我正在尝试获取使用 scikit-learn 的 OneVsRestClassifier 构建的分类器的指标,以解决多标签分类问题。但是,我无法让指标库正常工作,因为我尝试比较真实标签和预测标签的二进制指标大小不同。下面是代码,大部分取自使用 scikit-learn 分类为多个类别
import numpy as np
import collections
import csv
import os
import sys
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.svm import LinearSVC
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.multiclass import OneVsRestClassifier
from sklearn.preprocessing import MultiLabelBinarizer
import sklearn.metrics as metrics
np.set_printoptions(threshold=sys.maxsize)
csv_read_args = ({'mode': 'rb'} if sys.version_info[0] < 3 else
{'mode': 'rt', 'newline': '', 'encoding': 'latin1'})
with open(os.path.abspath('somefilepath'), **csv_read_args) as myfile:
reader = csv.reader(myfile)
next(reader)
a, b = [], []
# feed …Run Code Online (Sandbox Code Playgroud)