均值滤波：红色为原始带有噪声的数据，蓝色为滤波后的数据
# coding:utf-8
fromsklearn.datasetsimportfetch_20newsgroups
fromsklearn.datasetsimportfetch_california_housing
categories = ['comp.graphics',
'comp.os.ms-windows.misc',
'comp.sys.ibm.pc.hardware',
'comp.sys.mac.hardware',
'comp.windows.x'];
newsgroup_train = fetch_20newsgroups(subset='train',categories= categories);
house_price_train = fetch_california_housing()
print'down'
importnumpyasnp
importmatplotlib.pyplotasplt
importpandasaspd
##
#自制数据y = x1+2*x2 + 3 * x3
##
FEATURE_NUM =1
w = np.arange(3,4).reshape(FEATURE_NUM,-1)
x = np.random.randint(1,100,size= (1300,FEATURE_NUM))
y = x.dot(w) +9+ np.random.randint(1,50,(1300,1))
plt.plot(x,y,'*')
plt.show()
house_price_train.data = x
house_price_train.target = y
train_x = house_price_train.data[:1000]
train_y = np.array( house_price_train.target[:1000]).reshape(1000,-1)
test_x = house_price_train.data[100:]
test_y = np.array(house_price_train.target[100:])
# linear regression
feature_num =len(train_x[0])
train_sample_num =len(train_x)
test_sample_num =len(test_x)
train_x = np.concatenate((train_x,np.ones((train_sample_num,1))),axis=1)
test_x = np.concatenate((test_x,np.ones((test_sample_num,1))),axis=1)
# #步骤：
# 1.定义model输入theta x给出f(x)
# 2.计算误差
# 3.梯度下降求解
#后面可以用ufunc求解f = fromfunc(func,n_in,n_dout) f(ndarray)
defmodel(theta,x):
returnnp.sum(theta*x)
defcost(theta,x,y):
returny - model(theta,x)
w = np.zeros(feature_num +1)
deftrain(train_x,train_y):
globalw
theta = np.zeros((feature_num+1,1))
last_theta =np.zeros((feature_num+1,1))
eps=0.001
_cost=999
COUNT =10000
idx=0
change =999
whilechange >0.001andidx < COUNT:
total_cost = train_x.dot(theta)
_cost= np.linalg.norm(total_cost - train_y)
theta = theta -0.000001* (1.0/train_sample_num)* (train_x.T).dot((total_cost - train_y))
# theta = theta + 0.00000001 *(train_x.T).dot((train_y - total_cost ))
change = np.linalg.norm(theta - last_theta)
last_theta = theta
idx +=1
# print idx,change,_cost
printidx,change,theta.tolist()
ly = train_x.dot(theta)
plt.plot(train_x[::,0].reshape(train_sample_num,),ly.reshape(train_sample_num,),'r',x,y,'b*')
plt.show()
print"theta:",theta
returntheta
defpredict(x,theta):
returnmodel(theta,x)
if__name__ =="__main__":
theta = train(train_x,train_y)
print"done"
# least double multiply
