def _parse_parameters(self, kwds):
# pylint: disable=no-member
self._params = create_dataframe(self.all_parameters + [self.UPDATE_COLUMN_DESC])
self.params = DataFrameAsDict(self._params)
for (name,_,_) in self.all_parameters:
if name in kwds:
self.params[name] = kwds[name]
def __init__(self, column, percentiles=None, **kwds):
if not column:
raise ProgressiveError('Need a column name')
self._add_slots(kwds,'input_descriptors',
[SlotDescriptor('df', type=pd.DataFrame)])
super(Percentiles, self).__init__(dataframe_slot='percentiles', **kwds)
self._column = column
self.default_step_size = 1000
self.tdigest = TDigest()
if percentiles is None:
percentiles = np.array([0.25, 0.5, 0.75])
else:
# get them all to be in [0, 1]
percentiles = np.asarray(percentiles)
if (percentiles > 1).any():
percentiles = percentiles / 100.0
msg = ("percentiles should all be in the interval [0, 1]. "
"Try {0} instead.")
raise ValueError(msg.format(list(percentiles)))
if (percentiles != 0.5).all(): # median isn't included
lh = percentiles[percentiles < .5]
uh = percentiles[percentiles > .5]
percentiles = np.hstack([lh, 0.5, uh])
self._percentiles = percentiles
self.schema = [(_pretty_name(x), np.dtype(float), np.nan) for x in self._percentiles]
self.schema.append(DataFrameModule.UPDATE_COLUMN_DESC)
self._df = create_dataframe(self.schema)
def __init__(self, colormap=None, **kwds):
self._add_slots(kwds,'input_descriptors',
[SlotDescriptor('array', type=pd.DataFrame)])
super(Heatmap, self).__init__(dataframe_slot='heatmap', **kwds)
self.colormap = colormap
self.default_step_size = 1
self._df = create_dataframe(Heatmap.schema)
def __init__(self, x_column, y_column, **kwds):
self._x = x_column
self._y = y_column
self._add_slots(kwds,'input_descriptors',
[SlotDescriptor('inp', type=pd.DataFrame)])
super(LinearRegression, self).__init__(dataframe_slot='inp', **kwds)
self.default_step_size = 10000
self._df = create_dataframe(LinearRegression.schema)
def __init__(self, column, **kwds):
self._add_slots(kwds, 'input_descriptors',
[SlotDescriptor('df', type=pd.DataFrame, required=True),
SlotDescriptor('min', type=pd.DataFrame, required=True),
SlotDescriptor('max', type=pd.DataFrame, required=True)])
super(Histogram1D, self).__init__(dataframe_slot='df', **kwds)
self.column = column
self.total_read = 0
self._histo = None
self._edges = None
self._bounds = None
self._df = create_dataframe(Histogram1D.schema)
def __init__(self, **kwds):
self._add_slots(kwds, 'input_descriptors',
[SlotDescriptor('min', type=pd.DataFrame, required=True),
SlotDescriptor('max', type=pd.DataFrame, required=True),
SlotDescriptor('min_value', type=pd.DataFrame, required=True),
SlotDescriptor('max_value', type=pd.DataFrame, required=True)])
self._add_slots(kwds, 'output_descriptors',
[SlotDescriptor('min', type=pd.DataFrame, required=False),
SlotDescriptor('max', type=pd.DataFrame, required=False)])
super(RangeQuery, self).__init__(dataframe_slot='query', **kwds)
self.default_step_size = 1
self._df = create_dataframe(RangeQuery.schema, empty=True)
self._min = None
self._max = None
def __init__(self, x_column, y_column, **kwds):
self._add_slots(kwds,'input_descriptors',
[SlotDescriptor('df', type=pd.DataFrame, required=True),
SlotDescriptor('min', type=pd.DataFrame, required=True),
SlotDescriptor('max', type=pd.DataFrame, required=True)])
super(Histogram2D, self).__init__(dataframe_slot='df', **kwds)
self.x_column = x_column
self.y_column = y_column
self.default_step_size = 10000
self.total_read = 0
self._histo = None
self._xedges = None
self._yedges = None
self._bounds = None
self._df = create_dataframe(Histogram2D.schema)
def __init__(self, **kwds):
super(Input, self).__init__(**kwds)
self._df = create_dataframe(Input.schema,empty=True)
self._last = len(self._df)
self.default_step_size = 1000000