import numpy as np
if __name__ == "__main__":
srcX, y = regression.loadDataSet('temperature.txt')
m, n = srcX.shape
srcX = np.concatenate((srcX[:, 0], np.power(srcX[:, 0], 2)), axis=1)
# 特征缩放
X = regression.standardize(srcX.copy())
X = np.concatenate((np.ones((m, 1)), X), axis=1)
rate = 0.1
maxLoop = 1000
epsilon = 0.01
result, timeConsumed = regression.bgd(rate, maxLoop, epsilon, X, y)
theta, errors, thetas = result
# 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[:, 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 = []
# Author: Shibo Tang
import regression as re
import numpy as np
# Linear regression
print('Regression:')
testData = re.read_csv("regression/test.csv")
trainData = re.read_csv("regression/train.csv")
# Batch gradient descent algorithm
BGD1 = re.bgd(0.25, trainData['x'], trainData['y'])
costTest = re.cost(BGD1['weight'], testData['x'], testData['y'])
print('Batch gradient descent algorithm:')
print('Final cost function value of the training data:', BGD1['cost'][-1])
print('Final cost function value of the test data:', costTest)
print('r:', BGD1['r'])
print('Final weight:', BGD1['weight'])
# Stochastic gradient descent (SGD) algorithm
SGD1 = re.sgd(0.25, trainData['x'], trainData['y'])
costTest = re.cost(SGD1['weight'], testData['x'], testData['y'])
print('Stochastic gradient descent algorithm:')
print('Final cost function value of the training data:', SGD1['cost'][-1])
print('Final cost function value of the test data:', costTest)
print('r:', SGD1['r'])
print('Final weight:', SGD1['weight'])
# optimal weight vector with analytical form
w = re.analytical(trainData['x'], trainData['y'])
cost_train = re.cost(w, trainData['x'], trainData['y'])
cost_test = re.cost(w, testData['x'], testData['y'])