High Order NSFTS refactoring

pyFTS/models/nonstationary/common.py

@@ -55,7 +55,6 @@ class FuzzySet(FS.FuzzySet):
             inc = t
         else:
             l = len(self.location)
-
             inc = sum([self.location[k](t + self.location_roots[k], self.location_params[k]) for k in np.arange(0, l)])
 
         if self.mf == Membership.gaussmf:

pyFTS/models/nonstationary/honsfts.py

@@ -1,7 +1,8 @@
 import numpy as np
-from pyFTS.common import FuzzySet, FLR, fts, tree
+from pyFTS.common import FuzzySet, FLR, fts
 from pyFTS.models import hofts
-from pyFTS.models.nonstationary import common, flrg
+from pyFTS.models.nonstationary import common, flrg, nsfts
+from itertools import product
 
 
 class HighOrderNonStationaryFLRG(flrg.NonStationaryFLRG):
@@ -11,67 +12,121 @@ class HighOrderNonStationaryFLRG(flrg.NonStationaryFLRG):
 
         self.LHS = []
         self.RHS = {}
+        self.count = 0.0
+        self.strlhs = ""
+        self.w = None
 
-    def append_rhs(self, c, **kwargs):
+    def append_rhs(self, fset, **kwargs):
-        if c.name not in self.RHS:
+        count = kwargs.get('count',1.0)
-            self.RHS[c.name] = c
+        if fset not in self.RHS:
+            self.RHS[fset] = count
+        else:
+            self.RHS[fset] += count
+        self.count += count
 
     def append_lhs(self, c):
         self.LHS.append(c)
 
+    def weights(self):
+        if self.w is None:
+            self.w = np.array([self.RHS[c] / self.count for c in self.RHS.keys()])
+        return self.w
+
+    def get_midpoint(self, sets, perturb):
+        mp = np.array([sets[c].get_midpoint(perturb) for c in self.RHS.keys()])
+        midpoint = mp.dot(self.weights())
+        return midpoint
+
+    def get_lower(self, sets, perturb):
+        lw = np.array([sets[s].get_lower(perturb) for s in self.RHS.keys()])
+        lower = lw.dot(self.weights())
+        return lower
+
+    def get_upper(self, sets, perturb):
+        up = np.array([sets[s].get_upper(perturb) for s in self.RHS.keys()])
+        upper = up.dot(self.weights())
+        return upper
+
     def __str__(self):
-        tmp = ""
+        _str = ""
-        for c in sorted(self.RHS):
+        for k in self.RHS.keys():
-            if len(tmp) > 0:
+            _str += ", " if len(_str) > 0 else ""
-                tmp = tmp + ","
+            _str += k + " (" + str(round(self.RHS[k] / self.count, 3)) + ")"
-            tmp = tmp + c
+
-        return self.get_key() + " -> " + tmp
+        return self.get_key() + " -> " + _str
+
+    def __len__(self):
+        return len(self.RHS)
 
 
-class HighOrderNonStationaryFTS(hofts.HighOrderFTS):
+class HighOrderNonStationaryFTS(nsfts.NonStationaryFTS):
     """NonStationaryFTS Fuzzy Time Series"""
-    def __init__(self, name, **kwargs):
+    def __init__(self, **kwargs):
-        super(HighOrderNonStationaryFTS, self).__init__("HONSFTS " + name, **kwargs)
+        super(HighOrderNonStationaryFTS, self).__init__(**kwargs)
         self.name = "High Order Non Stationary FTS"
+        self.shortname = "HONSFTS"
         self.detail = ""
         self.flrgs = {}
+        self.is_high_order = True
+        self.order = kwargs.get("order",2)
+        self.configure_lags(**kwargs)
+
+    def configure_lags(self, **kwargs):
+        if "order" in kwargs:
+            self.order = kwargs.get("order", self.min_order)
+
+        if "lags" in kwargs:
+            self.lags = kwargs.get("lags", None)
+
+        if self.lags is not None:
+            self.max_lag = max(self.lags)
+        else:
+            self.max_lag = self.order
+            self.lags = np.arange(1, self.order + 1)
+
+    def train(self, data, **kwargs):
+
+        self.generate_flrg(data)
+
+        if self.method == 'conditional':
+            self.forecasts = self.forecast(data, no_update=True)
+            self.residuals = np.array(data[self.order:]) - np.array(self.forecasts)
+
+            self.variance_residual = np.var(self.residuals)  # np.max(self.residuals
+            self.mean_residual = np.mean(self.residuals)
+
+            self.residuals = self.residuals[-self.memory_window:].tolist()
+            self.forecasts = self.forecasts[-self.memory_window:]
+            self.inputs = np.array(data[-self.memory_window:]).tolist()
 
     def generate_flrg(self, data, **kwargs):
         l = len(data)
-        window_size = kwargs.get("window_size", 1)
         for k in np.arange(self.order, l):
             if self.dump: print("FLR: " + str(k))
 
             sample = data[k - self.order: k]
 
-            disp = common.window_index(k, window_size)
+            rhs = [key for key in self.partitioner.ordered_sets
-
+                   if self.partitioner.sets[key].membership(data[k], [0,1]) > 0.0]
-            rhs = [self.sets[key] for key in self.partitioner.ordered_sets
-                   if self.sets[key].membership(data[k], disp) > 0.0]
 
             if len(rhs) == 0:
-                rhs = [common.check_bounds(data[k], self.partitioner, disp)]
+                rhs = [common.check_bounds(data[k], self.partitioner, [0,1]).name]
 
-            lags = {}
+            lags = []
 
             for o in np.arange(0, self.order):
-                tdisp = common.window_index(k - (self.order - o), window_size)
+                tdisp = [0,1]
-                lhs = [self.sets[key] for key in self.partitioner.ordered_sets
+                lhs = [key for key in self.partitioner.ordered_sets
-                   if self.sets[key].membership(sample[o], tdisp) > 0.0]
+                   if self.partitioner.sets[key].membership(sample[o], tdisp) > 0.0]
 
                 if len(lhs) == 0:
-                    lhs = [common.check_bounds(sample[o], self.partitioner, tdisp)]
+                    lhs = [common.check_bounds(sample[o], self.partitioner, tdisp).name]
 
-                lags[o] = lhs
+                lags.append(lhs)
-
-            root = tree.FLRGTreeNode(None)
-
-            tree.build_tree_without_order(root, lags, 0)
 
             # Trace the possible paths
-            for p in root.paths():
+            for path in product(*lags):
                 flrg = HighOrderNonStationaryFLRG(self.order)
-                path = list(reversed(list(filter(None.__ne__, p))))
 
                 for c, e in enumerate(path, start=0):
                     flrg.append_lhs(e)
@@ -82,67 +137,45 @@ class HighOrderNonStationaryFTS(hofts.HighOrderFTS):
                 for st in rhs:
                     self.flrgs[flrg.get_key()].append_rhs(st)
 
-        # flrgs = sorted(flrgs, key=lambda flrg: flrg.get_midpoint(0, window_size=1))
+    def _affected_flrgs(self, sample, perturb):
-
-    def train(self, data, **kwargs):
-
-        if kwargs.get('order', None) is not None:
-            self.order = kwargs.get('order', 1)
-
-        if kwargs.get('sets', None) is not None:
-            self.sets = kwargs.get('sets', None)
-
-        window_size = kwargs.get('parameters', 1)
-        self.generate_flrg(data, window_size=window_size)
-
-    def _affected_flrgs(self, sample, k, time_displacement, window_size):
-        # print("input: " + str(ndata[k]))
 
         affected_flrgs = []
         affected_flrgs_memberships = []
 
-        lags = {}
+        lags = []
 
         for ct, dat in enumerate(sample):
-            tdisp = common.window_index((k + time_displacement) - (self.order - ct), window_size)
+            affected_sets = [[ct, self.partitioner.sets[key].membership(dat, perturb[ct])]
+                             for ct, key in enumerate(self.partitioner.ordered_sets)
+                             if self.partitioner.sets[key].membership(dat, perturb[ct]) > 0.0]
 
-            sel = [ct for ct, key in enumerate(self.partitioner.ordered_sets)
+            if len(affected_sets) == 0:
-                   if self.sets[key].membership(dat, tdisp) > 0.0]
 
-            if len(sel) == 0:
+                if dat < self.partitioner.lower_set().get_lower(perturb[0]):
-                sel.append(common.check_bounds_index(dat, self.partitioner, tdisp))
+                    affected_sets.append([0, 1])
+                elif dat > self.partitioner.upper_set().get_upper(perturb[-1]):
+                    affected_sets.append([self.partitioner.partitions - 1, 1])
 
-            lags[ct] = sel
+            lags.append([a[0] for a in affected_sets])
 
         # Build the tree with all possible paths
 
-        root = tree.FLRGTreeNode(None)
+        # Trace the possible paths
+        for path in product(*lags):
 
-        tree.build_tree_without_order(root, lags, 0)
-
-        # Trace the possible paths and build the PFLRG's
-
-        for p in root.paths():
-            path = list(reversed(list(filter(None.__ne__, p))))
             flrg = HighOrderNonStationaryFLRG(self.order)
 
             for kk in path:
-                flrg.append_lhs(self.sets[self.partitioner.ordered_sets[kk]])
+                flrg.append_lhs(self.partitioner.ordered_sets[kk])
 
             affected_flrgs.append(flrg)
-            # affected_flrgs_memberships.append_rhs(flrg.get_membership(sample, disp))
-
-            #                print(flrg.get_key())
-
-            # the FLRG is here because of the bounds verification
             mv = []
             for ct, dat in enumerate(sample):
-                td = common.window_index((k + time_displacement) - (self.order - ct), window_size)
+                fset = self.partitioner.sets[flrg.LHS[ct]]
-                tmp = flrg.LHS[ct].membership(dat, td)
+                ix = self.partitioner.ordered_sets.index(flrg.LHS[ct])
-
+                tmp = fset.membership(dat, perturb[ix])
 
                 mv.append(tmp)
-            # print(mv)
 
             affected_flrgs_memberships.append(np.prod(mv))
 
@@ -150,100 +183,67 @@ class HighOrderNonStationaryFTS(hofts.HighOrderFTS):
 
     def forecast(self, ndata, **kwargs):
 
-        time_displacement = kwargs.get("time_displacement",0)
+        explain = kwargs.get('explain', False)
 
-        window_size = kwargs.get("window_size", 1)
+        fuzzyfied = kwargs.get('fuzzyfied', False)
-
-        l = len(ndata)
-
-        ret = []
-
-        for k in np.arange(self.order, l+1):
-
-            sample = ndata[k - self.order: k]
-
-            affected_flrgs, affected_flrgs_memberships = self._affected_flrgs(sample, k,
-                                                                              time_displacement, window_size)
-
-            #print([str(k) for k in affected_flrgs])
-            #print(affected_flrgs_memberships)
-
-            tmp = []
-            tdisp = common.window_index(k + time_displacement, window_size)
-            if len(affected_flrgs) == 0:
-                tmp.append(common.check_bounds(sample[-1], self.sets, tdisp))
-            elif len(affected_flrgs) == 1:
-                flrg = affected_flrgs[0]
-                if flrg.get_key() in self.flrgs:
-                    tmp.append(self.flrgs[flrg.get_key()].get_midpoint(tdisp))
-                else:
-                    tmp.append(flrg.LHS[-1].get_midpoint(tdisp))
-            else:
-                for ct, aset in enumerate(affected_flrgs):
-                    if aset.get_key() in self.flrgs:
-                        tmp.append(self.flrgs[aset.get_key()].get_midpoint(tdisp) *
-                                   affected_flrgs_memberships[ct])
-                    else:
-                        tmp.append(aset.LHS[-1].get_midpoint(tdisp)*
-                                   affected_flrgs_memberships[ct])
-            pto = sum(tmp)
-
-            #print(pto)
-
-            ret.append(pto)
-
-        return ret
-
-    def forecast_interval(self, ndata, **kwargs):
 
         time_displacement = kwargs.get("time_displacement", 0)
 
         window_size = kwargs.get("window_size", 1)
 
-        l = len(ndata)
+        no_update = kwargs.get("no_update", False)
+
+        mode = kwargs.get('mode', 'mean')
 
         ret = []
 
-        for k in np.arange(self.order, l + 1):
+        l = len(ndata) if not explain else self.max_lag + 1
 
-            sample = ndata[k - self.order: k]
+        if l < self.max_lag:
+            return ndata
+        elif l == self.max_lag:
+            l += 1
 
-            affected_flrgs, affected_flrgs_memberships = self._affected_flrgs(sample, k,
+        for k in np.arange(self.max_lag, l):
-                                                                              time_displacement, window_size)
 
-            # print([str(k) for k in affected_flrgs])
+            sample = ndata[k - self.max_lag: k]
-            # print(affected_flrgs_memberships)
 
-            upper = []
+            if self.method == 'unconditional':
-            lower = []
+                perturb = common.window_index(k + time_displacement, window_size)
-
+            elif self.method == 'conditional':
-            tdisp = common.window_index(k + time_displacement, window_size)
+                if no_update:
-            if len(affected_flrgs) == 0:
+                    perturb = [[0, 1] for k in np.arange(self.partitioner.partitions)]
-                aset = common.check_bounds(sample[-1], self.sets, tdisp)
-                lower.append(aset.get_lower(tdisp))
-                upper.append(aset.get_upper(tdisp))
-            elif len(affected_flrgs) == 1:
-                _flrg = affected_flrgs[0]
-                if _flrg.get_key() in self.flrgs:
-                    lower.append(self.flrgs[_flrg.get_key()].get_lower(tdisp))
-                    upper.append(self.flrgs[_flrg.get_key()].get_upper(tdisp))
                 else:
-                    lower.append(_flrg.LHS[-1].get_lower(tdisp))
+                    perturb = self.conditional_perturbation_factors(sample[0])
-                    upper.append(_flrg.LHS[-1].get_upper(tdisp))
+
+
+            affected_flrgs, affected_flrgs_memberships = self._affected_flrgs(sample, perturb)
+
+            tmp = []
+
+            perturb2 = perturb[0]
+            if len(affected_flrgs) == 0:
+                tmp.append(common.check_bounds(sample[-1], self.partitioner.sets, perturb2))
+            elif len(affected_flrgs) == 1:
+                flrg = affected_flrgs[0]
+                if flrg.get_key() in self.flrgs:
+                    tmp.append(self.flrgs[flrg.get_key()].get_midpoint(self.partitioner.sets, perturb2))
+                else:
+                    fset = self.partitioner.sets[flrg.LHS[-1]]
+                    ix = self.partitioner.ordered_sets.index(flrg.LHS[-1])
+                    tmp.append(fset.get_midpoint(perturb[ix]))
             else:
                 for ct, aset in enumerate(affected_flrgs):
                     if aset.get_key() in self.flrgs:
-                        lower.append(self.flrgs[aset.get_key()].get_lower(tdisp) *
+
-                                     affected_flrgs_memberships[ct])
+                        tmp.append(self.flrgs[aset.get_key()].get_midpoint(self.partitioner.sets, perturb2) *
-                        upper.append(self.flrgs[aset.get_key()].get_upper(tdisp) *
                                    affected_flrgs_memberships[ct])
                     else:
-                        lower.append(aset.LHS[-1].get_lower(tdisp) *
+                        fset = self.partitioner.sets[aset.LHS[-1]]
-                                   affected_flrgs_memberships[ct])
+                        ix = self.partitioner.ordered_sets.index(aset.LHS[-1])
-                        upper.append(aset.LHS[-1].get_upper(tdisp) *
+                        tmp.append(fset.get_midpoint(perturb[ix])*affected_flrgs_memberships[ct])
-                                   affected_flrgs_memberships[ct])
+            pto = sum(tmp)
-
-            ret.append([sum(lower), sum(upper)])
 
+            ret.append(pto)
 
         return ret

pyFTS/models/nonstationary/partitioners.py

@@ -120,6 +120,7 @@ class SimpleNonStationaryPartitioner(partitioner.Partitioner):
                                                              func=part.membership_function, names=part.setnames,
                                                              prefix=part.prefix, transformation=part.transformation,
                                                              indexer=part.indexer)#, preprocess=False)
+        self.partitions = part.partitions
 
         for key in part.sets.keys():
             set = part.sets[key]

pyFTS/tests/nonstationary.py

@@ -12,155 +12,26 @@ from pyFTS.data import TAIEX, NASDAQ, SP500, artificial, mackey_glass
 
 #mackey_glass.get_data()
 
-datasets = {
+dataset =  TAIEX.get_data()
-    "TAIEX": TAIEX.get_data()[:4000],
-    "SP500": SP500.get_data()[10000:14000],
-    "NASDAQ": NASDAQ.get_data()[:4000],
-    # Incremental Mean and Incremental Variance
-    "IMIV": artificial.generate_gaussian_linear(1,0.2,0.2,0.05,it=100, num=40),
-    # Incremental Mean and Incremental Variance, lower bound equals to 0
-    "IMIV0": artificial.generate_gaussian_linear(1,0.2,0.,0.05, vmin=0,it=100, num=40),
-    # Constant Mean and Incremental Variance
-    "CMIV": artificial.generate_gaussian_linear(5,0.1,0,0.02,it=100, num=40),
-    # Incremental Mean and Constant Variance
-    "IMCV": artificial.generate_gaussian_linear(1,0.6,0.1,0,it=100, num=40)
-}
 
-train_split = 2000
+train_split = 1000
 test_length = 200
 
 from pyFTS.common import Transformations
 
-tdiff = Transformations.Differential(1)
-
-boxcox = Transformations.BoxCox(0)
-
-transformations = {
-    'None': None,
-    'Differential(1)': tdiff,
-    'BoxCox(0)': boxcox
-}
 
 from pyFTS.partitioners import Grid, Util as pUtil
 from pyFTS.benchmarks import benchmarks as bchmk
 from pyFTS.models import chen, hofts, pwfts, hwang
 
-partitions = {'CMIV': {'BoxCox(0)': 36, 'Differential(1)': 11, 'None': 8},
+train = dataset[:1000]
- 'IMCV': {'BoxCox(0)': 36, 'Differential(1)': 20, 'None': 16},
+test = dataset[1000:]
- 'IMIV': {'BoxCox(0)': 39, 'Differential(1)': 12, 'None': 6},
- 'IMIV0': {'BoxCox(0)': 39, 'Differential(1)': 12, 'None': 3},
- 'NASDAQ': {'BoxCox(0)': 39, 'Differential(1)': 13, 'None': 36},
- 'SP500': {'BoxCox(0)': 33, 'Differential(1)': 7, 'None': 33},
- 'TAIEX': {'BoxCox(0)': 39, 'Differential(1)': 31, 'None': 33}}
 
-from pyFTS.models.nonstationary import partitioners as nspart, cvfts, util as nsUtil
+from pyFTS.models.nonstationary import partitioners as nspart, nsfts, honsfts
-'''
+fs = nspart.simplenonstationary_gridpartitioner_builder(data=train,npart=35,transformation=None)
-#fs = nspart.simplenonstationary_gridpartitioner_builder(data=datasets['SP500'][:300],
+print(fs)
-#                                                        npart=partitions['SP500']['None'],
+model = honsfts.HighOrderNonStationaryFTS(partitioner=fs, order=2)
-#                                                        transformation=None)
+#model = nsfts.NonStationaryFTS(partitioner=fs)
-fs = Grid.GridPartitioner(data=datasets['SP500'][:300],
+model.fit(train)
-                                                        npart=15,
+forecasts = model.predict(test)
-                                                        transformation=None)
+print(forecasts)
-fig, axes = plt.subplots(nrows=1, ncols=1, figsize=[15, 5])
-
-fs.plot(axes)
-
-from pyFTS.common import Util
-
-Util.show_and_save_image(fig, "fig2.png", True)
-
-#nsUtil.plot_sets(fs)
-
-
-'''
-def model_details(ds, tf, train_split, test_split):
-    data = datasets[ds]
-    train = data[:train_split]
-    test = data[train_split:test_split]
-    transformation = transformations[tf]
-    fs = nspart.simplenonstationary_gridpartitioner_builder(data=train, npart=15, #partitions[ds][tf],
-                                                            transformation=transformation)
-    model = nsfts.NonStationaryFTS(partitioner=fs)
-    model.fit(train)
-    print(model)
-    forecasts = model.predict(test)
-    residuals = np.array(test[1:]) - np.array(forecasts[:-1])
-
-    fig, axes = plt.subplots(nrows=3, ncols=1, figsize=[15, 10])
-
-    axes[0].plot(test[1:], label="Original")
-    axes[0].plot(forecasts[:-1], label="Forecasts")
-    axes[0].set_ylabel("Univ. of Discourse")
-
-    #axes[1].set_title("Residuals")
-    axes[1].plot(residuals)
-    axes[1].set_ylabel("Error")
-    handles0, labels0 = axes[0].get_legend_handles_labels()
-    lgd = axes[0].legend(handles0, labels0, loc=2)
-
-    nsUtil.plot_sets_conditional(model, test, step=10, size=[10, 7],
-                                 save=True,file="fig.png", axes=axes[2], fig=fig)
-
-model_details('SP500','None',200,400)
-#'''
-print("ts")
-'''
-tag = 'benchmarks'
-
-
-for ds in datasets.keys():
-    dataset = datasets[ds]
-
-    for tf in transformations.keys():
-        transformation = transformations[tf]
-
-        partitioning = partitions[ds][tf]
-
-        bchmk.sliding_window_benchmarks(dataset, 3000, train=0.1, inc=0.1,
-                                        #methods=[
-                                        #    hwang.HighOrderFTS,
-                                        #    hofts.HighOrderFTS,
-                                        #    pwfts.ProbabilisticWeightedFTS],
-                                        #orders = [3],
-                                        benchmark_models=False,
-                                        transformations=[transformation],
-                                        partitions=[partitioning],
-                                        progress=False, type='point',
-                                        file="nsfts_benchmarks.db", dataset=ds, tag=tag)
-
-train_split = 200
-test_split = 2000
-for ds in datasets.keys():
-    dataset = datasets[ds]
-
-    print(ds)
-
-    for tf in ['None']: #transformations.keys():
-        transformation = transformations[tf]
-        train = dataset[:train_split]
-        test = dataset[train_split:test_split]
-
-        fs = nspart.simplenonstationary_gridpartitioner_builder(data=train,
-                                                                npart=partitions[ds][tf],
-                                                                transformation=transformation)
-        print(fs)
-        #cvfts1 = cvfts.ConditionalVarianceFTS(partitioner=fs)
-        model = nsfts.NonStationaryFTS(partitioner=fs)
-        model.fit(train)
-        print(model)
-
-        forecasts = model.predict(test)
-    
-        #print(forecasts)
-  
-        partitioning = partitions[ds][tf]
-
-        bchmk.sliding_window_benchmarks(dataset, 2000, train=0.2, inc=0.2,
-                                        benchmark_models=False,
-                                        methods=[cvfts.ConditionalVarianceFTS],
-                                        partitioners_methods=[nspart.simplenonstationary_gridpartitioner_builder],
-                                        transformations=[transformation],
-                                        partitions=[partitioning],
-                                        progress=False, type='point',
-                                        file="nsfts_benchmarks.db", dataset=ds, tag=tag)
-'''