Python数据挖掘实战4：基于水色图像的水质评价

Reference

《Python数据分析与挖掘实战（第2版）》
第9章，页码：P234，代码略有改进
images数据下载

分析过程

import numpy as np
import os, re
from PIL import Image
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score

pd.set_option('max_columns',1000)
pd.set_option('max_row',300)
pd.set_option('display.float_format', lambda x: '%.5f' % x)
plt.rcParams['font.sans-serif'] = ['SimHei']  #用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  #用来正常显示负号

#图像切割及特征提取
path = './images/'
#自定义获取图片名称函数
def getImageNames(path=path):
    #获取指定路径中所有图片的名称
    filenames = os.listdir(path)
    imageNames = []
    for i in filenames:
        if re.findall('^\d_\d+\.jpg$', i) != []:
            imageNames.append(i)
    return imageNames

#自定义获取三阶颜色矩函数
def Var(data=None):
    #获取给定像素矩阵的三阶颜色矩
    x = np.mean((data - data.mean())**3)
    return np.sign(x)*abs(x)**(1/3)

#批量处理图片数据
imageNames = getImageNames(path=path)  #获取所有图片名称
n = len(imageNames)  #图片张数
data = np.zeros([n, 9])  #用来装样本自变量
labels = np.zeros([n])  #用来放样本标签
# print(data)
# print(labels)

for i in range(n):
    img = Image.open(path + imageNames[i])  #读取图片
    M, N = img.size  #图片像素尺寸
    img = img.crop((M/2-50, N/2-50, M/2+50, N/2+50))  #图片切割
    r, g, b = img.split()  #将图片分割成三通道
    rd = np.asarray(r)/255  #转化成数组数据
    gd = np.asarray(g)/255
    bd = np.asarray(b)/255

    data[i, 0] = rd.mean()  #一阶颜色矩
    data[i, 1] = gd.mean()
    data[i, 2] = bd.mean()

    data[i, 3] = rd.std()  #二阶颜色矩
    data[i, 4] = gd.std()
    data[i, 5] = bd.std()

    data[i, 6] = Var(rd)  #三阶颜色矩
    data[i, 7] = Var(gd)
    data[i, 8] = Var(bd)

    labels[i] = imageNames[i][0]

print(data)
print(labels)

#模型构建
#使用决策树法构建水质评价模型
#数据拆分，训练集。测试集
data_tr, data_te, label_tr, label_te = train_test_split(data, labels, test_size=0.4, random_state=10)
#模型训练
model = DecisionTreeClassifier(random_state=5).fit(data_tr, label_tr)

#水质评价
pre_te = model.predict(data_te)
#混淆矩阵
cm_te = confusion_matrix(label_te, pre_te)
print(cm_te)
#准确率
print(accuracy_score(label_te, pre_te))