单隐层平面数据分类
程序步骤
1-模块导入
import numpy as np #使用Python进行科学计算的基本包
import matplotlib.pyplot as plt
from testCases_v2 import * #提供了一些测试示例来评估函数的正确性
import sklearn #为数据挖掘和数据分析提供了简单有效的工具
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
#提供了此赋值中使用的各种有用函数
%matplotlib inline
np.random.seed(1) #产生相同的随机数,保证随机运算后得到与参考答案相同的结果
2-导入数据
X, Y = load_planar_dataset()
# 数据可视化:
#plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);
plt.scatter(X[0, :], X[1, :], c=Y[0,:], s=40, cmap=plt.cm.Spectral);
返回值:
运行原始代码会报错,‘c’ argument has 1 elements, which is not acceptable for use with ‘x’ with size 400, ‘y’ with size 4,查了其他博主的文章,改为c=Y [0,:],即c等于数据Y第一列的数据,Y为400行一列0,1数据.
plt.scatter 表示散点图,c表示显示的颜色(Y= 0 红色,Y=1 绿色),s表示点的尺寸
cmap = plt.cm.Spectral实现的功能是给label为1的点一种颜色,给label为0的点另一种颜色。
#练习:你有多少个训练例子?另外,变量X和Y的形状是什么?
### START CODE HERE ### (≈ 3 lines of code)
shape_X = X.shape
shape_Y = Y.shape
m = X.shape[1] # training set size
### END CODE HERE ###
print ('The shape of X is: ' + str(shape_X))
print ('The shape of Y is: ' + str(shape_Y))
print ('I have m = %d training examples!' % (m))
返回值:
The shape of X is: (2, 400)
The shape of Y is: (1, 400)
I have m = 400 training examples!
3-简单Logistic回归
在构建完整的神经网络之前,让我们先看看logistic回归是如何处理这个问题的。您可以使用sklearn的内置函数来实现这一点。运行下面的代码在数据集上训练逻辑回归分类器。
# 训练logistic回归分类器
clf = sklearn.linear_model.LogisticRegressionCV(); #逻辑回归函数,CV表示交叉验证
#clf.fit(X.T, Y.T);
clf.fit(X.T, Y.flatten().T);
运行后会出现如下警告:/Users/zoudongyue/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
要求使用ravel()改变y的形状,同样我们也可以用flatten()将Y展平。按照提示更改后,再运行,警告就没有了
扩展:ravel()和flatten()都是将多维数组降为一维,其区别在于flatten()返回拷贝(copy)ravel()返回视图(view)
# 绘制logistic回归的决策边界
#plot_decision_boundary(lambda x: clf.predict(x), X, Y)
plot_decision_boundary(lambda x: clf.predict(x), X, Y.flatten())
plt.title("Logistic Regression")
# 打印精度
LR_predictions = clf.predict(X.T)
print ('Accuracy of logistic regression: %d ' % float((np.dot(Y,LR_predictions) + np.dot(1-Y,1-LR_predictions))/float(Y.size)*100) +
'% ' + "(percentage of correctly labelled datapoints)")
返回值:
Accuracy of logistic regression: 47 % (percentage of correctly labelled datapoints)
注意:此代码会出现和上一段代码同样的问题,需要用flatten将Y展平
解释:数据集不是线性可分的,所以逻辑回归的表现不好。希望神经网络能做得更好。我们现在就试试这个!
4-神经网络模型
Logistic回归在“花数据集”上不太有效。你要训练一个只有一个隐藏层的神经网络。
提醒:建立神经网络的一般方法是:
1.定义神经网络结构(输入单元、隐藏单元等);
2.初始化模型参数
3.循环:
1-实现正向传播 ; 2-计算损失
3-实现反向传播以获取梯度; 4-更新参数(梯度下降)
您经常构建一个函数来计算步骤1-3,然后将它们合并到一个我们称为nn_model()的函数中。一旦构建了nn_model()并学习了正确的参数,就可以对新数据进行预测。
4.1定义神经网络结构
练习:定义三个变量:
-n_x:输入层的大小
-n_h:隐藏层的大小(设置为4)
-núy:输出层的大小
提示:使用X和Y的形状来查找nx和ny。另外,硬编码隐藏层大小为4。
# GRADED FUNCTION: layer_sizes
def layer_sizes(X, Y):
"""
Arguments:
X -- input dataset of shape (input size, number of examples)
Y -- labels of shape (output size, number of examples)
Returns:
n_x -- the size of the input layer
n_h -- the size of the hidden layer
n_y -- the size of the output layer
"""
### START CODE HERE ### (≈ 3 lines of code)
n_x = X.shape[0]
n_h = 4
n_y = Y.shape[0]
### END CODE HERE ###
return (n_x, n_h, n_y)
X_assess, Y_assess = layer_sizes_test_case()
(n_x, n_h, n_y) = layer_sizes(X_assess, Y_assess)
print("The size of the input layer is: n_x = " + str(n_x))
print("The size of the hidden layer is: n_h = " + str(n_h))
print("The size of the output layer is: n_y = " + str(n_y))
返回值:
The size of the input layer is: n_x = 5
The size of the hidden layer is: n_h = 4
The size of the output layer is: n_y = 2
4.2-初始化模型参数
练习:实现initialize_parameters()函数。
说明:确保参数大小正确。如果需要,请参考上面的神经网络图。
您将使用随机值初始化权重矩阵。
使用:np.random.randn(a,b)*0.01随机初始化形状矩阵(a,b)。
您将把偏移向量初始化为零。
使用:np.zeros((a,b))初始化带零的形状矩阵(a,b)。
# GRADED FUNCTION: 初始化参数
def initialize_parameters(n_x, n_h, n_y):
"""
Argument:
n_x -- size of the input layer
n_h -- size of the hidden layer
n_y -- size of the output layer
Returns:
params -- python dictionary containing your parameters:
W1 -- weight matrix of shape (n_h, n_x)
b1 -- bias vector of shape (n_h, 1)
W2 -- weight matrix of shape (n_y, n_h)
b2 -- bias vector of shape (n_y, 1)
"""
np.random.seed(2) # 我们设置了一个种子,以便您的输出与我们的匹配,尽管初始化是随机的.
### START CODE HERE ### (≈ 4 lines of code)
W1 = np.random.randn(n_h, n_x) * 0.01
b1 = np.zeros((n_h, 1))
W2 = np.random.randn(n_y, n_h) * 0.01
b2 = np.zeros((n_y, 1))
### END CODE HERE ###
assert (W1.shape == (n_h, n_x))
assert (b1.shape == (n_h, 1))
assert (W2.shape == (n_y, n_h))
assert (b2.shape == (n_y, 1))
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
n_x, n_h, n_y = initialize_parameters_test_case()
parameters = initialize_parameters(n_x, n_h, n_y)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
返回值:
W1 = [[-0.00416758 -0.00056267]
[-0.02136196 0.01640271]
[-0.01793436 -0.00841747]
[ 0.00502881 -0.01245288]]
b1 = [[0.]
[0.]
[0.]
[0.]]
W2 = [[-0.01057952 -0.00909008 0.00551454 0.02292208]]
b2 = [[0.]]
4.3 - 循环过程
4.3.1问题:实现正向传播
说明:请看上面分类器的数学表示。
您可以使用函数sigmoid()。它内置(导入)在notebook中。
您可以使用函数np.tanh()。它是numpy库的一部分。
您必须执行的步骤是:
1.从字典“parameters”(即:initialize_parameters()的输出)中检索每个参数
2.实现正向传播。计算𝑍[1],𝐴[1],𝑍[2],𝐴[1](训练集中示例上所有预测的向量)。
𝑧1=𝑊[1]𝑥(𝑖)+𝑏[1]
𝑎1=tanh(𝑧1)
𝑧2=𝑊[2]𝑎1+𝑏[2]
𝑦̂(𝑖)=𝑎2=𝜎(𝑧2)
反向传播所需的值存储在“缓存”中。缓存将作为反向传播函数的输入。
# GRADED FUNCTION: 前向传播
def forward_propagation(X, parameters):
"""
Argument:
X -- input data of size (n_x, m)
parameters -- python dictionary containing your parameters (output of initialization function)
Returns:
A2 -- The sigmoid output of the second activation
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2"
"""
# Retrieve each parameter from the dictionary "parameters"
### START CODE HERE ### (≈ 4 lines of code)
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
### END CODE HERE ###
# Implement Forward Propagation to calculate A2 (probabilities)
### START CODE HERE ### (≈ 4 lines of code)
Z1 =np.dot(W1,X)+b1
A1 = np.tanh(Z1)
Z2 = np.dot(W2,A1)+b2
A2 = sigmoid(Z2)
### END CODE HERE ###
assert(A2.shape == (1, X.shape[1]))
cache = {"Z1": Z1,
"A1": A1,
"Z2": Z2,
"A2": A2}
return A2, cache
X_assess, parameters = forward_propagation_test_case()
A2, cache = forward_propagation(X_assess, parameters)
# Note: we use the mean here just to make sure that your output matches ours.
print(np.mean(cache['Z1']) ,np.mean(cache['A1']),np.mean(cache['Z2']),np.mean(cache['A2']))
返回值:0.26281864019752443 0.09199904522700109 -1.3076660128732143 0.21287768171914198
现在您已经计算了𝐴[2](在Python变量“A2”中),其中包含每个示例的𝑎[2](𝑖),您可以根据以下公式计算成本函数:
𝐽=−1/𝑚∑(𝑦(𝑖)log(𝑎2)+(1−𝑦(𝑖))log(1−𝑎2))
练习:实现compute_cost()以计算损失值J
实现交叉熵损失的方法有很多。为了帮助你,我们会告诉你−1/m∑𝑦(𝑖)log(𝑎2)
logprobs = np.multiply(np.log(A2),Y)
cost = - np.sum(logprobs) # no need to use a for loop!
(你可以用np.multiply() --> np.sum() 或者直接用np.dot()).
# GRADED FUNCTION: 损失函数
def compute_cost(A2, Y, parameters):
"""
Computes the cross-entropy cost given in equation (13)
Arguments:
A2 -- The sigmoid output of the second activation, of shape (1, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
parameters -- python dictionary containing your parameters W1, b1, W2 and b2
Returns:
cost -- cross-entropy cost given equation (13)
"""
m = Y.shape[1] # number of example
# Compute the cross-entropy cost
### START CODE HERE ### (≈ 2 lines of code)
logprobs = np.multiply(np.log(A2),Y)+np.multiply(np.log(1-A2),(1-Y))
cost = - np.sum(logprobs) /m
### END CODE HERE ###
cost = np.squeeze(cost) # makes sure cost is the dimension we expect.
# E.g., turns [[17]] into 17
assert(isinstance(cost, float))
return cost
A2, Y_assess, parameters = compute_cost_test_case()
print("cost = " + str(compute_cost(A2, Y_assess, parameters)))
返回值:cost = 0.6930587610394646
4.3.2问题:实现反向传播
def backward_propagation(parameters, cache, X, Y):
"""
Implement the backward propagation using the instructions above.
Arguments:
parameters -- python dictionary containing our parameters
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2".
X -- input data of shape (2, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
Returns:
grads -- python dictionary containing your gradients with respect to different parameters
"""
m = X.shape[1]
# First, retrieve W1 and W2 from the dictionary "parameters".
### START CODE HERE ### (≈ 2 lines of code)
W1 = parameters['W1']
W2 = parameters['W2']
### END CODE HERE ###
# Retrieve also A1 and A2 from dictionary "cache".
### START CODE HERE ### (≈ 2 lines of code)
A1 = cache['A1']
A2 = cache['A2']
### END CODE HERE ###
# Backward propagation: calculate dW1, db1, dW2, db2.
### START CODE HERE ### (≈ 6 lines of code, corresponding to 6 equations on slide above)
dZ2 = A2-Y
dW2 = np.dot(dZ2,A1.T)/m
db2 = np.sum(dZ2,axis = 1,keepdims = True)/m
dZ1 = np.multiply(W2.T,dZ2)*(1 - np.power(A1, 2))
dW1 = np.dot(dZ1,X.T)/m
db1 = np.sum(dZ1,axis = 1,keepdims = True)/m
### END CODE HERE ###
grads = {"dW1": dW1,
"db1": db1,
"dW2": dW2,
"db2": db2}
return grads
parameters, cache, X_assess, Y_assess = backward_propagation_test_case()
grads = backward_propagation(parameters, cache, X_assess, Y_assess)
print ("dW1 = "+ str(grads["dW1"]))
print ("db1 = "+ str(grads["db1"]))
print ("dW2 = "+ str(grads["dW2"]))
print ("db2 = "+ str(grads["db2"]))
返回值:dW1 = [[ 0.00301023 -0.00747267]
[ 0.00257968 -0.00641288]
[-0.00156892 0.003893 ]
[-0.00652037 0.01618243]]
db1 = [[ 0.00176201]
[ 0.00150995]
[-0.00091736]
[-0.00381422]]
dW2 = [[ 0.00078841 0.01765429 -0.00084166 -0.01022527]]
db2 = [[-0.16655712]]
4.3.3更新参数
def update_parameters(parameters, grads, learning_rate = 1.2):
"""
Updates parameters using the gradient descent update rule given above
Arguments:
parameters -- python dictionary containing your parameters
grads -- python dictionary containing your gradients
Returns:
parameters -- python dictionary containing your updated parameters
"""
# Retrieve each parameter from the dictionary "parameters"
### START CODE HERE ### (≈ 4 lines of code)
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
### END CODE HERE ###
# Retrieve each gradient from the dictionary "grads"
### START CODE HERE ### (≈ 4 lines of code)
dW1 = grads['dW1']
db1 = grads['db1']
dW2 = grads['dW2']
db2 = grads['db2']
## END CODE HERE ###
# Update rule for each parameter
### START CODE HERE ### (≈ 4 lines of code)
W1 = W1-learning_rate*dW1
b1 = b1-learning_rate*db1
W2 = W2-learning_rate*dW2
b2 = b2-learning_rate*db2
### END CODE HERE ###
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
parameters, grads = update_parameters_test_case()
parameters = update_parameters(parameters, grads)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
返回值:
W1 = [[-0.00643025 0.01936718]
[-0.02410458 0.03978052]
[-0.01653973 -0.02096177]
[ 0.01046864 -0.05990141]]
b1 = [[-1.02420756e-06]
[ 1.27373948e-05]
[ 8.32996807e-07]
[-3.20136836e-06]]
W2 = [[-0.01041081 -0.04463285 0.01758031 0.04747113]]
b2 = [[0.00010457]]
4.4 将4.1, 4.2 and 4.3 整合到一个神经网络模型中
def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False):
"""
Arguments:
X -- dataset of shape (2, number of examples)
Y -- labels of shape (1, number of examples)
n_h -- size of the hidden layer
num_iterations -- Number of iterations in gradient descent loop
print_cost -- if True, print the cost every 1000 iterations
Returns:
parameters -- parameters learnt by the model. They can then be used to predict.
"""
np.random.seed(3)
n_x = layer_sizes(X, Y)[0]
n_y = layer_sizes(X, Y)[2]
# Initialize parameters, then retrieve W1, b1, W2, b2. Inputs: "n_x, n_h, n_y". Outputs = "W1, b1, W2, b2, parameters".
### START CODE HERE ### (≈ 5 lines of code)
parameters = initialize_parameters(n_x, n_h, n_y)
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
### END CODE HERE ###
# Loop (gradient descent)
for i in range(0, num_iterations):
### START CODE HERE ### (≈ 4 lines of code)
# Forward propagation. Inputs: "X, parameters". Outputs: "A2, cache".
A2, cache = forward_propagation(X, parameters)
# Cost function. Inputs: "A2, Y, parameters". Outputs: "cost".
cost = compute_cost(A2, Y, parameters)
# Backpropagation. Inputs: "parameters, cache, X, Y". Outputs: "grads".
grads = backward_propagation(parameters, cache, X, Y)
# Gradient descent parameter update. Inputs: "parameters, grads". Outputs: "parameters".
parameters = update_parameters(parameters, grads, learning_rate = 1.2)
### END CODE HERE ###
# Print the cost every 1000 iterations
if print_cost and i % 1000 == 0:
print ("Cost after iteration %i: %f" %(i, cost))
return parameters
X_assess, Y_assess = nn_model_test_case()
parameters = nn_model(X_assess, Y_assess, 4, num_iterations=10000, print_cost=True)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
返回值:
Cost after iteration 0: 0.692739
Cost after iteration 1000: 0.000218
Cost after iteration 2000: 0.000107
Cost after iteration 3000: 0.000071
Cost after iteration 4000: 0.000053
Cost after iteration 5000: 0.000042
Cost after iteration 6000: 0.000035
Cost after iteration 7000: 0.000030
Cost after iteration 8000: 0.000026
Cost after iteration 9000: 0.000023
W1 = [[-0.65848169 1.21866811]
[-0.76204273 1.39377573]
[ 0.5792005 -1.10397703]
[ 0.76773391 -1.41477129]]
b1 = [[ 0.287592 ]
[ 0.3511264 ]
[-0.2431246 ]
[-0.35772805]]
W2 = [[-2.45566237 -3.27042274 2.00784958 3.36773273]]
b2 = [[0.20459656]]
4.5 预测
问题:通过构建predict()来使用模型进行预测。使用正向传播来预测结果。
def predict(parameters, X):
"""
Using the learned parameters, predicts a class for each example in X
Arguments:
parameters -- python dictionary containing your parameters
X -- input data of size (n_x, m)
Returns
predictions -- vector of predictions of our model (red: 0 / blue: 1)
"""
# Computes probabilities using forward propagation, and classifies to 0/1 using 0.5 as the threshold.
### START CODE HERE ### (≈ 2 lines of code)
A2, cache = forward_propagation(X, parameters)
predictions = (A2 > 0.5)
### END CODE HERE ###
return predictions
parameters, X_assess = predict_test_case()
predictions = predict(parameters, X_assess)
print("predictions mean = " + str(np.mean(predictions)))
返回值:predictions mean = 0.6666666666666666
现在是运行模型并查看它在平面数据集上的执行情况的时候了。运行下面的代码,用一个隐藏的层来测试您的模型。
# Build a model with a n_h-dimensional hidden layer
parameters = nn_model(X, Y, n_h = 4, num_iterations = 10000, print_cost=True)
# Plot the decision boundary
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y.flatten())
plt.title("Decision Boundary for hidden layer size " + str(4))
Cost after iteration 0: 0.693048
Cost after iteration 1000: 0.288083
Cost after iteration 2000: 0.254385
Cost after iteration 3000: 0.233864
Cost after iteration 4000: 0.226792
Cost after iteration 5000: 0.222644
Cost after iteration 6000: 0.219731
Cost after iteration 7000: 0.217504
Cost after iteration 8000: 0.219463
Cost after iteration 9000: 0.218560
Text(0.5, 1.0, ‘Decision Boundary for hidden layer size 4’)
# Print accuracy
predictions = predict(parameters, X)
print ('Accuracy: %d' % float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100) + '%')
返回值:Accuracy: 90%
与Logistic回归相比,准确度确实很高。模特已经学会了花的叶子图案!与logistic回归不同,神经网络能够学习甚至是高度非线性的决策边界。现在,让我们来试试几个隐藏层的大小。
# This may take about 2 minutes to run
plt.figure(figsize=(16, 32))
hidden_layer_sizes = [1, 2, 3, 4, 5, 20, 50]
for i, n_h in enumerate(hidden_layer_sizes):
plt.subplot(5, 2, i+1)
plt.title('Hidden Layer of size %d' % n_h)
parameters = nn_model(X, Y, n_h, num_iterations = 5000)
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y.flatten())
predictions = predict(parameters, X)
accuracy = float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100)
print ("Accuracy for {} hidden units: {} %".format(n_h, accuracy))
Accuracy for 1 hidden units: 67.5 %
Accuracy for 2 hidden units: 67.25 %
Accuracy for 3 hidden units: 90.75 %
Accuracy for 4 hidden units: 90.5 %
Accuracy for 5 hidden units: 91.25 %
Accuracy for 20 hidden units: 90.0 %
Accuracy for 50 hidden units: 90.25 %
解释:
较大的模型(具有更多隐藏单元)能够更好地适应训练集,直到最终最大的模型超过数据。
最佳隐藏层大小似乎在n_h=5左右。实际上,这里的一个值似乎很适合数据,而不会引起明显的过度拟合。
稍后您还将学习正则化,它允许您使用非常大的模型(如n_h=50),而不需要太多过拟合。
5-展示其他数据集
noisy_circles, noisy_moons, blobs, gaussian_quantiles, no_structure = load_extra_datasets()
datasets = {"noisy_circles": noisy_circles,
"noisy_moons": noisy_moons,
"blobs": blobs,
"gaussian_quantiles": gaussian_quantiles}
### START CODE HERE ### (choose your dataset)
dataset = "noisy_moons"
### END CODE HERE ###
X, Y = datasets[dataset]
X, Y = X.T, Y.reshape(1, Y.shape[0])
# make blobs binary
if dataset == "blobs":
Y = Y%2
# Visualize the data
plt.scatter(X[0, :], X[1, :], c=Y.flatten(), s=40, cmap=plt.cm.Spectral);
注意:可视化时,如果报错,将Y改为Y.flatten()即可。