def commit(self):
data = self.data
if not data or not len(self.selected):
self.Outputs.time_series.send(None)
return
X = []
attrs = []
invert = self.invert_direction
shift = self.shift_period
order = self.diff_order
op = self.chosen_operation
for var in self.selected:
col = np.ravel(data[:, var])
if invert:
col = col[::-1]
out = np.empty(len(col))
if op == self.Operation.DIFF and shift == 1:
out[order:] = np.diff(col, order)
out[:order] = np.nan
else:
if op == self.Operation.DIFF:
out[shift:] = col[shift:] - col[:-shift]
else:
out[shift:] = np.divide(col[shift:], col[:-shift])
if op == self.Operation.PERC:
out = (out - 1) * 100
out[:shift] = np.nan
if invert:
out = out[::-1]
X.append(out)
if op == self.Operation.DIFF and shift == 1:
details = f'order={order}'
else:
details = f'shift={shift}'
template = f'{var} ({op[:4].lower()}; {details})'
name = available_name(data.domain, template)
attrs.append(ContinuousVariable(name))
ts = Timeseries.from_numpy(Domain(data.domain.attributes + tuple(attrs),
data.domain.class_vars,
data.domain.metas),
np.column_stack((data.X, np.column_stack(X))),
data.Y, data.metas)
ts.time_variable = data.time_variable
self.Outputs.time_series.send(ts)
def commit(self):
data = self.data
if not data or not len(self.selected):
self.send(Output.TIMESERIES, None)
return
X = []
attrs = []
invert = self.invert_direction
shift = self.shift_period
order = self.diff_order
for var in self.selected:
col = np.ravel(data[:, var])
if invert:
col = col[::-1]
out = np.empty(len(col))
if shift == 1:
out[:-order] = np.diff(col, order)
out[-order:] = np.nan
else:
out[:-shift] = col[shift:] - col[:-shift]
out[-shift:] = np.nan
if invert:
out = out[::-1]
X.append(out)
template = '{} (diff; {})'.format(var,
'order={}'.format(order) if shift == 1 else
'shift={}'.format(shift))
name = available_name(data.domain, template)
attrs.append(ContinuousVariable(name))
ts = Timeseries(Domain(data.domain.attributes + tuple(attrs),
data.domain.class_vars,
data.domain.metas),
np.column_stack((data.X, np.column_stack(X))),
data.Y, data.metas)
ts.time_variable = data.time_variable
self.send(Output.TIMESERIES, ts)
def commit(self):
data = self.data
if not data or not len(self.selected):
self.send(Output.TIMESERIES, None)
return
X = []
attrs = []
invert = self.invert_direction
shift = self.shift_period
order = self.diff_order
for var in self.selected:
col = np.ravel(data[:, var])
if invert:
col = col[::-1]
out = np.empty(len(col))
if shift == 1:
out[:-order] = np.diff(col, order)
out[-order:] = np.nan
else:
out[:-shift] = col[shift:] - col[:-shift]
out[-shift:] = np.nan
if invert:
out = out[::-1]
X.append(out)
template = '{} (diff; {})'.format(
var, 'order={}'.format(order)
if shift == 1 else 'shift={}'.format(shift))
name = available_name(data.domain, template)
attrs.append(ContinuousVariable(name))
ts = Timeseries(
Domain(data.domain.attributes + tuple(attrs),
data.domain.class_vars, data.domain.metas),
np.column_stack((data.X, np.column_stack(X))), data.Y, data.metas)
ts.time_variable = data.time_variable
self.send(Output.TIMESERIES, ts)
def moving_transform(data, spec, fixed_wlen=0):
"""
Return data transformed according to spec.
Parameters
----------
data : Timeseries
A table with features to transform.
spec : list of lists
A list of lists [feature:Variable, window_length:int, function:callable].
fixed_wlen : int
If not 0, then window_length in spec is disregarded and this length
is used. Also the windows don't shift by one but instead align
themselves side by side.
Returns
-------
transformed : Timeseries
A table of original data its transformations.
"""
from itertools import chain
from Orange.data import ContinuousVariable, Domain
from orangecontrib.timeseries import Timeseries
from orangecontrib.timeseries.widgets.utils import available_name
from orangecontrib.timeseries.agg_funcs import Cumulative_sum, Cumulative_product
X = []
attrs = []
for var, wlen, func in spec:
col = np.ravel(data[:, var])
if fixed_wlen:
wlen = fixed_wlen
if func in (Cumulative_sum, Cumulative_product):
out = list(chain.from_iterable(func(col[i:i + wlen])
for i in range(0, len(col), wlen)))
else:
# In reverse cause lazy brain. Also prefer informative ends, not beginnings as much
col = col[::-1]
out = [func(col[i:i + wlen])
for i in range(0, len(col), wlen if bool(fixed_wlen) else 1)]
out = out[::-1]
X.append(out)
template = '{} ({}; {})'.format(var.name, wlen, func.__name__.lower().replace('_', ' '))
name = available_name(data.domain, template)
attrs.append(ContinuousVariable(name))
dataX, dataY, dataM = data.X, data.Y, data.metas
if fixed_wlen:
n = len(X[0])
dataX = dataX[::-1][::fixed_wlen][:n][::-1]
dataY = dataY[::-1][::fixed_wlen][:n][::-1]
dataM = dataM[::-1][::fixed_wlen][:n][::-1]
ts = Timeseries(Domain(data.domain.attributes + tuple(attrs),
data.domain.class_vars,
data.domain.metas),
np.column_stack(
(dataX, np.column_stack(X))) if X else dataX,
dataY, dataM)
ts.time_variable = data.time_variable
return ts
def seasonal_decompose(data, model='multiplicative', period=12, *, callback=None):
"""
Return table of decomposition components of original features and
original features seasonally adjusted.
Parameters
----------
data : Timeseries
A table of featres to decompose/adjust.
model : str {'additive', 'multiplicative'}
A decompostition model. See:
https://en.wikipedia.org/wiki/Decomposition_of_time_series
period : int
The period length of season.
callback : callable
Optional callback to call (with no parameters) after each iteration.
Returns
-------
table : Timeseries
Table with columns: original series seasonally adjusted, original
series' seasonal components, trend components, and residual components.
"""
from operator import sub, truediv
from Orange.data import Domain, ContinuousVariable
from orangecontrib.timeseries import Timeseries
from orangecontrib.timeseries.widgets.utils import available_name
import statsmodels.api as sm
def _interp_trend(trend):
first = next(i for i, val in enumerate(trend) if val == val)
last = trend.size - 1 - next(
i for i, val in enumerate(trend[::-1]) if val == val)
d = 3
first_last = min(first + d, last)
last_first = max(first, last - d)
k, n = np.linalg.lstsq(
np.column_stack((np.arange(first, first_last), np.ones(first_last - first))),
trend[first:first_last])[0]
trend[:first] = np.arange(0, first) * k + n
k, n = np.linalg.lstsq(
np.column_stack((np.arange(last_first, last), np.ones(last - last_first))),
trend[last_first:last])[0]
trend[last + 1:] = np.arange(last + 1, trend.size) * k + n
return trend
attrs = []
X = []
recomposition = sub if model == 'additive' else truediv
interp_data = data.interp()
for var in data.domain.variables:
decomposed = sm.tsa.seasonal_decompose(np.ravel(interp_data[:, var]),
model=model,
freq=period)
adjusted = recomposition(decomposed.observed,
decomposed.seasonal)
season = decomposed.seasonal
trend = _interp_trend(decomposed.trend)
resid = recomposition(adjusted, trend)
# Re-apply nans
isnan = np.isnan(data[:, var]).ravel()
adjusted[isnan] = np.nan
trend[isnan] = np.nan
resid[isnan] = np.nan
attrs.extend(
ContinuousVariable(
available_name(data.domain,
var.name + ' ({})'.format(transform)))
for transform in
('season. adj.', 'seasonal', 'trend', 'residual')
)
X.extend((adjusted, season, trend, resid))
if callback:
callback()
ts = Timeseries(Domain(attrs), np.column_stack(X))
return ts
def moving_transform(data, spec, fixed_wlen=0):
"""
Return data transformed according to spec.
Parameters
----------
data : Timeseries
A table with features to transform.
spec : list of lists
A list of lists [feature:Variable, window_length:int, function:callable].
fixed_wlen : int
If not 0, then window_length in spec is disregarded and this length
is used. Also the windows don't shift by one but instead align
themselves side by side.
Returns
-------
transformed : Timeseries
A table of original data its transformations.
"""
from itertools import chain
from Orange.data import ContinuousVariable, Domain
from orangecontrib.timeseries import Timeseries
from orangecontrib.timeseries.widgets.utils import available_name
from orangecontrib.timeseries.agg_funcs import Cumulative_sum, Cumulative_product
X = []
attrs = []
for var, wlen, func in spec:
col = np.ravel(data[:, var])
if fixed_wlen:
wlen = fixed_wlen
if func in (Cumulative_sum, Cumulative_product):
out = list(
chain.from_iterable(
func(col[i:i + wlen]) for i in range(0, len(col), wlen)))
else:
# In reverse cause lazy brain. Also prefer informative ends, not beginnings as much
col = col[::-1]
out = [
func(col[i:i + wlen])
for i in range(0, len(col), wlen if bool(fixed_wlen) else 1)
]
out = out[::-1]
X.append(out)
template = '{} ({}; {})'.format(
var.name, wlen,
func.__name__.lower().replace('_', ' '))
name = available_name(data.domain, template)
attrs.append(ContinuousVariable(name))
dataX, dataY, dataM = data.X, data.Y, data.metas
if fixed_wlen:
n = len(X[0])
dataX = dataX[::-1][::fixed_wlen][:n][::-1]
dataY = dataY[::-1][::fixed_wlen][:n][::-1]
dataM = dataM[::-1][::fixed_wlen][:n][::-1]
ts = Timeseries.from_numpy(
Domain(data.domain.attributes + tuple(attrs), data.domain.class_vars,
data.domain.metas),
np.column_stack((dataX, np.column_stack(X))) if X else dataX, dataY,
dataM)
ts.time_variable = data.time_variable
return ts
def seasonal_decompose(data,
model='multiplicative',
period=12,
*,
callback=None):
"""
Return table of decomposition components of original features and
original features seasonally adjusted.
Parameters
----------
data : Timeseries
A table of featres to decompose/adjust.
model : str {'additive', 'multiplicative'}
A decompostition model. See:
https://en.wikipedia.org/wiki/Decomposition_of_time_series
period : int
The period length of season.
callback : callable
Optional callback to call (with no parameters) after each iteration.
Returns
-------
table : Timeseries
Table with columns: original series seasonally adjusted, original
series' seasonal components, trend components, and residual components.
"""
from operator import sub, truediv
from Orange.data import Domain, ContinuousVariable
from orangecontrib.timeseries import Timeseries
from orangecontrib.timeseries.widgets.utils import available_name
import statsmodels.api as sm
def _interp_trend(trend):
first = next(i for i, val in enumerate(trend) if val == val)
last = trend.size - 1 - next(
i for i, val in enumerate(trend[::-1]) if val == val)
d = 3
first_last = min(first + d, last)
last_first = max(first, last - d)
k, n = np.linalg.lstsq(
np.column_stack(
(np.arange(first, first_last), np.ones(first_last - first))),
trend[first:first_last])[0]
trend[:first] = np.arange(0, first) * k + n
k, n = np.linalg.lstsq(
np.column_stack((np.arange(last_first,
last), np.ones(last - last_first))),
trend[last_first:last])[0]
trend[last + 1:] = np.arange(last + 1, trend.size) * k + n
return trend
attrs = []
X = []
recomposition = sub if model == 'additive' else truediv
interp_data = data.interp()
for var in data.domain.variables:
decomposed = sm.tsa.seasonal_decompose(np.ravel(interp_data[:, var]),
model=model,
freq=period)
adjusted = recomposition(decomposed.observed, decomposed.seasonal)
season = decomposed.seasonal
trend = _interp_trend(decomposed.trend)
resid = recomposition(adjusted, trend)
# Re-apply nans
isnan = np.isnan(data[:, var]).ravel()
adjusted[isnan] = np.nan
trend[isnan] = np.nan
resid[isnan] = np.nan
attrs.extend(
ContinuousVariable(
available_name(data.domain, var.name +
' ({})'.format(transform)))
for transform in ('season. adj.', 'seasonal', 'trend', 'residual'))
X.extend((adjusted, season, trend, resid))
if callback:
callback()
ts = Timeseries.from_numpy(Domain(attrs), np.column_stack(X))
return ts
