def as_ctrait(thandler):
if hasattr(thandler, 'as_ctrait'):
return thandler.as_ctrait()
if hasattr(thandler, 'aType'):
ttype = thandler.aType
elif hasattr(thandler, 'aClass'):
ttype = thandler.aClass
else:
ttype = thandler
if isinstance(ttype, type):
if ttype.__name__ == 'str':
ttype = traits.Str()
elif ttype.__name__ == 'bytes':
ttype = traits.Bytes()
elif ttype.__name__ == 'unicode':
ttype = traits.Unicode()
#else:
#ttype = ttype()
if hasattr(ttype, 'as_ctrait'):
ttype = ttype.as_ctrait()
return ttype
class Signal1DCalibration(SpanSelectorInSignal1D):
left_value = t.Float(t.Undefined, label='New left value')
right_value = t.Float(t.Undefined, label='New right value')
offset = t.Float()
scale = t.Float()
units = t.Unicode()
def __init__(self, signal):
super(Signal1DCalibration, self).__init__(signal)
if signal.axes_manager.signal_dimension != 1:
raise SignalDimensionError(
signal.axes_manager.signal_dimension, 1)
self.units = self.axis.units
self.scale = self.axis.scale
self.offset = self.axis.offset
self.last_calibration_stored = True
def _left_value_changed(self, old, new):
if self.span_selector is not None and \
self.span_selector.range is None:
return
else:
self._update_calibration()
def _right_value_changed(self, old, new):
if self.span_selector.range is None:
return
else:
self._update_calibration()
def _update_calibration(self, *args, **kwargs):
# If the span selector or the new range values are not defined do
# nothing
if np.isnan(self.ss_left_value) or np.isnan(self.ss_right_value) or\
t.Undefined in (self.left_value, self.right_value):
return
lc = self.axis.value2index(self.ss_left_value)
rc = self.axis.value2index(self.ss_right_value)
self.offset, self.scale = self.axis.calibrate(
(self.left_value, self.right_value), (lc, rc),
modify_calibration=False)
def apply(self):
if np.isnan(self.ss_left_value) or np.isnan(self.ss_right_value):
_logger.warning("Select a range by clicking on the signal figure "
"and dragging before pressing Apply.")
return
elif self.left_value is t.Undefined or self.right_value is t.Undefined:
_logger.warning("Select the new left and right values before "
"pressing apply.")
return
axis = self.axis
axis.scale = self.scale
axis.offset = self.offset
axis.units = self.units
self.span_selector_switch(on=False)
self.signal._replot()
self.span_selector_switch(on=True)
self.last_calibration_stored = True
class SubSet(_traits.HasTraits):
'''FIXME: deprecated by Level'''
id = _traits.Str()
name = _traits.Unicode()
# Index label list
row_selector = _traits.List()
# col_selector = _traits.List(_traits.Int())
gr_style = VisualStyle()
class Signal1DCalibration(SpanSelectorInSignal1D):
left_value = t.Float(label='New left value')
right_value = t.Float(label='New right value')
offset = t.Float()
scale = t.Float()
units = t.Unicode()
view = tu.View(tu.Group(
'left_value',
'right_value',
tu.Item('ss_left_value', label='Left', style='readonly'),
tu.Item('ss_right_value', label='Right', style='readonly'),
tu.Item(name='offset', style='readonly'),
tu.Item(name='scale', style='readonly'),
'units',
),
handler=CalibrationHandler,
buttons=[OKButton, OurApplyButton, CancelButton],
kind='live',
title='Calibration parameters')
def __init__(self, signal):
super(Signal1DCalibration, self).__init__(signal)
if signal.axes_manager.signal_dimension != 1:
raise SignalDimensionError(signal.axes_manager.signal_dimension, 1)
self.units = self.axis.units
self.last_calibration_stored = True
def _left_value_changed(self, old, new):
if self.span_selector is not None and \
self.span_selector.range is None:
messages.information('Please select a range in the spectrum figure'
'by dragging the mouse over it')
return
else:
self._update_calibration()
def _right_value_changed(self, old, new):
if self.span_selector.range is None:
messages.information('Please select a range in the spectrum figure'
'by dragging the mouse over it')
return
else:
self._update_calibration()
def _update_calibration(self, *args, **kwargs):
if self.left_value == self.right_value:
return
lc = self.axis.value2index(self.ss_left_value)
rc = self.axis.value2index(self.ss_right_value)
self.offset, self.scale = self.axis.calibrate(
(self.left_value, self.right_value), (lc, rc),
modify_calibration=False)
class DataSet(_traits.HasTraits):
'''Data set for holding one matrix
and associated metadata
The reccomended access methods as properties for the DataSet object:
* id: An identity string that is unique for each object
* display_name: An human friendly name that for the datataset
* kind: The data set type
* missing_data: Boolean value indicatin if the data set have "holes"
* n_vars: Number of variables
* n_objs: Number of objects
* var_n: List containing variable names
* obj_n: List containing object names
* values: The matrix values as an 2D Numpy array
* mat: The matrix as an Pandas DataFrame
'''
mat = _traits.Instance(_pd.DataFrame, ())
_id = _traits.Int()
id = _traits.Property()
new_id = _itr.count(start=101).next
display_name = _traits.Unicode('Unnamed data set')
kind = _traits.Enum(DS_TYPES)
# FIXME: Only color
style = _traits.Instance('VisualStyle', ())
# Example: {'species': [SubSet, SubSet], 'location': [SubSet, SubSet]}
# Column subsets
subs = _traits.Dict(_traits.Unicode, _traits.List)
# Row subsets
rsubs = _traits.Dict(_traits.Unicode, _traits.List)
row_factors = _traits.List()
col_factors = _traits.List()
# FIXME: This data set has missing data
# do you want to do somthing about it?
# * throw rows/cols with missing data
# * do imputation
missing_data = _traits.Property(_traits.Bool)
n_vars = _traits.Property()
n_objs = _traits.Property()
var_n = _traits.Property()
obj_n = _traits.Property()
values = _traits.Property()
# FIXME: This is a dubious solution
matcat = _traits.Instance(_pd.DataFrame)
valuescat = _traits.Property()
def _get_values(self):
if self.missing_data:
return _np.ma.masked_invalid(self.mat.values)
else:
return self.mat.values
def _make_matcat(self):
matcat = self.mat.copy()
for cn, ssl in self.subs.items():
cs = _pd.Series(index=self.mat.index)
for ss in ssl:
cs[list(ss.row_selector)] = ss.id
matcat[cn] = cs
for cn, ssl in self.rsubs.items():
cs = _pd.Series(index=self.mat.index)
for ss in ssl:
cs[list(ss.row_selector)] = ss.id
matcat[cn] = cs
self.matcat = matcat
def _get_valuescat(self):
try:
return self.matcat.values
except AttributeError:
# self._make_matcat()
return self.matcat.values
def _get_n_vars(self):
return self.mat.shape[1]
def _get_n_objs(self):
return self.mat.shape[0]
def _get_var_n(self):
return list(self.mat.columns)
def _get_obj_n(self):
return list(self.mat.index)
def __id_default(self):
return DataSet.new_id()
def __eq__(self, other):
return self.id == other
def __ne__(self, other):
return self.id != other
def _get_id(self):
return str(self._id)
def _get_missing_data(self):
# FIXME: I must look more into this
try:
return _np.any(_np.isnan(self.mat.values))
except TypeError:
return False
def get_subset_groups(self):
return self.subs.keys()
def get_subsets(self, group):
return self.subs[group]
def get_subset_rows(self, subset):
''' Return a subset from given subset id'''
return self.mat.loc[list(subset.row_selector)]
def copy(self, transpose=False):
new = self.clone_traits(traits=['display_name', 'kind', 'style', 'subs'])
if transpose:
tmp = self.mat.copy()
new.mat = tmp.transpose()
else:
new.mat = self.mat.copy()
return new
class Factor(_traits.HasTraits):
'''Represent different factors as independent variables
FIXME: is the order of levels important, the uniqueness?
looks more like a mapping type than a sequences type
'''
name = _traits.Unicode()
levels = _traits.Dict(_traits.Unicode, Level)
# Can be used to check if this can be used for a given dataset
size = _traits.Property()
_size = _traits.Int()
default_ds_axis = _traits.Enum(("row", "col"))
def __init__(self, name, size, *levels, **kwargs):
'''Create a factor object
name: The factor name
levels: none, one or several level objects
check_idx: check index strategy; no, toss_overlaping
'''
check_idx = kwargs.pop('check_idx', "no")
super(Factor, self).__init__(name=name, size=size, **kwargs)
for level in levels:
self.add_level(level, check_idx)
def add_level(self, level, check_idx="no"):
'''Add level
level: a level object
check_idx: "no", "toss_overlaping", "excpet_overlapping", "return_overlapping"
'''
self.name_check(level.name)
self.bound_check(level.selector)
if check_idx == "no":
self.levels[level.name] = level
elif check_idx == "toss_overlaping":
self.toss_overlaping(level)
self.levels[level.name] = level
else:
msg = "Not valid value for check_idx: {0}".format(check_idx)
raise ValueError(msg)
def name_check(self, new_name):
if new_name in self.levels:
msg = "Level name collision. Name: {0} already exist in factor: {1}".format(
new_name, self.name)
raise ValueError(msg)
def bound_check(self, selector):
if self.size <= max(selector):
msg = "Index in level out of bounds"
raise IndexError(msg)
def toss_overlaping(self, level):
'''
FIXME: This will mainpulate an existing object. Is that unproblematic?
'''
existing_idx = []
for lv in self.levels.itervalues():
existing_idx.extend(lv.selector)
exist = set(existing_idx)
unique = set(level.selector).difference(exist)
level.selector = list(unique)
def get_values(self, dataset, name, axis=None):
'''Return numpy subarray
'''
idx = self.levels[name].selector
if axis is not None:
if axis == 0:
return dataset.mat.values[idx,:]
elif axis == 1:
return dataset.mat.values[:,idx]
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
return dataset.mat.values[idx,:]
else:
return dataset.mat.values[:,idx]
def get_labels(self, dataset, name, axis=None):
'''Return list of selected labels
'''
idx = self.levels[name].selector
if axis is not None:
if axis == 0:
return dataset.mat.index[idx]
elif axis == 1:
return dataset.mat.columns[idx]
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
return dataset.mat.index[idx]
else:
return dataset.mat.columns[idx]
def _get_all_leveled(self):
'''The index combined from all the levels
'''
return list(_itr.chain.from_iterable([lv.selector for lv in self.levels.itervalues()]))
def get_combined_levels_subset(self, dataset, axis=None):
'''Return numpy subarray
'''
sub_ds = dataset.copy()
idx = self._get_all_leveled()
if axis is not None:
if axis == 0:
sub_ds.mat = dataset.mat.iloc[idx,:]
return sub_ds
elif axis == 1:
sub_ds.mat = dataset.mat.iloc[:,idx]
return sub_ds
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
sub_ds.mat = dataset.mat[idx,:]
return sub_ds
else:
sub_ds.mat = dataset.mat[:,idx]
return sub_ds
def get_combined_levels_values(self, dataset, axis=None):
'''Return numpy subarray
'''
idx = self._get_all_leveled()
if axis is not None:
if axis == 0:
return dataset.mat.values[idx,:]
elif axis == 1:
return dataset.mat.values[:,idx]
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
return dataset.mat.values[idx,:]
else:
return dataset.mat.values[:,idx]
def get_combined_levels_labels(self, dataset, axis=None):
'''Return list of all selected labels
'''
idx = self._get_all_leveled()
if axis is not None:
if axis == 0:
return dataset.mat.index[idx]
elif axis == 1:
return dataset.mat.columns[idx]
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
return dataset.mat.index[idx]
else:
return dataset.mat.columns[idx]
def _get_nonleveled(self, dataset, axis):
'''The indexes for a dataset that is not in a level
'''
lvs = self._get_all_leveled()
return list(set(range(dataset.mat.shape[axis])).difference(set(lvs)))
def get_rest_values(self, dataset, axis=None):
'''Return numpy subarray
'''
if axis is not None:
if axis == 0:
idx = self._get_nonleveled(dataset, 0)
return dataset.mat.values[idx,:]
elif axis == 1:
idx = self._get_nonleveled(dataset, 1)
return dataset.mat.values[:,idx]
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
idx = self._get_nonleveled(dataset, 0)
return dataset.mat.values[idx,:]
else:
idx = self._get_nonleveled(dataset, 1)
return dataset.mat.values[:,idx]
def get_rest_labels(self, dataset, axis=None):
'''Return list of not selected labels
'''
if axis is not None:
if axis == 0:
idx = self._get_nonleveled(dataset, 0)
return dataset.mat.index[idx]
elif axis == 1:
idx = self._get_nonleveled(dataset, 1)
return dataset.mat.columns[idx]
raise ValueError('Illegale value for axis')
else:
if self.default_ds_axis == "row":
idx = self._get_nonleveled(dataset, 0)
return dataset.mat.index[idx]
else:
idx = self._get_nonleveled(dataset, 1)
return dataset.mat.columns[idx]
def __len__(self):
return len(self.levels)
# def __getitem__(self, key):
# pass
# def __setitem__(self, key, value):
# pass
# def __iter__(self):
# pass
def _set_size(self, sz):
self._size = sz
def _get_size(self):
return self._size
class Level(_traits.HasTraits):
'''Represent a level in a factor
If we have gender as a factor, the levels can be for instance male or female.
If we have a age group factor, the levels can bel for instance 1, 2, 3.
'''
# Require name
name = _traits.Unicode()
# Accept list of integers or numpy vector (1 dim array) that we convert to list
selector = _traits.List(_traits.Int)
# Autoasign unique style if style is not explicit specified
# style = VisualStyle()
color = ColorTrait()
def __init__(self, idx, name, color=None):
'''Create level group
idx: list of numerical indexes to make selection from matrix
name: name for this group
style: color tuple (r, g, b, a) to color this level in plots
'''
self.selector = list(idx)
self.name = name
if color is None:
self.color = from_palette()
else:
self.color = color
def get_values(self, dataset, axis=0):
'''Get selected row or columns values
dataset: the dataset to get from
axis: 0 - vertical, columns labels, 1 - horizontal, row labels
'''
if axis == 0:
return dataset.mat[self.selector,:]
elif axis == 1:
return dataset.mat[:,self.selector]
raise ValueError('Illegale value for axis')
def get_labels(self, dataset, axis=0):
'''Get selected row or columns labels
dataset: the dataset to get from
axis: 0 - vertical, columns labels, 1 - horizontal, row labels
'''
if axis == 0:
return dataset.mat.index[self.selector]
elif axis == 1:
return dataset.mat.columns[:,self.selector]
raise ValueError('Illegale value for axis')
def __eq__(self, other):
return self.name == other.name
def __ne__(self, other):
return self.name != other.name
