import numpy as np import matplotlib.pyplot as plt import matplotlib
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
matplotlib.rcParams['font.family']='sans-serif'
matplotlib.rcParams['axes.unicode_minus'] = False
In [2]:
def loadDataSet(filename): X = [] Y = [] with open(filename, 'rb') as f: for
idx, line in enumerate(f): line = line.decode('utf-8').strip() if not line:
continue eles = line.split() if idx == 0: numFea = len(eles) eles = map(float,
eles) X.append(eles[:-1]) Y.append([eles[-1]]) return np.array(X), np.array(Y)
Our hypothetical function is :

hθ(x)=θXhθ(x)=θX

X:m∗nX:m∗n
θ:n∗1θ:n∗1
hθ:m∗1hθ:m∗1

In [3]:
def h(theta, X): return np.dot(X, theta)
Our cost function is :

J(θ0,θ1)=12m∑i=1m(hθ(x(i))−y(i))2J(θ0,θ1)=12m∑i=1m(hθ(x(i))−y(i))2

In [4]:
def J(theta, X, Y): m = len(X) return np.sum(np.dot((h(theta,X)-Y).T ,
(h(theta,X)-Y)) / (2 * m))
Our gradient descent update formula is :

θ0:=θ0−α1m∑i=1m(hθ(x(i))−y(i))θ0:=θ0−α1m∑i=1m(hθ(x(i))−y(i))

θ1:=θ1−α1m∑i=1m(hθ(x(i))−y(i))⋅x(i)θ1:=θ1−α1m∑i=1m(hθ(x(i))−y(i))⋅x(i)

In [5]:
def bgd(alpha, maxloop, epsion, X, Y): m,n = X.shape #
m Is the number of samples ,n Is the characteristic number , In fact, they are parameters theta The number of theta = np.zeros((2,1)) # parameter theta All initialized to 0 count = 0
# Record iteration rounds converged = False # Is the sign converged error = np.inf # Current cost function value errors = [] #
Record the cost function value of each iteration thetas = {0:[theta[0,0]],1:[theta[1,0]]} # Record the parameters of each round theta Update of while
count<=maxloop: if(converged): break count = count + 1 temp1 = theta[0, 0] -
alpha / m * (h(theta, X) - Y).sum() temp2 = theta[1, 0] - alpha / m *
(np.dot(X[:,1][:,np.newaxis].T,(h(theta,X) - Y))).sum() # Synchronous update theta[0, 0] =
temp1 theta[1, 0] = temp2 thetas[0].append(temp1) thetas[1].append(temp2) error
= J(theta, X, Y) errors.append(error) if(error < epsilon): converged = True
return theta,errors,thetas
Gradient descent completed , Let's get the data ready !

In [6]:
X, Y = loadDataSet('./data/ex1.txt') print X.shape print Y.shape (97, 1)
(97, 1)
In [7]:
m, n = X.shape X = np.concatenate((np.ones((m ,1)), X), axis=1)
In [8]:
X.shape
Out[8]:
(97, 2)
In [9]:
alpha = 0.02 # Learning rate maxloop = 1500 # Maximum number of iterations epsilon = 0.01 # Convergence criteria result =
bgd(alpha, maxloop, epsilon, X, Y) theta, errors, thetas = result
In [10]:
xCopy = X.copy() xCopy.sort(0) yHat = h(theta, xCopy) # predicted value
In [11]:
xCopy[:,1].shape,yHat.shape, theta.shape
Out[11]:
((97,), (97, 1), (2, 1))
In [12]:
# Draw regression line plt.xlabel(u' urban population ( ten thousand )') plt.ylabel(u' profit ( Ten thousand yuan )') plt.plot(xCopy[:,1],
yHat,color='r') plt.scatter(X[:,1].flatten(), Y.T.flatten()) plt.show()
/Users/sunkepeng/anaconda2/lib/python2.7/site-packages/matplotlib/font_manager.py:1331:
UserWarning: findfont: Font family [u'sans-serif'] not found. Falling back to
DejaVu Sans (prop.get_family(), self.defaultFamily[fontext]))

In [13]:
# Drawing the cost curve plt.xlim(-1,1600) plt.ylim(4,20) plt.xlabel(u' Number of iterations ')
plt.ylabel(u' Cost function J') plt.plot(range(len(errors)), errors)
Out[13]:
[<matplotlib.lines.Line2D at 0x1186f8ed0>]

In [16]:
# Preparing grid data , In order to draw the gradient descent process diagram %matplotlib inline from mpl_toolkits.mplot3d import
axes3d size = 100 theta0Vals = np.linspace(-10,10, size) theta1Vals =
np.linspace(-2, 4, size) JVals = np.zeros((size, size)) for i in range(size):
for j in range(size): col = np.matrix([[theta0Vals[i]], [theta1Vals[j]]])
JVals[i,j] = J(col, X, Y) theta0Vals, theta1Vals = np.meshgrid(theta0Vals,
theta1Vals) JVals = JVals.T
In [18]:
# draw 3D Cost function graph contourSurf = plt.figure() ax = contourSurf.gca(projection='3d')
ax.plot_surface(theta0Vals, theta1Vals, JVals, rstride=2, cstride=2, alpha=0.3,
cmap=matplotlib.cm.rainbow, linewidth=0, antialiased=False) ax.plot(theta[0],
theta[1], 'rx') ax.set_xlabel(r'$\theta_0$') ax.set_ylabel(r'$\theta_1$')
ax.set_zlabel(r'$J(\theta)$')
Out[18]:
Text(0.5,0,'$J(\\theta)$')

In [19]:
# Drawing contour map of cost function %matplotlib inline plt.figure(figsize=(12,6)) CS =
plt.contour(theta0Vals, theta1Vals, JVals, np.logspace(-2,3,30), alpha=.75)
plt.clabel(CS, inline=1, fontsize=10) # Draw the optimal solution plt.plot(theta[0,0], theta[1,0],
'rx', markersize=10, linewidth=3) # Draw gradient descent process plt.plot(thetas[0], thetas[1],
'rx', markersize=3, linewidth=1) # every time theta Value plt.plot(thetas[0], thetas[1],
'r-',markersize=3, linewidth=1) # Connect it with a thread
Out[19]:
[<matplotlib.lines.Line2D at 0x11cc4d910>]

Technology
©2019-2020 Toolsou All rights reserved,
C Review of basic language knowledge Go Language learning notes (GUI programming )Java Misunderstanding —— Method overloading is a manifestation of polymorphism ? How to achieve low cost and high stability for cloud native applications ?elementui Shuttle box el-transfer Display list content text too long C/C++ Memory model Element-Ui assembly Message Message prompt , alert Popup C# Making a simplified version of calculator Python In pycharm editor Interface style modification Tiktok refresh progress bar ( Two little balls turn ), The code is simple