": cat.get("Med", None),
            f"Med. Resp. Len. ({selected_category})": cat.get("Med Resp", None),
        }
        rows.append(row)
    df = pd.DataFrame(rows)
    return df

def get_length_category_list(data_prefix: str = "open/"):
    """
    Returns the list of available categories in length_data.json (excluding 'Overall').
    """
    abs_path = Path(__file__).parent
    json_path = abs_path / "data" / data_prefix / "length_data.json"
    with open(json_path, "r", encoding="utf-8") as f:
        data = json.load(f)
    if not data:
        return []
    # Get categories from the first model
    first_model = next(iter(data.values()))
    categories = [k for k in first_model.keys() if k != "Overall"]
    return categories

def get_time_category_df(selected_category, data_prefix: str = "open/"):
    """
    Loads time_data.json and returns a DataFrame for the selected category.
    Columns: Model Name, {Category} Min, {Category} Max, {Category} Med,  {Category} Med Resp
    """
    abs_path = Path(__file__).parent
    json_path = abs_path / "data" / data_prefix / "time_data.json"
    with open(json_path, "r", encoding="utf-8") as f:
        data = json.load(f)
    rows = []
    for model_name, stats in data.items():
        cat = stats.get(selected_category, {})
        row = {
            "Model Name": model_name,
            f"Min Len. ({selected_category})": cat.get("Min", None),
            f"Max Len. ({selected_category}))": cat.get("Max", None),
            f"Med. ({selected_category})": cat.get("Med", None),
        }
        rows.append(row)
    df = pd.DataFrame(rows)
    return df

def get_time_category_list(data_prefix: str = "open/"):
    """
    Returns the list of available categories in time_data.json (excluding 'Overall').
    """
    abs_path = Path(__file__).parent
    json_path = abs_path / "data" / data_prefix / "time_data.json"
    with open(json_path, "r", encoding="utf-8") as f:
        data = json.load(f)
    if not data:
        return []
    # Get categories from the first model
    first_model = next(iter(data.values()))
    categories = [k for k in first_model.keys() if k != "Overall"]
    return categories