title = 'polynomial with bgd: rate=%.2f, maxLoop=%d, epsilon=%.3f \n time: %ds' % (
rate, maxLoop, epsilon, timeConsumed)
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(srcX[:, 1].flatten().A[0], y[:, 0].flatten().A[0])
print(theta)
# 打印拟合曲线
xx = np.linspace(50, 100, 50)
xx2 = np.power(xx, 2)
yHat = []
for i in range(50):
normalizedSize = (xx[i] - xx.mean()) / xx.std(0)
normalizedSize2 = (xx2[i] - xx2.mean()) / xx2.std(0)
x = np.matrix([[1, normalizedSize, normalizedSize2]])
yHat.append(regression.h(theta, x.T))
fittingLine, = ax.plot(xx2, yHat, color='g')
ax.set_xlabel('Yield')
ax.set_ylabel('temperature')
plt.legend([trainingSet, fittingLine],
['Training Set', 'Polynomial Regression'])
plt.show()
# 打印误差曲线
errorsFig = plt.figure()
ax = errorsFig.add_subplot(111)
ax.yaxis.set_major_formatter(mtick.FormatStrFormatter('%.2e'))
ax.plot(range(len(errors)), errors)
rate = 1
maxLoop = 50
epsilon = 1
result, timeConsumed = regression.bgd(rate, maxLoop, epsilon, X, y)
theta, errors, thetas = result
print('theta is:')
print(theta)
print('........')
# 预测价格
normalizedSize = (1650 - srcX[:, 0].mean(0)) / srcX[:, 0].std(0)
normalizedBr = (3 - srcX[:, 1].mean(0)) / srcX[:, 1].std(0)
predicateX = np.matrix([[1, normalizedSize, normalizedBr]])
price = regression.h(theta, predicateX.T)
print('Predicted price of a 1650 sq-ft, 3 br house: $%.4f' % price)
print('........')
# 打印拟合平面
fittingFig = plt.figure(figsize=(16, 12))
title = 'polynomial with bgd: rate=%.3f, maxLoop=%d, epsilon=%.3f \n time: %ds' % (
rate, maxLoop, epsilon, timeConsumed)
ax = fittingFig.add_subplot(111, projection='3d', title=title)
xx = np.linspace(0, 5000, 25)
yy = np.linspace(0, 5, 25)
zz = np.zeros((25, 25))
for i in range(25):
for j in range(25):
normalizedSize = (xx[i] - srcX[:, 0].mean(0)) / srcX[:, 0].std(0)
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(srcX[:, 0].flatten().A[0], y[:, 0].flatten().A[0])
print theta
print theta2
# 打印拟合曲线
xx = np.linspace(1, 7, 50)
xx2 = np.power(xx, 2)
yHat1 = []
yHat2 = []
for i in range(50):
normalizedSize = (xx[i] - xx.mean()) / xx.std(0)
normalizedSize2 = (xx2[i] - xx2.mean()) / xx2.std(0)
x = np.matrix([[1, normalizedSize, normalizedSize2]])
yHat1.append(regression.h(theta, x.T))
yHat2.append(regression.h(theta2, x.T))
fittingLine1, = ax.plot(xx, yHat1, color='g')
fittingLine2, = ax.plot(xx, yHat2, color='r')
ax.set_xlabel('temperature')
ax.set_ylabel('yield')
plt.legend([trainingSet, fittingLine1, fittingLine2],
['Training Set', r'LWR with $\tau$=1', r'LWR with $\tau$=0.1'])
plt.show()
# 打印误差曲线
errorsFig = plt.figure()
ax = errorsFig.add_subplot(111)
ax.yaxis.set_major_formatter(mtick.FormatStrFormatter('%.2e'))
# 打印特征点
fittingFig = plt.figure()
title = 'polynomial with bgd: rate=%.2f, maxLoop=%d, epsilon=%.3f \n time: %ds' % (rate, maxLoop, epsilon, timeConsumed)
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(srcX[:, 0].flatten().A[0], y[:, 0].flatten().A[0])
# 打印拟合曲线
xx = np.linspace(50, 100, 50)
xx2 = np.power(xx, 2)
yHat = []
for i in range(50):
normalizedSize = (xx[i] - xx.mean()) / xx.std(0)
normalizedSize2 = (xx2[i] - xx2.mean()) / xx2.std(0)
x = np.matrix([[1, normalizedSize, normalizedSize2]])
yHat.append(re.h(theta, x.T))
fittingLine, = ax.plot(xx, yHat, color='g')
ax.set_xlabel('Yield')
ax.set_ylabel('temperature')
plt.legend([trainingSet, fittingLine], ['Training Set', 'Polynomial Regression']) #显示图中标签
plt.show()
# 打印误差曲线
errorsFig = plt.figure()
ax = errorsFig.add_subplot(111)
ax.yaxis.set_major_formatter(mtick.FormatStrFormatter('%.2e'))
ax.plot(range(len(errors)), errors)