模式识别（四）K邻近分类器（KNN）识别MNIST数据集

KNN

from sklearn.model_selection import train_test_split
from sklearn import datasets
import numpy as np
from math import sqrt
from collections import Counter

class KNNClassifier:

    def __init__(self, k):
        # 初始化
        assert k >= 1
        self.k = k
        self._X_train = None
        self._y_train = None

    def fit(self, X_train, y_train):
        assert X_train.shape[0] == y_train.shape[0]
        assert self.k <= X_train.shape[0]

        self._X_train = X_train
        self._y_train = y_train
        return self

    def predict(self, X_predict):
        # 给定待预测数据集X_predict，返回表示X_predict的结果向量
        assert self._X_train is not None and self._y_train is not None
        assert X_predict.shape[1] == self._X_train.shape[1]

        y_predict = [self._predict(x) for x in X_predict]
        return np.array(y_predict)

    def _predict(self, x):
        # 给定单个待预测数据x，返回x的预测结果值
        assert x.shape[0] == self._X_train.shape[1]

        distances = [sqrt(np.sum((x_train - x) ** 2))
                     for x_train in self._X_train]
        nearest = np.argsort(distances)
        topK_y = [self._y_train[i] for i in nearest[:self.k]]
        votes = Counter(topK_y)

        return votes.most_common(1)[0][0]

    def __repr__(self):
        return "KNN(k=%d)" % self.k

# 导入MNIST数据
digits = datasets.load_digits()
X=digits.data
y=digits.target

X_train, X_test, y_train, y_test = train_test_split(X,y)

knn_clf=KNNClassifier(k=3)
knn_clf.fit(X_train,y_train)
y_predict=knn_clf.predict(X_test)

print(sum(y_predict==y_test)/len(y_test))

PCA+KNN

from numpy import *
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA
import time


def loadDataSet(filedir):
    DateSet = pd.read_csv(filedir)
    len_data = len(DateSet)
    Data = DateSet.iloc[1:int(len_data), 1:].as_matrix()  # len_data 可以自己设置len_data的大小来测试算法对数据量的敏感程度
    # PCA降维
    pca = PCA(n_components=25, whiten=True)
    Data = pca.fit_transform(Data)
    # print('Data size: ', shape(Data))
    label = DateSet.iloc[1:int(len_data), :1].as_matrix()
    # 分配训练数据和测试数据
    train_data, test_data, train_label, test_label = train_test_split(Data, label, test_size=0.3, random_state=0,shuffle=True)
    return train_data, test_data, train_label, test_label


def kNN_classify(classify_data, train_data, train_label, k):
    # 计算欧式距离
    m = shape(train_data)[0]
    diff = tile(classify_data, (m, 1)) - train_data
    dist = sqrt(sum(diff ** 2, axis=1))
    data_index = argsort(dist)  # 升序排序,得到索引值
    # 取前k个与classify_data距离最小的训练数据的标签
    data_label = []
    for i in range(k):
        data_label.append(train_label[data_index[i]][0])
    # 选取数量最多的标签作为classify_data的分类标签
    classify_label = {}
    for j in range(k):
        votelabel = data_label[j]
        classify_label[votelabel] = classify_label.get(votelabel, 0) + 1
    # print('classify_label: ', classify_label)
    maxValue = 0
    class_label = None
    for label, value in classify_label.items():
        if value > maxValue:
            maxValue = value
            class_label = label
    return class_label


def train_model(train_data, test_data, train_label, test_label, k=10):
    m = shape(test_data)[0]
    err_num = 0
    for i in range(m):
        result = kNN_classify(test_data[i], train_data, train_label, k)
        if result != test_label[i]:
            err_num += 1
    accuracy = (m - err_num) / m
    return accuracy

path="D:\\STUDYFILE\\RUN\\mnist_train.csv"
train_data, test_data, train_label, test_label = loadDataSet(path)
accuracy = train_model(train_data, test_data, train_label, test_label, k=10)


print(accuracy)

这里用到了.csv格式文件，下面是原始文件转换的代码。

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


convert("MNIST/train-images.idx3-ubyte", "MNIST/train-labels.idx1-ubyte",
        "mnist_train.csv", 60000)
convert("MNIST/t10k-images.idx3-ubyte", "MNIST/t10k-labels.idx1-ubyte",
        "mnist_test.csv", 10000)

print("Convert Finished!")