experiments_logging.py

import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
import pandas as pd
import data_generation as dg
from data_generation import synthetic_cube_in_cube


def plot_data_3d(data):
    fig = plt.figure()
    ax = fig.add_subplot(111, projection='3d')
    # data = data[np.logical_and(data[0] < 0, data[1] > 0)]

    ## 3d parity problem
    # color_cond = {'b': np.logical_and(data[0] < 0, np.logical_and(data[1] > 0, data[2] < 0)),
    #               'k': np.logical_and(data[0] < 0, np.logical_and(data[1] > 0, data[2] > 0)),
    #               'g': np.logical_and(data[0] > 0, data[1] < 0),
    #               'r': np.logical_and(data[0] < 0, data[1] < 0),
    #               'c': np.logical_and(data[0] > 0, data[1] > 0),
    #               }
    # for c in color_cond:
    #     ax.scatter(data[0][color_cond[c]], data[1][color_cond[c]], data[2][color_cond[c]], c=c, s=1)

    ## without coloring
    ax.scatter(data[0], data[1], data[2], c='k', s=1)

    ax.set_xlabel('X0')
    ax.set_ylabel('X1')
    ax.set_zlabel('X2')

    plt.show()

def plot_data_2d(data):
    plt.scatter(data[0], data[1], s=1, c='k')
    plt.show()


def write_out_file(name, disc_intervals, disc_points, class_labels):
    with open(name, 'w') as out:
        out.write('@relation DB\n\n')
        counter = [1]
        for i in range(len(disc_intervals)):
            out.write(
                '@attribute dim' + str(i) + ' {' + ','.join([str(j + counter[-1]) for j in disc_intervals[i]]) + '}\n')
            counter.append(counter[-1] + len(disc_intervals[i]))
        out.write('@attribute class {' + ','.join(['"' + str(i) + '"' for i in class_labels.unique()]) + '}\n\n')
        out.write('@data\n')

        for i in range(len(disc_points[0])):
            for j in range(len(disc_points)):
                out.write(str(disc_points[j][i] + counter[j]))
                out.write(',')
            out.write('"' + str(class_labels[i]) + '"\n')


def write_cut_file(name, disc_intervals):
    with open(name, 'w') as out:
        for i in range(len(disc_intervals)):
            out.write('dimension ' + str(i) + ' (' + str(len(disc_intervals[i])) + ' bins)\n')
            for bin in disc_intervals[i]:
                out.write(str(disc_intervals[i][bin][1]) + '\n')
            out.write('-------------------------------------\n')


if __name__ == '__main__':
    # rows = 20000
    # data = np.concatenate((synthetic_cube_in_cube(rows, 2, 0), np.zeros((rows, 1))), axis=1)
    # data = pd.read_csv("synthetic_cases/synthetic_cube_in_sparse_cube_3_0.csv", delimiter=";", header=None, na_values='?')
    data = pd.read_csv("synthetic_cases/3d_4_blobs_1_aligned_xor.csv", delimiter=";", header=None, na_values='?')
    plot_data_3d(data)