Question

%pylab inline

import numpy as np
import pandas as pd

import random
import time
import scipy
import sklearn.feature_extraction
import pickle

from sklearn.cross_validation import StratifiedKFold
from sklearn.svm import LinearSVC
from sklearn.externals import joblib
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics import confusion_matrix
bedsizes = {'None':0,
       'Rest All':1}
invbedsizes = {v: k for k, v in bedsizes.items()} 

model = joblib.load('model_bed_size.pkl')
vocab = pickle.load(open('dictionary', 'rb'))
var=pd.read_csv('Train_variables.csv')
dtest = pd.read_csv('/home/ubuntu/test_null_new.csv', usecols=   ("Bed_size","title","short_description","long_description","primary_shelf.all_paths_str","attributes.all_shelves.0","attributes.all_shelves.1","attributes.all_shelves.2","attributes.all_shelves.3","attributes.all_shelves.4","attributes.type.0","attributes.type.1","attributes.type.2","item_id","last_updated_at"),encoding='ISO-8859-1')
lentest = len(dtest)
vocab=vocab["Vocabulary"].to_dict()

Xall = []
i=1
for col in var['Variable']:
    vectorizer = CountVectorizer(min_df=1, vocabulary=(vocab[i]),          token_pattern = '\\b\\w+\\b')
    Xall.append(vectorizer.transform(dtest[col].astype(str)))
    j=i
    i=j+1
    print (col, 'Done', shape(Xall[-1]))
Xspall = scipy.sparse.hstack(Xall)
X_test_final = scipy.sparse.csr_matrix(Xspall)
print (shape(X_test_final))   
ypred = model.decision_function(X_test_final)
ypredc = model.classes_[np.argmax(ypred, axis = 0)]   

ypredcon = (np.max(ypred, axis = 1) + 2.) / 8. 
ypredcon[ypredcon < 0.] = 0 .
ypredcon[ypredcon > 1.] = 1.

dfinal = pd.DataFrame()
dfinal['item_id '] = dtest['item_id']
dfinal['Predictions'] = ypredc
dfinal['Predictions'].replace(invbedsizes, inplace = True)
dfinal['confidence_score'] = ypredcon

上面的代码给出了索引错误，指出索引14328超出了轴0和大小2的范围。错误就在这条线上 ypredc = model.classes_ [np.argmax（ypred，axis = 0）]
任何人都可以帮我吗？

Answer 1

在不了解代码中的变量的情况下，错误表明在

 ypred = model.decision_function(X_test_final)
 ypredc = model.classes_[np.argmax(ypred, axis = 0)]   

 error: index 14328 is out of bounds for axis 0 and size 2

model.classes_是一个或多个维度，第一个是大小2，换句话说是2 rows/classes，可能还有很多列。

ypred可能非常大，np.argmax(ypred...)是其最大值（沿轴0）的索引，即14328。

Maye正确使用model.classes_[:, np.argmax...]。

您需要查看ypred, and model.classes_`的形状，以及此区域中可能的其他变量。

索引错误索引14238超出轴0的大小为2的范围

1 个答案: