支持向量机svm的完整实现并配有解析

标签：use   除了   cat   evel   dict   splay   .sh   level   datasets   

from future import print_function
from time import time
import logging
#绘图工具
import matplotlib.pyplot as plt
#cross_validation：交叉验证，这里现在使用model_selection
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_lfw_people
#grid_search:网格搜索，现在该模块也被移除了python3中使用GridSearchCV
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import RandomizedPCA
from sklearn.svm import SVC

print(doc)
#Display progress logs on stdout
#把程序的一些进展信息打印出来
logging.basicConfig(level=logging.INFO, format=‘%(asctime)s %(message)s‘)

###############################################################################
#Download the data, if not already on disk and load it as numpy arrays
#下载数据 `
lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)

#introspect the images arrays to find the shapes (for plotting)
#提取各种特征信息
n_samples, h, w = lfw_people.images.shape

#for machine learning we use the 2 data directly (as relative pixel
#positions info is ignored by this model)
#X是关于特征向量的矩阵
X = lfw_people.data
#通过行数或者列数来得到特征值的数量
n_features = X.shape[1]

#the label to predict is the id of the person
#每个实例数据对应的人脸
y = lfw_people.target
target_names = lfw_people.target_names
#有多少人需要区分
n_classes = target_names.shape[0]

print("Total dataset size:")
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
print("n_classes: %d" % n_classes)

###############################################################################
#Split into a training set and a test set using a stratified k fold

#split into a training and testing set
#把数据分成训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25)

###############################################################################
#Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
#dataset): unsupervised feature extraction / dimensionality reduction
#n_components组成元素的数量，是一个参数
n_components = 150

print("Extracting the top %d eigenfaces from %d faces"
% (n_components, X_train.shape[0]))
t0 = time()
#RandomizedPCA方法可以把一个高维的特征向量变成一个低维的
pca = RandomizedPCA(n_components=n_components, whiten=True).fit(Xtrain)
print("done in %0.3fs" % (time() - t0))
#提取一些特征值，叫做eigenfaces
eigenfaces = pca.components.reshape((n_components, h, w))

print("Projecting the input data on the eigenfaces orthonormal basis")
t0 = time()
#转化一个低维的特征向量，完成降维工作
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
print("done in %0.3fs" % (time() - t0))

###############################################################################
#Train a SVM classification model

print("Fitting the classifier to the training set")
t0 = time()
#设置参数
#C:对于错误部分进行处罚
#gamma:多少的feature启动
#30种组合
param_grid = {‘C‘: [1e3, 5e3, 1e4, 5e4, 1e5],
‘gamma‘: [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
#class_weight：权重-------kernel：核函数
clf = GridSearchCV(SVC(kernel=‘rbf‘, class_weight=‘auto‘), param_grid)
clf = clf.fit(X_train_pca, y_train)
print("done in %0.3fs" % (time() - t0))
print("Best estimator found by grid search:")
print(clf.bestestimator)

###############################################################################
#Quantitative evaluation of the model quality on the test set

#对模型的好坏进行质量评估
print("Predicting people‘s names on the test set")
t0 = time()
y_pred = clf.predict(X_test_pca)
print("done in %0.3fs" % (time() - t0))
#看到分类器到底预测对了多少
print(classification_report(y_test, y_pred, target_names=target_names))
#n*n的方格，对角线数目，表示预测对的
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))

#画图
###############################################################################
#Qualitative evaluation of the predictions using matplotlib

def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
"""Helper function to plot a gallery of portraits"""
plt.figure(figsize=(1.8 n_col, 2.4 n_row))
plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
for i in range(n_row * n_col):
plt.subplot(n_row, n_col, i + 1)
plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray)
plt.title(titles[i], size=12)
plt.xticks(())
plt.yticks(())

#plot the result of the prediction on a portion of the test set

def title(y_pred, y_test, target_names, i):
pred_name = target_names[y_pred[i]].rsplit(‘ ‘, 1)[-1]
true_name = target_names[y_test[i]].rsplit(‘ ‘, 1)[-1]
return ‘predicted: %s\ntrue: %s‘ % (pred_name, true_name)

prediction_titles = [title(y_pred, y_test, target_names, i)
for i in range(y_pred.shape[0])]

plot_gallery(X_test, prediction_titles, h, w)

#plot the gallery of the most significative eigenfaces

eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)

plt.show()

支持向量机svm的完整实现并配有解析

标签：use   除了   cat   evel   dict   splay   .sh   level   datasets   

原文地址：http://blog.51cto.com/13831593/2173895