Pandas version: TypeError: drop() got an unexpected keyword argument 'columns'

[salma1601]

Hi, I am trying to run the starting kit but got the following error for the evaluation function

results = evaluation(data_train, labels_train)

>
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-21-1247bf8432df> in <module>()
----> 1 results = evaluation(data_train, labels_train)
      2 
      3 print("Training score ROC-AUC: {:.3f} +- {:.3f}".format(np.mean(results['train_roc_auc']),
      4                                                         np.std(results['train_roc_auc'])))
      5 print("Validation score ROC-AUC: {:.3f} +- {:.3f} \n".format(np.mean(results['test_roc_auc']),

<ipython-input-17-e7b8911b304f> in evaluation(X, y)
      8     results = cross_validate(pipe, X, y, scoring=['roc_auc', 'accuracy'], cv=cv,
      9                              verbose=1, return_train_score=True,
---> 10                              n_jobs=1)
     11 
     12     return results

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/model_selection/_validation.pyc in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score)
    204             fit_params, return_train_score=return_train_score,
    205             return_times=True)
--> 206         for train, test in cv.split(X, y, groups))
    207 
    208     if return_train_score:

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
    777             # was dispatched. In particular this covers the edge
    778             # case of Parallel used with an exhausted iterator.
--> 779             while self.dispatch_one_batch(iterator):
    780                 self._iterating = True
    781             else:

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
    623                 return False
    624             else:
--> 625                 self._dispatch(tasks)
    626                 return True
    627 

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
    586         dispatch_timestamp = time.time()
    587         cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588         job = self._backend.apply_async(batch, callback=cb)
    589         self._jobs.append(job)
    590 

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

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in __init__(self, batch)
    330         # Don't delay the application, to avoid keeping the input
    331         # arguments in memory
--> 332         self.results = batch()
    333 
    334     def get(self):

/home/salma/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/salma/anaconda2/lib/python2.7/site-packages/sklearn/model_selection/_validation.pyc in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
    456             estimator.fit(X_train, **fit_params)
    457         else:
--> 458             estimator.fit(X_train, y_train, **fit_params)
    459 
    460     except Exception as e:

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/pipeline.pyc in fit(self, X, y, **fit_params)
    246             This estimator
    247         """
--> 248         Xt, fit_params = self._fit(X, y, **fit_params)
    249         if self._final_estimator is not None:
    250             self._final_estimator.fit(Xt, y, **fit_params)

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/pipeline.pyc in _fit(self, X, y, **fit_params)
    211                 Xt, fitted_transformer = fit_transform_one_cached(
    212                     cloned_transformer, None, Xt, y,
--> 213                     **fit_params_steps[name])
    214                 # Replace the transformer of the step with the fitted
    215                 # transformer. This is necessary when loading the transformer

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/memory.pyc in __call__(self, *args, **kwargs)
    360 
    361     def __call__(self, *args, **kwargs):
--> 362         return self.func(*args, **kwargs)
    363 
    364     def call_and_shelve(self, *args, **kwargs):

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/pipeline.pyc in _fit_transform_one(transformer, weight, X, y, **fit_params)
    579                        **fit_params):
    580     if hasattr(transformer, 'fit_transform'):
--> 581         res = transformer.fit_transform(X, y, **fit_params)
    582     else:
    583         res = transformer.fit(X, y, **fit_params).transform(X)

/home/salma/anaconda2/lib/python2.7/site-packages/sklearn/base.pyc in fit_transform(self, X, y, **fit_params)
    518         else:
    519             # fit method of arity 2 (supervised transformation)
--> 520             return self.fit(X, y, **fit_params).transform(X)
    521 
    522 

<ipython-input-18-6d322cc43f0d> in transform(self, X_df)
     10         # get only the anatomical information
     11         X = X_df[[col for col in X_df.columns if col.startswith('anatomy')]]
---> 12         return X.drop(columns='anatomy_select')

TypeError: drop() got an unexpected keyword argument 'columns'

[glemaitre]

I assume that you have a older version of pandas. columns has been added in pandas 0.21. Can you update to the last release of pandas (0.22)

pip install -U pandas

conda update pandas

[salma1601]

Yes now it works. Thanks !

[aboucaud]

@glemaitre, if you're using this new pandas feature in the kit, should we not put a minversion requirement in the requirements.txt and environment.yml ?