Appending margin, upper_margin and lower_margin parameters to Partitioner class.

pyFTS/partitioners/partitioner.py

@@ -35,6 +35,12 @@ class Partitioner(object):
         """A ordered list of the fuzzy sets names, sorted by their middle point"""
         self.kdtree = None
         """A spatial index to help in fuzzyfication"""
+        self.margin  = kwargs.get("margin", 0.1)
+        """The upper and lower exceeding margins for the known UoD. The default value is .1"""
+        self.lower_margin = kwargs.get("lower_margin", self.margin)
+        """Specific lower exceeding margins for the known UoD. The default value is the self.margin parameter"""
+        self.upper_margin = kwargs.get("lower_margin", self.margin)
+        """Specific upper exceeding margins for the known UoD. The default value is the self.margin parameter"""
 
         if kwargs.get('preprocess',True):
 
@@ -58,10 +64,10 @@ class Partitioner(object):
                 ndata[ndata == -np.inf] = 0
                 _min = np.nanmin(ndata)
 
-            self.min = float(_min * 1.1 if _min < 0 else _min * 0.9)
+            self.min = float(_min * (1 + self.lower_margin) if _min < 0 else _min * (1 - self.lower_margin))
 
             _max = np.nanmax(ndata)
-            self.max = float(_max * 1.1 if _max > 0 else _max * 0.9)
+            self.max = float(_max * (1 + self.upper_margin) if _max > 0 else _max * (1 - self.upper_margin))
 
             self.sets = self.build(ndata)
 

pyFTS/tests/nonstationary.py

@@ -19,46 +19,37 @@ test_length = 200
 
 from pyFTS.common import Transformations
 
-
+from pyFTS.benchmarks import naive
-from pyFTS.partitioners import Grid, Util as pUtil
-from pyFTS.benchmarks import benchmarks as bchmk
-from pyFTS.models import chen, hofts, pwfts, hwang
 from pyFTS.models.incremental import TimeVariant, IncrementalEnsemble
+from pyFTS.models.nonstationary import common, perturbation, partitioners as nspart
+from pyFTS.models.nonstationary import nsfts, util as nsUtil
+from pyFTS.partitioners import Grid
+from pyFTS.models import hofts, pwfts
+from pyFTS.benchmarks import Measures
+from pyFTS.common import Transformations, Util as cUtil
+
+diff = Transformations.Differential(lag=1)
 
 train = dataset[:1000]
 test = dataset[1000:]
 
-window = 100
+#grid = Grid.GridPartitioner(data=train, transformation=diff)
+#model = pwfts.ProbabilisticWeightedFTS(partitioner=grid)
+#model.append_transformation(diff)
 
-batch = 10
+model = naive.Naive()
 
-num_models = 3
+model.fit(train)
 
-model1 = TimeVariant.Retrainer(partitioner_method=Grid.GridPartitioner, partitioner_params={'npart': 35},
+for ct, ttrain, ttest in cUtil.sliding_window(test, 1000, .95, inc=.5):
-                               fts_method=pwfts.ProbabilisticWeightedFTS, fts_params={}, order=1,
+  if model.shortname not in ('PWFTS','Naive'):
-                               batch_size=batch, window_length=window * num_models)
+    model.predict(ttrain)
-
+  print(ttest)
-model2 = IncrementalEnsemble.IncrementalEnsembleFTS(partitioner_method=Grid.GridPartitioner,
+  if len(ttest) > 0:
-                                                    partitioner_params={'npart': 35},
+    forecasts = model.predict(ttest, steps_ahead=10)
-                                                    fts_method=pwfts.ProbabilisticWeightedFTS, fts_params={}, order=1,
+    measures = Measures.get_point_ahead_statistics(ttest[1:11], forecasts)
-                                                    batch_size=int(batch / 3), window_length=window,
-                                                    num_models=num_models)
-
-model1.fit(train)
-model2.fit(train)
-
-print(len(test))
-'''
-forecasts1 = model1.predict(test[:-10])
-print(len(forecasts1))
-forecasts1 = model1.predict(test[-10:], steps_ahead=10)
-print(len(forecasts1))
-'''
-forecasts2 = model2.predict(test[:-10])
-print(len(forecasts2))
-forecasts2 = model2.predict(test[-10:], steps_ahead=10)
-print(len(forecasts2))
 
+  print(measures)
 
 '''
 from pyFTS.models.nonstationary import partitioners as nspart, nsfts, honsfts