Created
June 2, 2020 09:54
-
-
Save azizkayumov/dba2c89d766b87aece4929c43884cc0c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import matplotlib.pyplot as plt | |
import time | |
import math | |
class GradientDescent: | |
def __init__(self, x, y, a): | |
self.x = x | |
self.y = y | |
# learning rate | |
self.a = a | |
# number of features | |
self.n = len(x) | |
# thetas | |
self.w = [0,0,0] | |
# number of training data | |
self.m = len(x[0]) | |
print("Initialized with training data:") | |
print("n = " + str(self.n) + ", m = " + str(self.m)) | |
print("w = " + str(self.w)) | |
def hypothesis(self, x): | |
h = 0 | |
for i in range(self.n): | |
h += self.w[i] * x[i] | |
return 1 / (1 + math.exp(-h)) | |
def decision(self,probability): | |
if probability >= 0.5: | |
return 1 | |
return 0 | |
def cost(self): | |
sum = 0 | |
for i in range(self.m): | |
sum += -1 * self.y[i] * math.log(self.hypothesis(self.x[:, i])) - (1 - self.y[i]) * math.log( | |
self.hypothesis(1 - self.x[:, i])) | |
return sum / (2 * self.m) | |
def train(self, number_of_iterations): | |
# starting with o | |
# repeat until convergence | |
i = 0 | |
while i < number_of_iterations: | |
temp_w = [0] * self.n | |
for j in range(self.n): | |
temp_w[j] = self.w[j] - self.a * self.sum(self.x[j]) / self.m | |
# global optimum is found: | |
if self.w == temp_w: | |
print("Global optimum is found, stopping training") | |
return | |
for j in range(self.n): | |
self.w[j] = temp_w[j] | |
i += 1 | |
def sum(self, feature_x): | |
s = 0 | |
for i in range(self.m): | |
s += (self.hypothesis(self.x[:, i]) - self.y[i]) * feature_x[i] | |
return s | |
# prepare training data: each item in the form of [bias, x1, x2] | |
# read from data.txt | |
x = [[],[],[]] | |
y = [] | |
dataFile = open("data.txt", "r") | |
for line in dataFile.readlines(): | |
split = line.split(",") | |
x[0].append(1) | |
x[1].append(float(split[0])) | |
x[2].append(float(split[1])) | |
y.append(float(split[2])) | |
print(len(x)) | |
dataFile.close() | |
x = np.array(x) | |
# Training | |
np_x = np.array(x) | |
gd = GradientDescent(np_x, y, 0.0001) | |
print("Training on x and y ...") | |
current_time = int(round(time.time() * 1000)) | |
gd.train(1000) | |
current_time = int(round(time.time() * 1000)) - current_time | |
print("Training duration: " + str(current_time / 1000) + " seconds") | |
print("Trained w = " + str(gd.w) + ", cost = " + str(gd.cost())) | |
# plot Class 1 and Class 2 data points | |
plot_x1, plot_y1 = [], [] | |
plot_x2, plot_y2 = [], [] | |
for i in range(len(x[0])): | |
if y[i] == 0: | |
plot_x1.append(x[1][i]) | |
plot_y1.append(x[2][i]) | |
else: | |
plot_x2.append(x[1][i]) | |
plot_y2.append(x[2][i]) | |
scatter_class1 = plt.scatter(plot_x1, plot_y1, color='r') | |
scatter_class2 = plt.scatter(plot_x2, plot_y2, color='b') | |
plt.legend((scatter_class1, scatter_class2), ("Class 1", "Class 2"), scatterpoints=1, loc='lower right', ncol=3, fontsize=8) | |
# plot decision boundary | |
X = np.linspace(-5, 10, 100) | |
H = -(gd.w[0] + gd.w[1] * X) / gd.w[2] | |
plt.plot(X, H, '-g') | |
plt.title('Assignment #2. Task 2.b') | |
plt.grid() | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment