sam/pyFTS
1
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects Releases Wiki Activity

Improvements and bugfixes on pwfts.forecast_interval and pwfts.point_expected_value

Browse Source
This commit is contained in:
Petrônio Cândido 2018-04-11 00:19:05 -03:00
parent 24c4fadc08
commit 581f404b18
4 changed files with 60 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pyFTS/benchmarks/benchmarks.py
View File

@ -16,6 +16,7 @@ import numpy as np
from mpl_toolkits.mplot3d import Axes3D
from pyFTS.probabilistic import ProbabilityDistribution
from pyFTS.common import Transformations
from pyFTS.models import song, chen, yu, ismailefendi, sadaei, hofts, pwfts, ifts, cheng, hwang
from pyFTS.models.ensemble import ensemble
from pyFTS.benchmarks import Measures, naive, arima, ResidualAnalysis, quantreg
@ -833,10 +834,6 @@ def plot_density_rectange(ax, cmap, density, fig, resolution, time_from, time_to
cb.set_label('Density')
from pyFTS.common import Transformations
def plot_distribution(ax, cmap, probabilitydist, fig, time_from, reference_data=None):
from matplotlib.patches import Rectangle
from matplotlib.collections import PatchCollection

43
pyFTS/models/pwfts.py
View File

@ -257,6 +257,16 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
return ret
def forecast(self, data, **kwargs):
method = kwargs.get('method','heuristic')
if method == 'heuristic':
return self.point_heuristic(data, **kwargs)
elif method == 'expected_value':
return self.point_expected_value(data, **kwargs)
else:
raise Exception("Unknown point forecasting method!")
def point_heuristic(self, data, **kwargs):
ndata = np.array(self.apply_transformations(data))
@ -292,10 +302,26 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
return ret
def point_expected_value(self, data, **kwargs):
l = len(data)
ret = []
for k in np.arange(self.order - 1, l):
sample = data[k - (self.order - 1): k + 1]
tmp = self.forecast_distribution(sample)[0].expected_value()
ret.append(tmp)
ret = self.apply_inverse_transformations(ret, params=[data[self.order - 1:]])
return ret
def forecast_interval(self, data, **kwargs):
if 'method' in kwargs:
self.interval_method = kwargs.get('method','quantile')
self.interval_method = kwargs.get('method','heuristic')
if 'alpha' in kwargs:
self.alpha = kwargs.get('alpha', 0.05)
@ -308,8 +334,8 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
for k in np.arange(self.order - 1, l):
if self.interval_method == 'extremum':
self.interval_extremum(k, ndata, ret)
if self.interval_method == 'heuristic':
self.interval_heuristic(k, ndata, ret)
else:
self.interval_quantile(k, ndata, ret)
@ -321,9 +347,9 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
dist = self.forecast_distribution(ndata)
lo_qt = dist[0].quantile(self.alpha)
up_qt = dist[0].quantile(1.0 - self.alpha)
ret.append_rhs([lo_qt, up_qt])
ret.append([lo_qt, up_qt])
def interval_extremum(self, k, ndata, ret):
def interval_heuristic(self, k, ndata, ret):
sample = ndata[k - (self.order - 1): k + 1]
@ -335,7 +361,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
for flrg in flrgs:
norm = self.flrg_lhs_conditional_probability(sample, flrg)
if norm == 0:
norm = self.flrg_lhs_unconditional_probability(flrg) # * 0.001
norm = self.flrg_lhs_unconditional_probability(flrg)
up.append(norm * self.get_upper(flrg))
lo.append(norm * self.get_lower(flrg))
norms.append(norm)
@ -349,7 +375,6 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
up_ = sum(up) / norm
ret.append([lo_, up_])
def forecast_distribution(self, data, **kwargs):
if not isinstance(data, (list, set, np.ndarray)):
@ -425,8 +450,8 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
1] >= self.original_max):
ret.append(ret[-1])
else:
lower = self.forecast_interval([ret[x][0] for x in np.arange(k - self.order, k)])
upper = self.forecast_interval([ret[x][1] for x in np.arange(k - self.order, k)])
lower = self.forecast_interval([ret[x][0] for x in np.arange(k - self.order, k)], **kwargs)
upper = self.forecast_interval([ret[x][1] for x in np.arange(k - self.order, k)], **kwargs)
ret.append([np.min(lower), np.max(upper)])

5
pyFTS/probabilistic/ProbabilityDistribution.py
View File

@ -95,6 +95,9 @@ class ProbabilityDistribution(object):
return ret
def expected_value(self):
return np.nansum([v * self.distribution[v] for v in self.bins])
def build_cdf_qtl(self):
ret = 0.0
self.cdf = {}
@ -137,7 +140,7 @@ class ProbabilityDistribution(object):
ret.append(self.qtl[str(k)][0])
else:
k = self.quantile_index.find_ge(values)
ret = self.qtl[str(k)[0]]
ret = self.qtl[str(k)]
return ret

21
pyFTS/tests/general.py
View File

@ -9,6 +9,8 @@ import matplotlib.pylab as plt
import pandas as pd
from pyFTS.common import Transformations
tdiff = Transformations.Differential(1)
from pyFTS.data import TAIEX
dataset = TAIEX.get_data()
@ -30,17 +32,28 @@ test_length = 200
from pyFTS.partitioners import Grid, Util as pUtil
partitioner = Grid.GridPartitioner(data=dataset[:train_split], npart=30)
#partitioner = Grid.GridPartitioner(data=dataset[:train_split], npart=10, transformation=tdiff)
from pyFTS.common import fts,tree
from pyFTS.models import hofts, pwfts
pfts1_taiex = pwfts.ProbabilisticWeightedFTS("1", partitioner=partitioner)
#pfts1_taiex.append_transformation(tdiff)
pfts1_taiex.fit(dataset[:train_split], save_model=True, file_path='pwfts')
pfts1_taiex.shortname = "1st Order"
print(pfts1_taiex)
tmp = pfts1_taiex.predict(dataset[train_split:train_split+200], type='distribution', steps_ahead=20)
tmp = pfts1_taiex.predict(dataset[train_split:train_split+200], type='interval',
method='quantile', alpha=.05, steps_ahead=10)
'''
tmp = pfts1_taiex.predict(dataset[train_split:train_split+200], type='diPedro Pazzini
stribution', steps_ahead=20)
f, ax = plt.subplots(3, 4, figsize=[20,15])
tmp[0].plot(ax[0][0], title='t=1')
tmp[2].plot(ax[0][1], title='t=20')
@ -53,3 +66,9 @@ tmp[14].plot(ax[1][3], title='t=140')
tmp[16].plot(ax[2][0], title='t=160')
tmp[18].plot(ax[2][1], title='t=180')
tmp[20].plot(ax[2][2], title='t=200')
f, ax = plt.subplots(1, 1, figsize=[20,15])
bchmk.plot_distribution(ax, 'blue', tmp, f, 0, reference_data=dataset[train_split:train_split+200])
'''