Small bugfix in pwfts and hofts

pyFTS/common/flrg.py

@@ -37,9 +37,13 @@ class FLRG(object):
             self.key = ""
 
             for n in names:
+                try:
                     if len(self.key) > 0:
                         self.key += ","
-                self.key = self.key + n
+                    self.key += n
+                except Exception as ex:
+                    print(self.key, n)
+                    raise ex
         return self.key
 
     def get_membership(self, data, sets):

pyFTS/models/hofts.py

@@ -23,6 +23,10 @@ class HighOrderFLRG(flrg.FLRG):
             self.RHS[c] = c
 
     def append_lhs(self, c):
+        if isinstance(c,(tuple,list)):
+            for k in c:
+                self.LHS.append(k)
+        else:
             self.LHS.append(c)
 
     def __str__(self):

pyFTS/models/pwfts.py

@@ -616,7 +616,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
         ret.append(dist)
 
         for k in np.arange(start + self.max_lag, steps + start + self.max_lag):
-            dist = self.forescast_distribution_from_distribution(ret[k-self.max_lag:], smooth, uod, _bins, **kwargs)
+            dist = self.forecast_distribution_from_distribution(ret[k-self.max_lag:], smooth, uod, _bins, **kwargs)
             ret.append(dist)
 
         return ret[-steps:]

pyFTS/partitioners/partitioner.py

@@ -142,7 +142,7 @@ class Partitioner(object):
         :returns a list with the fuzzyfied values, depending on the mode
         """
 
-        if isinstance(data, (list, np.ndarray)):
+        if isinstance(data, (tuple, list, np.ndarray)):
             ret = []
             for inst in data:
                 mv = self.fuzzyfy(inst, **kwargs)

pyFTS/tests/general.py

@@ -19,6 +19,32 @@ from pyFTS.fcm import fts, common, GA
 
 from pyFTS.data import TAIEX, NASDAQ, SP500
 
+from pyFTS.data import TAIEX, NASDAQ, SP500
+from pyFTS.common import Util
+
+train = TAIEX.get_data()[1000:1800]
+test = TAIEX.get_data()[1800:2000]
+
+from pyFTS.models import pwfts
+from pyFTS.partitioners import Grid
+
+fs = Grid.GridPartitioner(data=train, npart=45)
+
+model = pwfts.ProbabilisticWeightedFTS(partitioner=fs, order=1)
+model.fit(train)
+
+forecasts = model.predict(test[9:20], type='point')
+intervals = model.predict(test[9:20], type='interval')
+distributions = model.predict(test[9:20], type='distribution')
+
+
+horizon = 10
+
+forecasts = model.predict(test[9:20], type='point', steps_ahead=horizon)
+intervals = model.predict(test[9:20], type='interval', steps_ahead=horizon)
+distributions = model.predict(test[9:20], type='distribution', steps_ahead=horizon)
+
+
 '''
 train = TAIEX.get_data()[:800]
 test = TAIEX.get_data()[800:1000]
@@ -45,115 +71,3 @@ Util.plot_distribution2(distributions, test[:10], start_at=model.order, ax=ax, c
 
 print("")
 '''
-
-from pyFTS.data import SONDA, Malaysia
-
-
-def sample_by_hour(data):
-  return [np.nanmean(data[k:k+60]) for k in np.arange(0,len(data),60)]
-
-
-datasets = {}
-
-
-sonda = SONDA.get_dataframe()[['datahora','glo_avg','ws_10m']]
-
-sonda = sonda.drop(sonda.index[np.where(sonda["ws_10m"] <= 0.01)])
-sonda = sonda.drop(sonda.index[np.where(sonda["glo_avg"] <= 0.01)])
-sonda = sonda.dropna()
-
-
-malaysia = Malaysia.get_dataframe()
-
-datasets['SONDA.ws_10m'] = sample_by_hour(sonda["ws_10m"].values)
-datasets['SONDA.glo_avg'] = sample_by_hour(sonda["glo_avg"].values)
-datasets['Malaysia.temperature'] = malaysia["temperature"].values
-datasets['Malaysia.load'] = malaysia["load"].values
-
-
-#'''
-for dataset_name, dataset in datasets.items():
-    bchmk.sliding_window_benchmarks2(dataset, 10000, train=0.9, inc=0.25,
-                                     methods=[hofts.HighOrderFTS, hofts.WeightedHighOrderFTS, pwfts.ProbabilisticWeightedFTS],
-                                     benchmark_models=False,
-                                     transformations=[None],
-                                     orders=[2],
-                                     partitions=[50],
-                                     progress=False, type='point',
-                                     distributed=True, nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'],
-                                     file="experiments.db", dataset=dataset_name,
-                                     tag="experiments")
-
-for dataset_name, dataset in datasets.items():
-    bchmk.sliding_window_benchmarks2(dataset, 10000, train=0.9, inc=0.25,
-                                     methods=[ensemble.SimpleEnsembleFTS, ifts.IntervalFTS,
-                                              ifts.WeightedIntervalFTS, pwfts.ProbabilisticWeightedFTS],
-                                     methods_parameters=[{'partitions': [45, 50, 55], 'alpha':.05},
-                                                         {},{},{}],
-                                     benchmark_models=False,
-                                     transformations=[None],
-                                     orders=[2],
-                                     partitions=[50],
-                                     progress=False, type='interval',
-                                     distributed=True, nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'],
-                                     file="experiments.db", dataset=dataset_name,
-                                     tag="experiments")
-
-for dataset_name, dataset in datasets.items():
-    bchmk.sliding_window_benchmarks2(dataset, 10000, train=0.9, inc=0.25,
-                                     methods=[ensemble.SimpleEnsembleFTS, pwfts.ProbabilisticWeightedFTS],
-                                     methods_parameters=[{'partitions':[45,50,55]}, {}],
-                                     benchmark_models=False,
-                                     transformations=[None],
-                                     orders=[2],
-                                     partitions=[50],
-                                     progress=False, type='distribution',
-                                     distributed=True, nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'],
-                                     file="experiments.db", dataset=dataset_name,
-                                     tag="experiments")
-
-'''
-
-competitor_methods = []
-competitor_methods.extend([arima.ARIMA]*3)
-competitor_methods.extend([quantreg.QuantileRegression]*2)
-competitor_methods.extend([BSTS.ARIMA]*3)
-competitor_methods.extend([knn.KNearestNeighbors]*2)
-
-competitor_methods_parameters = [
-    {'order': (1, 0, 0)},
-    {'order': (1, 0, 1)},
-    {'order': (2, 0, 0)},
-    {'order': 1, 'alpha': .5},
-    {'order': 2, 'alpha': .5},
-    {'order': (1, 0, 0)},
-    {'order': (1, 0, 1)},
-    {'order': (2, 0, 0)},
-    {'order': 1},
-    {'order': 2}
-]
-
-proposed_methods = [
-    hofts.HighOrderFTS, hofts.WeightedHighOrderFTS, pwfts.ProbabilisticWeightedFTS
-]
-proposed_methods_parameters=[
-    {},{},{}
-]
-
-for dataset_name, dataset in datasets.items():
-    bchmk.sliding_window_benchmarks2(dataset, 1000, train=0.8, inc=0.2,
-                                     benchmark_models=True,
-                                     benchmark_methods=competitor_methods,
-                                     benchmark_methods_parameters=competitor_methods_parameters,
-                                     methods=proposed_methods,
-                                     methods_parameters=proposed_methods_parameters,
-                                    orders=[1],
-                                    partitions=[35],
-                                    steps_ahead=[10],
-                                    progress=False, type='point',
-                                    distributed=True, nodes=['192.168.0.110', '192.168.0.107','192.168.0.106'],
-                                    file="experiments.db", dataset=dataset_name,
-                                    tag="experiments")
-
-
-'''