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

Enabling 'standard_horizon' parameter in PWFTS model

Browse Source
This commit is contained in:
Petrônio Cândido 2021-01-15 10:16:12 -03:00
parent cb71bee2bc
commit ad6d82825e
3 changed files with 12 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
pyFTS/models/hofts.py
View File

@ -166,7 +166,7 @@ class HighOrderFTS(fts.FTS):
sample = data[k - self.max_lag: k] sample = data[k - self.max_lag: k]
rhs = self.partitioner.fuzzyfy(data[k+_tmp_steps], mode="sets", alpha_cut=self.alpha_cut) rhs = self.partitioner.fuzzyfy(data[k + _tmp_steps], mode="sets", alpha_cut=self.alpha_cut)
flrgs = self.generate_lhs_flrg(sample) flrgs = self.generate_lhs_flrg(sample)
@ -181,12 +181,12 @@ class HighOrderFTS(fts.FTS):
def generate_flrg_fuzzyfied(self, data): def generate_flrg_fuzzyfied(self, data):
_tmp_steps = self.standard_horizon - 1 _tmp_steps = self.standard_horizon - 1
l = len(data) l = len(data)
for k in np.arange(self.max_lag, l): for k in np.arange(self.max_lag, l - _tmp_steps):
if self.dump: print("FLR: " + str(k)) if self.dump: print("FLR: " + str(k))
sample = data[k - self.max_lag: k] sample = data[k - self.max_lag: k]
rhs = data[k+_tmp_steps] rhs = data[k + _tmp_steps]
flrgs = self.generate_lhs_flrg_fuzzyfied(sample) flrgs = self.generate_lhs_flrg_fuzzyfied(sample)

12
pyFTS/models/pwfts.py
View File

@ -137,8 +137,9 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
self.generate_flrg_fuzzyfied(fuzz) self.generate_flrg_fuzzyfied(fuzz)
def generate_flrg_fuzzyfied(self, data): def generate_flrg_fuzzyfied(self, data):
_tmp_steps = self.standard_horizon - 1
l = len(data) l = len(data)
for k in np.arange(self.max_lag, l): for k in np.arange(self.max_lag, l - _tmp_steps):
sample = data[k - self.max_lag: k] sample = data[k - self.max_lag: k]
set_sample = [] set_sample = []
for instance in sample: for instance in sample:
@ -154,8 +155,8 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
lhs_mv = self.pwflrg_lhs_memberhip_fuzzyfied(flrg, sample) lhs_mv = self.pwflrg_lhs_memberhip_fuzzyfied(flrg, sample)
mvs = [] mvs = []
inst = data[k] rhs = data[k + _tmp_steps]
for set, mv in inst: for set, mv in rhs:
self.flrgs[flrg.get_key()].append_rhs(set, count=lhs_mv * mv) self.flrgs[flrg.get_key()].append_rhs(set, count=lhs_mv * mv)
mvs.append(mv) mvs.append(mv)
@ -203,8 +204,9 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
return flrgs return flrgs
def generate_flrg(self, data): def generate_flrg(self, data):
_tmp_steps = self.standard_horizon - 1
l = len(data) l = len(data)
for k in np.arange(self.max_lag, l): for k in np.arange(self.max_lag, l - _tmp_steps):
if self.dump: print("FLR: " + str(k)) if self.dump: print("FLR: " + str(k))
sample = data[k - self.max_lag: k] sample = data[k - self.max_lag: k]
@ -218,7 +220,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
if flrg.get_key() not in self.flrgs: if flrg.get_key() not in self.flrgs:
self.flrgs[flrg.get_key()] = flrg; self.flrgs[flrg.get_key()] = flrg;
fuzzyfied = self.partitioner.fuzzyfy(data[k], mode='both', method='fuzzy', fuzzyfied = self.partitioner.fuzzyfy(data[k+_tmp_steps], mode='both', method='fuzzy',
alpha_cut=self.alpha_cut) alpha_cut=self.alpha_cut)
mvs = [] mvs = []

4
pyFTS/tests/general.py
View File

@ -38,8 +38,8 @@ l = len(dados)
particionador = Grid.GridPartitioner(data = dados, npart = 10, func = Membership.trimf) particionador = Grid.GridPartitioner(data = dados, npart = 10, func = Membership.trimf)
modelo = pwfts.ProbabilisticWeightedFTS(partitioner = particionador, order = 1) modelo = pwfts.ProbabilisticWeightedFTS(partitioner = particionador, order = 1, standard_horizon=3)
#modelo = hofts.WeightedHighOrderFTS(partitioner = particionador, order = 1, standard_horizon=1, lags=[2]) #modelo = hofts.WeightedHighOrderFTS(partitioner = particionador, order = 1, standard_horizon=2)
#modelo = chen.ConventionalFTS(partitioner = particionador, standard_horizon=3) #modelo = chen.ConventionalFTS(partitioner = particionador, standard_horizon=3)
modelo.fit(dados) modelo.fit(dados)