ValueError：未知在sklearn中不支持.RFECV

Question

我試圖使用rfecv縮小與分類器真正相關的功能數量。這是我寫

import sklearn 
import pandas as p 
import numpy as np 
import scipy as sp 
import pylab as pl 
from sklearn import linear_model, cross_validation, metrics 
from sklearn.svm import SVC 
from sklearn.feature_selection import RFECV 
from sklearn.metrics import zero_one_loss 
from sklearn import preprocessing 
#from sklearn.feature_extraction.text import CountVectorizer 
#from sklearn.feature_selection import SelectKBest, chi2 

modelType = "notext" 

# ---------------------------------------------------------- 
# Prepare the Data 
# ---------------------------------------------------------- 
training_data = np.array(p.read_table('F:/NYC/NYU/SM/3/SNLP/Project/Data/train.tsv')) 
print ("Read Data\n") 

# get the target variable and set it as Y so we can predict it 
Y = training_data[:,-1] 

print(Y) 

# not all data is numerical, so we'll have to convert those fields 
# fix "is_news": 
training_data[:,17] = [0 if x == "?" else 1 for x in training_data[:,17]] 

# fix -1 entries in hasDomainLink 
training_data[:,14] = [0 if x =="-1" else x for x in training_data[:,10]] 

# fix "news_front_page": 
training_data[:,20] = [999 if x == "?" else x for x in training_data[:,20]] 
training_data[:,20] = [1 if x == "1" else x for x in training_data[:,20]] 
training_data[:,20] = [0 if x == "0" else x for x in training_data[:,20]] 

# fix "alchemy category": 
training_data[:,3] = [0 if x=="arts_entertainment" else x for x in training_data[:,3]] 
training_data[:,3] = [1 if x=="business" else x for x in training_data[:,3]] 
training_data[:,3] = [2 if x=="computer_internet" else x for x in training_data[:,3]] 
training_data[:,3] = [3 if x=="culture_politics" else x for x in training_data[:,3]] 
training_data[:,3] = [4 if x=="gaming" else x for x in training_data[:,3]] 
training_data[:,3] = [5 if x=="health" else x for x in training_data[:,3]] 
training_data[:,3] = [6 if x=="law_crime" else x for x in training_data[:,3]] 
training_data[:,3] = [7 if x=="recreation" else x for x in training_data[:,3]] 
training_data[:,3] = [8 if x=="religion" else x for x in training_data[:,3]] 
training_data[:,3] = [9 if x=="science_technology" else x for x in training_data[:,3]] 
training_data[:,3] = [10 if x=="sports" else x for x in training_data[:,3]] 
training_data[:,3] = [11 if x=="unknown" else x for x in training_data[:,3]] 
training_data[:,3] = [12 if x=="weather" else x for x in training_data[:,3]] 
training_data[:,3] = [999 if x=="?" else x for x in training_data[:,3]] 

print ("Corrected outliers data\n") 

# ---------------------------------------------------------- 
# Models 
# ---------------------------------------------------------- 
if modelType == "notext": 
    print ("no text model\n") 
    #ignore features which are useless 
    X = training_data[:,list([3, 5, 6, 7, 8, 9, 10, 14, 15, 16, 17, 19, 20, 22, 25])] 
    scaler = preprocessing.StandardScaler() 
    print("initialized scaler \n") 
    scaler.fit(X,Y) 
    print("fitted train data and labels\n") 
    X = scaler.transform(X) 
    print("Transformed train data\n") 
    svc = SVC(kernel = "linear") 
    print("Initialized SVM\n") 
    rfecv = RFECV(estimator = svc, cv = 5, loss_func = zero_one_loss, verbose = 1) 
    print("Initialized RFECV\n") 
    rfecv.fit(X,Y) 
    print("Fitted train data and label\n") 
    rfecv.support_ 
    print ("Optimal Number of features : %d" % rfecv.n_features_) 
    savetxt('rfecv.csv', rfecv.ranking_, delimiter=',', fmt='%f') 

在「（X，Y）rfecv.fit」的調用的代碼我的代碼從metrices.py文件拋出一個錯誤「ValueError異常：未知，不支持」

在sklearn.metrics.metrics錯誤豆芽：

# No metrics support "multiclass-multioutput" format 
    if (y_type not in ["binary", "multiclass", "multilabel-indicator", "multilabel-sequences"]): 
     raise ValueError("{0} is not supported".format(y_type)) 

這是一個分類問題，目標值只有0或1 該數據集可以在Kaggle Competition Data

可以找到

如果任何人都可以指出我要出錯的地方，我將不勝感激。

Answer 1

RFECV檢查目標/火車數據是類型binary，multiclass，multilabel-indicator或multilabel-sequences之一：

• '二進制'：y包含< = 2的離散值和是1D或列 向量。
• '多類'：y包含多於兩個離散值，不是 序列序列，並且是1d或列向量。
• 「mutliclass-多輸出」：y是包含多個 比兩個離散值的2D陣列，是不是序列的序列，並且兩個 尺寸大小> 1
• 「多標記指示符」的：y是標籤指示符矩陣，具有至少兩列的兩維數組以及至多2個唯一值的數組。

而你Y是unknown，即

• 「未知」：y是陣列狀，但沒有上述，諸如3D陣列，或非序列對象的數組。

的原因是你的目標數據串（形式"0"和"1"）並裝有read_table爲對象：

>>> training_data[:, -1].dtype 
dtype('O') 
>>> type_of_target(training_data[:, -1]) 
'unknown' 

爲了解決這個問題，你可以轉換爲int：

>>> Y = training_data[:, -1].astype(int) 
>>> type_of_target(Y) 
'binary'