Actividad 2.3

andres_bravo_dataset_generator.py

import pandas as pd
import numpy as np
from tensorflow.python.lib.io import file_io
import json
import csv

total_examples = 100
filename = './andres_bravo_dataset.csv'
# x4 mean and standard distribution values
mu, sigma = 0, 1

# Generates Dataset for Activity 2.3 with:
# * 1 feature strong dependant
# * 3 features weekly dependant
# * 1 feature independant (gausian distribution)
def generate_dataset():
    global total_examples, filename
    total_examples_generated = 0

    f = csv.writer(open(filename, "wb+"))

    # Write CSV Header, If you dont need that, remove this line
    f.writerow(["x0", "x1", "x2", "x3", "x4", "class"])

    for x0 in [0, 1]:
        for x1 in [0, 1]:
            for x2 in [0, 1]:
                for x3 in [0, 1]:
                    for x4 in np.random.normal(mu, sigma, 10):
                        if total_examples_generated == total_examples:
                            return
                        f.writerow([x0,x1,x2,x3,x4,class_function(x0, x1, x2, x3, x4)])
                        total_examples_generated = total_examples_generated + 1


# Defines the class funcition for the dataset
def class_function(x0, x1, x2, x3, x4):
    return x0 or (x1 and x2 and x3)


generate_dataset()