20
Май
2017

Ошибка многоклассовой классификация на python (xgboost)?

Моя первая многоклассовая классификация. У меня есть значения Xtrn и Ytrn. Ytrn имеет пять возможных исходов [0,1,2,3,4]. Но при запуске выдает ошибку

"multiclass format is not supported".

Это пример данных:

 Xtrn                                                         Ytrn
-1.35173485 1.50224188  2.04951167  0.43759658  0.24381777      2
2.81047260  1.31259056  1.39265240  0.16384002  0.65438366      3
2.32878809  -1.92845940 -2.06453246 0.73132270  0.11771229      2
-0.12810555 -2.07268765 -2.40760215 0.97855042  0.11144164      1
1.88682063  0.75792329  -0.09754671 0.46571931  0.62111648      2
-1.09361266 1.74758304  2.49960891  0.36679883  0.88895562      2
0.71760095  -1.30711698 -2.15681966 0.33700593  0.07171119      2
4.60060308  -1.60544855 -1.88996123 0.94500124  0.63776116      4
-0.84223064 2.78233537  3.07299711  0.31470071  0.34424704      1
-0.71236435 0.53140549  0.46677096  0.12320728  0.58829090      2
-0.35333909 1.12463059  1.70104349  0.89084673  0.16585229      2
3.04322100  -1.36878116 -2.31056167 0.81178387  0.04095645      1
-1.04088918 -1.97497570 -1.93285343 0.54101882  0.02528487      1
-0.41624939 0.54592833  0.95458283  0.40004902  0.55062705      2
-1.77706795 0.29061278  0.68186697  0.17430716  0.75095729      0

Это код:

#import data
import pandas as pd
import numpy as np
from sklearn.cross_validation import train_test_split
import xgboost as xgb
from sklearn import metrics, cross_validation, grid_search, preprocessing
Xtrn = pd.read_csv('x_train_secret.csv', header=None, delimiter=';', na_values='?')
Ytrn = pd.read_csv('y_train_secret.csv', header=None)
Test = pd.read_csv('x_test_secret.csv', header=None, delimiter=';', na_values='?')

#Number of unique values Ytrn
n_classes_ = len(np.unique(Ytrn))

#learning model
X_train, X_test, y_train, y_test = train_test_split(Xtrn, Ytrn, test_size=0.30, random_state=42)

xgb_model = xgb.XGBClassifier(objective='multi:softmax')

xgb_params = [{'num_class': n_classes_}]
xgb_params  = [
    {    
    "n_estimators": range(50, 501, 50),
    }
]
#cv
cv = cross_validation.StratifiedShuffleSplit(y_train, n_iter=5, test_size=0.3, random_state=42)

xgb_grid = grid_search.GridSearchCV(xgb_model, xgb_params, scoring='roc_auc', cv=cv, n_jobs=-1, verbose=3)
xgb_grid.fit(X_train, y_train)

Ошибка:

Fitting 5 folds for each of 10 candidates, totalling 50 fits
[CV] n_estimators=50 .................................................
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-233-77d3e8d4b8c3> in <module>()
     10 
     11 xgb_grid = grid_search.GridSearchCV(xgb_model, xgb_params, scoring='roc_auc', cv=cv, n_jobs=-1, verbose=3)
---> 12 xgb_grid.fit(X_train, y_train)

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/grid_search.pyc in fit(self, X, y)
    827 
    828         """
--> 829         return self._fit(X, y, ParameterGrid(self.param_grid))
    830 
    831 

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/grid_search.pyc in _fit(self, X, y, parameter_iterable)
    571                                     self.fit_params, return_parameters=True,
    572                                     error_score=self.error_score)
--> 573                 for parameters in parameter_iterable
    574                 for train, test in cv)
    575 

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
    756             # was dispatched. In particular this covers the edge
    757             # case of Parallel used with an exhausted iterator.
--> 758             while self.dispatch_one_batch(iterator):
    759                 self._iterating = True
    760             else:

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
    606                 return False
    607             else:
--> 608                 self._dispatch(tasks)
    609                 return True
    610 

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
    569         dispatch_timestamp = time.time()
    570         cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571         job = self._backend.apply_async(batch, callback=cb)
    572         self._jobs.append(job)
    573 

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in apply_async(self, func, callback)
    107     def apply_async(self, func, callback=None):
    108         """Schedule a func to be run"""
--> 109         result = ImmediateResult(func)
    110         if callback:
    111             callback(result)

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in __init__(self, batch)
    324         # Don't delay the application, to avoid keeping the input
    325         # arguments in memory
--> 326         self.results = batch()
    327 
    328     def get(self):

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/cross_validation.pyc in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, error_score)
   1682 
   1683     else:
-> 1684         test_score = _score(estimator, X_test, y_test, scorer)
   1685         if return_train_score:
   1686             train_score = _score(estimator, X_train, y_train, scorer)

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/cross_validation.pyc in _score(estimator, X_test, y_test, scorer)
   1739         score = scorer(estimator, X_test)
   1740     else:
-> 1741         score = scorer(estimator, X_test, y_test)
   1742     if hasattr(score, 'item'):
   1743         try:

/home/rudolf/anaconda2/lib/python2.7/site-packages/sklearn/metrics/scorer.pyc in __call__(self, clf, X, y, sample_weight)
    169         y_type = type_of_target(y)
    170         if y_type not in ("binary", "multilabel-indicator"):
--> 171             raise ValueError("{0} format is not supported".format(y_type))
    172 
    173         if is_regressor(clf):

ValueError: multiclass format is not supported

Источник: https://ru.stackoverflow.com/questions/668484/%D0%9E%D1%88%D0%B8%D0%B1%D0%BA%D0%B0-%D0%BC%D0%BD%D0%BE%D0%B3%D0%BE%D0%BA%D0%BB%D0%B0%D1%81%D1%81%D0%BE%D0%B2%D0%BE%D0%B9-%D0%BA%D0%BB%D0%B0%D1%81%D1%81%D0%B8%D1%84%D0%B8%D0%BA%D0%B0%D1%86%D0%B8%D1%8F-%D0%BD%D0%B0-python-xgboost

Share

Тебе может это понравится...