将scikit学习特征表示转换为LibSVM格式

from sklearn.datasets import load_iris
from sklearn.feature_extraction import DictVectorizer
from sklearn.preprocessing import LabelEncoder

data = load_iris()
features = data.data
target = data.target

# 将特征表示转换为字典格式
feature_dicts = [dict(enumerate(sample)) for sample in features]

vectorizer = DictVectorizer(sparse=False)
sparse_features = vectorizer.fit_transform(feature_dicts)

label_encoder = LabelEncoder()
encoded_target = label_encoder.fit_transform(target)

with open('data.libsvm', 'w') as f:
    for i in range(len(encoded_target)):
        line = str(encoded_target[i]) + ' '
        line += ' '.join([f'{index+1}:{value}' for index, value in enumerate(sparse_features[i])])
        f.write(line + '\n')