Real-bogus scores for active anomaly detection

Data description for Semenikhin et al., 2024 The dataset consists of the following files: feature_snad4_r_100.dat contains light curve feature data for objects, where each object is represented by 54 feature values. These values are encoded as little-endian single-precision IEEE-754 floating-point numbers (32-bit floats). Feature names are listed in the plain text file feature_snad4_r_100.name, with one name per line.sid_snad4_r_100.dat contains ZTF DR object identifiers, encoded as little-endian 64-bit unsigned integers. exp_feature_snad4_r_100.dat contains the same features as feature_snad4_r_100.dat, but with an additional column representing the real-bogus classifier prediction. Each object in this file corresponds to 55 features: the original 54 features plus 1 additional feature. Feature names for this file are provided in exp_feature_snad4_r_100.name. The files sid_snad4_r_100.dat, feature_snad4_r_100.dat, and exp_feature_snad4_r_100.dat share the same object order. Below is a sample Python script for accessing the data using NumPy: import numpy as np # Load object IDsoid = np.memmap('sid_snad4_r_100.dat', mode='c', dtype=np.uint64) # Load features and reshapefeature = np.memmap('feature_snad4_r_100.dat', mode='c', dtype=np.float32).reshape(oid.shape[0], -1) # Print dataset informationprint(f'Number of objects: {len(oid)}')print(f'Features shape: {feature.shape}')Semenikhin等人2024年数据集说明 本数据集包含以下文件： 1. `feature_snad4_r_100.dat`：存储天体的光变曲线特征数据，每个天体由54个特征值表征。所有特征值采用小端序（little-endian）单精度IEEE-754浮点数（single-precision IEEE-754 floating-point numbers，即32位浮点数）编码。特征名称列表以纯文本形式存储于`feature_snad4_r_100.name`文件中，每行对应一个特征名称。 2. `sid_snad4_r_100.dat`：存储ZTF DR天体标识符，采用小端序（little-endian）64位无符号整数编码。 3. `exp_feature_snad4_r_100.dat`：与`feature_snad4_r_100.dat`包含完全相同的特征集合，但额外新增一列用于表征真伪甄别分类器（real-bogus classifier）预测结果的特征。该文件中每个天体对应55个特征：原始的54个特征外加1个新增特征。本文件的特征名称列表存储于`exp_feature_snad4_r_100.name`中。 上述`sid_snad4_r_100.dat`、`feature_snad4_r_100.dat`与`exp_feature_snad4_r_100.dat`三个文件的天体排序完全一致。 以下为使用NumPy读取该数据集的示例Python脚本： python import numpy as np # 加载天体标识符 oid = np.memmap('sid_snad4_r_100.dat', mode='c', dtype=np.uint64) # 加载特征数据并重塑数组形状 feature = np.memmap('feature_snad4_r_100.dat', mode='c', dtype=np.float32).reshape(oid.shape[0], -1) # 输出数据集相关信息 print(f"天体总数：{len(oid)}") print(f"特征数组形状：{feature.shape}")