machinelearning_notebook/1_logistic_regression/linear_regression.py

import matplotlib.pyplot as plt
import numpy as np
import sklearn
from sklearn import datasets

# load data
d = datasets.load_diabetes()

X = d.data[:, 2]
Y = d.target

# draw original data
plt.scatter(X, Y)
plt.show()


###############################################################################
# Least squares
###############################################################################

# L = \sum_{i=1, N} (y_i - a*x_i - b)^2
N = X.shape[0]

S_X2 = np.sum(X*X)
S_X  = np.sum(X)
S_XY = np.sum(X*Y)
S_Y  = np.sum(Y)

A1 = np.array([[S_X2, S_X], [S_X, N]])
B1 = np.array([S_XY, S_Y])

coeff = np.linalg.inv(A1).dot(B1)

x_min = np.min(X)
x_max = np.max(X)
y_min = coeff[0] * x_min + coeff[1]
y_max = coeff[0] * x_max + coeff[1]

plt.scatter(X, Y)
plt.plot([x_min, x_max], [y_min, y_max], 'r')
plt.show()


###############################################################################
# Linear regression
###############################################################################
# the loss function
#   L = \sum_{i=1, N} (y_i - a*x_i - b)^2

n_train = 1000


a, b = 1, 1
epsilon = 0.001

for i in range(n_train):
    for j in range(N):
        a = a + epsilon*2*(Y[j] - a*X[j] - b)*X[j]
        b = b + epsilon*2*(Y[j] - a*X[j] - b)

    L = 0
    for j in range(N):
        L = L + (Y[j]-a*X[j]-b)**2
    print("epoch %4d: loss = %f" % (i, L))