ADASYN自适应综合过采样python实现

ADASYN（Adaptive Synthetic Sampling）是一种针对不平衡数据集的过采样方法，它可以根据不同类别之间的分布差异性来生成合成样本。相比于传统的过采样方法，ADASYN可以更好地保留原始数据的特征信息，从而提高分类器的性能。

以下是ADASYN自适应综合过采样的Python实现：

from collections import Counter
import numpy as np
from sklearn.neighbors import NearestNeighbors

def ADASYN(X, y, k=5, ratio=0.5):
    """
    ADASYN自适应综合过采样
    :param X: 特征矩阵
    :param y: 标签矩阵
    :param k: 邻居数，默认为5
    :param ratio: 合成样本比例，默认为0.5
    :return: 合成后的特征矩阵和标签矩阵
    """
    # 统计每个类别的样本数
    counter = Counter(y)
    # 计算少数类样本数目
    minority_num = min(counter.values())
    # 计算多数类样本数目
    majority_num = max(counter.values())
    # 计算需要合成的新样本数目
    synthetic_num = int((minority_num * ratio) / (1 - ratio))
    # 初始化合成后的特征矩阵和标签矩阵
    synthetic_X = np.zeros((synthetic_num, X.shape[1]))
    synthetic_y = np.zeros(synthetic_num)
    # 计算每个少数类样本需要合成的新样本数目
    for i, minority_class in enumerate(counter.keys()):
        # 获取少数类样本的索引
        minority_indices = np.where(y == minority_class)[0]
        # 计算每个少数类样本需要合成的新样本数目
        if i == 0:
            synthetic_minority_num = synthetic_num
        else:
            synthetic_minority_num = int(synthetic_num * (counter[minority_class] / minority_num))
        # 使用K近邻算法生成新样本
        knn = NearestNeighbors(n_neighbors=k).fit(X[minority_indices])
        for j in range(synthetic_minority_num):
            # 随机选择一个少数类样本
            index = np.random.randint(0, minority_num)
            # 找到该样本的k个近邻
            _, neighbors = knn.kneighbors(X[minority_indices[index]].reshape(1, -1))
            # 随机选择一个近邻
            nn_index = np.random.randint(0, k)
            # 计算插值权重
            weight = np.random.rand()
            # 生成新样本
            synthetic_X[j] = X[minority_indices[index]] + weight * (X[minority_indices[neighbors[0][nn_index]]] - X[minority_indices[index]])
            synthetic_y[j] = minority_class
    # 合并原始样本和新样本
    X_resampled = np.vstack((X, synthetic_X))
    y_resampled = np.hstack((y, synthetic_y))
    return X_resampled, y_resampled