predict = output.argmax(dim = 1)
confusion_matrix =torch.zeros(2,2)
for t, p in zip(predict.view(-1), target.view(-1)):
    confusion_matrix[t.long(), p.long()] += 1
a_p =(confusion_matrix.diag() / confusion_matrix.sum(1))[0]
b_p = (confusion_matrix.diag() / confusion_matrix.sum(1))[1]
a_r =(confusion_matrix.diag() / confusion_matrix.sum(0))[0]
b_r = (confusion_matrix.diag() / confusion_matrix.sum(0))[1]

def eval():
    net.eval()
    test_loss = 0
    correct = 0
    total = 0
    classnum = 9
    target_num = torch.zeros((1,classnum))
    predict_num = torch.zeros((1,classnum))
    acc_num = torch.zeros((1,classnum))
    for batch_idx, (inputs, targets) in enumerate(testloader):
        if use_cuda:
            inputs, targets = inputs.cuda(), targets.cuda()
        inputs, targets = Variable(inputs, volatile=True), Variable(targets)
        outputs = net(inputs)
        loss = criterion(outputs, targets)
        # loss is variable , if add it(+=loss) directly, there will be a bigger ang bigger graph.
        test_loss += loss.data[0]
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += predicted.eq(targets.data).cpu().sum()
        pre_mask = torch.zeros(outputs.size()).scatter_(1, predicted.cpu().view(-1, 1), 1.)
        predict_num += pre_mask.sum(0)
        tar_mask = torch.zeros(outputs.size()).scatter_(1, targets.data.cpu().view(-1, 1), 1.)
        target_num += tar_mask.sum(0)
        acc_mask = pre_mask*tar_mask
        acc_num += acc_mask.sum(0)
    recall = acc_num/target_num
    precision = acc_num/predict_num
    F1 = 2*recall*precision/(recall+precision)
    accuracy = acc_num.sum(1)/target_num.sum(1)
#精度调整
    recall = (recall.numpy()[0]*100).round(3)
    precision = (precision.numpy()[0]*100).round(3)
    F1 = (F1.numpy()[0]*100).round(3)
    accuracy = (accuracy.numpy()[0]*100).round(3)
# 打印格式方便复制
    print('recall'," ".join('%s' % id for id in recall))
    print('precision'," ".join('%s' % id for id in precision))
    print('F1'," ".join('%s' % id for id in F1))
    print('accuracy',accuracy)

from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report
 
# 加载数据集 从scikit-learn官网下载新闻数据集(共20个类别)
news = fetch_20newsgroups(subset='all')  # all表示下载训练集和测试集
 
# 进行数据分割 (划分训练集和测试集)
x_train, x_test, y_train, y_test = train_test_split(news.data, news.target, test_size=0.25)
 
# 对数据集进行特征抽取 (进行特征提取，将新闻文档转化成特征词重要性的数字矩阵)
tf = TfidfVectorizer()  # tf-idf表示特征词的重要性
# 以训练集数据统计特征词的重要性 (从训练集数据中提取特征词)
x_train = tf.fit_transform(x_train)
 
print(tf.get_feature_names())  # ["condensed", "condescend", ...]
 
x_test = tf.transform(x_test)  # 不需要重新fit()数据，直接按照训练集提取的特征词进行重要性统计。
 
# 进行朴素贝叶斯算法的预测
mlt = MultinomialNB(alpha=1.0)  # alpha表示拉普拉斯平滑系数，默认1
print(x_train.toarray())  # toarray() 将稀疏矩阵以稠密矩阵的形式显示。
'''
[[ 0.     0.          0.   ...,  0.04234873  0.   0. ]
 [ 0.     0.          0.   ...,  0.          0.   0. ]
 ...,
 [ 0.     0.03934786  0.   ...,  0.          0.   0. ]
'''
mlt.fit(x_train, y_train)  # 填充训练集数据
 
# 预测类别
y_predict = mlt.predict(x_test)
print("预测的文章类别为：", y_predict)  # [4 18 8 ..., 15 15 4]
 
# 准确率
print("准确率为：", mlt.score(x_test, y_test))  # 0.853565365025
 
print("每个类别的精确率和召回率：", classification_report(y_test, y_predict, target_names=news.target_names))
'''
                precision  recall  f1-score  support
    alt.atheism   0.86      0.66     0.75      207
  comp.graphics   0.85      0.75     0.80      238
 sport.baseball   0.96      0.94     0.95      253
 ...,
'''