sklearn实战之构建SVM多分类器

77 阅读 0 评论 51 点赞

我是靠谱客的博主纯真汉堡，最近开发中收集的这篇文章主要介绍sklearn实战之构建SVM多分类器，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

利用sklearn库构建SVM分类器十分简单，因为这个库已经封装好了，只用调用相应的函数即可。

# -*- coding: utf-8 -*-
"""
Created on Fri Nov 23 18:44:37 2018
@author: 13260
"""
import os
import numpy as np
import matplotlib.pyplot as plt
from itertools import cycle
from sklearn import svm, metrics, preprocessing
from sklearn.metrics import roc_curve, auc, classification_report
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
from sklearn.multiclass import OneVsRestClassifier
from sklearn.externals import joblib
from scipy import interp
# 加载图像特征及标签
'''
def read_features(filedir):
file_list = os.listdir(filedir)
X = []
tmp_y = os.listdir("F:/shiyan/TensorFlow/retrain/data/train")
# print(len(y))
y = []
for file in file_list:
tmp_file = filedir + "/" + file
tmp = np.loadtxt(tmp_file,dtype=str)
# np格式转换
feature = tmp.astype(np.float)
X.append(feature)
old_filename = file[:-3].split("_")
filename = "_".join(old_filename[:-1])
# tmp_filename = filter(str.isalpha,file[:-3])
# print(filename)
y.append(tmp_y.index(filename))
# 特征数据保存到txt文件的格式是str,因此在进行运算时应进行格式转换
tmp = "F:/python/airplane_001.txt"
tmp_data = np.loadtxt(tmp,dtype=str)
res = tmp_data.astype(np.float)
X.append(res)
'''
# 加载特征和标签文件
def load_features_and_labels(features_path,labels_path):
features = np.load(features_path)
labels = np.load(labels_path)
print("[INFO] Feature and label file have been loaded !")
return features,labels
def train_and_test_model(feature,label):
# X_scaled = preprocessing.scale(X)
# print(y)
# y = label_binarize(y,classes=list(range(45)))
label_list = os.listdir("F:/shiyan/TensorFlow/retrain/data/train")
# print(label.shape)
# print(label)
label = LabelBinarizer().fit_transform(label)
# print(label)
# print(label[:45])
# print(label.shape[1])
# print(y[:45])
# 训练模型并进行预测
random_state = np.random.RandomState(0)
n_samples, n_feature = feature.shape
# 随机化数据，并划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(feature, label, test_size=.2,random_state=0)
# 训练模型
model = OneVsRestClassifier(svm.SVC(kernel='linear',probability=True,random_state=random_state))
print("[INFO] Successfully initialize a new model !")
print("[INFO] Training the model…… ")
clt = model.fit(X_train,y_train)
print("[INFO] Model training completed !")
# 保存训练好的模型，下次使用时直接加载就可以了
joblib.dump(clt,"F:/python/model/conv_19_80%.pkl")
print("[INFO] Model has been saved !")
'''
# 加载保存的模型
clt = joblib.load("F:/python/model/SVM.pkl")
print("model has been loaded !")
# y_train_pred = clt.predict(X_train)
'''
y_test_pred = clt.predict(X_test)
ov_acc = metrics.accuracy_score(y_test_pred,y_test)
print("overall accuracy: %f"%(ov_acc))
print("===========================================")
acc_for_each_class = metrics.precision_score(y_test,y_test_pred,average=None)
print("acc_for_each_class:n",acc_for_each_class)
print("===========================================")
avg_acc = np.mean(acc_for_each_class)
print("average accuracy:%f"%(avg_acc))
print("===========================================")
classification_rep = classification_report(y_test,y_test_pred,
target_names=label_list)
print("classification report: n",classification_rep)
print("===========================================")
#print("===========================================")
confusion_matrix = metrics.confusion_matrix(y_test.argmax(axis=1),y_test_pred.argmax(axis=1))
print("confusion metrix:n",confusion_matrix)
print("===========================================")
# print("accuracy: %f"%(acc_r))
print("[INFO] Successfully get SVM's classification overall accuracy ! ")
if __name__ == "__main__":
features_path = "F:/python/features/DenseNet/densenet_fv_flatten.npy"
labels_path = "F:/python/features/VGG19/VGG19_labels.npy"
feature,label = load_features_and_labels(features_path,labels_path)
train_and_test_model(feature,label)