def test_is_nd(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.assertTrue(utils.is_nd(nd))
self.assertTrue(utils.is_nd(sa))
def plot_on_timeline(col, verbose=True):
"""Plots points on a timeline
Parameters
----------
col : np.array
verbose : boolean
iff True, display the graph
Returns
-------
matplotlib.figure.Figure
Figure containing plot
Returns
-------
matplotlib.figure.Figure
"""
col = utils.check_col(col)
# http://stackoverflow.com/questions/1574088/plotting-time-in-python-with-matplotlib
if is_nd(col):
col = col.astype(datetime)
dates = matplotlib.dates.date2num(col)
fig = plt.figure()
plt.plot_date(dates, [0] * len(dates))
if verbose:
plt.show()
return fig
def plot_on_timeline(col, verbose=True):
"""Plots points on a timeline
Parameters
----------
col : np.array
verbose : boolean
iff True, display the graph
Returns
-------
matplotlib.figure.Figure
Figure containing plot
Returns
-------
matplotlib.figure.Figure
"""
col = utils.check_col(col)
# http://stackoverflow.com/questions/1574088/plotting-time-in-python-with-matplotlib
if is_nd(col):
col = col.astype(datetime)
dates = matplotlib.dates.date2num(col)
fig = plt.figure()
plt.plot_date(dates, [0] * len(dates))
if verbose:
plt.show()
return fig
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_col(self):
valid1 = np.array([1, 2, 3, 4])
valid2 = np.array([[1.0], [2], [3], [4]])
valid3 = [3.0, 2.0, 1.8]
valid4 = pd.Series(valid1)
for valid in (valid1, valid2, valid3, valid4):
self.assertTrue(utils.is_nd(utils.check_col(valid)))
self.assertRaises(ValueError, utils.check_col, None)
self.assertRaises(ValueError, utils.check_col, "lalala")
self.assertRaises(ValueError, utils.check_col, np.array(
[[1, 2], [3, 4]]))
utils.check_col(valid1, n_rows=4)
self.assertRaises(ValueError, utils.check_col, valid1, n_rows=5)
