def test_planar_data():
x, y = load_planar_dataset() # 加载平面点数据集
print "x shape: " + str(x.shape)
print "y shape: " + str(y.shape)
iteration_num = 3000
learning_rate = 0.6
params, cost_list = regression(x, y, iteration_num, learning_rate)
print "params: %s" % str(params)
print "cost_list: %s" % str(cost_list)
predicts = predict(x, params)
cal_accuracy(predicts, y)
from utils.testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from utils.planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
from layer_sizes import layer_sizes
from initialize_parameters import initialize_parameters
from forward_propagation import forward_propagation
from compute_cost import compute_cost
from backward_propagation import backward_propagation
from update_parameters import update_parameters
np.random.seed(1) # set a seed so that the results are consistent
X, Y = load_planar_dataset()
# shape_X = X.shape
# shape_Y = Y.shape
# m = X.shape[1] # training set size
# # 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))
# # Train the logistic regression classifier
# clf = sklearn.linear_model.LogisticRegressionCV()
# clf.fit(X.T, Y.T)
# # Plot the decision boundary for logistic regression
# LR_predictions = clf.predict(X.T)
grads = backward_propagate(params, cache, x, y)
params = update_params(params, grads, learning_rate)
if print_cost and i % 1000 == 0:
print('cost after iter %i:%f' % (i, cost))
return params
def predict(params, x):
a2, cache = forward_propagate(x, params)
pred = np.round(a2)
return pred
if __name__ == "__main__":
np.random.seed(1)
x, y = load_planar_dataset()
# plt.figure(figsize=(5,8))
# plt.scatter(x[0,:],x[1,:],c=y,s=20,cmap=plt.cm.Spectral)
# plt.show()
# sample_linear_logistic(x,y)
print('the shape x is:' + str(x.shape))
print('the shape y is:' + str(y.shape))
m = x.shape[1]
# params = nn_model(x,y,n_h=4,num_iter=10000,print_cost=True,learning_rate=1.2)
# plot_decision_boundary(lambda x:predict(params,x.T),x,y)
# plt.show()
# pred = predict(params,x)
# print('Accuracy: %d' % float((np.dot(y,pred.T) +np.dot(1-y,1-pred.T))/float(y.size)*100) + '%')
plt.figure(figsize=(20, 20))
hidden_layer_sizes = [1, 2, 3, 4, 5, 20, 50]