def commit(self):
self.Error.seasonal_decompose_fail.clear()
data = self.data
if not data or not self.selected:
self.Outputs.time_series.send(data)
return
selected_subset = Timeseries(
Domain(self.selected, source=data.domain),
data) # FIXME: might not pass selected interpolation method
with self.progressBar(len(self.selected)) as progress:
try:
adjusted_data = seasonal_decompose(
selected_subset,
self.DECOMPOSITION_MODELS[self.decomposition],
self.n_periods,
callback=lambda *_: progress.advance())
except ValueError as ex:
self.Error.seasonal_decompose_fail(str(ex))
adjusted_data = None
if adjusted_data is not None:
ts = Timeseries(Timeseries.concatenate((data, adjusted_data)))
ts.time_variable = data.time_variable
else:
ts = None
self.Outputs.time_series.send(ts)
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(
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 finance_data(symbol, since=None, until=None, granularity='d'):
"""Fetch Yahoo Finance data for stock or index `symbol` within the period
after `since` and before `until` (both inclusive).
Parameters
----------
symbol: str
A stock or index symbol, as supported by Yahoo Finance.
since: date
A start date (default: 1900-01-01).
until: date
An end date (default: today).
granularity: 'd' or 'w' or 'm' or 'v'
What data to get: daily, weekly, monthly, or dividends.
Returns
-------
data : Timeseries
"""
if since is None:
since = date(1900, 1, 1)
if until is None:
until = date.today()
YAHOO_URL = (
'http://chart.finance.yahoo.com/table.csv?'
's={SYMBOL}&d={TO_MONTH}&e={TO_DAY}&f={TO_YEAR}&'
'g={GRANULARITY}&a={FROM_MONTH}&b={FROM_DAY}&c={FROM_YEAR}&ignore=.csv'
)
url = YAHOO_URL.format(SYMBOL=symbol,
GRANULARITY=granularity,
TO_MONTH=until.month - 1,
TO_DAY=until.day,
TO_YEAR=until.year,
FROM_MONTH=since.month - 1,
FROM_DAY=since.day,
FROM_YEAR=since.year)
data = Timeseries.from_url(url)[::-1]
# Make Adjusted Close a class variable
attrs = [var.name for var in data.domain.attributes]
attrs.remove('Adj Close')
data = Timeseries(
Domain(attrs, [data.domain['Adj Close']], None, source=data.domain),
data)
data.name = symbol
data.time_variable = data.domain['Date']
return data
def finance_data(symbol,
since=None,
until=None,
granularity='d'):
"""Fetch Yahoo Finance data for stock or index `symbol` within the period
after `since` and before `until` (both inclusive).
Parameters
----------
symbol: str
A stock or index symbol, as supported by Yahoo Finance.
since: date
A start date (default: 1900-01-01).
until: date
An end date (default: today).
granularity: 'd' or 'w' or 'm' or 'v'
What data to get: daily, weekly, monthly, or dividends.
Returns
-------
data : Timeseries
"""
if since is None:
since = date(1900, 1, 1)
if until is None:
until = date.today()
YAHOO_URL = ('http://chart.finance.yahoo.com/table.csv?'
's={SYMBOL}&d={TO_MONTH}&e={TO_DAY}&f={TO_YEAR}&'
'g={GRANULARITY}&a={FROM_MONTH}&b={FROM_DAY}&c={FROM_YEAR}&ignore=.csv')
url = YAHOO_URL.format(SYMBOL=symbol,
GRANULARITY=granularity,
TO_MONTH=until.month - 1,
TO_DAY=until.day,
TO_YEAR=until.year,
FROM_MONTH=since.month - 1,
FROM_DAY=since.day,
FROM_YEAR=since.year)
data = Timeseries.from_url(url)[::-1]
# Make Adjusted Close a class variable
attrs = [var.name for var in data.domain.attributes]
attrs.remove('Adj Close')
data = Timeseries(Domain(attrs, [data.domain['Adj Close']], None, source=data.domain), data)
data.name = symbol
data.time_variable = data.domain['Date']
return data
def commit(self):
data = self.data
if not data or not self.selected:
self.send(Output.TIMESERIES, data)
return
selected_subset = Timeseries(Domain(self.selected, source=data.domain), data) # FIXME: might not pass selected interpolation method
with self.progressBar(len(self.selected)) as progress:
adjusted_data = seasonal_decompose(
selected_subset,
self.DECOMPOSITION_MODELS[self.decomposition],
self.n_periods,
callback=lambda *_: progress.advance())
ts = Timeseries(Timeseries.concatenate((data, adjusted_data)))
ts.time_variable = data.time_variable
self.send(Output.TIMESERIES, ts)
def commit(self):
data = self.data
self.Error.clear()
if data is None or (self.selected_attr not in data.domain
and not self.radio_sequential):
self.Outputs.time_series.send(None)
return
attrs = data.domain.attributes
cvars = data.domain.class_vars
metas = data.domain.metas
X = data.X
Y = np.column_stack((data.Y, )) # make 2d
M = data.metas
# Set sequence attribute
if self.radio_sequential:
for i in chain(('', ), range(10)):
name = '__seq__' + str(i)
if name not in data.domain:
break
time_var = ContinuousVariable(name)
attrs = attrs.__class__((time_var, )) + attrs
X = np.column_stack((np.arange(1, len(data) + 1), X))
data = Table(Domain(attrs, cvars, metas), X, Y, M)
else:
# Or make a sequence attribute one of the existing attributes
# and sort all values according to it
time_var = data.domain[self.selected_attr]
values = Table.from_table(Domain([], [], [time_var]),
source=data).metas.ravel()
if np.isnan(values).any():
self.Error.nan_times(time_var.name)
self.Outputs.time_series.send(None)
return
ordered = np.argsort(values)
if (ordered != np.arange(len(ordered))).any():
data = data[ordered]
ts = Timeseries(data.domain, data)
# TODO: ensure equidistant
ts.time_variable = time_var
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
self.Error.clear()
if data is None or (self.selected_attr not in data.domain and not self.radio_sequential):
self.Outputs.time_series.send(None)
return
attrs = data.domain.attributes
cvars = data.domain.class_vars
metas = data.domain.metas
X = data.X
Y = np.column_stack((data.Y,)) # make 2d
M = data.metas
# Set sequence attribute
if self.radio_sequential:
for i in chain(('',), range(10)):
name = '__seq__' + str(i)
if name not in data.domain:
break
time_var = ContinuousVariable(name)
attrs = attrs.__class__((time_var,)) + attrs
X = np.column_stack((np.arange(1, len(data) + 1), X))
data = Table(Domain(attrs, cvars, metas), X, Y, M)
else:
# Or make a sequence attribute one of the existing attributes
# and sort all values according to it
time_var = data.domain[self.selected_attr]
values = Table.from_table(Domain([], [], [time_var]),
source=data).metas.ravel()
if np.isnan(values).any():
self.Error.nan_times(time_var.name)
self.Outputs.time_series.send(None)
return
ordered = np.argsort(values)
if (ordered != np.arange(len(ordered))).any():
data = data[ordered]
ts = Timeseries(data.domain, data)
# TODO: ensure equidistant
ts.time_variable = time_var
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 finance_data(symbol,
since=None,
until=None,
granularity='d'):
"""Fetch Yahoo Finance data for stock or index `symbol` within the period
after `since` and before `until` (both inclusive).
Parameters
----------
symbol: str
A stock or index symbol, as supported by Yahoo Finance.
since: date
A start date (default: 1900-01-01).
until: date
An end date (default: today).
granularity: 'd' or 'w' or 'm' or 'v'
What data to get: daily, weekly, monthly, or dividends.
Returns
-------
data : Timeseries
"""
if since is None:
since = date(1900, 1, 1)
if until is None:
until = date.today()
f = web.DataReader(symbol, 'yahoo', since, until)
data = Timeseries(table_from_frame(f))
# Make Adjusted Close a class variable
attrs = [var.name for var in data.domain.attributes]
attrs.remove('Adj Close')
data = Timeseries(Domain(attrs, [data.domain['Adj Close']], None, source=data.domain), data)
data.name = symbol
data.time_variable = data.domain['Date']
return data
def finance_data(symbol, since=None, until=None, granularity='d'):
"""Fetch Yahoo Finance data for stock or index `symbol` within the period
after `since` and before `until` (both inclusive).
Parameters
----------
symbol: str
A stock or index symbol, as supported by Yahoo Finance.
since: date
A start date (default: 1900-01-01).
until: date
An end date (default: today).
granularity: 'd' or 'w' or 'm' or 'v'
What data to get: daily, weekly, monthly, or dividends.
Returns
-------
data : Timeseries
"""
if since is None:
since = date(1900, 1, 1)
if until is None:
until = date.today()
f = web.DataReader(symbol, 'yahoo', since, until)
data = Timeseries(table_from_frame(f))
# Make Adjusted Close a class variable
attrs = [var.name for var in data.domain.attributes]
attrs.remove('Adj Close')
data = Timeseries(
Domain(attrs, [data.domain['Adj Close']], None, source=data.domain),
data)
data.name = symbol
data.time_variable = data.domain['Date']
return data
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 test_create_time_variable(self):
table = Table("iris")
time_series = Timeseries(table)
id_1 = id(time_series.attributes)
time_series.time_variable = time_series.domain.attributes[0]
self.assertNotEqual(id_1, id(time_series.attributes))
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
