功能选择类型错误：不可损坏类型：'努比·恩达雷'

Question

我有一个工作，我想使用最小冗余最大相关算法。代码如下。在

import numpy as np
import pandas as pd
from skfeature.function import information_theoretical_based

dataset=pd.read_csv("cancer.csv")
data=pd.DataFrame(dataset)
X= data.iloc[:,:1].values
y=data.iloc[:,1:].values

information_theoretical_based.MRMR.mrmr(X,y)

程序显示错误“TypeError:unhashable type:”努比·恩达雷'”：

TypeError Traceback (most recent call last) in () ----> 1 information_theoretical_based.MRMR.mrmr(X,y)

/usr/local/lib/python3.6/dist-packages/skfeature/function/information_theoretical_based/MRMR.py in mrmr(X, y, **kwargs) 33 F, J_CMI, MIfy = LCSI.lcsi(X, y, gamma=0, function_name='MRMR', n_selected_features=n_selected_features) 34 else: ---> 35 F, J_CMI, MIfy = LCSI.lcsi(X, y, gamma=0, function_name='MRMR') 36 return F, J_CMI, MIfy

/usr/local/lib/python3.6/dist-packages/skfeature/function/information_theoretical_based/LCSI.py in lcsi(X, y, **kwargs) 65 for i in range(n_features): 66 f = X[:, i] ---> 67 t1[i] = midd(f, y) 68 69 # make sure that j_cmi is positive at the very beginning

/usr/local/lib/python3.6/dist-packages/skfeature/utility/entropy_estimators.py in midd(x, y) 101 """ 102 --> 103 return -entropyd(list(zip(x, y)))+entropyd(x)+entropyd(y) 104 105

/usr/local/lib/python3.6/dist-packages/skfeature/utility/entropy_estimators.py in entropyd(sx, base) 93 """ 94 ---> 95 return entropyfromprobs(hist(sx), base=base) 96 97

/usr/local/lib/python3.6/dist-packages/skfeature/utility/entropy_estimators.py in hist(sx) 116 d = dict() 117 for s in sx: --> 118 d[s] = d.get(s, 0) + 1 119 return map(lambda z: float(z)/len(sx), d.values()) 120

TypeError: unhashable type: 'numpy.ndarray'

Answer 1

你的X比你的y小

也许改成：

X = data.iloc[:,1:].values

y = data.iloc[:,:1].values