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

Bugfixes

Browse Source
This commit is contained in:
Petrônio Cândido 2018-04-25 13:03:14 -03:00
parent abe9a45a47
commit a446cec232
2 changed files with 29 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
pyFTS/models/ensemble/ensemble.py
View File

@ -18,7 +18,7 @@ def sampler(data, quantiles):
class EnsembleFTS(fts.FTS): class EnsembleFTS(fts.FTS):
def __init__(self, name, **kwargs): def __init__(self, name, **kwargs):
super(EnsembleFTS, self).__init__(1, "Ensemble FTS") super(EnsembleFTS, self).__init__(1, "Ensemble FTS", **kwargs)
self.shortname = "Ensemble FTS " + name self.shortname = "Ensemble FTS " + name
self.name = "Ensemble FTS" self.name = "Ensemble FTS"
self.flrgs = {} self.flrgs = {}
@ -266,17 +266,17 @@ class AllMethodEnsembleFTS(EnsembleFTS):
ho_methods = [hofts.HighOrderFTS, hwang.HighOrderFTS] ho_methods = [hofts.HighOrderFTS, hwang.HighOrderFTS]
for method in fo_methods: for method in fo_methods:
model = method("") model = method("", partitioner=self.partitioner)
self.set_transformations(model) self.set_transformations(model)
model.train(data, **kwargs) model.fit(data, **kwargs)
self.append_model(model) self.append_model(model)
for method in ho_methods: for method in ho_methods:
for o in np.arange(1, order+1): for o in np.arange(1, order+1):
model = method("") model = method("", partitioner=self.partitioner)
if model.min_order >= o: if model.min_order >= o:
self.set_transformations(model) self.set_transformations(model)
model.train(data, **kwargs) model.fit(data, **kwargs)
self.append_model(model) self.append_model(model)

49
pyFTS/tests/general.py
View File

@ -14,17 +14,22 @@ tdiff = Transformations.Differential(1)
from pyFTS.data import TAIEX from pyFTS.data import TAIEX
dataset = TAIEX.get_data() dataset = TAIEX.get_data()
'''
from pyFTS.partitioners import Grid, Util as pUtil
partitioner = Grid.GridPartitioner(data=dataset[:800], npart=10) #, transformation=tdiff)
'''
from pyFTS.benchmarks import benchmarks as bchmk, Util as bUtil, Measures, knn, quantreg, arima from pyFTS.benchmarks import benchmarks as bchmk, Util as bUtil, Measures, knn, quantreg, arima
'''
from pyFTS.models import pwfts, song, ifts from pyFTS.models import pwfts, song, ifts
from pyFTS.models.ensemble import ensemble
model = arima.ARIMA("", order=(1,0,0)) model = ensemble.AllMethodEnsembleFTS(partitioner=partitioner)
model.fit(dataset[:800]) model.fit(dataset[:800])
tmp = model.predict(dataset[800:1000], type='distribution') tmp = model.predict(dataset[800:1000], type='distribution')
for tmp2 in tmp: for tmp2 in tmp:
print(tmp2) print(tmp2)
'''
''' '''
@ -40,39 +45,33 @@ print(Measures.get_distribution_statistics(dataset[800:1000], model, steps_ahead
# print(tmp2) # print(tmp2)
''' '''
''' #'''
from pyFTS.benchmarks import arima, naive, quantreg from pyFTS.benchmarks import arima, naive, quantreg
bchmk.sliding_window_benchmarks(dataset, 1000, train=0.8, inc=0.2, bchmk.sliding_window_benchmarks(dataset, 1000, train=0.8, inc=0.2,
methods=[ifts.IntervalFTS], #[pwfts.ProbabilisticWeightedFTS], #methods=[ifts.IntervalFTS], #[pwfts.ProbabilisticWeightedFTS],
benchmark_models=True, benchmark_models=False,
benchmark_methods=[arima.ARIMA for k in range(8)] benchmark_methods=[arima.ARIMA for k in range(4)]
+ [quantreg.QuantileRegression for k in range(4)], + [quantreg.QuantileRegression for k in range(2)],
benchmark_methods_parameters=[ benchmark_methods_parameters=[
{'order': (1, 0, 0), 'alpha': .05}, {'order': (1, 0, 0)},
{'order': (1, 0, 0), 'alpha': .25}, {'order': (1, 0, 1)},
{'order': (1, 0, 1), 'alpha': .05}, {'order': (2, 0, 1)},
{'order': (1, 0, 1), 'alpha': .25}, {'order': (2, 0, 2)},
{'order': (2, 0, 1), 'alpha': .05}, {'order': 1, 'dist': True},
{'order': (2, 0, 1), 'alpha': .25}, {'order': 2, 'dist': True},
{'order': (2, 0, 2), 'alpha': .05},
{'order': (2, 0, 2), 'alpha': .25},
{'order': 1, 'alpha': .05},
{'order': 1, 'alpha': .25},
{'order': 2, 'alpha': .05},
{'order': 2, 'alpha': .25},
], ],
transformations=[None, tdiff], #transformations=[None, tdiff],
orders=[1], #2, 3], orders=[1, 2, 3],
partitions=[3], #np.arange(3, 25, 2), partitions=np.arange(30, 80, 5),
progress=False, type='interval', progress=False, type='distribution',
#steps_ahead=[1,4,7,10], #steps_ahead=[1] #steps_ahead=[1,4,7,10], #steps_ahead=[1]
distributed=True, nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'], distributed=True, nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'],
file="benchmarks.db", dataset="TAIEX", tag="comparisons") file="benchmarks.db", dataset="TAIEX", tag="comparisons")
''' #'''
''' '''
dat = pd.read_csv('pwfts_taiex_partitioning.csv', sep=';') dat = pd.read_csv('pwfts_taiex_partitioning.csv', sep=';')
print(bUtil.analytic_tabular_dataframe(dat)) print(bUtil.analytic_tabular_dataframe(dat))