def get_top_features(clf, M=None, col_names=None, n=10, verbose=True):
"""Gets the top features for a fitted clf
Parameters
----------
clf : sklearn.base.BaseEstimator
Fitted classifier with a feature_importances_ attribute
M : numpy.ndarray or None
Structured array corresponding to fitted clf. Used here to deterimine
column names
col_names : list of str or None
List of column names corresponding to fitted clf.
n : int
Number of features to return
verbose : boolean
iff True, prints ranked features
Returns
-------
numpy.ndarray
structured array with top feature names and scores
"""
if not isinstance(clf, BaseEstimator):
raise ValueError('clf must be an instance of sklearn.Base.BaseEstimator')
scores = clf.feature_importances_
if col_names is None:
if is_sa(M):
col_names = M.dtype.names
else:
col_names = ['f{}'.format(i) for i in xrange(len(scores))]
else:
col_names = utils.check_col_names(col_names, n_cols = scores.shape[0])
ranked_name_and_score = [(col_names[x], scores[x]) for x in
scores.argsort()[::-1]]
ranked_name_and_score = convert_to_sa(
ranked_name_and_score[:n],
col_names=('feat_name', 'score'))
if verbose:
pprint_sa(ranked_name_and_score)
return ranked_name_and_score
def get_top_features(clf, M=None, col_names=None, n=10, verbose=True):
"""Gets the top features for a fitted clf
Parameters
----------
clf : sklearn.base.BaseEstimator
Fitted classifier with a feature_importances_ attribute
M : numpy.ndarray or None
Structured array corresponding to fitted clf. Used here to deterimine
column names
col_names : list of str or None
List of column names corresponding to fitted clf.
n : int
Number of features to return
verbose : boolean
iff True, prints ranked features
Returns
-------
numpy.ndarray
structured array with top feature names and scores
"""
if not isinstance(clf, BaseEstimator):
raise ValueError(
'clf must be an instance of sklearn.Base.BaseEstimator')
scores = clf.feature_importances_
if col_names is None:
if is_sa(M):
col_names = M.dtype.names
else:
col_names = ['f{}'.format(i) for i in xrange(len(scores))]
else:
col_names = utils.check_col_names(col_names, n_cols=scores.shape[0])
ranked_name_and_score = [(col_names[x], scores[x])
for x in scores.argsort()[::-1]]
ranked_name_and_score = convert_to_sa(ranked_name_and_score[:n],
col_names=('feat_name', 'score'))
if verbose:
pprint_sa(ranked_name_and_score)
return ranked_name_and_score
def test_check_col_names(self):
self.assertEqual(utils.check_col_names('f0'), ['f0'])
utils.check_col_names(['f0', 'f1', 'f2'])
self.assertEqual(utils.check_col_names([u'f0', 'f1', u'f2']), ['f0', 'f1', 'f2'])
self.assertRaises(ValueError, utils.check_col_names, {})
self.assertRaises(ValueError, utils.check_col_names, ['f0', 4, 'f2'])