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()