宽度学习(BLS)实战——python复刻MNIST数据集的数据预处理及训练过程

目录

1.宽度学习(Broad Learning System)

2.MNIST数据集

3.复刻MNIST数据集的预处理及训练过程

---

1.宽度学习(Broad Learning System)

对宽度学习的理解可见于这篇博客宽度学习（Broad Learning System）_颹蕭蕭的博客-CSDN博客_宽度学习

这里不再做详细解释

2.MNIST数据集

mnist数据集官网（下载地址）：MNIST handwritten digit database, Yann LeCun, Corinna Cortes and Chris Burges

MNIST数据集有称手写体数据集，其中中训练集一共包含了 60,000 张图像和标签，而测试集一共包含了 10,000 张图像和标签。测试集中前5000个来自最初NIST项目的训练集.，后5000个来自最初NIST项目的测试集。前5000个比后5000个要规整，这是因为前5000个数据来自于美国人口普查局的员工，而后5000个来自于大学生。
MNIST数据集自1998年起，被广泛地应用于机器学习和深度学习领域，用来测试算法的效果，相当于该领域的"hello world!"

3.复刻MNIST数据集的预处理及训练过程

原bls代码下载地址：Broad Learning System

下载后，我先用原代码中带的数据和代码进行训练，运行结果如下：

1.不含增量的bls代码：

2.含有增量的bls代码：

可以看到bls训练模型的时间非常短并且精确度达到0.93以上

然后我们回过头来看它用的训练集和测试集，它共输入三个csv文件，分别为test.csv，train.csv，sample_submission.csv

其中格式为：

这就是我们处理完MNIST数据之后需要bls代码中训练的数据，统计得到以下信息

数据集	数据总数
test.csv(测试集)	28000张
train.csv(训练集)	42000张

其中sample_submission.csv是提交样例，它最后会用来保存训练出的模型对测试集打的标签为csv文件。

那么得到这些信息我们就可以开始处理我们的mnist数据集了，在官网下载完数据集后我们得到了四个文件：

这个时候如果你是初学者，你就会奇怪明明是图像数据为什么下载完会是这四个东西？

这是因为为了方便使用，官方已经将70000张图片处理之后存入了这四个二进制文件中，因此我们要对这四个文件进行解析才能看到原本的图片。

此处用到struct包进行解析，详情见于Mnist数据集简介_查里王的博客-CSDN博客_mnist数据集

解析代码：

import os
import struct
import numpy as np

# 读取标签数据集
with open('../data/train-labels.idx1-ubyte', 'rb') as lbpath:
    labels_magic, labels_num = struct.unpack('>II', lbpath.read(8))
    labels = np.fromfile(lbpath, dtype=np.uint8)

# 读取图片数据集
with open('../data/train-images.idx3-ubyte', 'rb') as imgpath:
    images_magic, images_num, rows, cols = struct.unpack('>IIII', imgpath.read(16))
    images = np.fromfile(imgpath, dtype=np.uint8).reshape(images_num, rows * cols)

# 打印数据信息
print('labels_magic is {} \n'.format(labels_magic),
      'labels_num is {} \n'.format(labels_num),
      'labels is {} \n'.format(labels))

print('images_magic is {} \n'.format(images_magic),
      'images_num is {} \n'.format(images_num),
      'rows is {} \n'.format(rows),
      'cols is {} \n'.format(cols),
      'images is {} \n'.format(images))

# 测试取出一张图片和对应标签
import matplotlib.pyplot as plt

choose_num = 1  # 指定一个编号，你可以修改这里
label = labels[choose_num]
image = images[choose_num].reshape(28, 28)

plt.imshow(image)
plt.title('the label is : {}'.format(label))
plt.show()

运行结果：

 但是这并不是我们要的东西，我们需要的是将二进制文件解析后存入csv文件中用于训练。

在观察了原代码中所用的csv文件的格式以及bls代码中读取数据的方式后，我发现需要再存入之前对数据添加一个index，其中包括"label"和"pixel0~pixel784"，其中pixel是一维数组的元素编码，由于mnist数据集是28*28的图片，所以，转为一维数组后一共有784个元素。

知道这个原理后，编写代码如下：

import csv

def pixel(p_array, outf):
    with open(outf, "w",newline='') as csvfile:
            writer = csv.writer(csvfile)
            # 先写入columns_name
            writer.writerow(p_array)

def convert(imgf, labelf, outf, n):
    f = open(imgf, "rb")
    o = open(outf, "a")
    l = open(labelf, "rb")

    f.read(16)
    l.read(8)
    images = []

    for i in range(n):
        image = [ord(l.read(1))]
        for j in range(28*28):
            image.append(ord(f.read(1)))
        images.append(image)

    for image in images:
        o.write(",".join(str(pix) for pix in image)+"\n")
    f.close()
    o.close()
    l.close()

if __name__ == '__main__':

    p_array = []
    for j in range(0, 785):
        if j == 0 :
            b1 = "label"
            p_array.append(b1)
        else:
            b1 = 'pixel' + str(j - 1)
            p_array.append(b1)
    pixel(p_array,"../data/mnist_train.csv")
    pixel(p_array,"../data/mnist_test.csv")

    convert("../data/train-images.idx3-ubyte", "../data/train-labels.idx1-ubyte",
        "../data/mnist_train2.csv", 42000)
    convert("../data/t10k-images.idx3-ubyte", "../data/t10k-labels.idx1-ubyte",
        "../data/mnist_test2.csv", 28000)

    print("success!")

代码运行结果;

得到经过二进制文件解析以及格式处理后的数据：

现在训练集文件格式与源代码格式一样了，但是，既然是复刻那么我们还有一个问题没有解决——数据总数不一样，根据源代码中信息，训练集有42000张，测试集28000张，但是我们的训练集有60000张，测试集有10000张，所以我们需要稍微处理一下我们数量，其实这个很简单，只要将训练集中的数据匀18000张给测试集就可以了，另外测试集中标签一行需要删除，因为测试集好比高考试卷，标签相当于答案，没有人会把高考答案告诉你然后让你考对不对。这个过程可以用python代码实现，只要加入一点点功能，编写功能代码如下:

(记得删除测试集中的标签)

import csv
def test_add(train_imgf,train_labelf,outf):
    f = open(train_imgf, "rb")
    o = open(outf, "a")
    l = open(train_labelf, "rb")
    f.read(16)
    l.read(8)
    images = []

    for i in range(42001, 60001):
        image = [ord(l.read(1))]
        for j in range(28 * 28):
            image.append(ord(f.read(1)))
        images.append(image)

    for image in images:
        o.write(",".join(str(pix) for pix in image) + "\n")
    f.close()
    o.close()
    l.close()


def pixel(p_array, outf):
    with open(outf, "w",newline='') as csvfile:
            writer = csv.writer(csvfile)
            # 先写入columns_name
            writer.writerow(p_array)

def convert(imgf, labelf, outf, n):
    f = open(imgf, "rb")
    o = open(outf, "a")
    l = open(labelf, "rb")

    f.read(16)
    l.read(8)
    images = []

    for i in range(n):
        image = [ord(l.read(1))]
        for j in range(28*28):
            image.append(ord(f.read(1)))
        images.append(image)

    for image in images:
        o.write(",".join(str(pix) for pix in image)+"\n")
    f.close()
    o.close()
    l.close()

if __name__ == '__main__':

    p_array = []
    for j in range(0, 785):
        if j == 0 :
            b1 = "label"
            p_array.append(b1)
        else:
            b1 = 'pixel' + str(j - 1)
            p_array.append(b1)
    pixel(p_array,"../data/mnist_train2.csv")
    pixel(p_array,"../data/mnist_test2.csv")

    convert("../data/train-images.idx3-ubyte", "../data/train-labels.idx1-ubyte",
        "../data/mnist_train2.csv", 42000)
    convert("../data/t10k-images.idx3-ubyte", "../data/t10k-labels.idx1-ubyte",
        "../data/mnist_test2.csv", 10000)
    test_add("../data/train-images.idx3-ubyte", "../data/train-labels.idx1-ubyte", "../data/mnist_test2.csv")

    print("success!")

处理后，与提交案例一起加入bls训练，可以得到：

可以看到这与之前原始数据训练的结果几乎相同

4.补充（bls增量代码）

import numpy as np
import pandas as pd
import datetime
from sklearn import preprocessing  # 用来转化为独热编码
from sklearn.model_selection import train_test_split
from scipy import linalg as LA  # 用来求正交基
import joblib

# 在第一次求权重时，并未使用岭回归，还是直接求了伪逆，对于小型数据集这种方法足够了

def show_accuracy(predictLabel, Label):
    Label = np.ravel(Label).tolist()
    predictLabel = predictLabel.tolist()
    count = 0
    for i in range(len(Label)):
        if Label[i] == predictLabel[i]:
            count += 1
    return (round(count / len(Label), 5))


class node_generator(object):
    def __init__(self, isenhance=False):
        self.Wlist = []
        self.blist = []
        self.function_num = 0
        self.isenhance = isenhance

    def sigmoid(self, x):
        return 1.0 / (1 + np.exp(-x))

    def relu(self, x):
        return np.maximum(x, 0)

    def tanh(self, x):
        return (np.exp(x) - np.exp(-x)) / (np.exp(x) + np.exp(-x))

    def linear(self, x):
        return x

    def generator(self, shape, times):
        # times是多少组mapping nodes
        for i in range(times):
            W = 2 * np.random.random(size=shape) - 1
            if self.isenhance == True:
                W = LA.orth(W)  # 求正交基，只在增强层使用。也就是原始输入X变成mapping nodes的W和mapping nodes变成enhancement nodes的W要正交
            b = 2 * np.random.random() - 1
            yield (W, b)

    def generator_nodes(self, data, times, batchsize, function_num):
        # 按照bls的理论，mapping layer是输入乘以不同的权重加上不同的偏差之后得到的
        # 若干组，所以，权重是一个列表，每一个元素可作为权重与输入相乘
        self.Wlist = [elem[0] for elem in self.generator((data.shape[1], batchsize), times)]
        self.blist = [elem[1] for elem in self.generator((data.shape[1], batchsize), times)]

        self.function_num = {'linear': self.linear,
                             'sigmoid': self.sigmoid,
                             'tanh': self.tanh,
                             'relu': self.relu}[function_num]  # 激活函数供不同的层选择
        # 下面就是先得到一组mapping nodes，再不断叠加，得到len(Wlist)组mapping nodes
        nodes = self.function_num(data.dot(self.Wlist[0]) + self.blist[0])
        for i in range(1, len(self.Wlist)):
            nodes = np.column_stack((nodes, self.function_num(data.dot(self.Wlist[i]) + self.blist[i])))
        return nodes

    def transform(self, testdata):
        testnodes = self.function_num(testdata.dot(self.Wlist[0]) + self.blist[0])
        for i in range(1, len(self.Wlist)):
            testnodes = np.column_stack((testnodes, self.function_num(testdata.dot(self.Wlist[i]) + self.blist[i])))
        return testnodes

    def update(self, otherW, otherb):
        # 权重更新
        self.Wlist += otherW
        self.blist += otherb


class scaler:
    def __init__(self):
        self._mean = 0
        self._std = 0

    def fit_transform(self, traindata):
        self._mean = traindata.mean(axis=0)
        self._std = traindata.std(axis=0)
        return (traindata - self._mean) / (self._std + 0.001)

    def transform(self, testdata):
        return (testdata - self._mean) / (self._std + 0.001)


class broadNet(object):
    def __init__(self, map_num=10, enhance_num=10, DESIRED_ACC=0.99, EPOCH=10, STEP=1, map_function='linear',
                 enhance_function='linear', batchsize='auto'):
        self.map_num = map_num  # 多少组mapping nodes
        self.enhance_num = enhance_num  # 多少组engance nodes
        self.batchsize = batchsize
        self.map_function = map_function
        self.enhance_function = enhance_function
        self.DESIRED_ACC = DESIRED_ACC
        self.EPOCH = EPOCH
        self.STEP = STEP

        self.W = 0
        self.pseudoinverse = 0
        self.normalscaler = scaler()
        self.onehotencoder = preprocessing.OneHotEncoder(sparse=False)
        self.mapping_generator = node_generator()
        self.enhance_generator = node_generator(isenhance=True)

    def fit(self, data, label):
        if self.batchsize == 'auto':
            self.batchsize = data.shape[1]

        data = self.normalscaler.fit_transform(data)
        label = self.onehotencoder.fit_transform(np.mat(label).T)

        mappingdata = self.mapping_generator.generator_nodes(data, self.map_num, self.batchsize, self.map_function)
        enhancedata = self.enhance_generator.generator_nodes(mappingdata, self.enhance_num, self.batchsize,
                                                             self.enhance_function)

        print('number of mapping nodes {0}, number of enhence nodes {1}'.format(mappingdata.shape[1],
                                                                                enhancedata.shape[1]))
        print('mapping nodes maxvalue {0} minvalue {1} '.format(round(np.max(mappingdata), 5),
                                                                round(np.min(mappingdata), 5)))
        print('enhence nodes maxvalue {0} minvalue {1} '.format(round(np.max(enhancedata), 5),
                                                                round(np.min(enhancedata), 5)))

        inputdata = np.column_stack((mappingdata, enhancedata))
        print('input shape ', inputdata.shape)
        # 求伪逆
        self.pseudoinverse = np.linalg.pinv(inputdata)
        # 新的输入到输出的权重
        print('pseudoinverse shape:', self.pseudoinverse.shape)
        self.W = self.pseudoinverse.dot(label)

        # 查看当前的准确率
        Y = self.predict(data)
        accuracy = self.accuracy(Y, label)
        print("inital setting, number of mapping nodes {0}, number of enhence nodes {1}, accuracy {2}".format(
            mappingdata.shape[1], enhancedata.shape[1], round(accuracy, 5)))
        # 如果准确率达不到要求并且训练次数小于设定次数，重复添加enhance_nodes
        epoch_now = 0
        while accuracy < self.DESIRED_ACC and epoch_now < self.EPOCH:
            Y = self.addingenhance_predict(data, label, self.STEP, self.batchsize)
            accuracy = self.accuracy(Y, label)
            epoch_now += 1
            print("enhencing {3}, number of mapping nodes {0}, number of enhence nodes {1}, accuracy {2}".format(
                len(self.mapping_generator.Wlist) * self.batchsize,
                len(self.enhance_generator.Wlist) * self.batchsize,
                round(accuracy, 5),
                epoch_now))

    def decode(self, Y_onehot):
        Y = []
        for i in range(Y_onehot.shape[0]):
            lis = np.ravel(Y_onehot[i, :]).tolist()
            Y.append(lis.index(max(lis)))
        return np.array(Y)

    def accuracy(self, predictlabel, label):
        # print('predictlabel shape', predictlabel.shape)bbb
        # print('label shape:', label.shape)
        labels = []
        for i in range(len(label)):
            labels.append(np.argmax(label[i]))
        labels = np.ravel(labels).tolist()
        predictlabel = predictlabel.tolist()
        count = 0
        for i in range(len(labels)):
            if labels[i] == predictlabel[i]:
                count += 1
        return (round(count / len(labels), 5))

    def predict(self, testdata):
        # print(self.W.shape)
        testdata = self.normalscaler.transform(testdata)
        test_inputdata = self.transform(testdata)
        return self.decode(test_inputdata.dot(self.W))

    def transform(self, data):
        mappingdata = self.mapping_generator.transform(data)
        enhancedata = self.enhance_generator.transform(mappingdata)
        return np.column_stack((mappingdata, enhancedata))

    def addingenhance_nodes(self, data, label, step=1, batchsize='auto'):
        if batchsize == 'auto':
            batchsize = data.shape[1]

        mappingdata = self.mapping_generator.transform(data)
        inputdata = self.transform(data)
        localenhance_generator = node_generator()
        extraenhance_nodes = localenhance_generator.generator_nodes(mappingdata, step, batchsize, self.enhance_function)

        D = self.pseudoinverse.dot(extraenhance_nodes)
        C = extraenhance_nodes - inputdata.dot(D)
        BT = np.linalg.pinv(C) if (C == 0).any() else np.mat((D.T.dot(D) + np.eye(D.shape[1]))).I.dot(D.T).dot(
            self.pseudoinverse)

        self.W = np.row_stack((self.W - D.dot(BT).dot(label), BT.dot(label)))
        self.enhance_generator.update(localenhance_generator.Wlist, localenhance_generator.blist)
        self.pseudoinverse = np.row_stack((self.pseudoinverse - D.dot(BT), BT))

    def addingenhance_predict(self, data, label, step=1, batchsize='auto'):
        self.addingenhance_nodes(data, label, step, batchsize)
        test_inputdata = self.transform(data)
        return self.decode(test_inputdata.dot(self.W))


if __name__ == '__main__':
    # load the data
    train_data = pd.read_csv('../train.csv')
    test_data = pd.read_csv('../test.csv')
    samples_data = pd.read_csv('../sample_submission.csv')


    label = train_data['label'].values
    data = train_data.drop('label', axis=1)
    data = data.values
    print(data.shape, max(label) + 1)

    traindata, valdata, trainlabel, vallabel = train_test_split(data, label, test_size=0.2, random_state=0)
    print(traindata.shape, trainlabel.shape, valdata.shape, vallabel.shape)

    bls = broadNet(map_num=20,  # 初始时多少组mapping nodes
                   enhance_num=20,  # 初始时多少enhancement nodes
                   EPOCH=20,  # 训练多少轮
                   map_function='sigmoid',
                   enhance_function='sigmoid',
                   batchsize=200,  # 每一组的神经元个数
                   DESIRED_ACC=0.95,  # 期望达到的准确率
                   STEP=10 # 一次增加多少组enhancement nodes
                   )
    starttime = datetime.datetime.now()
    bls.fit(traindata, trainlabel)
    endtime = datetime.datetime.now()
    joblib.dump(bls, "model_allin.pkl")
    print('the training time of BLS is {0} seconds'.format((endtime - starttime).total_seconds()))

    predictlabel = bls.predict(valdata)
    print(show_accuracy(predictlabel, vallabel))

    predicts = bls.predict(test_data)

    # save as csv file
    samples = samples_data['ImageId']
    result = {'ImageId': samples,
              'Label': predicts}
    result = pd.DataFrame(result)

    result.to_csv('../output/bls_addenhancenodes.csv', index=False)