运用sklearn自带的数据集做一个分类任务
from sklearn.datasets import fetch_lfw_people
faces = fetch_lfw_people(min_faces_per_person=60)
fig, ax = plt.subplots(3, 5)
for i, axi in enumerate(ax.flat):
axi.imshow(faces.images[i], cmap='bone')
axi.set(xticks=[], yticks=[],
xlabel=faces.target_names[faces.target[i]])
打印结果:
from sklearn.svm import SVC
#from sklearn.decomposition import RandomizedPCA
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline
pca = PCA(n_components=150, whiten=True, random_state=42)
svc = SVC(kernel='rbf', class_weight='balanced')
model = make_pipeline(pca, svc)
from sklearn.model_selection import train_test_split
Xtrain, Xtest, ytrain, ytest = train_test_split(faces.data, faces.target,
random_state=40)
from sklearn.model_selection import GridSearchCV
param_grid = {'svc__C': [1, 5, 10],
'svc__gamma': [0.0001, 0.0005, 0.001]}
grid = GridSearchCV(model, param_grid)
model = grid.best_estimator_
yfit = model.predict(Xtest)
fig, ax = plt.subplots(4, 6)
for i, axi in enumerate(ax.flat):
axi.imshow(Xtest[i].reshape(62, 47), cmap='bone')
axi.set(xticks=[], yticks=[])
axi.set_ylabel(faces.target_names[yfit[i]].split()[-1],
color='black' if yfit[i] == ytest[i] else 'red')
fig.suptitle('Predicted Names; Incorrect Labels in Red', size=14);
打印结果:
from sklearn.metrics import classification_report
print(classification_report(ytest, yfit,
target_names=faces.target_names))
打印结果:
from sklearn.metrics import confusion_matrix
mat = confusion_matrix(ytest, yfit)
sns.heatmap(mat.T, square=True, annot=True, fmt='d', cbar=False,
xticklabels=faces.target_names,
yticklabels=faces.target_names)
plt.xlabel('true label')
plt.ylabel('predicted label');
打印结果:
有什么问题,欢迎留言探讨。