机器学习-神经网络算法应用(二)

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

 

# -*- coding:utf-8 -*-
from NeuralNetwork import NeuralNetwork
import numpy 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))

结果：

[0, 0] [-0.01209026]
[0, 1] [ 0.99815739]
[1, 0] [ 0.99815649]
[1, 1] [-0.01949152]

 

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

查看数据集：

# -*- coding:utf-8 -*-
from sklearn.datasets import load_digits
import pylab as  pl

digits = load_digits()
print(digits.data.shape)

pl.gray()
pl.matshow(digits.images[0])
pl.show()

　结果：(1797, 64) 1797个图片实例，每个实例有8x8=64个特征向量(像素点)

# -*- coding:utf-8 -*-

# 每个图片8x8  识别数字：0,1,2,3,4,5,6,7,8,9

import numpy as np
from sklearn.datasets import load_digits
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.preprocessing import LabelBinarizer
from NeuralNetwork import NeuralNetwork
from sklearn.cross_validation import train_test_split

#加载数据
digits = load_digits()
x = digits.data #特征向量
y = digits.target #类标签
x -= x.min()  # normalize the values to bring them into the range 0-1
x /= x.max()  #所有x减去他的最小值，再除以他的最大值

nn = NeuralNetwork([64, 100, 10], 'logistic')
x_train, x_test, y_train, y_test = train_test_split(x, y)
#转化为0 1
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 in range(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))

 

 结果：

start fitting
[[48  0  0  0  0  0  0  0  0  0]
 [ 0 37  1  0  0  0  0  0  0  4]
 [ 0  1 44  1  0  0  0  0  0  0]
 [ 0  0  0 44  0  1  0  1  0  0]
 [ 1  1  0  0 39  0  0  1  1  0]
 [ 0  0  0  0  0 49  1  0  0  0]
 [ 0  1  0  0  0  0 43  0  0  0]
 [ 0  0  0  0  0  0  0 33  1  0]
 [ 0  3  0  1  0  4  1  0 35  1]
 [ 0  0  0  6  0  2  0  4  0 40]]
             precision    recall  f1-score   support

          0       0.98      1.00      0.99        48
          1       0.86      0.88      0.87        42
          2       0.98      0.96      0.97        46
          3       0.85      0.96      0.90        46
          4       1.00      0.91      0.95        43
          5       0.88      0.98      0.92        50
          6       0.96      0.98      0.97        44
          7       0.85      0.97      0.90        34
          8       0.95      0.78      0.85        45
          9       0.89      0.77      0.82        52

avg / total       0.92      0.92      0.91       450

　　

# -*- coding:utf-8 -*-
from sklearn.datasets import load_digits
import pylab as  pl

digits = load_digits()
print(digits.data.shape)

pl.gray()
pl.matshow(digits.images[0])
pl.show()