Add files via upload

Author: wzy6642

NeuralNetwork_Project1/MLP.py

@@ -0,0 +1,95 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Aug 14 22:21:25 2018
+
+@author: wzy
+"""
+"""
+# =============神经网络用于分类=============
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.neural_network import MLPClassifier
+from sklearn.preprocessing import StandardScaler
+data = [
+    [-0.017612, 14.053064, 0],[-1.395634, 4.662541, 1],[-0.752157, 6.53862, 0],[-1.322371, 7.152853, 0],[0.423363, 11.054677, 0],
+    [0.406704, 7.067335, 1],[0.667394, 12.741452, 0],[-2.46015, 6.866805, 1],[0.569411, 9.548755, 0],[-0.026632, 10.427743, 0],
+    [0.850433, 6.920334, 1],[1.347183, 13.1755, 0],[1.176813, 3.16702, 1],[-1.781871, 9.097953, 0],[-0.566606, 5.749003, 1],
+    [0.931635, 1.589505, 1],[-0.024205, 6.151823, 1],[-0.036453, 2.690988, 1],[-0.196949, 0.444165, 1],[1.014459, 5.754399, 1],
+    [1.985298, 3.230619, 1],[-1.693453, -0.55754, 1],[-0.576525, 11.778922, 0],[-0.346811, -1.67873, 1],[-2.124484, 2.672471, 1],
+    [1.217916, 9.597015, 0],[-0.733928, 9.098687, 0],[1.416614, 9.619232, 0],[1.38861, 9.341997, 0],[0.317029, 14.739025, 0]
+]
+dataMat = np.array(data)
+X = dataMat[:,0:2]
+y = dataMat[:,2]
+# 神经网络对数据尺度敏感，所以最好在训练前标准化，或者归一化，或者缩放到[-1,1]
+scaler = StandardScaler() # 标准化转换
+scaler.fit(X)  # 训练标准化对象
+X = scaler.transform(X)   # 转换数据集
+# solver='lbfgs',  MLP的求解方法：L-BFGS 在小数据上表现较好，Adam 较为鲁棒，SGD在参数调整较优时会有最佳表现（分类效果与迭代次数）；SGD标识随机梯度下降。
+# alpha:L2的参数：MLP是可以支持正则化的，默认为L2，具体参数需要调整
+# hidden_layer_sizes=(5, 2) hidden层2层,第一层5个神经元，第二层2个神经元)，2层隐藏层，也就有3层神经网络
+
+clf = MLPClassifier(solver='lbfgs', alpha=1e-5,hidden_layer_sizes=(5,2), random_state=1)  # 神经网络输入为2，第一隐藏层神经元个数为5，第二隐藏层神经元个数为2，输出结果为2分类。
+clf.fit(X, y)
+print('每层网络层系数矩阵维度：\n',[coef.shape for coef in clf.coefs_])
+y_pred = clf.predict([[0.317029, 14.739025]])
+print('预测结果：',y_pred)
+y_pred_pro =clf.predict_proba([[0.317029, 14.739025]])
+print('预测结果概率：\n',y_pred_pro)
+
+cengindex = 0
+for wi in clf.coefs_:
+    cengindex += 1  # 表示底第几层神经网络。
+    print('第%d层网络层:' % cengindex)
+    print('权重矩阵维度:',wi.shape)
+    print('系数矩阵:\n',wi)
+
+# 绘制分割区域
+x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1 # 寻找每个维度的范围
+y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1 # 寻找每个维度的范围
+xx1, xx2 = np.meshgrid(np.arange(x_min, x_max, 0.01),np.arange(y_min, y_max,0.01)) # 在特征范围以0.01位步长预测每一个点的输出结果
+Z = clf.predict(np.c_[xx1.ravel(), xx2.ravel()]) # 先形成待测样本的形式，在通过模型进行预测。
+Z = Z.reshape(xx1.shape) # 将输出结果转换为和网格的矩阵形式，以便绘图
+# 绘制区域网格图
+plt.pcolormesh(xx1, xx2, Z, cmap=plt.cm.Paired)
+# 绘制样本点
+plt.scatter(X[:,0],X[:,1],c=y)
+plt.show()
+
+"""
+# # =============神经网络用于回归=============
+
+import numpy as np
+from sklearn.neural_network import MLPRegressor  # 多层线性回归
+from sklearn.preprocessing import StandardScaler
+data = [
+         [ -0.017612,14.053064,14.035452],[ -1.395634, 4.662541, 3.266907],[ -0.752157, 6.53862,5.786463],[ -1.322371, 7.152853, 5.830482],
+         [0.423363,11.054677,11.47804 ],[0.406704, 7.067335, 7.474039],[0.667394,12.741452,13.408846],[ -2.46015,6.866805, 4.406655],
+         [0.569411, 9.548755,10.118166],[ -0.026632,10.427743,10.401111],[0.850433, 6.920334, 7.770767],[1.347183,13.1755,14.522683],
+         [1.176813, 3.16702,4.343833],[ -1.781871, 9.097953, 7.316082],[ -0.566606, 5.749003, 5.182397],[0.931635, 1.589505, 2.52114 ],
+         [ -0.024205, 6.151823, 6.127618],[ -0.036453, 2.690988, 2.654535],[ -0.196949, 0.444165, 0.247216],[1.014459, 5.754399, 6.768858],
+         [1.985298, 3.230619, 5.215917],[ -1.693453,-0.55754, -2.250993],[ -0.576525,11.778922,11.202397],[ -0.346811,-1.67873, -2.025541],
+         [ -2.124484, 2.672471, 0.547987],[1.217916, 9.597015,10.814931],[ -0.733928, 9.098687, 8.364759],[1.416614, 9.619232,11.035846],
+         [1.38861,9.341997,10.730607],[0.317029,14.739025,15.056054]
+]
+
+dataMat = np.array(data)
+X=dataMat[:,0:2]
+y = dataMat[:,2]
+scaler = StandardScaler() # 标准化转换
+scaler.fit(X)  # 训练标准化对象
+X = scaler.transform(X)   # 转换数据集
+
+# solver='lbfgs',  MLP的求解方法：L-BFGS 在小数据上表现较好，Adam 较为鲁棒，SGD在参数调整较优时会有最佳表现（分类效果与迭代次数）；SGD标识随机梯度下降。
+# alpha:L2的参数：MLP是可以支持正则化的，默认为L2，具体参数需要调整
+# hidden_layer_sizes=(5, 2) hidden层2层,第一层5个神经元，第二层2个神经元)，2层隐藏层，也就有3层神经网络
+clf = MLPRegressor(solver='lbfgs', alpha=1e-5,hidden_layer_sizes=(5, 2), random_state=1)
+clf.fit(X, y)
+print('预测结果：', clf.predict([[0.317029, 14.739025]]))  # 预测某个输入对象
+
+cengindex = 0
+for wi in clf.coefs_:
+    cengindex += 1  # 表示底第几层神经网络。
+    print('第%d层网络层:' % cengindex)
+    print('权重矩阵维度:',wi.shape)
+

NeuralNetwork_Project1/NN.py

@@ -0,0 +1,138 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Aug 13 16:25:47 2018
+神经网络通过调整隐藏节点数、世代数以及学习率改善训练结果
+hidden_nodes、epochs、learning_rate
+
+@author: wzy
+"""
+import numpy as np
+# scipy.special for the sigmoid function expit()
+import scipy.special
+import matplotlib.pyplot as plt
+
+"""
+类说明：构建神经网络
+
+Parameters:
+    None
+    
+Returns:
+    None
+
+Modify:
+    2018-08-13
+"""
+class neuralNetwork:
+    # 神经网络的构造函数
+    # 初始化函数——设定输入层节点、隐藏层节点和输出层节点的数量。
+    def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
+        # 输入节点、隐藏节点、输出节点、学习率
+        self.inodes = inputnodes
+        self.hnodes = hiddennodes
+        self.onodes = outputnodes
+        self.lr = learningrate
+        # 通过wih和who链接权重矩阵
+        # weights inside the arrays are w_i_j,where link is from node i to node j in the next layer
+        # 使用正态概率分布采样权重，平均值为0.0，标准方差为节点传入链接数目的开方，即1/sqrt(传入链接数目)
+        self.wih = np.random.normal(0.0, pow(self.hnodes, -0.5), (self.hnodes, self.inodes))
+        self.who = np.random.normal(0.0, pow(self.onodes, -0.5), (self.onodes, self.hnodes))
+        # activation function is the sigmoid function
+        self.activation_function = lambda x: scipy.special.expit(x)
+        pass
+    
+    # 神经网络的训练函数
+    # 训练——学习给定训练集样本后，优化权重。
+    def train(self, inputs_list, targets_list):
+        # convert inputs list to 2d array
+        inputs = np.array(inputs_list, ndmin=2).T
+        targets = np.array(targets_list, ndmin=2).T
+        # calculate signals into hidden layer
+        hidden_inputs = np.dot(self.wih, inputs)
+        # calculate the signals emerging from hidden layer
+        hidden_outputs = self.activation_function(hidden_inputs)
+        # calculate signals into final output layer
+        final_inputs = np.dot(self.who, hidden_outputs)
+        # calculate the signals emerging from final output layer
+        final_outputs = self.activation_function(final_inputs)
+        # error is the (target - actual)
+        output_errors = targets - final_outputs
+        # hidden layer error is the output_errors, split by weights, recombined at hidden nodes
+        hidden_errors = np.dot(self.who.T, output_errors)
+        # update the weights for the links between the hidden and output layers
+        self.who += self.lr * np.dot((output_errors * final_outputs * (1.0 - final_outputs)), np.transpose(hidden_outputs))
+        # update the weights for the links between the input and hidden layers
+        self.wih += self.lr * np.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)), np.transpose(inputs))
+        pass
+    
+    # 神经网络的查询函数
+    # 查询——给定输入，从输出节点给出答案。
+    def query(self, inputs_list):
+        # convert inputs list to 2d array
+        inputs = np.array(inputs_list, ndmin=2).T
+        # calculate signals into hidden layer
+        hidden_inputs = np.dot(self.wih, inputs)
+        # calculate the signals emerging from hidden layer
+        hidden_outputs = self.activation_function(hidden_inputs)
+        # calculate signals into final output layer
+        final_inputs = np.dot(self.who, hidden_outputs)
+        # calculate the signals emerging from final output layer
+        final_outputs = self.activation_function(final_inputs)
+        return final_outputs
+   
+
+if __name__ == '__main__':
+    input_nodes = 784
+    hidden_nodes = 200
+    output_nodes = 10
+    learning_rate = 0.2
+    # 进行两轮训练
+    epochs = 5
+    n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
+    # 导入训练数据
+    training_data_file = open('mnist_dataset/mnist_train_100.csv', 'r')
+    training_data_list = training_data_file.readlines()
+    training_data_file.close()
+    # 数据可视化处理
+    for e in range(epochs):
+        for record in training_data_list:
+            all_values = record.split(',')
+            # 将数据进行归一化处理，落在区间[0.01, 1.0]内
+            inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
+            # np.asfarray()将文本字符串转换成实数，并创建这些数字的数组
+            # image_array = np.asfarray(all_values[1:]).reshape((28, 28))
+            # output nodes is 10(example)
+            targets = np.zeros(output_nodes) + 0.01
+            # all_values[0] is the target label for this record
+            targets[int(all_values[0])] = 0.99
+            # cmap='Greys'灰度图
+            # plt.imshow(image_array, cmap='Greys', interpolation='None')
+            n.train(inputs, targets)
+    # 导入测试数据
+    test_data_file = open('mnist_dataset/mnist_test_10.csv', 'r')
+    test_data_list = test_data_file.readlines()
+    test_data_file.close()
+    # scorecard for how well the network performs, initially empty
+    scorecard = []
+    # go through all the records in the test data set
+    for record in test_data_list:
+        all_values = record.split(',')
+        correct_label = int(all_values[0])
+        print(correct_label, 'correct label')
+        # 将数据进行归一化处理，落在区间[0.01, 1.0]内
+        inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
+        # 查询神经网络
+        outputs = n.query(inputs)
+        # np.argmax()发现数组中的最大值，并告诉我们它的位置
+        label = np.argmax(outputs)
+        print(label, "network's answer")
+        if (label == correct_label):
+            scorecard.append(1)
+        else:
+            scorecard.append(0)
+    scorecard_array = np.asarray(scorecard)
+    print("performance = ", scorecard_array.sum() / scorecard_array.size)
+    # print(all_values[0])
+    # image_array = np.asfarray(all_values[1:]).reshape((28, 28))
+    # plt.imshow(image_array, cmap='Greys', interpolation='None')
+    # print(n.query((np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01))

NeuralNetwork_Project1/mnist_dataset/mnist_readme.txt

@@ -0,0 +1,3 @@
+These are small subsets of the MNIST data set, transformed into CSV, and made available for easy testing as your code develops.
+
+The full dataset in CSV format is available at: http://pjreddie.com/projects/mnist-in-csv/