ml udacity error

foobar.md

given

from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import make_scorer
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import precision_score

def fit_model(X, y):
    """ Performs grid search over the 'max_depth' parameter for a 
        decision tree regressor trained on the input data [X, y]. """
    
    print('The scikit-learn version is {}.'.format(sklearn.__version__))
    
    # Create cross-validation sets from the training data
    print(X.shape[0])
    cv_sets = ShuffleSplit(X.shape[0], n_iter = 10, test_size = 0.20, random_state = 0)

    # TODO: Create a decision tree regressor object
    regressor = DecisionTreeRegressor()

    # TODO: Create a dictionary for the parameter 'max_depth' with a range from 1 to 10
    params = { 'max_depth': range(1, 11) }

    # TODO: Transform 'performance_metric' into a scoring function using 'make_scorer' 
    scoring_fnc = make_scorer(precision_score)

    # TODO: Create the grid search object
    grid = GridSearchCV(regressor, params, scoring_fnc, cv_sets)

    # Fit the grid search object to the data to compute the optimal model
    grid = grid.fit(X, y)

    # Return the optimal model after fitting the data
    return grid.best_estimator_

The scikit-learn version is 0.17.1.
391
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-26-192f7c286a58> in <module>()
      1 # Fit the training data to the model using grid search
----> 2 reg = fit_model(X_train, y_train)
      3 
      4 # Produce the value for 'max_depth'
      5 print "Parameter 'max_depth' is {} for the optimal model.".format(reg.get_params()['max_depth'])

<ipython-input-25-d72c80aed4d6> in fit_model(X, y)
     27 
     28     # Fit the grid search object to the data to compute the optimal model
---> 29     grid = grid.fit(X, y)
     30 
     31     # Return the optimal model after fitting the data

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/grid_search.pyc in fit(self, X, y)
    802 
    803         """
--> 804         return self._fit(X, y, ParameterGrid(self.param_grid))
    805 
    806 

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/grid_search.pyc in _fit(self, X, y, parameter_iterable)
    551                                     self.fit_params, return_parameters=True,
    552                                     error_score=self.error_score)
--> 553                 for parameters in parameter_iterable
    554                 for train, test in cv)
    555 

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
    798             # was dispatched. In particular this covers the edge
    799             # case of Parallel used with an exhausted iterator.
--> 800             while self.dispatch_one_batch(iterator):
    801                 self._iterating = True
    802             else:

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
    656                 return False
    657             else:
--> 658                 self._dispatch(tasks)
    659                 return True
    660 

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
    564 
    565         if self._pool is None:
--> 566             job = ImmediateComputeBatch(batch)
    567             self._jobs.append(job)
    568             self.n_dispatched_batches += 1

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __init__(self, batch)
    178         # Don't delay the application, to avoid keeping the input
    179         # arguments in memory
--> 180         self.results = batch()
    181 
    182     def get(self):

/Users/mariogintili/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self)
     70 
     71     def __call__(self):
---> 72         return [func(*args, **kwargs) for func, args, kwargs in self.items]
     73 
     74     def __len__(self):

/Users/mariogintili/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)
   1515     fit_params = fit_params if fit_params is not None else {}
   1516     fit_params = dict([(k, _index_param_value(X, v, train))
-> 1517                       for k, v in fit_params.items()])
   1518 
   1519     if parameters is not None:

AttributeError: 'ShuffleSplit' object has no attribute 'items'

Thank you!!!

Thanks! Saved my day.

Thanks!!!

Thanks !!

Thanks!

Thank you so much Pojda!

Thank you very much! :)

I can answer the why...

The first three parameters are the correct positional parameters of the function. The fourth parameter is not. Positionally, cv is the eighth parameter, so cv_sets without the 'cv=' is actually setting fit_params, which is the fourth positional parameter.

Therefore 'cv=cv_sets' is required.

thanks

Thanks a lot ! that saves a lot of time

Thank you so much. You are a damn life saver :)

thanks @pojda and @jimtipr

thx!

Thank you so much @pojda and @jimtipr! I spent about 20 minutes checking my codes, reloading the page... etc. ended up its because of the order of parameters is off. Good lesson learned.

Thank you very much

Thank you, i spent 2 hours for this!

Thank you @pojda

Thank you so much !

Thanks @pojda for the solution and @jimtipr for the explanation!

Thank a lot.But why can't I just type cv? It's still wrong.
original:
grid = GridSearchCV(regressor, params, scoring_fnc, cv_sets)
Still Wrong?
grid = GridSearchCV(regressor, params, scoring_fnc, cv)

Thanks @pojda and @jimtipr

Thanks @pojda you are the real rockstar .

Thanks @pojda !

amazing, thanks so much!

Well thank you good sir ! Made my day !

thanks a lot

Thanks!

thanks a lot dude @pojda

Thanks.

Thank you :)