def test_is_sa(self):
nd = np.array([[1, 2, 3], [4, 5, 6]], dtype=int)
dtype = np.dtype({'names': map('f{}'.format, xrange(3)),
'formats': [float] * 3})
sa = np.array([(-1.0, 2.0, -1.0), (0.0, -1.0, 2.0)], dtype=dtype)
self.assertFalse(utils.is_sa(nd))
self.assertTrue(utils.is_sa(sa))
def __init__(self,
M,
labels,
clfs=[{
'clf': RandomForestClassifier
}],
subsets=[{
'subset': s_i.SubsetNoSubset
}],
cvs=[{
'cv': KFold
}],
trials=None):
if M is not None:
if utils.is_nd(M) and not utils.is_sa(M):
# nd_array, short circuit the usual type checking and coersion
if M.ndim != 2:
raise ValueError('Expected 2-dimensional array for M')
self.M = M
self.col_names = ['f{}'.format(i) for i in xrange(M.shape[1])]
self.labels = utils.check_col(labels,
n_rows=M.shape[0],
argument_name='labels')
else:
# M is either a structured array or something that should
# be converted
(M, self.labels) = utils.check_consistent(
M, labels, col_argument_name='labels')
self.col_names = M.dtype.names
self.M = utils.cast_np_sa_to_nd(M)
else:
self.col_names = None
if trials is None:
clfs = utils.check_arguments(
clfs, {'clf': lambda clf: issubclass(clf, BaseEstimator)},
optional_keys_take_lists=True,
argument_name='clfs')
subsets = utils.check_arguments(subsets, {
'subset':
lambda subset: issubclass(subset, s_i.BaseSubsetIter)
},
optional_keys_take_lists=True,
argument_name='subsets')
cvs = utils.check_arguments(
cvs, {'cv': lambda cv: issubclass(cv, _PartitionIterator)},
optional_keys_take_lists=True,
argument_name='cvs')
self.clfs = clfs
self.subsets = subsets
self.cvs = cvs
self.trials = trials
def __init__(
self,
M,
labels,
clfs=[{'clf': RandomForestClassifier}],
subsets=[{'subset': s_i.SubsetNoSubset}],
cvs=[{'cv': KFold}],
trials=None):
if M is not None:
if utils.is_nd(M) and not utils.is_sa(M):
# nd_array, short circuit the usual type checking and coersion
if M.ndim != 2:
raise ValueError('Expected 2-dimensional array for M')
self.M = M
self.col_names = ['f{}'.format(i) for i in xrange(M.shape[1])]
self.labels = utils.check_col(
labels,
n_rows=M.shape[0],
argument_name='labels')
else:
# M is either a structured array or something that should
# be converted
(M, self.labels) = utils.check_consistent(
M,
labels,
col_argument_name='labels')
self.col_names = M.dtype.names
self.M = utils.cast_np_sa_to_nd(M)
else:
self.col_names = None
if trials is None:
clfs = utils.check_arguments(
clfs,
{'clf': lambda clf: issubclass(clf, BaseEstimator)},
optional_keys_take_lists=True,
argument_name='clfs')
subsets = utils.check_arguments(
subsets,
{'subset': lambda subset: issubclass(subset, s_i.BaseSubsetIter)},
optional_keys_take_lists=True,
argument_name='subsets')
cvs = utils.check_arguments(
cvs,
{'cv': lambda cv: issubclass(cv, _PartitionIterator)},
optional_keys_take_lists=True,
argument_name='cvs')
self.clfs = clfs
self.subsets = subsets
self.cvs = cvs
self.trials = trials
def test_check_sa(self):
valid1 = np.array([(1, 'a'), (2, 'b'), (3, 'c')],
dtype=[('int', int), ('s', 'S0')])
valid2 = np.array([[1, 2, 3], [4, 5, 6]])
valid3 = [[1, 2, 3], [4, 5, 6]]
valid4 = pd.DataFrame(valid1)
for valid in (valid1, valid2, valid3, valid4):
self.assertTrue(utils.is_sa(utils.check_sa(valid)))
self.assertRaises(ValueError, utils.check_sa, None)
self.assertRaises(ValueError, utils.check_sa, "lalala")
utils.check_sa(valid1, n_rows=3, n_cols=2)
self.assertRaises(ValueError, utils.check_sa, valid1, n_rows=4)
self.assertRaises(ValueError, utils.check_sa, valid1, n_cols=3)
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
