def main():
np.random.seed(1) # 设置一个种子，使得结果是一致的
# 导入花型的 2 类数据集
# X: 输入数据集，维度为（输入特征的数量，样本数量）
# Y: 标签数据集，维度为（输出特征的数量，样本数量）
X, Y = load_planar_dataset()
shape_X = X.shape
shape_Y = Y.shape
m = Y.shape[1] # 训练样本数
print("X 的维度：" + str(shape_X))
print("Y 的维度：" + str(shape_Y))
print("训练样本数：" + str(m))
# 训练得到参数
parameters = nn_model(X, Y, n_h = 4, num_iterations = 10000, print_cost = True)
# 预测并绘制分类边界
plot_decision_boundary(lambda x: predict(parameters, x.T), X, np.squeeze(Y))
plt.title("Decision Boundary for hidden layer size " + str(4))
plt.show() # 否则不显示
# 预测并打印准确率
predictions = predict(parameters, X)
print("准确率：%d" % float((np.dot(Y, predictions.T) + np.dot(1 - Y, 1 - predictions.T)) / float(Y.size) * 100) + '%')
def loadData():
np.random.seed(1) # set a seed so that the results are consistent
X, Y = load_planar_dataset()
# plt.figure(1)
# plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral)
#
# shape_X = X.shape
# shape_Y = Y.shape
# m = shape_X[1]
# # Train the logistic regression classifier
#
# clf = sklearn.linear_model.LogisticRegressionCV();
# clf.fit(X.T, Y.T);
#
# # Plot the decision boundary for logistic regression
# plot_decision_boundary(lambda x: clf.predict(x), X, Y)
# plt.title("Logistic Regression")
#
# # Print accuracy
# 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)")
# plt.show()
return X, Y
def load():
X, Y = load_planar_dataset()
name = 'flower'
X = X.T
Y = Y[0]
# plt.scatter(X[:, 0], X[:, 1], c=Y , s=40, cmap=plt.cm.Spectral);
# plt.title(name+'_original')
# plt.savefig(os.path.join('pic', name+'_original'))
# plt.show()
# load dataset
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}
datas = [(name, X, Y), ]
for name, dataset in datasets.items():
X, Y = datasets[name]
datas.append((name, X, Y))
# print(X.shape)
# print(Y.shape)
# Visualize the data
# plt.scatter(X[:, 0], X[:, 1], c=Y, s=40, cmap=plt.cm.Spectral)
# plt.title(name+'_original')
# plt.savefig(os.path.join('pic', name+'_original'))
# plt.show()
return datas
def runML():
X, Y = load_planar_dataset()
plt.scatter(X[0, :], X[1, :], c=Y.ravel(), s=40, cmap=plt.cm.Spectral)
shape_X = X.shape
shape_Y = Y.shape
m = len(Y.T) # 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))
clf = sklearn.linear_model.LogisticRegression()
clf.fit(X.T, Y.T)
# plot_decision_boundary(lambda x: clf.predict(x), X, Y.ravel())
# plt.title("Logistic Regression")
# plt.show(block=True)
# Print accuracy
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)")
print('\n')
def main():
X, Y = load_planar_dataset()
# Visualize the data:
# plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);
shape_X = X.shape
shape_Y = Y.shape
m = Y.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))
# log_regression_case(X, Y)
# test_layer_sizes()
# test_init_params()
# test_forward_prop()
# test_compute_cost()
# test_backward_prop()
# test_update_params()
# test_nn_model()
# test_predict()
# 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)
plt.title("Decision Boundary for hidden layer size " + str(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) + '%')
def play():
X, Y = load_planar_dataset()
# print(X)
# print(Y)
# Visualize the data:
# plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);
shape_X = X.shape
shape_Y = Y.shape
m = X.shape[1]
print(shape_X)
print(shape_Y)
print(m)
# Train the logistic regression classifier
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
# Plot the decision boundary for logistic regression
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
plt.title("Logistic Regression")
# Print accuracy
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)")
def test_planar_dataset_2classification(self):
"""
对于二分类问题, 检查损失(loss)是否随着迭代而不断降低
:return:
"""
X, Y = load_planar_dataset()
X = X.T
Y = Y.T.flatten()
# Visualize the data:
plt.scatter(X[:, 0], X[:, 1], c=Y, s=40, cmap=plt.cm.Spectral)
# plt.show() # 展示图片(使用 jupyter notebook 不用指明需要显示)
shape_X = X.shape
shape_Y = Y.shape
N = shape_X[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!' % (N))
clf = MLP_2Classifier(use_reg=0)
clf.fit(X=X,
y=Y,
layers_dims=[2, 4, 1],
learning_rate=1,
max_iter=10000)
def Test1():
X, Y = load_planar_dataset()
model = SingleHiddenLayer(4, 1.2)
model.initializeData(X, Y)
model.train_model(num_iterations=10000)
predictions = model.predict(X)
print('Accuracy: {0}%'.format(
float((np.dot(Y, predictions.T) + np.dot(1 - Y, 1 - predictions.T)) /
float(Y.size) * 100)))
plot_decision_boundary(lambda x: model.predict(x.T), X, Y.ravel())
plt.title('Decision boundary for hidden layer size: 5')
plt.show()
def main():
X, Y = load_planar_dataset()
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)
predictions = predict(parameters, X)
accuracy = np.sum(predictions == Y) / float(Y.shape[1]) * 100.0
print("Accuracy for {} hidden units: {}%".format(n_h, accuracy))
plt.show()
def runNN():
X, Y = load_planar_dataset()
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.ravel())
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))
plt.show(block=True)
def __init__(self):
self.X, self.Y = load_planar_dataset()
self.sample_amount = self.X.shape[1]
self.n_x = self.X.shape[0]
self.n_h = 4
self.n_y = self.Y.shape[0]
np.random.seed(2)
self.W1 = np.random.randn(self.n_h, self.n_x) * 0.01 # (后一层，前一层)
print self.W1
self.b1 = np.zeros((self.n_h, 1))
self.W2 = np.random.randn(self.n_y, self.n_h) * 0.01
print self.W2
self.b2 = np.zeros((self.n_y, 1))
self.A1 = np.zeros((self.n_h, self.sample_amount))
self.A2 = np.zeros((self.n_y, self.sample_amount))
self.current_cost = 0
self.is_trained = False
def baseline_lr():
X, Y = load_planar_dataset()
# 1. baseline: logistic regression
# Train the logistic regression classifier
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
# Plot the decision boundary for logistic regression
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
plt.title("Logistic Regression")
# Print accuracy
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)")
def main():
"""
参数:
返回值:
"""
# 加载数据
train_x, train_y, test_x, test_y = planar_utils.load_planar_dataset()
# 训练模型
parameters = nn_model(train_x, train_y, n_h=4, num_iterations=10000, print_cost=True)
# 预测训练集
predictions = predict(parameters, train_x)
# 输出准确率
print('Train Accuracy: %d' % float((np.dot(train_y, predictions.T) +
np.dot(1 - train_y, 1 - predictions.T)) /
float(train_y.size) * 100) + '%')
# 预测测试集
predictions = predict(parameters, test_x)
print('Test Accuracy: %d' % float((np.dot(test_y, predictions.T) +
np.dot(1 - test_y, 1 - predictions.T)) /
float(test_y.size) * 100) + '%')
def load_data():
"""
载入数据，数据项包括：
train_set_x_orig：原始训练数据集
train_set_y：原始训练数据标签
test_set_x_orig：原始测试数据集
test_set_y：原始测试数据标签
classes(cat/non-cat)：分类list
Args:
Return:
"""
global TRAINING_SET, TEST_SET, DATADIM
train_set_x, train_set_y, test_set_x, test_set_y = planar_utils.load_planar_dataset()
# 定义纬度
DATADIM = 2
TRAINING_SET = np.hstack((train_set_x.T, train_set_y.T))
TEST_SET = np.hstack((test_set_x.T, test_set_y.T))
def LogisticRegression():
# - a numpy-array (matrix) X that contains your features (x1, x2)
# - a numpy-array (vector) Y that contains your labels (red:0, blue:1).
X, Y = load_planar_dataset()
# Visualize the data:
# plt.scatter 画散列点图，参数c指定类别label，
# 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。
plt.scatter(X[0, :], X[1, :], c=Y[0, :], s=40, cmap=plt.cm.Spectral)
plt.show()
### START CODE HERE ### (≈ 3 lines of code)
shape_X = X.shape
shape_Y = Y.shape
m = Y.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))
# Simple Logistic Regression
# Train the logistic regression classifier
# sklearn's built-in functions
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
# Plot the decision boundary for logistic regression
# plot_decision_boundary在planar_utils.py里
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
plt.title("Logistic Regression")
# Print accuracy
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)")
def main():
X, Y = load_planar_dataset()
#hyper-parameters
num_hidden_units = 4
num_iterations = 10000
learning_rate = 1.2
learner_parameters = nn_model(X,
Y,
num_hidden_units,
num_iterations,
learning_rate,
print_cost=True)
predictions = predict(learner_parameters, X)
print('Accuracy: %d' %
float((np.dot(Y, predictions.T) + np.dot(1 - Y, 1 - predictions.T)) /
float(Y.size) * 100) + '%')
plot_decision_boundary(lambda x: predict(learner_parameters, x.T), X, Y)
plt.title("Decision Boundary for hidden layer size " + str(4))
plt.show()
import numpy as np # fundamental package for scientific computing with Python
import matplotlib.pyplot as plt # a library for plotting graphs in Python
from testCases_v2 import * # provides some test examples
import sklearn # provides simple and efficent tools for data mining and data analysis
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets # provides various usefull functions used in this assignment
np.random.seed(1) # set a seed so that the results are consistent
X, Y = load_planar_dataset(
) # will load "flower" 2-class dataset into variables X and Y
plt.scatter(X[0, :], X[1, :], c=Y.ravel(), s=40, cmap=plt.cm.Spectral)
# Returns a contiguous flattened array
plt.show()
# - a numpy-array (matrix) X that contains your features (x1, x2)
# - a numpy-array (vector) Y that contains your labels (red:0, blue:1)
shape_X = X.shape
shape_Y = Y.shape
m = X.shape[1]
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))
# Before building a full neural network, lets first see how logistic regression performs on this problem.
# You can use sklearn's built-in functions to do that. Run the code below to train a logistic regression classifier on the dataset.
# Train the logistic regression classifier
Returns
predictions -- vector of predictions of our model (red: 0 / blue: 1)
"""
A2, cache = forward_propagation(X, parameters)
predictions = (A2 > 0.5)
return predictions
while True:
print("Select the data you want:")
print("0. Flower \n1. Noisy Circles \n2. Noisy Moons \n3. Blobs \n4. Gaussian Quantiles\n5. Testing with differend hidden neurons")
i = int(input("Enter no: "))
noisy_circles, noisy_moons, blobs, gaussian_quantiles = load_extra_datasets()
if i != 5:
datasets = [load_planar_dataset(), noisy_circles, noisy_moons, blobs, gaussian_quantiles]
X, Y = datasets[i]
if i >0:
X, Y = X.T, Y.reshape(1, Y.shape[0])
if i == 3:
Y = Y%2
plt.scatter(X[0, :], X[1, :], c=np.squeeze(Y), s=40, cmap=plt.cm.Spectral)
plt.show()
n_h = int(input("Enter number of hidden layers: "))
num_iterations = int(input("Enter number of iterations"))
parameters = nn_model(X, Y, n_h, num_iterations, print_cost=True)
plot_decision_boundary(lambda x: predict(parameters, x.T), X, np.squeeze(Y))
predictions = predict(parameters, X)
accuracy = float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100)
plt.title("Accuracy for {} hidden units: {} %".format(n_h, accuracy))
def load_data():
global TRAINING_DATA, TEST_DATA_X, TEST_DATA_Y, TEST_DATA
X, Y = load_planar_dataset()
TRAINING_DATA = np.hstack([X.T, Y.T])
@author: Francis Chen
"""
# Package Area
import numpy as np
import matplotlib.pyplot as plt
from testCases import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
np.random.seed(1)
# Here comes the Function
X, Y = load_planar_dataset() # X is point and Y is label
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral)
shape_X = X.shape # The raw data
shape_Y = Y.shape # The label of data
m = Y.shape[1] # Total Data number, in here is 400
print("The dimension for X is " + str(shape_X))
print("THe dimension for Y is " + str(shape_Y))
print("The dataset has total data " + str(m))
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
import numpy as np
import matplotlib.pyplot as plt
from testCases import * # 提供了一些测试示例来评估函数的正确性
import sklearn # sklearn：为数据挖掘和数据分析提供的简单高效的工具。
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
# 提供了在这个任务中使用的各种有用的功能
np.random.seed(1) # 设置一个固定的随机种子，以保证接下来的步骤中我们的结果是一致的。
# 只要random.seed( * ) seed里面的值一样，那随机出来的结果就一样。
# seed的作用是让随机结果可重现
#==================================Load and Visualize Dataset===============================
X, Y = load_planar_dataset() # 生成400个样本集，正负样本各一半
plt.scatter(X[0, :], X[1, :], c=np.squeeze(Y), s=40,
cmap=plt.cm.Spectral) # 绘制散点图
# c-标记颜色
# s-标记大小
# cmap-色彩盘，实际上就是一个三列的矩阵(shape 为 [N,3]的array),每一行代表一个颜色(RGB)
# np.squeeze(Y)生成的(400,)是秩为1的数组，(1,400)是一个二维数组，它们是不匹配的
plt.show()
# plt.imshow()函数负责对图像进行处理，并显示其格式
# plt.show()则是将plt.imshow()处理后的函数显示出来
shape_X = X.shape
shape_Y = Y.shape
m = shape_Y[1]
print('The shape of X is: ' + str(shape_X))
def main():
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: {}'.format(shape_X))
print('The shape of Y is: {}'.format(shape_Y))
print('I have m = {} training examples!'.format(m))
# Visualize the data:
plt.figure()
plt.scatter(X[0, :],
X[1, :],
c=Y.ravel(),
s=40,
cmap=plt.cm.get_cmap('Spectral'))
# Train the logistic regression classifier
clf = sklearn.linear_model.LogisticRegression(solver='lbfgs')
clf.fit(X.T, Y.flatten())
# Plot the decision boundary for logistic regression
plt.figure()
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
plt.title("Logistic Regression")
# Print accuracy
LR_predictions = clf.predict(X.T)
print(
'Accuracy of logistic regression: {}% (percentage of correctly labelled datapoints)'
.format(
float(
(np.dot(Y, LR_predictions) + np.dot(1 - Y, 1 - LR_predictions))
/ float(Y.size) * 100)))
# 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
plt.figure()
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
plt.title('Decision Boundary for hidden layer size {}'.format(4))
# Print accuracy
predictions = predict(parameters, X)
print('Accuracy: {}%'.format(
float((np.dot(Y, predictions.T) + np.dot(1 - Y, 1 - predictions.T)) /
float(Y.size) * 100)))
# # Tuning hidden layer size
# 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 {}'.format(n_h))
# parameters = nn_model(X, Y, n_h, num_iterations = 5000)
# plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
# 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))
# # Performance on other datasets
# 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}
# dataset = "noisy_moons"
# 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.figure()
# plt.scatter(X[0, :], X[1, :], c=Y.ravel(), s=40, cmap=plt.cm.get_cmap('Spectral'))
# # 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 with other datasets
# plt.figure()
# plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
# plt.title('Decision Boundary for hidden layer size {}'.format(4))
# # Print accuracy
# predictions = predict(parameters, X)
# print ('Accuracy: {}%'.format(float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100)))
plt.show()
# # Planar data classification with one hidden layer
import matplotlib.pyplot as plt
import sklearn.linear_model
from planar_utils import plot_decision_boundary, load_planar_dataset
from assignment02_utils import *
np.random.seed(1) # set a seed so that the results are consistent
# import pdb; pdb.set_trace
# ========================================================
# Load and visualise the data
# load the data
X, Y = load_planar_dataset()
# plot a scatter of the data
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral)
plt.show()
shape_X = X.shape
shape_Y = Y.shape
m = shape_X[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))
# ========================================================
# Simple Logistic Regression
# Package imports
import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
from funcs import *
np.random.seed(1) # set a seed so that the results are consistent
"""
2 - Dataset
"""
X, Y = load_planar_dataset() # X: 2 x 400 , Y: 1 x 400
# Visualize the data:
plt.scatter(X[0, :], X[1, :], c=np.reshape(Y, -1), s=40, cmap=plt.cm.Spectral)
### 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))
"""
3 - Simple Logistic Regression
"""
# Train the logistic regression classifier
import numpy as np import matplotlib.pyplot as plt from testCases_v2 import * import sklearn import sklearn.datasets import sklearn.linear_model from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets %matplotlib inline np.random.seed(1) # set a seed so that the results are consistent X, Y = load_planar_dataset() # Load dataset # Visualize the data: plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral); #Shape of X, Y and the size of the training data set shape_X = X.shape shape_Y = Y.shape m = X.shape[1] # training set size # Train the logistic regression classifier clf = sklearn.linear_model.LogisticRegressionCV(); clf.fit(X.T, Y.T); # Plot the decision boundary for logistic regression plot_decision_boundary(lambda x: clf.predict(x), X, Y)
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn #provides simple and efficient tools for data mining and data analysis
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets # various various useful functions needed here
get_ipython().magic('matplotlib inline')
np.random.seed(1) # set a seed so that the results are consistent
# ## 2 - Dataset ##
#
X, Y = load_planar_dataset() # Obtain the data set, which will load a flow 2-class data set into variables 'X' and 'Y'
# Visualize the dataset using matplotlib. The data looks like a "flower" with some red (label y=0) and some blue (y=1) points.
# Goal is to build a model to fit this data. In other words, want the classifier to define regions as either red or blue.
# Visualize the data:
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);
# Have:
# - a numpy-array (matrix) X that contains your features (x1, x2)
# - a numpy-array (vector) Y that contains your labels (red:0, blue:1).
#
# To get the shape of a numpy array: [(help)](https://docs.scipy.org/doc/numpy/reference/generated/numpy.ndarray.shape.html)
self.dz[self.l - 1] = self.a[self.l - 1] - y # 确定最后一层是sigmoid
self.dw[self.l - 1] = 1.0 / m * np.dot(self.dz[self.l - 1],
self.a[self.l - 2].T)
self.db[self.l - 1] = 1.0 / m * np.sum(
self.dz[self.l - 1], axis=1, keepdims=True)
self.da[self.l - 2] = np.dot(self.w[self.l - 1].T,
self.dz[self.l - 1])
for i in range(self.l - 2, -1, -1): # 1 0
self.backPpRelu(i)
#print(self.w)
self.update(lr)
def predict(self, x):
for i in range(self.l - 1): # 0,1
self.forPpRelu(i, x)
self.forPpSig(self.l - 1) # 2
return np.where(self.a[self.l - 1] > 0.5, 1, 0)
x, y = load_planar_dataset()
y = y.ravel()
para = [4, 5, 1]
dnn = deepNN()
dnn.train(x, y, 10000, 0.8)
yhat = dnn.predict(x)
print(yhat.shape)
print("precision of nn:" + str(100 - (np.sum(np.abs(yhat - y))) / 4) + "%")
plot_decision_boundary(lambda x: dnn.predict(x.T), x, y)
plt.show()
# 计算预测的精度
y_c = np.where(y_c > 0.5, 1, 0)
# y_c = np.round(y_c)
return np.mean(y == y_c)
def predict(n_n, x):
y = n_n.predict(x)
y = np.where(y > 0.5, 1, 0)
return y
if __name__ == '__main__':
np.seterr(all='raise') # numpy设置异常
origin_x, origin_y = load_planar_dataset()
train_x, train_y, test_x, test_y = split_train_test(
origin_x, origin_y, 0.3)
layers = (
Layer(7, origin_x.shape[0], g=ReLu, alpha=0.3),
# Layer(6, 5, g=ReLu, alpha=0.3, ),
# Layer(7, 6, g=ReLu, alpha=0.3, ),
Layer(
8,
7,
g=tanh,
alpha=0.3,
),
Layer(1, 8, g=sigmoid, alpha=0.3, op=True),
)
nn = NN(origin_x, origin_y, layers, num_iterations=10000)
def do_something():
X, Y = load_planar_dataset()
# Visualize the data:
plt.scatter(X[0, :], X[1, :], c=Y.ravel(), s=40, cmap=plt.cm.Spectral);
### Shapes
### START CODE HERE ### (≈ 3 lines of code)
shape_X = X.shape
shape_Y = Y.shape
m = Y.size # 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))
### Logistic Regression
# Train the logistic regression classifier
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
# Plot the decision boundary for logistic regression
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
plt.title("Logistic Regression")
# Print accuracy
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)")
# plt.show()
### Layer sizes
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))
### Initialize 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"]))
## The Loop
### Forward propagation
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']))
### Cost function
A2, Y_assess, parameters = compute_cost_test_case()
print("cost = " + str(compute_cost(A2, Y_assess, parameters)))
### Backward propagation
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"]))
### Update 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"]))
## End of Loop
## Integrate parts 4.1, 4.2 and 4.3 in nn_model()
X_assess, Y_assess = nn_model_test_case()
parameters = nn_model(X_assess, Y_assess, 4, num_iterations=10000, print_cost=False)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
## Predictions
parameters, X_assess = predict_test_case()
predictions = predict(parameters, X_assess)
print("predictions mean = " + str(np.mean(predictions)))
## Neural network
# 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)
plt.title("Decision Boundary for hidden layer size " + str(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) + '%')
## Tuning hidden layer size (optional)
# 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)
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))
## Performance on other datasets
# Datasets
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.ravel(), s=40, cmap=plt.cm.Spectral)
plt.show()
'''
# Package imports
import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
#%matplotlib inline
np.random.seed(1) # set a seed so that the results are consistent
#loading dataset
X, Y = load_planar_dataset()
#Visualize the data:
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);
#How many training examples do you have
shape_X = X.shape
shape_Y = Y.shape
m = shape_X[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))
########## first simple logistic regression
np.random.seed(1) # set a seed so that the results are consistent
imageNp = imgNp.getImageNpArray('classification_kiank.png')
print(imageNp.shape)
imgNp.drawImageWithNpArray(imageNp)
imageNp = imgNp.getImageNpArray('grad_summary.png')
imgNp.drawImageWithNpArray(imageNp)
imageNp = imgNp.getImageNpArray('sgd.gif')
imgNp.drawImageWithNpArray(imageNp)
imageNp = imgNp.getImageNpArray('sgd_bad.gif')
imgNp.drawImageWithNpArray(imageNp)
X, Y = planarUtils.load_planar_dataset()
n_x, n_h, n_y = testCases.initialize_parameters_test_case()
try:
print(
"layer 1 is the first layer, it inputs X (x1 and x2) and outputs A1."
)
print("layer 2 is the output layer, it inputs A1 and outputs A2")
n_h = int(
input('Give me the number of hiddent units for the layer 1:'))
num_iterations = int(input('Give me the number of iterations:'))
except ValueError:
print("This is not a number.")
quit()
print("\n------------Start------------")
