python - FCBF Python 特征选择技术
问题描述
我想使用来自 github https://github.com/shiralkarprashant/FCBF 的 FCBF 技术我面临的问题是我正在使用 Python 3 广告该模块是为 python 2 用户实现的。我收到以下错误，描述未定义名称“xrange”，因为我在 python3 上工作，我认为只需通过 xrange 更改范围即可解决问题
from FCBF_module import FCBF, FCBFK, FCBFiP, get_i
from sklearn.datasets import load_digits
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
import time
from sklearn.grid_search import GridSearchCV
classifiers = [('DecisionTree', DecisionTreeClassifier(), {'max_depth' : [5, 10, 15]}),
('LogisticRegression', LogisticRegression(), {'C' : [0.1, 1, 10]})]
n_features = dataCAD.shape[1]
npieces = get_i(n_features)
模块代码仅包含一个 xrange 出现，我试图按范围更改它，但它不能解决问题：
# -*- coding: utf-8 -*-
import numpy as np
def count_vals(x):
vals = np.unique(x)
occ = np.zeros(shape = vals.shape)
for i in range(vals.size):
occ[i] = np.sum(x == vals[i])
return occ
def entropy(x):
n = float(x.shape[0])
ocurrence = count_vals(x)
px = ocurrence / n
return -1* np.sum(px*np.log2(px))
def symmetricalUncertain(x,y):
n = float(y.shape[0])
vals = np.unique(y)
# Computing Entropy for the feature x.
Hx = entropy(x)
# Computing Entropy for the feature y.
Hy = entropy(y)
#Computing Joint entropy between x and y.
partial = np.zeros(shape = (vals.shape[0]))
for i in range(vals.shape[0]):
partial[i] = entropy(x[y == vals[i]])
partial[np.isnan(partial)==1] = 0
py = count_vals(y).astype(dtype = 'float64') / n
Hxy = np.sum(py[py > 0]*partial)
IG = Hx-Hxy
return 2*IG/(Hx+Hy)
def suGroup(x, n):
m = x.shape[0]
x = np.reshape(x, (n,m/n)).T
m = x.shape[1]
SU_matrix = np.zeros(shape = (m,m))
for j in range(m-1):
x2 = x[:,j+1::]
y = x[:,j]
temp = np.apply_along_axis(symmetricalUncertain, 0, x2, y)
for k in range(temp.shape[0]):
SU_matrix[j,j+1::] = temp
SU_matrix[j+1::,j] = temp
return 1/float(m-1)*np.sum(SU_matrix, axis = 1)
def isprime(a):
return all(a % i for i in xrange(2, a))
"""
get
"""
def get_i(a):
if isprime(a):
a -= 1
return filter(lambda x: a % x == 0, range(2,a))
"""
FCBF - Fast Correlation Based Filter
L. Yu and H. Liu. Feature Selection for High‐Dimensional Data: A Fast Correlation‐Based Filter Solution.
In Proceedings of The Twentieth International Conference on Machine Leaning (ICML‐03), 856‐863.
Washington, D.C., August 21‐24, 2003.
"""
class FCBF:
idx_sel = []
def __init__(self, th = 0.01):
'''
Parameters
---------------
th = The initial threshold
'''
self.th = th
def fit(self, x, y):
'''
This function executes FCBF algorithm and saves indexes
of selected features in self.idx_sel
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
self.idx_sel = []
"""
First Stage: Computing the SU for each feature with the response.
"""
SU_vec = np.apply_along_axis(symmetricalUncertain, 0, x, y)
SU_list = SU_vec[SU_vec > self.th]
SU_list[::-1].sort()
m = x[:,SU_vec > self.th].shape
x_sorted = np.zeros(shape = m)
for i in range(m[1]):
ind = np.argmax(SU_vec)
SU_vec[ind] = 0
x_sorted[:,i] = x[:,ind].copy()
self.idx_sel.append(ind)
"""
Second Stage: Identify relationships between feature to remove redundancy.
"""
j = 0
while True:
"""
Stopping Criteria:The search finishes
"""
if j >= x_sorted.shape[1]: break
y = x_sorted[:,j].copy()
x_list = x_sorted[:,j+1:].copy()
if x_list.shape[1] == 0: break
SU_list_2 = SU_list[j+1:]
SU_x = np.apply_along_axis(symmetricalUncertain, 0,
x_list, y)
comp_SU = SU_x >= SU_list_2
to_remove = np.where(comp_SU)[0] + j + 1
if to_remove.size > 0:
x_sorted = np.delete(x_sorted, to_remove, axis = 1)
SU_list = np.delete(SU_list, to_remove, axis = 0)
to_remove.sort()
for r in reversed(to_remove):
self.idx_sel.remove(self.idx_sel[r])
j = j + 1
def fit_transform(self, x, y):
'''
This function fits the feature selection
algorithm and returns the resulting subset.
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
self.fit(x, y)
return x[:,self.idx_sel]
def transform(self, x):
'''
This function applies the selection
to the vector x.
Parameters
---------------
x = dataset [NxM]
'''
return x[:, self.idx_sel]
"""
FCBF# - Fast Correlation Based Filter
B. Senliol, G. Gulgezen, et al. Fast Correlation Based Filter (FCBF) with a Different Search Strategy.
In Computer and Information Sciences (ISCIS ‘08) 23rd International Symposium on, pages 1‐4.
Istanbul, October 27‐29, 2008.
"""
class FCBFK(FCBF):
idx_sel = []
def __init__(self, k = 10):
'''
Parameters
---------------
k = Number of features to include in the
subset.
'''
self.k = k
def fit(self, x, y):
'''
This function executes FCBFK algorithm and saves indexes
of selected features in self.idx_sel
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
self.idx_sel = []
"""
First Stage: Computing the SU for each feature with the response.
"""
SU_vec = np.apply_along_axis(symmetricalUncertain, 0, x, y)
SU_list = SU_vec[SU_vec > 0]
SU_list[::-1].sort()
m = x[:,SU_vec > 0].shape
x_sorted = np.zeros(shape = m)
for i in range(m[1]):
ind = np.argmax(SU_vec)
SU_vec[ind] = 0
x_sorted[:,i] = x[:,ind].copy()
self.idx_sel.append(ind)
"""
Second Stage: Identify relationships between features to remove redundancy with stopping
criteria (features in x_best == k).
"""
j = 0
while True:
y = x_sorted[:,j].copy()
SU_list_2 = SU_list[j+1:]
x_list = x_sorted[:,j+1:].copy()
"""
Stopping Criteria:The search finishes
"""
if x_list.shape[1] == 0: break
SU_x = np.apply_along_axis(symmetricalUncertain, 0,
x_list, y)
comp_SU = SU_x >= SU_list_2
to_remove = np.where(comp_SU)[0] + j + 1
if to_remove.size > 0 and x.shape[1] > self.k:
for i in reversed(to_remove):
x_sorted = np.delete(x_sorted, i, axis = 1)
SU_list = np.delete(SU_list, i, axis = 0)
self.idx_sel.remove(self.idx_sel[i])
if x_sorted.shape[1] == self.k: break
if x_list.shape[1] == 1 or x_sorted.shape[1] == self.k:
break
j = j + 1
if len(self.idx_sel) > self.k:
self.idx_sel = self.idx_sel[:self.k]
"""
FCBFiP - Fast Correlation Based Filter in Pieces
"""
class FCBFiP(FCBF):
idx_sel = []
def __init__(self, k = 10, npieces = 2):
'''
Parameters
---------------
k = Number of features to include in the
subset.
npieces = Number of pieces to divide the
feature space.
'''
self.k = k
self.npieces = npieces
def fit(self, x, y):
'''
This function executes FCBF algorithm and saves indexes
of selected features in self.idx_sel
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
"""
First Stage: Computing the SU for each feature with the response. We sort the
features. When we have a prime number of features we remove the last one from the
sorted features list.
"""
m = x.shape
nfeaturesPieces = int(m[1] / float(self.npieces))
SU_vec = np.apply_along_axis(symmetricalUncertain, 0, x, y)
x_sorted = np.zeros(shape = m, dtype = 'float64')
idx_sorted = np.zeros(shape = m[1], dtype = 'int64')
for i in range(m[1]):
ind = np.argmax(SU_vec)
SU_vec[ind] = -1
idx_sorted[i]= ind
x_sorted[:,i] = x[:,ind].copy()
if isprime(m[1]):
x_sorted = np.delete(x_sorted, m[1]-1, axis = 1 )
ind_prime = idx_sorted[m[1]-1]
idx_sorted = np.delete(idx_sorted, m[1]-1)
#m = x_sorted.shape
"""
Second Stage: Identify relationships between features into its vecinity
to remove redundancy with stopping criteria (features in x_best == k).
"""
x_2d = np.reshape(x_sorted.T, (self.npieces, nfeaturesPieces*m[0])).T
SU_x = np.apply_along_axis(suGroup, 0, x_2d, nfeaturesPieces)
SU_x = np.reshape(SU_x.T, (self.npieces*nfeaturesPieces,))
idx_sorted2 = np.zeros(shape = idx_sorted.shape, dtype = 'int64')
SU_x[np.isnan(SU_x)] = 1
for i in range(idx_sorted.shape[0]):
ind = np.argmin(SU_x)
idx_sorted2[i] = idx_sorted[ind]
SU_x[ind] = 10
"""
Scoring step
"""
self.scores = np.zeros(shape = m[1], dtype = 'int64')
for i in range(m[1]):
if i in idx_sorted:
self.scores[i] = np.argwhere(i == idx_sorted) + np.argwhere(i == idx_sorted2)
if isprime(m[1]):
self.scores[ind_prime] = 2*m[1]
self.set_k(self.k)
def set_k(self, k):
self.k = k
scores_temp = -1*self.scores
self.idx_sel = np.zeros(shape = self.k, dtype = 'int64')
for i in range(self.k):
ind = np.argmax(scores_temp)
scores_temp[ind] = -100000000
self.idx_sel[i] = ind
解决方案
尝试使用 python 的 2to3 包来自动转换文件。为我工作！
推荐阅读
- java - JVM 堆问题
- javascript - JSON文件中的搜索和返回算法
- python - 如何在短时间内制作矩阵（9 * 9）
- flutter - Flutter：通过 Navigator.Push 传递多个数据，然后将数据弹回
- css - CSS 网格：无效的属性值
- javascript - 使用带有故事书的 svg-spritemap-webpack-plugin
- android - 如何使我的代码适用于所有屏幕尺寸？
- google-apps-script - 使用谷歌应用脚本构建实时仪表板
- single-sign-on - 我无法为 Dropbox Business 设置自定义 SSO
- r - 将闪亮的数据框保存到 Postgresql 数据库