from glob import glob
from subprocess import run
from sys import executable

from numpy import mean, std
from pandas import DataFrame, ExcelWriter


def file_list(path):
    file_list = []
    for fname in glob(path):
        file_list.append(fname)
    return file_list


def create_dataframes():
    greedy = DataFrame()
    local = DataFrame()
    return greedy, local


def process_output(results):
    distances = []
    time = []
    for element in results:
        for line in element:
            if line.startswith(bytes("Total distance:", encoding="utf-8")):
                line_elements = line.split(sep=bytes(":", encoding="utf-8"))
                distances.append(float(line_elements[1]))
            if line.startswith(bytes("Execution time:", encoding="utf-8")):
                line_elements = line.split(sep=bytes(":", encoding="utf-8"))
                time.append(float(line_elements[1]))
    return distances, time


def populate_dataframes(greedy, local, greedy_list, local_list, dataset):
    greedy_distances, greedy_time = process_output(greedy_list)
    local_distances, local_time = process_output(local_list)
    greedy_dict = {
        "dataset": dataset.removeprefix("data/"),
        "media distancia": mean(greedy_distances),
        "desviacion distancia": std(greedy_distances),
        "media tiempo": mean(greedy_time),
        "desviacion tiempo": std(greedy_time),
    }
    local_dict = {
        "dataset": dataset.removeprefix("data/"),
        "media distancia": mean(local_distances),
        "desviacion distancia": std(local_distances),
        "media tiempo": mean(local_time),
        "desviacion tiempo": std(local_time),
    }
    greedy = greedy.append(greedy_dict, ignore_index=True)
    local = local.append(local_dict, ignore_index=True)
    return greedy, local


def script_execution(filenames, greedy, local, iterations=3):
    script = "src/main.py"
    for dataset in filenames:
        print(f"Running on dataset {dataset}")
        greedy_list = []
        local_list = []
        for _ in range(iterations):
            greedy_cmd = run(
                [executable, script, dataset, "greedy"], capture_output=True
            ).stdout.splitlines()
            local_cmd = run(
                [executable, script, dataset, "local"], capture_output=True
            ).stdout.splitlines()
            greedy_list.append(greedy_cmd)
            local_list.append(local_cmd)
        greedy, local = populate_dataframes(
            greedy, local, greedy_list, local_list, dataset
        )
    return greedy, local


def export_results(greedy, local):
    dataframes = {"Greedy": greedy, "Local search": local}
    writer = ExcelWriter(path="docs/algorithm-results.xlsx", engine="xlsxwriter")
    for name, df in dataframes.items():
        df.to_excel(writer, sheet_name=name, index=False)
        worksheet = writer.sheets[name]
        for index, column in enumerate(df):
            series = df[column]
            max_length = max(series.astype(str).str.len().max(), len(str(series.name)))
            worksheet.set_column(index, index, width=max_length + 5)
    writer.save()


def main():
    datasets = file_list(path="data/*.txt")
    greedy, local = create_dataframes()
    populated_greedy, populated_local = script_execution(datasets, greedy, local)
    export_results(populated_greedy, populated_local)


if __name__ == "__main__":
    main()