泥石流图像分类

from pathlib import Path
import random
import os
import matplotlib.pyplot as plt
import numpy as np
from sklearn import preprocessing
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
from sklearn import tree

#数据存放地址
arr_path = Path('C:/Users/Administrator/Desktop/sc_data')#路径分隔符号/or\\
#获取子文件路径
l = list(arr_path.iterdir())#遍历子文件路径
# print(l)

all_file_list = []#用list存放npy文件的地址
all_label_list = []#用list存放npy文件的标签，标签为子文件的名称（建议给子文件夹取名为0,1,2,...）

for i in l:
    print(f'i==={i}')
    temp_file_list = list(i.glob("**/*.npy"))#返回所有npy文件的地址的list
    temp_label_list = [int(i.name)]*len(temp_file_list)#生成list[]，[1]*3=[1,1,1]以此类推
    print(f'{int(i.name)}含有样本数量:{len(temp_file_list)}')
    print(temp_file_list)
    #子文件路径
    all_file_list += temp_file_list
    #子文件标签
    all_label_list += temp_label_list
#     folder_list.append(str(i.name))

all_data = list(zip(all_file_list,all_label_list))
# print(all_data[:10])

data_x = []#用list存放npy文件的数值变量
data_y = []#用list存放label
#按照路径读取numpy数组
for i in range(len(all_data)):
    arr = np.load(all_data[i][0])
    '''
    # print(arr.shape)
    # print(all_data[i][1])
    # if i >10:
    #     break
    # data_x.append(arr.reshape(5,224,224))
    '''
    data_x.append(arr)
    data_y.append(all_data[i][1])

# print(data_x[:5],data_y[:5])

#svm需要的数据类型为numpy.array,上面用的是list存放数据，所以要把list变成array
data_feature  = np.array(data_x)
data_label = np.array(data_y)
print(data_feature.shape,data_label.shape)

data_feature = data_feature.reshape(1060,-1)
print(data_feature.shape,data_label.shape)

# 数据归一（可以比较一下归一化对分类结果是否有影响）
data_feature = preprocessing.MinMaxScaler().fit_transform(data_feature)

X_train, X_test, y_train, y_test = train_test_split(data_feature, data_label, test_size=0.3, random_state=1000)

# from sklearn import svm
# predictor = svm.SVC(gamma='scale', C=1.0,max_iter = 1000)
# # 进行训练
# predictor.fit(X_train, y_train)
#
# predictions_labels = predictor.predict(X_train)
# print(classification_report(y_train, predictions_labels))
# predictions_labels = predictor.predict(X_test)
# print(classification_report(y_test, predictions_labels))

from sklearn.ensemble import RandomForestClassifier
# 创建随机森林分类器
predictor = RandomForestClassifier(n_estimators=120)
# 进行训练
predictor.fit(X_train, y_train)

predictions_labels = predictor.predict(X_train)
print(classification_report(y_train, predictions_labels,digits=4))
predictions_labels = predictor.predict(X_test)
print(classification_report(y_test, predictions_labels,digits=4))
'''
#分类树
from sklearn import tree  # 导入模块

# predictor = tree.DecisionTreeClassifier()  # 实例化
predictor = tree.DecisionTreeClassifier(criterion="entropy")
predictor.fit(X_train[:100], y_train[:100])

# clf = predictor.fit(X_train, y_train)
# score = clf.score(X_test, y_test)  # 导入测试集，从接口中调用需要的信息
# print(score)

# predictions_labels = predictor.predict(X_train)
# print(classification_report(y_train, predictions_labels))
# predictions_labels = predictor.predict(X_test)
# print(classification_report(y_test, predictions_labels))


#将分类树可视化
tree.plot_tree(predictor, filled=True,
               class_names=['0','1'])
plt.show()
'''