特征选择算法之ReliefF算法python实现

#特征选择算法之ReliefF算法python实现| 来源: 网络整理| 查看: 265

ReliefF算法python实现一、ReliefF算法简介（一）原理（二）伪算法二、ReliefF算法python实现（一）代码（二）文件：西瓜数据集

一、ReliefF算法简介

ReliefF算法是Relief算法的拓展，其适用于处理多分类问题。

（一）原理

假设数据集D中的样本分属于N个类别，对于样本xi，若它属于第n类，则ReliefF算法首先在同类即第n类的样本中寻找xi的k个最近邻样本作为猜中近邻；然后在第n类之外的每个类中均找到xi的k个最近邻样本作为猜错近邻，其相关统计量对应于属性j的分量则为：

（二）伪算法

待补充

二、ReliefF算法python实现（一）代码

代码片

// An highlighted block # _*_ coding:utf8 _*_ """ # 说明：特征选择方法一：过滤式特征选择（ReliefF算法） # 思想：先用特征选择过程对初始特征进行"过滤"，然后再用过滤后的特征训练模型 # 时间：2019-1-16 # 问题： """ import pandas as pd import numpy as np import numpy.linalg as la import random # 异常类 class ReliefError: pass class Relief: def __init__(self, data_df, sample_rate, t, k): """ # :param data_df: 数据框（字段为特征，行为样本） :param sample_rate: 抽样比例 :param t: 统计量分量阈值 :param k: k近邻的个数 """ self.__data = data_df self.__feature = data_df.columns self.__sample_num = int(round(len(data_df) * sample_rate)) self.__t = t self.__k = k # 数据处理（将离散型数据处理成连续型数据，比如字符到数值） def get_data(self): new_data = pd.DataFrame() for one in self.__feature[:-1]: col = self.__data[one] if (str(list(col)[0]).split(".")[0]).isdigit() or str(list(col)[0]).isdigit() or (str(list(col)[0]).split('-')[-1]).split(".")[-1].isdigit(): new_data[one] = self.__data[one] # print '%s 是数值型' % one else: # print '%s 是离散型' % one keys = list(set(list(col))) values = list(xrange(len(keys))) new = dict(zip(keys, values)) new_data[one] = self.__data[one].map(new) new_data[self.__feature[-1]] = self.__data[self.__feature[-1]] return new_data # 返回一个样本的k个猜中近邻和其他类的k个猜错近邻 def get_neighbors(self, row): df = self.get_data() row_type = row[df.columns[-1]] right_df = df[df[df.columns[-1]] == row_type].drop(columns=[df.columns[-1]]) aim = row.drop(df.columns[-1]) f = lambda x: eulidSim(np.mat(x), np.mat(aim)) right_sim = right_df.apply(f, axis=1) right_sim_two = right_sim.drop(right_sim.idxmin()) right = dict() right[row_type] = list(right_sim_two.sort_values().index[0:self.__k]) # print list(right_sim_two.sort_values().index[0:self.__k]) types = list(set(df[df.columns[-1]]) - set([row_type])) wrong = dict() for one in types: wrong_df = df[df[df.columns[-1]] == one].drop(columns=[df.columns[-1]]) wrong_sim = wrong_df.apply(f, axis=1) wrong[one] = list(wrong_sim.sort_values().index[0:self.__k]) print right, wrong return right, wrong # 计算特征权重 def get_weight(self, feature, index, NearHit, NearMiss): # data = self.__data.drop(self.__feature[-1], axis=1) data = self.__data row = data.iloc[index] right = 0 for one in NearHit.values()[0]: nearhit = data.iloc[one] if (str(row[feature]).split(".")[0]).isdigit() or str(row[feature]).isdigit() or (str(row[feature]).split('-')[-1]).split(".")[-1].isdigit(): max_feature = data[feature].max() min_feature = data[feature].min() right_one = pow(round(abs(row[feature] - nearhit[feature]) / (max_feature - min_feature), 2), 2) else: right_one = 0 if row[feature] == nearhit[feature] else 1 right += right_one right_w = round(right / self.__k, 2) wrong_w = 0 # 样本row所在的种类占样本集的比例 p_row = round(float(list(data[data.columns[-1]]).count(row[data.columns[-1]])) / len(data), 2) for one in NearMiss.keys(): # 种类one在样本集中所占的比例 p_one = round(float(list(data[data.columns[-1]]).count(one)) / len(data), 2) wrong_one = 0 for i in NearMiss[one]: nearmiss = data.iloc[i] if (str(row[feature]).split(".")[0]).isdigit() or str(row[feature]).isdigit() or (str(row[feature]).split('-')[-1]).split(".")[-1].isdigit(): max_feature = data[feature].max() min_feature = data[feature].min() wrong_one_one = pow(round(abs(row[feature] - nearmiss[feature]) / (max_feature - min_feature), 2), 2) else: wrong_one_one = 0 if row[feature] == nearmiss[feature] else 1 wrong_one += wrong_one_one wrong = round(p_one / (1 - p_row) * wrong_one / self.__k, 2) wrong_w += wrong w = wrong_w - right_w return w # 过滤式特征选择 def reliefF(self): sample = self.get_data() # print sample m, n = np.shape(self.__data) # m为行数，n为列数 score = [] sample_index = random.sample(range(0, m), self.__sample_num) print '采样样本索引为 %s ' % sample_index num = 1 for i in sample_index: # 采样次数 one_score = dict() row = sample.iloc[i] NearHit, NearMiss = self.get_neighbors(row) print '第 %s 次采样，样本index为 %s，其NearHit k近邻行索引为 %s ，NearMiss k近邻行索引为 %s' % (num, i, NearHit, NearMiss) for f in self.__feature[0:-1]: w = self.get_weight(f, i, NearHit, NearMiss) one_score[f] = w print '特征 %s 的权重为 %s.' % (f, w) score.append(one_score) num += 1 f_w = pd.DataFrame(score) print '采样各样本特征权重如下：' print f_w print '平均特征权重如下：' print f_w.mean() return f_w.mean() # 返回最终选取的特征 def get_final(self): f_w = pd.DataFrame(self.reliefF(), columns=['weight']) final_feature_t = f_w[f_w['weight'] > self.__t] print final_feature_t # final_feature_k = f_w.sort_values('weight').head(self.__k) # print final_feature_k return final_feature_t # 几种距离求解 def eulidSim(vecA, vecB): return la.norm(vecA - vecB) def cosSim(vecA, vecB): """ :param vecA: 行向量 :param vecB: 行向量 :return: 返回余弦相似度（范围在0-1之间） """ num = float(vecA * vecB.T) denom = la.norm(vecA) * la.norm(vecB) cosSim = 0.5 + 0.5 * (num / denom) return cosSim def pearsSim(vecA, vecB): if len(vecA)

【本文地址】

公司简介

联系我们