- FLRG improvements and refactorings on affected classes

pyFTS/chen.py

@@ -29,8 +29,6 @@ class ConventionalFLRG(flrg.FLRG):
         return tmp + tmp2
 
 
-
-
 class ConventionalFTS(fts.FTS):
     """Conventional Fuzzy Time Series"""
     def __init__(self, name, **kwargs):
@@ -74,9 +72,8 @@ class ConventionalFTS(fts.FTS):
                 ret.append(actual.centroid)
             else:
                 flrg = self.flrgs[actual.name]
-                mp = self.getMidpoints(flrg)
 
-                ret.append(sum(mp) / len(mp))
+                ret.append(flrg.get_midpoint())
 
         ret = self.doInverseTransformations(ret, params=[data[self.order - 1:]])
 

pyFTS/flrg.py

@@ -1,3 +1,4 @@
+import numpy as np
 
 
 class FLRG(object):
@@ -10,6 +11,33 @@ class FLRG(object):
         self.lower = None
         self.upper = None
 
+    def get_midpoint(self):
+        if self.midpoint is None:
+            self.midpoint = sum(self.get_midpoints())/len(self.RHS)
+        return self.midpoint
+
+    def get_midpoints(self):
+        if isinstance(self.RHS, list):
+            return np.array([s.centroid for s in self.RHS])
+        elif isinstance(self.RHS, dict):
+            return np.array([self.RHS[s].centroid for s in self.RHS.keys()])
+
+    def get_lower(self):
+        if self.lower is None:
+            if isinstance(self.RHS, list):
+                self.lower = min([rhs.lower for rhs in self.RHS])
+            elif isinstance(self.RHS, dict):
+                self.lower = min([self.RHS[s].lower for s in self.RHS.keys()])
+        return self.lower
+
+    def get_upper(self, t):
+        if self.upper is None:
+            if isinstance(self.RHS, list):
+                self.upper = max([rhs.upper for rhs in self.RHS])
+            elif isinstance(self.RHS, dict):
+                self.upper = max([self.RHS[s].upper for s in self.RHS.keys()])
+        return self.upper
+
     def __len__(self):
         return len(self.RHS)
 

pyFTS/fts.py

@@ -132,10 +132,6 @@ class FTS(object):
         """
         pass
 
-    def getMidpoints(self, flrg):
-        ret = np.array([s.centroid for s in flrg.RHS])
-        return ret
-
     def appendTransformation(self, transformation):
         if transformation is not None:
             self.transformations.append(transformation)

pyFTS/hofts.py

@@ -84,10 +84,6 @@ class HighOrderFTS(fts.FTS):
         flrs = FLR.generateRecurrentFLRs(tmpdata)
         self.flrgs = self.generateFLRG(flrs)
 
-    def getMidpoints(self, flrg):
-        ret = np.array([self.setsDict[s].centroid for s in flrg.RHS])
-        return ret
-
     def forecast(self, data, **kwargs):
 
         ret = []
@@ -109,9 +105,7 @@ class HighOrderFTS(fts.FTS):
                 ret.append(tmpdata[-1].centroid)
             else:
                 flrg = self.flrgs[tmpflrg.strLHS()]
-                mp = self.getMidpoints(flrg)
+                ret.append(flrg.get_midpoint())
-
-                ret.append(sum(mp) / len(mp))
 
         ret = self.doInverseTransformations(ret, params=[data[self.order-1:]])
 

pyFTS/ifts.py

@@ -23,27 +23,27 @@ class IntervalFTS(hofts.HighOrderFTS):
         self.has_interval_forecasting = True
         self.is_high_order = True
 
-    def getUpper(self, flrg):
+    def get_upper(self, flrg):
         if flrg.strLHS() in self.flrgs:
             tmp = self.flrgs[flrg.strLHS()]
-            ret = max(np.array([self.setsDict[s].upper for s in tmp.RHS]))
+            ret = tmp.get_upper()
         else:
             ret = flrg.LHS[-1].upper
         return ret
 
-    def getLower(self, flrg):
+    def get_lower(self, flrg):
         if flrg.strLHS() in self.flrgs:
             tmp = self.flrgs[flrg.strLHS()]
-            ret = min(np.array([self.setsDict[s].lower for s in tmp.RHS]))
+            ret = tmp.get_lower()
         else:
             ret = flrg.LHS[-1].lower
         return ret
 
-    def getSequenceMembership(self, data, fuzzySets):
+    def get_sequence_membership(self, data, fuzzySets):
         mb = [fuzzySets[k].membership(data[k]) for k in np.arange(0, len(data))]
         return mb
 
-    def buildTree(self, node, lags, level):
+    def build_tree(self, node, lags, level):
         if level >= self.order:
             return
 
@@ -51,7 +51,7 @@ class IntervalFTS(hofts.HighOrderFTS):
             node.appendChild(tree.FLRGTreeNode(s))
 
         for child in node.getChildren():
-            self.buildTree(child, lags, level + 1)
+            self.build_tree(child, lags, level + 1)
 
     def forecastInterval(self, data, **kwargs):
 
@@ -96,7 +96,7 @@ class IntervalFTS(hofts.HighOrderFTS):
 
                 root = tree.FLRGTreeNode(None)
 
-                self.buildTree(root, lags, 0)
+                self.build_tree(root, lags, 0)
 
                 # Traça os possíveis caminhos e costrói as HOFLRG's
 
@@ -132,8 +132,8 @@ class IntervalFTS(hofts.HighOrderFTS):
             count = 0
             for flrg in affected_flrgs:
                 # achar o os bounds de cada FLRG, ponderados pela pertinência
-                up.append(affected_flrgs_memberships[count] * self.getUpper(flrg))
+                up.append(affected_flrgs_memberships[count] * self.get_upper(flrg))
-                lo.append(affected_flrgs_memberships[count] * self.getLower(flrg))
+                lo.append(affected_flrgs_memberships[count] * self.get_lower(flrg))
                 count = count + 1
 
             # gerar o intervalo

pyFTS/ismailefendi.py

@@ -70,10 +70,6 @@ class ImprovedWeightedFTS(fts.FTS):
         flrs = FLR.generateRecurrentFLRs(tmpdata)
         self.flrgs = self.generateFLRG(flrs)
 
-    def getMidpoints(self, flrg):
-        ret = np.array([self.setsDict[s].centroid for s in flrg.RHS])
-        return ret
-
     def forecast(self, data, **kwargs):
         l = 1
 
@@ -94,7 +90,7 @@ class ImprovedWeightedFTS(fts.FTS):
                 ret.append(actual.centroid)
             else:
                 flrg = self.flrgs[actual.name]
-                mp = self.getMidpoints(flrg)
+                mp = flrg.get_midpoints()
 
                 ret.append(mp.dot(flrg.weights()))
 

pyFTS/nonstationary/flrg.py

@@ -11,24 +11,16 @@ class NonStationaryFLRG(flrg.FLRG):
 
     def get_midpoint(self, t):
         if self.midpoint is None:
-            tmp = []
+            tmp = [r.get_midpoint(t) for r in self.RHS]
-            for r in self.RHS:
-                tmp.append(r.get_midpoint(t))
             self.midpoint = sum(tmp) / len(tmp)
         return self.midpoint
 
     def get_lower(self, t):
         if self.lower is None:
-            tmp = []
+            self.lower = min([r.get_lower(t) for r in self.RHS])
-            for r in self.RHS:
-                tmp.append(r.get_midpoint(t))
-            self.lower = min(tmp)
         return self.lower
 
     def get_upper(self, t):
         if self.upper is None:
-            tmp = []
+            self.upper = min([r.get_upper(t) for r in self.RHS])
-            for r in self.RHS:
-                tmp.append(r.get_midpoint(t))
-            self.upper = max(tmp)
         return self.upper

pyFTS/nonstationary/honsfts.py

@@ -1,55 +1,64 @@
 import numpy as np
 from pyFTS.common import FuzzySet, FLR
 from pyFTS import fts, hofts
-from pyFTS.nonstationary import common
+from pyFTS.nonstationary import common, flrg
 
 
-class HighOrderNonStationaryFLRG(hofts.HighOrderFLRG):
+class HighOrderNonStationaryFLRG(flrg.NonStationaryFLRG):
     """First Order NonStationary Fuzzy Logical Relationship Group"""
-    def __init__(self, order):
+    def __init__(self, order, **kwargs):
-        super(HighOrderNonStationaryFLRG, self).__init__(order)
+        super(HighOrderNonStationaryFLRG, self).__init__(order, **kwargs)
 
-    def get_midpoint(self, t):
+        self.LHS = []
-        if self.midpoint is None:
+        self.RHS = {}
-            tmp = []
+        self.strlhs = ""
-            for r in self.RHS:
-                tmp.append(r.get_midpoint(t))
-            self.midpoint = sum(tmp)/len(tmp)
-        return self.midpoint
 
-    def get_lower(self, t):
+    def appendRHS(self, c):
-        if self.lower is None:
+        if c.name not in self.RHS:
-            tmp = []
+            self.RHS[c.name] = c
-            for r in self.RHS:
-                tmp.append(r.get_midpoint(t))
-            self.lower = min(tmp)
-        return self.lower
 
-    def get_upper(self, t):
+    def strLHS(self):
-        if self.upper is None:
+        if len(self.strlhs) == 0:
-            tmp = []
+            for c in self.LHS:
-            for r in self.RHS:
+                if len(self.strlhs) > 0:
-                tmp.append(r.get_midpoint(t))
+                    self.strlhs += ", "
-            self.upper = max(tmp)
+                self.strlhs = self.strlhs + c.name
-        return self.upper
+        return self.strlhs
+
+    def appendLHS(self, c):
+        self.LHS.append(c)
+
+    def __str__(self):
+        tmp = ""
+        for c in sorted(self.RHS):
+            if len(tmp) > 0:
+                tmp = tmp + ","
+            tmp = tmp + c
+        return self.strLHS() + " -> " + tmp
 
 
-class NonStationaryFTS(fts.FTS):
+class HighOrderNonStationaryFTS(hofts.HighOrderFLRG):
     """NonStationaryFTS Fuzzy Time Series"""
     def __init__(self, name, **kwargs):
-        super(NonStationaryFTS, self).__init__(1, "NSFTS " + name, **kwargs)
+        super(HighOrderNonStationaryFTS, self).__init__(1, "HONSFTS " + name, **kwargs)
-        self.name = "Non Stationary FTS"
+        self.name = "High Order Non Stationary FTS"
         self.detail = ""
         self.flrgs = {}
 
     def generateFLRG(self, flrs):
         flrgs = {}
-        for flr in flrs:
+        l = len(flrs)
-            if flr.LHS.name in flrgs:
+        for k in np.arange(self.order + 1, l):
-                flrgs[flr.LHS.name].append(flr.RHS)
+            flrg = HighOrderNonStationaryFLRG(self.order)
+
+            for kk in np.arange(k - self.order, k):
+                flrg.appendLHS(flrs[kk].LHS)
+
+            if flrg.strLHS() in flrgs:
+                flrgs[flrg.strLHS()].appendRHS(flrs[k].RHS)
             else:
-                flrgs[flr.LHS.name] = NonStationaryFLRG(flr.LHS)
+                flrgs[flrg.strLHS()] = flrg;
-                flrgs[flr.LHS.name].append(flr.RHS)
+                flrgs[flrg.strLHS()].appendRHS(flrs[k].RHS)
         return (flrgs)
 
     def train(self, data, sets=None,order=1,parameters=None):

pyFTS/pwfts.py

@@ -15,25 +15,28 @@ class ProbabilisticWeightedFLRG(hofts.HighOrderFLRG):
     def __init__(self, order):
         super(ProbabilisticWeightedFLRG, self).__init__(order)
         self.RHS = {}
+        self.rhs_count = {}
         self.frequency_count = 0.0
         self.Z = None
 
     def appendRHS(self, c):
         self.frequency_count += 1.0
         if c.name in self.RHS:
-            self.RHS[c.name] += 1.0
+            self.rhs_count[c.name] += 1.0
         else:
-            self.RHS[c.name] = 1.0
+            self.RHS[c.name] = c
+            self.rhs_count[c.name] = 1.0
 
     def appendRHSFuzzy(self, c, mv):
         self.frequency_count += mv
         if c.name in self.RHS:
-            self.RHS[c.name] += mv
+            self.rhs_count[c.name] += mv
         else:
-            self.RHS[c.name] = mv
+            self.RHS[c.name] = c
+            self.rhs_count[c.name] = mv
 
     def get_RHSprobability(self, c):
-        return self.RHS[c] / self.frequency_count
+        return self.rhs_count[c] / self.frequency_count
 
     def lhs_probability(self, x, norm, uod, nbins):
         pk = self.frequency_count / norm
@@ -44,8 +47,8 @@ class ProbabilisticWeightedFLRG(hofts.HighOrderFLRG):
 
     def rhs_conditional_probability(self, x, sets, uod, nbins):
         total = 0.0
-        for rhs in self.RHS:
+        for rhs in self.RHS.keys():
-            set = sets[rhs]
+            set = self.RHS[rhs]
             wi = self.get_RHSprobability(rhs)
             mv = set.membership(x) / set.partition_function(uod, nbins=nbins)
             total += wi * mv
@@ -58,7 +61,7 @@ class ProbabilisticWeightedFLRG(hofts.HighOrderFLRG):
             mv.append(set.membership(x[count]))
 
         min_mv = np.prod(mv)
-        return  min_mv
+        return min_mv
 
     def partition_function(self, uod, nbins=100):
         if self.Z is None:
@@ -69,12 +72,24 @@ class ProbabilisticWeightedFLRG(hofts.HighOrderFLRG):
 
         return self.Z
 
+    def get_midpoint(self):
+        return sum(np.array([self.get_RHSprobability(s.name) * self.RHS[s].centroid
+                             for s in self.RHS.keys()]))
+
+    def get_upper(self):
+        return sum(np.array([self.get_RHSprobability(s.name) * self.RHS[s].upper
+                             for s in self.RHS.keys()]))
+
+    def get_lower(self):
+        return sum(np.array([self.get_RHSprobability(s.name) * self.RHS[s].lower
+                             for s in self.RHS.keys()]))
+
     def __str__(self):
         tmp2 = ""
-        for c in sorted(self.RHS):
+        for c in sorted(self.RHS.keys()):
             if len(tmp2) > 0:
                 tmp2 = tmp2 + ", "
-            tmp2 = tmp2 + "(" + str(round(self.RHS[c] / self.frequency_count, 3)) + ")" + c
+            tmp2 = tmp2 + "(" + str(round(self.rhs_count[c] / self.frequency_count, 3)) + ")" + c
         return self.strLHS() + " -> " + tmp2
 
 
@@ -136,7 +151,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
             root = tree.FLRGTreeNode(None)
 
-            self.buildTreeWithoutOrder(root, lags, 0)
+            self.build_tree_without_order(root, lags, 0)
 
             # Trace the possible paths
             for p in root.paths():
@@ -214,10 +229,10 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
             self.add_new_PWFLGR(flrg)
             return self.get_flrg_global_probability(flrg)
 
-    def getMidpoints(self, flrg):
+    def get_midpoint(self, flrg):
         if flrg.strLHS() in self.flrgs:
             tmp = self.flrgs[flrg.strLHS()]
-            ret = sum(np.array([tmp.get_RHSprobability(s) * self.setsDict[s].centroid for s in tmp.RHS]))
+            ret = tmp.get_midpoint() #sum(np.array([tmp.get_RHSprobability(s) * self.setsDict[s].centroid for s in tmp.RHS]))
         else:
             pi = 1 / len(flrg.LHS)
             ret = sum(np.array([pi * s.centroid for s in flrg.LHS]))
@@ -241,25 +256,25 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
             ret = sum(np.array([pi * self.setsDict[s].membership(x) for s in flrg.LHS]))
         return ret
 
-    def getUpper(self, flrg):
+    def get_upper(self, flrg):
         if flrg.strLHS() in self.flrgs:
             tmp = self.flrgs[flrg.strLHS()]
-            ret = sum(np.array([tmp.get_RHSprobability(s) * self.setsDict[s].upper for s in tmp.RHS]))
+            ret = tmp.get_upper()
         else:
             pi = 1 / len(flrg.LHS)
             ret = sum(np.array([pi * s.upper for s in flrg.LHS]))
         return ret
 
-    def getLower(self, flrg):
+    def get_lower(self, flrg):
         if flrg.strLHS() in self.flrgs:
             tmp = self.flrgs[flrg.strLHS()]
-            ret = sum(np.array([tmp.get_RHSprobability(s) * self.setsDict[s].lower for s in tmp.RHS]))
+            ret = tmp.get_lower()
         else:
             pi = 1 / len(flrg.LHS)
             ret = sum(np.array([pi * s.lower for s in flrg.LHS]))
         return ret
 
-    def buildTreeWithoutOrder(self, node, lags, level):
+    def build_tree_without_order(self, node, lags, level):
 
         if level not in lags:
             return
@@ -268,7 +283,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
             node.appendChild(tree.FLRGTreeNode(s))
 
         for child in node.getChildren():
-            self.buildTreeWithoutOrder(child, lags, level + 1)
+            self.build_tree_without_order(child, lags, level + 1)
 
 
     def forecast(self, data, **kwargs):
@@ -316,7 +331,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
                 root = tree.FLRGTreeNode(None)
 
-                self.buildTree(root, lags, 0)
+                self.build_tree(root, lags, 0)
 
                 # Trace the possible paths and build the PFLRG's
 
@@ -331,7 +346,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
                     affected_flrgs.append(flrg)
 
                     # Find the general membership of FLRG
-                    affected_flrgs_memberships.append(min(self.getSequenceMembership(subset, flrg.LHS)))
+                    affected_flrgs_memberships.append(min(self.get_sequence_membership(subset, flrg.LHS)))
 
             else:
 
@@ -358,7 +373,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
                 norm = self.get_flrg_global_probability(flrg) * affected_flrgs_memberships[count]
                 if norm == 0:
                     norm = self.get_flrg_global_probability(flrg)  # * 0.001
-                mp.append(norm * self.getMidpoints(flrg))
+                mp.append(norm * self.get_midpoint(flrg))
                 norms.append(norm)
 
             # gerar o intervalo
@@ -438,7 +453,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
             root = tree.FLRGTreeNode(None)
 
-            self.buildTree(root, lags, 0)
+            self.build_tree(root, lags, 0)
 
             # Trace the possible paths and build the PFLRG's
 
@@ -453,7 +468,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
                 affected_flrgs.append(flrg)
 
                 # Find the general membership of FLRG
-                affected_flrgs_memberships.append(min(self.getSequenceMembership(subset, flrg.LHS)))
+                affected_flrgs_memberships.append(min(self.get_sequence_membership(subset, flrg.LHS)))
 
         else:
 
@@ -480,8 +495,8 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
             norm = self.get_flrg_global_probability(flrg) * affected_flrgs_memberships[count]
             if norm == 0:
                 norm = self.get_flrg_global_probability(flrg)  # * 0.001
-            up.append(norm * self.getUpper(flrg))
+            up.append(norm * self.get_upper(flrg))
-            lo.append(norm * self.getLower(flrg))
+            lo.append(norm * self.get_lower(flrg))
             norms.append(norm)
 
         # gerar o intervalo
@@ -613,7 +628,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
                 root = tree.FLRGTreeNode(None)
 
-                self.buildTreeWithoutOrder(root, lags, 0)
+                self.build_tree_without_order(root, lags, 0)
 
                 # Trace the possible paths
                 for p in root.paths():
@@ -661,7 +676,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
                 root = tree.FLRGTreeNode(None)
 
-                self.buildTreeWithoutOrder(root, lags, 0)
+                self.build_tree_without_order(root, lags, 0)
 
                 # Trace the possible paths
                 for p in root.paths():
@@ -683,8 +698,6 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
         return ret
 
-
-
     def __str__(self):
         tmp = self.name + ":\n"
         for r in sorted(self.flrgs):

pyFTS/sadaei.py

@@ -92,7 +92,7 @@ class ExponentialyWeightedFTS(fts.FTS):
                 ret.append(actual.centroid)
             else:
                 flrg = self.flrgs[actual.name]
-                mp = self.getMidpoints(flrg)
+                mp = flrg.get_midpoints()
 
                 ret.append(mp.dot(flrg.weights()))
 

pyFTS/yu.py

@@ -84,7 +84,7 @@ class WeightedFTS(fts.FTS):
                 ret.append(actual.centroid)
             else:
                 flrg = self.flrgs[actual.name]
-                mp = self.getMidpoints(flrg)
+                mp = flrg.get_midpoints()
 
                 ret.append(mp.dot(flrg.weights()))