4d_parity_statistics.py

import datetime
import numpy as np
import pandas as pd
import util
import os
import interaction_distance as id
from correlation_measures.binning import Binning


# def write(*args):
#     log.write(' '.join([str(a) for a in args]))
#     log.write('\n')


def average_id(bin1, bin2, dim_maxes):
    data0 = data[bin1]
    data1 = data[bin2]
    orig_binning0 = Binning(data0)
    orig_binning1 = Binning(data1)
    bin0_map = orig_binning0.equal_frequency_binning(0, int(data0.shape[0] / 141))
    bin1_map = orig_binning1.equal_frequency_binning(0, int(data1.shape[0] / 141))
    # distinct bins
    dist_bins0 = bin0_map.unique()
    dist_bins1 = bin1_map.unique()
    data0.pop(0)
    data1.pop(0)
    return sum([id.compute_ID(data0.loc[bin0_map == dist0], data1.loc[bin1_map == dist1], dim_maxes)
                 for dist0 in dist_bins0 for dist1 in dist_bins1]) / (len(dist_bins0) * len(dist_bins1))


if __name__ == "__main__":
    data_file = 'synthetic_cases/synthetic_4d_parity_problem.csv'
    # reading data from the file with delimiter and NaN values as "?"
    data = pd.read_csv(data_file, delimiter=";", header=None, na_values='?')
    # drop a data point if it contains inconsistent data
    data = data.dropna(axis=0, how='any')
    data.pop(4)

    # defining prefix for the output files
    # file_name = util.get_file_name(data_file)
    # dir = 'logs/id_statistics_' + file_name + "_" + \
    #       datetime.datetime.now().strftime("_%Y%m%d_%H%M%S") + "/"
    # os.makedirs(dir)

    # print('output files are:', dir + '*')
    # log_file = dir + "log.txt"

    # with open(log_file, 'w') as log:
    data_max = data.max(0)
    print('INSIDE NEGATIVE MACROBIN')
    print('+++ <-> +++')
    bin1_1 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] > 0, data[3] > 0)),
                        np.logical_and(data[1] > 0, np.logical_and(data[2] > 0, data[3] > 0)), data_max)
    print(bin1_1)
    print('+-- <-> +--')
    bin1_2 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] > 0, np.logical_and(data[2] < 0, data[3] < 0)), data_max)
    print(bin1_2)
    print('+++ <-> +--')
    bin1_3 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] > 0, data[3] > 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)), data_max)
    print(bin1_3)
    print('+-- <-> -+-')
    bin1_4 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] < 0)), data_max)
    print(bin1_4)
    print('average ID in bin1: ', (bin1_1 * 1 + bin1_2 * 3 + bin1_2 * 3 + bin1_3 * 3) / 10)
    print('BETWEEN MACROBINS')
    print('+-- <-> ---')
    bwn_1 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)), data_max)
    print(bwn_1)
    print('+++ <-> ---')
    bwn_2 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] > 0, data[3] > 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)), data_max)
    print(bwn_2)
    print('+++ <-> -++')
    bwn_3 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] > 0, data[3] > 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] > 0)), data_max)
    print(bwn_3)
    print('+-- <-> -++')
    bwn_4 = average_id(np.logical_and(data[1] > 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] > 0)), data_max)
    print(bwn_4)
    print('-+- <-> -++')
    bwn_5 = average_id(np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] < 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] > 0)), data_max)
    print(bwn_5)
    print('average ID in bwn: ', (bwn_2 + bwn_1 * 3 + bwn_3 * 3 + bwn_4 * 3 + bwn_5 * 6) / 16)
    print('INSIDE POSITIVE MACROBIN')
    print('--- <-> ---')
    bin2_1 = average_id(np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)), data_max)
    print(bin2_1)
    print('-++ <-> -++')
    bin2_2 = average_id(np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] > 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] > 0)), data_max)
    print(bin2_2)
    print('--- <-> -++')
    bin2_3 = average_id(np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] < 0, np.logical_and(data[2] > 0, data[3] > 0)), data_max)
    print(bin2_3)
    print('-++ <-> +-+')
    bin2_4 = average_id(np.logical_and(data[1] < 0, np.logical_and(data[2] < 0, data[3] < 0)),
                   np.logical_and(data[1] > 0, np.logical_and(data[2] < 0, data[3] > 0)), data_max)
    print(bin2_4)
    print('average ID in bin2: ', (bin2_1 * 1 + bin2_2 * 3 + bin2_2 * 3 + bin2_3 * 3) / 10)