Codigo

from numpy.random.mtrand import randint
from sklearn.datasets import make_classification
import matplotlib.pyplot as plt
import numpy as np
import random
np.random.seed(97)

X, Y = make_classification( n_features=2, n_redundant=0, n_informative=1, n_clusters_per_class=1 )

plt.scatter(X[:, 0], X[:, 1], marker='o', c=Y, edgecolor='K')


def plotModel(w1, w2, b):
  x = np.linspace(-2, 4, 50)
  y = (-w1*x -b)/w2

  xmin, xmax = plt.gca().get_xlim()
  ymin, ymax = plt.gca().get_ylim()

  plt.axvline(0, -1, 1, color='k', linewidth=1)
  plt.axhline(0, -1, 4, color='k', linewidth=1)
  plt.plot(x, y)
  plt.grid(True)

  plt.xlim(xmin, xmax)
  plt.ylim(xmin, ymax)


w1 = -5
w2 = 0.5
b  = -1.5

plotModel(w1, w2, b)

p = [random.uniform(-2.0, 2.9), random.uniform(-2.0, 2.9)]
print("Distancia da reta:", w1* p[0] + w2 * p[1] + b)


def classify(ponto, w1, w2, b):
  ret = w1 * ponto[0] + w2 * ponto[1] + b
  if(ret >= 0):
    return 0, 'blue'
  else:
    return 1, 'yellow'

classe, cor = classify(p, w1, w2, b)
print("Classificação: ", classe, cor)

plotModel(w1, w2, b)
plt.scatter(p[0], p[1], marker='x', color='r' )

acertos = 0
for k in range(len(X)):
  categ, _ = classify(X[k], w1, w2, b)
  if categ == Y[k]:
    acertos += 1

print("Acertos: ", acertos)
print("Acurácia: {0}%".format((acertos/len(X)*100)))