from pathlib import Path
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import scipy
from glob import glob


def read_xy(path: str):
    df = pd.read_csv(path, skipinitialspace=True)
    df['N'] = df.index + 1
    df['r'] = (df.x ** 2 + df.y ** 2) ** 0.5
    df['cr'] = df.r.cummax()
    df['fd'] = np.log(df.N) / np.log(df.cr)

    return df


def read_all(load_dir: str):
    paths = glob(f'{load_dir}/*.csv')
    return [read_xy(path) for path in paths]


def stick_prob_from_load_dir(load_dir: str):
    return float(Path(load_dir).name)


def read_sp_dir(load_dir: str):
    return stick_prob_from_load_dir(load_dir), read_all(load_dir)


def read_sp_full(probabilities_dir: str):
    a = [read_sp_dir(load_dir) for load_dir in glob(f'{probabilities_dir}/*')]
    b = [fd_of_dfs(dfs) for (p, dfs) in a]
    ps = [p for (p, dfs) in a]
    means, stds = list(zip(*b))
    c = pd.DataFrame(zip(ps, means, stds), columns=['p', 'fd_mean', 'fd_std'])
    c.sort_values(by='p', inplace=True)
    return c


def convergent_tail_index(series, tol):
    diffs = np.abs(np.ediff1d(series))
    for i in range(0, len(diffs)):
        if np.max(diffs[i:]) <= tol:
            return i

    # No convergence found
    return None


def mean_of_tail(series, tol=0.05):
    tail_index = convergent_tail_index(series, tol)
    return np.mean(series[tail_index:])


def fd_of_dfs(dfs):
    fds = [mean_of_tail(df.fd, 0.001) for df in dfs]
    fds_clean = [f for f in fds if f < np.inf]
    return np.mean(fds_clean), np.std(fds_clean)


import sys
print(sys.argv)
np.seterr(divide='ignore')

argv_ = sys.argv[1]
print(read_sp_full(argv_))