模式识别（六）聚类算法（AdaBoost和随机森林）识别细胞数据集

import os
import cv2 as cv
import numpy as np
import time
from sklearn.decomposition import PCA
from sklearn.ensemble import AdaBoostClassifier as Ada
from sklearn.ensemble import RandomForestClassifier as Ran
#from imblearn.over_sampling import SMOTE

def get_path(filepath):
    filelist = []
    filedirs = []
    for root, _, files in os.walk(filepath, topdown = False):
        for name in files:
            filelist.append(name)
            filedirs.append(os.path.join(root, name))
    return filelist, filedirs

def read_file(path,filelist, filedirs, n_component = 1, Use_smote = False):
    dic ={'DCIS':0, 'IDC':0, 'Muc':0, 'ILC':0, 'MC':0,
          'normal':1,
          'TIL':2}
    datalist = []
    claslist = []
    for path in filedirs:
        img = cv.imread(path, 0) #单通道读入灰度图像
        vec = img.flatten() / 255
        name = filelist[filedirs.index(path)]
        clas = name.split('_')[0] #保留_前面的字符串即：'DCIS'...
        if len(vec) == 51*51:
            datalist.append(vec)
            claslist.append(dic[clas])
    claslist = np.array(claslist)
    datalist = np.array(datalist)
    pca = PCA(n_component)
    datalist_n = pca.fit_transform(datalist)
    if Use_smote == True:
        smo = SMOTE(random_state = 40)
        datalist_smo, claslist_smo = smo.fit_sample(datalist_n, claslist)
        return datalist_smo, claslist_smo
    else:
        return datalist_n, claslist

def AdaBoost_Classifier(datalist, claslist):
    classifier = Ada( algorithm="SAMME", n_estimators=100, learning_rate=0.1)
    classifier.fit(datalist, claslist)
    return classifier.score(datalist, claslist)

def RandomForest_Classifier(datalist, claslist):
    classifier = Ran(n_estimators=10 )
    classifier.fit(datalist, claslist)
    return classifier.score(datalist, claslist)

#————————————————————————————————————————————————————————————————————————
time_start = time.time()
path = './cells/train'
n_components = 100
if n_components < 1:
    print('方差下限为：', n_components)
else:
    print('PCA降维至：', n_components)
filepath, filedirs = get_path(path)
# print(filepath)
# print(filedirs)
datalist, claslist = read_file(path,filepath, filedirs, n_components, Use_smote = False)
acc1 = RandomForest_Classifier(datalist, claslist)
acc2 = AdaBoost_Classifier(datalist, claslist)

print('随机森林正确率为：', acc1)
print('AdaBoost正确率为：', acc2)
time_end = time.time()
print('耗时：', time_end-time_start, 's')