Last active
September 22, 2021 13:52
-
-
Save antondevv/c37402d5b13048868b3ba4af79f8618a to your computer and use it in GitHub Desktop.
final_file
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 pandas as pd | |
import matplotlib.pyplot as plt | |
import numpy as np | |
data = pd.read_csv('data.csv') | |
# print(data) | |
def cost_function(m, b, points): | |
the_total_error = 0 | |
sum_error = 0 | |
for i in range(len(points)): | |
x = points.iloc[i].weight | |
y = points.iloc[i].height | |
the_total_error += (y - (m * x + b)) ** 2 | |
sum_error += the_total_error | |
print(sum_error) | |
return sum_error | |
def gradient_descent(m_now, b_now, points, L): | |
the_slope_of_thecost_depending_on_m = 0 | |
the_slope_of_thecost_depending_on_b = 0 | |
n = len(points) | |
for i in range(n): | |
x = points.iloc[i].weight | |
y = points.iloc[i].height | |
the_slope_of_thecost_depending_on_m += - (2/n) * x * (y - (m_now * x + b_now)) | |
the_slope_of_thecost_depending_on_b += - (2/n) * (y - (m_now * x + b_now)) | |
m = m_now - L * the_slope_of_thecost_depending_on_m | |
b = b_now - the_slope_of_thecost_depending_on_b * L | |
return m, b | |
m = 0 | |
b = 0 | |
Learning_rate = 0.001 | |
times_to_iterate = 10000 | |
#Here we calculate the cost, but it's not needed becuase the gradient descent do that basically for us. | |
# for i in range(-2, 2): | |
# c = cost_function(i, i, data) | |
# print("The Error") | |
# print(c) | |
for i in range(times_to_iterate): | |
m, b = gradient_descent(m, b, data, Learning_rate) | |
print(f"m AND b: {m, b}") | |
plt.scatter(data['weight'], data['height']) | |
plt.plot(list(range(0, 5)), [m * x + b for x in range(0 , 5)], color="red") | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment