---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-160-531a7478134b> in <module>()
      4 for idx,stn in enumerate(stns):
      5     stn_dict[idx] = stn
----> 6     df.loc[df[cat] == stn,cat] = idx

/Users/mikhail/anaconda/lib/python2.7/site-packages/pandas/core/indexing.pyc in __setitem__(self, key, value)
     96             indexer = self._convert_to_indexer(key, is_setter=True)
     97 
---> 98         self._setitem_with_indexer(indexer, value)
     99 
    100     def _has_valid_type(self, k, axis):

/Users/mikhail/anaconda/lib/python2.7/site-packages/pandas/core/indexing.pyc in _setitem_with_indexer(self, indexer, value)
    404                 # scalar
    405                 for item in labels:
--> 406                     setter(item, value)
    407 
    408         else:

KeyboardInterrupt: 

An array of all zeros gives an RMSE of: 0.863841709437
An array of all ones gives an RMSE of: 0.503763338322
An array of random ones and zeros gives an RMSE of: 0.70685723912

Root-mean-square error:  0.59582966275

Precision: Of all predicted CFAs, what fraction actually succeeded?
0.823697236354

Recall: Of all actual CFAs, what fraction did we predict correctly?
0.667139953785

F_1 Score:  0.737198320284

Accuracy:  0.78 (+/- 0.01)

Root-mean-square error:  0.500098691559

Precision: Of all predicted CFAs, what fraction actually succeeded?
0.834598896018

Recall: Of all actual CFAs, what fraction did we predict correctly?
0.829254711991

F_1 Score:  0.831918221428

Feature ranking:
 1 - Anon Student Id     : 0.2705 (std: 0.0026)
 2 - Hints               : 0.2593 (std: 0.0011)
 3 - Step Duration (sec) : 0.2261 (std: 0.0032)
 4 - Problem Name        : 0.1125 (std: 0.0022)
 5 - Problem View        : 0.0444 (std: 0.0010)
 6 - Problem Section     : 0.0358 (std: 0.0014)
 7 - Problem Hierarchy   : 0.0306 (std: 0.0011)
 8 - Problem Unit        : 0.0208 (std: 0.0011)

---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-162-8de7c3d2ecea> in <module>()
----> 1 scores = cross_val_score(model, X, y)
      2 print 'Accuracy: {0:5.2f} (+/-{1:5.2f})'.format(scores.mean(), scores.std()*2)

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/cross_validation.pyc in cross_val_score(estimator, X, y, scoring, cv, n_jobs, verbose, fit_params, score_func, pre_dispatch)
   1149                                               train, test, verbose, None,
   1150                                               fit_params)
-> 1151                       for train, test in cv)
   1152     return np.array(scores)[:, 0]
   1153 

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
    651             self._iterating = True
    652             for function, args, kwargs in iterable:
--> 653                 self.dispatch(function, args, kwargs)
    654 
    655             if pre_dispatch == "all" or n_jobs == 1:

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch(self, func, args, kwargs)
    398         """
    399         if self._pool is None:
--> 400             job = ImmediateApply(func, args, kwargs)
    401             index = len(self._jobs)
    402             if not _verbosity_filter(index, self.verbose):

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __init__(self, func, args, kwargs)
    136         # Don't delay the application, to avoid keeping the input
    137         # arguments in memory
--> 138         self.results = func(*args, **kwargs)
    139 
    140     def get(self):

/Users/mikhail/anaconda/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)
   1237         estimator.fit(X_train, **fit_params)
   1238     else:
-> 1239         estimator.fit(X_train, y_train, **fit_params)
   1240     test_score = _score(estimator, X_test, y_test, scorer)
   1241     if return_train_score:

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/ensemble/forest.pyc in fit(self, X, y, sample_weight)
    277                 sample_weight,
    278                 verbose=self.verbose)
--> 279             for i in range(n_jobs))
    280 
    281         # Reduce

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
    651             self._iterating = True
    652             for function, args, kwargs in iterable:
--> 653                 self.dispatch(function, args, kwargs)
    654 
    655             if pre_dispatch == "all" or n_jobs == 1:

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch(self, func, args, kwargs)
    398         """
    399         if self._pool is None:
--> 400             job = ImmediateApply(func, args, kwargs)
    401             index = len(self._jobs)
    402             if not _verbosity_filter(index, self.verbose):

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __init__(self, func, args, kwargs)
    136         # Don't delay the application, to avoid keeping the input
    137         # arguments in memory
--> 138         self.results = func(*args, **kwargs)
    139 
    140     def get(self):

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/ensemble/forest.pyc in _parallel_build_trees(trees, forest, X, y, sample_weight, verbose)
     87             tree.fit(X, y,
     88                      sample_weight=curr_sample_weight,
---> 89                      check_input=False)
     90 
     91             tree.indices_ = sample_counts > 0.

/Users/mikhail/anaconda/lib/python2.7/site-packages/sklearn/tree/tree.pyc in fit(self, X, y, sample_mask, X_argsorted, check_input, sample_weight)
    265                                            max_leaf_nodes)
    266 
--> 267         builder.build(self.tree_, X, y, sample_weight)
    268 
    269         if self.n_outputs_ == 1:

KeyboardInterrupt: