#1.#关于非线性转化方程(non - linear#transformation#function)#
#sigmoid函数(S#曲线)用来作为activation#function:#
#1.1#双曲函数(tanh)#
#1.2#逻辑函数(logistic#function)#
#
#2.#实现一个简单的神经网络算法
importnumpy as npdeftanh(x):returnnp.tanh(x)deftanh_deriv(x):return 1.0 - np.tanh(x) *np.tanh(x)deflogistic(x):return 1 / (1 + np.exp(-x))deflogistic_derivative(x):return logistic(x) * (1 -logistic(x))classNeuralNetwork:def __init__(self, layers, activation='tanh'):""":param layers: A list containing the number of units in each layer.
Should be at least two values
:param activation: The activation function to be used. Can be
"logistic" or "tanh""""
if activation == 'logistic':
self.activation=logistic
self.activation_deriv=logistic_derivativeelif activation == 'tanh':
self.activation=tanh
self.activation_deriv=tanh_deriv
self.weights=[]for i in range(1, len(layers) - 1):#layers[i - 1]为前一输入层节点数 +1是加上一个偏置点,
#layers[i]为当前层的输出节点数 +1是加上一个偏置点,
self.weights.append((2 * np.random.random((layers[i - 1] + 1, layers[i] + 1)) - 1) * 0.25)
self.weights.append((2 * np.random.random((layers[i] + 1, layers[i + 1])) - 1) * 0.25)def fit(self, X, y, learning_rate=0.2, epochs=10000):
X= np.atleast_2d(X) #判断输入训练集是否为二维
temp = np.ones([X.shape[0], X.shape[1] + 1])
temp[:, 0:-1] = X #adding the bias unit to the input layer
X =temp
y=np.array(y)for k inrange(epochs):
i=np.random.randint(X.shape[0])
a=[X[i]]#len(self.weights)为输出节点个数,每个输出节点对应了一组权值是weight中的一行self.weights[l]
for l in range(len(self.weights)): #going forward network, for each layer
#Computer the node value for each layer (O_i) using activation function
#a[l] 为输入数据的特征值
print(a[l])print(self.weights[l])
a.append(self.activation(np.dot(a[l], self.weights[l])))
error= y[i] - a[-1] #Computer the error at the top layer
deltas = [error * self.activation_deriv(a[-1])] #For output layer, Err calculation (delta is updated error)
#Staring backprobagation
for l in range(len(a) - 2, 0, -1): #we need to begin at the second to last layer
#Compute the updated error (i,e, deltas) for each node going from top layer to input layer
deltas.append(deltas[-1].dot(self.weights[l].T) *self.activation_deriv(a[l]))
deltas.reverse()for i inrange(len(self.weights)):
layer=np.atleast_2d(a[i])
delta=np.atleast_2d(deltas[i])
self.weights[i]+= learning_rate *layer.T.dot(delta)defpredict(self, x):
x=np.array(x)
temp= np.ones(x.shape[0] + 1)
temp[0:-1] =x
a=tempfor l inrange(0, len(self.weights)):
a=self.activation(np.dot(a, self.weights[l]))returnaprint("简单非线性关系数据集测试(XOR)")#1. 简单非线性关系数据集测试(XOR):#
#X: Y#0 0 0#0 1 1#1 0 1#1 1 0
#from NeuralNetwork import NeuralNetwork
importnumpy as np
nn= NeuralNetwork([2,2,1], 'tanh')
X= np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y= np.array([0, 1, 1, 0])
nn.fit(X, y)for i in [[0, 0], [0, 1], [1, 0], [1,1]]:print(i, nn.predict(i))print("\n\n手写数字识别")#2. 手写数字识别:#
#每个图片8x8#识别数字:0,1,2,3,4,5,6,7,8,9
importnumpy as npfrom sklearn.datasets importload_digitsfrom sklearn.metrics importconfusion_matrix, classification_reportfrom sklearn.preprocessing importLabelBinarizer#from NeuralNetwork import NeuralNetwork
from sklearn.cross_validation importtrain_test_split
digits=load_digits()
X=digits.data
y=digits.target
X-= X.min() #normalize the values to bring them into the range 0-1
X /=X.max()
nn= NeuralNetwork([64,100,10],'logistic')
X_train, X_test, y_train, y_test=train_test_split(X, y)
labels_train=LabelBinarizer().fit_transform(y_train)
labels_test=LabelBinarizer().fit_transform(y_test)print("start fitting")
nn.fit(X_train,labels_train,epochs=3000)
predictions=[]for i inrange(X_test.shape[0]):
o=nn.predict(X_test[i] )
predictions.append(np.argmax(o))print(confusion_matrix(y_test,predictions))print (classification_report(y_test,predictions))