import json
import os

import numpy as np
import pandas as pd

from src.display.formatting import has_no_nan_values, make_clickable_model
from src.display.utils import EvalQueueColumn
from src.leaderboard.read_evals import get_raw_eval_results
from src.display.utils import AutoEvalColumnRGB, AutoEvalColumnPGB,\
    AutoEvalColumnGUE, AutoEvalColumnGB
from src.about import TasksRGB, TasksPGB, TasksGUE, TasksGB


def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
    """Creates a dataframe from all the individual experiment results"""
    print(f"RESULTS PATH: {results_path}")
    raw_data = get_raw_eval_results(results_path, requests_path)
    for result in raw_data:
        result.average = np.mean(list(result.results.values()))
    sorted_results = sorted(raw_data, key=lambda r: r.average, reverse=True)
    print(sorted_results)
    # ranks = [rank+1 for rank, value in enumerate(sorted_results)]
    # rank = [rank+1 for rank, value in enumerate(average)]
    if "RGB" in results_path:
        all_data_json = [v.to_dict(i+1, AutoEvalColumnRGB, TasksRGB) for i, v in enumerate(raw_data)]
    elif "PGB" in results_path:
        all_data_json = [v.to_dict(i+1, AutoEvalColumnPGB, TasksPGB) for i, v in enumerate(raw_data)]
    elif "GUE" in results_path:
        all_data_json = [v.to_dict(i+1, AutoEvalColumnGUE, TasksGUE) for i, v in enumerate(raw_data)]
    else:
        all_data_json = [v.to_dict(i+1, AutoEvalColumnGB, TasksGB) for i, v in enumerate(raw_data)]
    # all_data_json = [v.to_dict(i + 1) for i, v in enumerate(raw_data)]

    df = pd.DataFrame.from_records(all_data_json)
    # df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
    print(f"Cols: {cols}")
    print(f"DF: {df}")
    df = df[cols].round(decimals=2)

    # filter out if any of the benchmarks have not been produced
    df = df[has_no_nan_values(df, benchmark_cols)]
    print(df)
    return df


def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
    """Creates the different dataframes for the evaluation queues requestes"""
    entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")]
    all_evals = []
    print(entries)
    entries = [entry for entry in entries if not entry.startswith(".")]
    print(entries)
    for entry in entries:
        print(entries)
        if ".json" in entry:
            file_path = os.path.join(save_path, entry)
            with open(file_path) as fp:
                data = json.load(fp)

            data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
            data[EvalQueueColumn.revision.name] = data.get("revision", "main")

            all_evals.append(data)
        elif ".md" not in entry:
            # this is a folder
            entries = [e for e in os.listdir(f"{save_path}/{entry}") if not e.startswith(".")]
            # for sub_entry in sub_entries:
            #     file_path = os.path.join(save_path, entry, sub_entry)
            #     with open(file_path) as fp:
            #         data = json.load(fp)

                # data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
                # data[EvalQueueColumn.revision.name] = data.get("revision", "main")
                # all_evals.append(data)

    pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]]
    running_list = [e for e in all_evals if e["status"] == "RUNNING"]
    finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"]
    df_pending = pd.DataFrame.from_records(pending_list, columns=cols)
    df_running = pd.DataFrame.from_records(running_list, columns=cols)
    df_finished = pd.DataFrame.from_records(finished_list, columns=cols)
    return df_finished[cols], df_running[cols], df_pending[cols]