西瓜书《机器学习》课后答案——chapter11_11.1 Relief特征选择算法

试编程实现Relief算法，并考察其在西瓜数据集3.0上的运行结果。

# -*- coding: gbk -*-"""Author: VictoriaDate: 201.11.14 16:00"""import numpy as npimport operatorimport xlrddef diff(x, y, discrete=True):    """    Input:        x: value        y: value    """    if discrete:        if x==y:            return 0        else:            return 1    else:        return abs(x-y)def nearest(X, y, x, x_label):    """    Compute near-hit and near-miss in binary classification problem.    Input:        X: list, instances        y: list, labels        x: instance        x_label: label for instance x    Return:        near_hit: list, instance        near_miss: list, instance    """    near_hit_dist = float("inf")    near_miss_dist = float("inf")    for i in range(len(X)):        dist = np.sum((np.array(x) - np.array(X[i]))**2)        if y[i]==x_label:                      if dist < near_hit_dist and dist!=0:                near_hit = X[i]                near_hit_dist = dist        else:            if dist < near_miss_dist:                near_miss = X[i]                near_miss_dist = dist    return near_hit, near_missdef relief(X, y, k, discrete):    """    Input:        X: list        y: list        k: selecting features number        discrete: list, whether the corresponding feature is discrete or not    """    N = len(X)    d = len(X[0])    delta = []    for i in range(d):        delta_i = 0        for j in range(N):            near_hit, near_miss = nearest(X, y, X[j], y[j])                        delta_i += -diff(X[j][i], near_hit[i], discrete[i])**2 + diff(X[j][i], near_miss[i], discrete[i])**2        delta.append(delta_i)    print delta    features_and_delta = zip(range(d), delta)    features_and_delta = sorted(features_and_delta, key=operator.itemgetter(1), reverse=True)    print features_and_delta    select_features_index = [features_and_delta[i][0] for i in range(k)]    return select_features_indexif __name__=="__main__":    workbook = xlrd.open_workbook("../../数据/3.0.xlsx")    sheet = workbook.sheet_by_name("Sheet1")    X = []    y = []    for i in range(17):        X.append(sheet.col_values(i)[:-1])    y = sheet.row_values(8)    relief(X, y, 1, [1, 1, 1, 1, 1, 1, 0, 0])

特征[色泽，根蒂，敲声，纹理，脐部，触感，密度，含糖量]对应的统计量为：

[-4, 6, -1, 8, 2, -3, -0.40418499999999996, 0.26350200000000007]

可以看出Relief算法认为最好的特征是纹理，其次是根蒂。