Improvements for forecasting ahead in ClusteredMVFTS

pyFTS/models/multivariate/cmvfts.py

@@ -38,7 +38,7 @@ class ClusteredMVFTS(mvfts.MVFTS):
 
     def fuzzyfy(self,data):
         ndata = []
-        for index, row in data.iterrows():
+        for index, row in data.iterrows() if isinstance(data, pd.DataFrame) else enumerate(data):
             data_point = self.format_data(row)
             ndata.append(self.partitioner.fuzzyfy(data_point, mode=self.fuzzyfy_mode))
 
@@ -83,16 +83,7 @@ class ClusteredMVFTS(mvfts.MVFTS):
 
         return self.model.forecast_interval(data, fuzzyfied=pre_fuzz, **kwargs)
 
-    def forecast_ahead_interval(self, data, steps, **kwargs):
 
-        if not self.model.has_interval_forecasting:
-            raise Exception("The internal method does not support interval forecasting!")
-
-        data = self.check_data(data)
-
-        pre_fuzz = kwargs.get('pre_fuzzyfy', self.pre_fuzzyfy)
-
-        return self.model.forecast_ahead_interval(data, steps, fuzzyfied=pre_fuzz, **kwargs)
 
     def forecast_distribution(self, data, **kwargs):
 
@@ -107,14 +98,48 @@ class ClusteredMVFTS(mvfts.MVFTS):
 
     def forecast_ahead_distribution(self, data, steps, **kwargs):
 
-        if not self.model.has_probability_forecasting:
+        generators = kwargs.get('generators', None)
-            raise Exception("The internal method does not support probabilistic forecasting!")
 
-        data = self.check_data(data)
+        if generators is None:
+            raise Exception('You must provide parameter \'generators\'! generators is a dict where the keys' +
+                            ' are the dataframe column names (except the target_variable) and the values are ' +
+                            'lambda functions that accept one value (the actual value of the variable) '
+                            ' and return the next value or trained FTS models that accept the actual values and '
+                            'forecast new ones.')
 
-        pre_fuzz = kwargs.get('pre_fuzzyfy', self.pre_fuzzyfy)
+        ndata = self.apply_transformations(data)
 
-        return self.model.forecast_ahead_distribution(data, steps, fuzzyfied=pre_fuzz, **kwargs)
+        start = kwargs.get('start_at', self.order)
+
+        ret = []
+        sample = ndata.iloc[start - self.max_lag:]
+        for k in np.arange(0, steps):
+            tmp = self.forecast_distribution(sample.iloc[-self.max_lag:], **kwargs)[0]
+
+            ret.append(tmp)
+
+            new_data_point = {}
+
+            for data_label in generators.keys():
+                if data_label != self.target_variable.data_label:
+                    if isinstance(generators[data_label], LambdaType):
+                        last_data_point = sample.iloc[-1]
+                        new_data_point[data_label] = generators[data_label](last_data_point[data_label])
+
+                    elif isinstance(generators[data_label], fts.FTS):
+                        gen_model = generators[data_label]
+                        last_data_point = sample.iloc[-gen_model.order:]
+
+                        if not gen_model.is_multivariate:
+                            last_data_point = last_data_point[data_label].values
+
+                        new_data_point[data_label] = gen_model.forecast(last_data_point)[0]
+
+            new_data_point[self.target_variable.data_label] = tmp.expected_value()
+
+            sample = sample.append(new_data_point, ignore_index=True)
+
+        return ret[-steps:]
 
     def forecast_multivariate(self, data, **kwargs):
 

pyFTS/models/multivariate/mvfts.py

@@ -264,11 +264,11 @@ class MVFTS(fts.FTS):
 
         ret = []
         ix = ndata.index[start - self.max_lag:]
-        lo = [ndata.loc[k] for k in ix]
+        lo = ndata.loc[ix] #[ndata.loc[k] for k in ix]
-        up = [ndata.loc[k] for k in ix]
+        up = ndata.loc[ix] #[ndata.loc[k] for k in ix]
         for k in np.arange(0, steps):
-            tmp_lo = self.forecast_interval(lo[-self.max_lag:], **kwargs)
+            tmp_lo = self.forecast_interval(lo[-self.max_lag:], **kwargs)[0]
-            tmp_up = self.forecast_interval(up[-self.max_lag:], **kwargs)
+            tmp_up = self.forecast_interval(up[-self.max_lag:], **kwargs)[0]
 
             ret.append([min(tmp_lo), max(tmp_up)])
 
@@ -300,7 +300,7 @@ class MVFTS(fts.FTS):
             lo = lo.append(new_data_point_lo, ignore_index=True)
             up = up.append(new_data_point_up, ignore_index=True)
 
-        return ret[-steps]
+        return ret[-steps:]
 
     def clone_parameters(self, model):
         super(MVFTS, self).clone_parameters(model)

pyFTS/models/pwfts.py

@@ -171,6 +171,9 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
         return np.nanprod(vals)
 
     def generate_lhs_flrg(self, sample, explain=False):
+        if not isinstance(sample, (list, np.ndarray)):
+            sample = [sample]
+
         nsample = [self.partitioner.fuzzyfy(k, mode="sets", alpha_cut=self.alpha_cut)
                    for k in sample]
 
@@ -440,6 +443,8 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
         smooth = kwargs.get("smooth", "none")
 
+        from_distribution = kwargs.get('from_distribution', False)
+
         fuzzyfied = kwargs.get('fuzzyfied', False)
 
         l = len(ndata)
@@ -457,6 +462,10 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
         for k in np.arange(self.max_lag - 1, l):
             sample = ndata[k - (self.max_lag - 1): k + 1]
 
+            if from_distribution:
+                dist = self.forecast_distribution_from_distribution(sample,smooth,uod,_bins)
+            else:
+
                 if not fuzzyfied:
                     flrgs = self.generate_lhs_flrg(sample)
                 else:
@@ -532,7 +541,7 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
         start = kwargs.get('start_at', 0)
 
-        fuzzyfied = kwargs.get('fuzzyfied', False)
+        fuzzyfied = kwargs.pop('fuzzyfied')
 
         sample = data[start: start + self.max_lag]
 
@@ -541,12 +550,12 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
         else:
             ret = []
             for k in sample:
-                kv = self.partitioner.deffuzyfy(k,mode='both')
+                kv = self.partitioner.defuzzyfy(k, mode='both')
-                ret.append([kv,kv])
+                ret.append([kv, kv])
         
         ret.append(self.forecast_interval(sample, **kwargs)[0])
 
-        for k in np.arange(self.max_lag+1, steps+self.max_lag):
+        for k in np.arange(start + self.max_lag, steps + start + self.max_lag):
 
             if len(ret) > 0 and self.__check_interval_bounds(ret[-1]):
                 ret.append(ret[-1])
@@ -562,6 +571,9 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
         ret = []
 
+        if 'type' in kwargs:
+            kwargs.pop('type')
+
         smooth = kwargs.get("smooth", "none")
 
         uod = self.get_UoD()
@@ -575,49 +587,60 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
         start = kwargs.get('start_at', 0)
 
+        fuzzyfied = kwargs.pop('fuzzyfied')
+
+        if not fuzzyfied:
             sample = ndata[start: start + self.max_lag]
+        else:
+            sample = []
+            for k in ndata[start: start + self.max_lag]:
+                kv = self.partitioner.defuzzyfy(k, mode='both')
+                sample.append(kv)
 
         for dat in sample:
-            if 'type' in kwargs:
+            if not isinstance(dat, ProbabilityDistribution.ProbabilityDistribution):
-                kwargs.pop('type')
                 tmp = ProbabilityDistribution.ProbabilityDistribution(smooth, uod=uod, bins=_bins, **kwargs)
                 tmp.set(dat, 1.0)
                 ret.append(tmp)
+            else:
+                ret.append(dat)
 
-        dist = self.forecast_distribution(sample, bins=_bins, **kwargs)[0]
+        dist = self.forecast_distribution_from_distribution(ret, smooth,uod,_bins,**kwargs)
 
         ret.append(dist)
 
-        for k in np.arange(self.max_lag+1, steps+self.max_lag+1):
+        for k in np.arange(start + self.max_lag, steps + start + self.max_lag):
-            dist = ProbabilityDistribution.ProbabilityDistribution(smooth, uod=uod, bins=_bins, **kwargs)
+            dist = self.forescast_distribution_from_distribution(ret[k-self.max_lag:], smooth, uod, _bins, **kwargs)
+            ret.append(dist)
+
+        return ret[-steps:]
+
+    def forecast_distribution_from_distribution(self, previous_dist, smooth, uod, bins, **kwargs):
+        dist = ProbabilityDistribution.ProbabilityDistribution(smooth, uod=uod, bins=bins, **kwargs)
 
         lags = []
 
         # Find all bins of past distributions with probability greater than zero
 
         for ct, lag in enumerate(self.lags):
-                dd = ret[k - lag]
+            dd = previous_dist[-lag]
             vals = [float(v) for v in dd.bins if np.round(dd.density(v), 4) > 0.0]
-                lags.append( sorted(vals) )
+            lags.append(sorted(vals))
-
 
         # Trace all possible combinations between the bins of past distributions
 
         for path in product(*lags):
 
             # get the combined probabilities for this path
-                pk = np.prod([ret[k - (self.max_lag + lag)].density(path[ct])
+            pk = np.prod([previous_dist[-lag].density(path[ct])
                           for ct, lag in enumerate(self.lags)])
 
-
             d = self.forecast_distribution(path)[0]
 
-                for bin in _bins:
+            for bin in bins:
                 dist.set(bin, dist.density(bin) + pk * d.density(bin))
 
-            ret.append(dist)
+        return dist
-
-        return ret[-steps:]
 
     def __str__(self):
         tmp = self.name + ":\n"

pyFTS/partitioners/partitioner.py

@@ -185,29 +185,26 @@ class Partitioner(object):
         if not isinstance(values, list):
             values = [values]
 
-        ret = []
-        for val in values:
-            if mode == 'both':
         num = []
         den = []
-                for fset, mv in val:
+        for val in values:
+            fset = val[0]
+            mv = val[1]
+            if mode == 'both':
                 num.append( self.sets[fset].centroid * mv )
                 den.append(mv)
-                ret.append(np.sum(num)/np.sum(den))
+            elif mode == 'sets':
-            elif mode == 'both':
+                num.append(self.sets[fset].centroid)
-                num = np.mean([self.sets[fset].centroid for fset in val ])
-                ret.append(num)
             elif mode == 'vector':
-                num = []
-                den = []
-                for fset, mv in enumerate(val):
                 num.append(self.sets[self.ordered_sets[fset]].centroid * mv)
                 den.append(mv)
-                ret.append(np.sum(num) / np.sum(den))
             else:
                 raise Exception('Unknown deffuzyfication mode')
 
-        return ret
+        if mode in ('both','vector'):
+            return np.sum(num) / np.sum(den)
+        else:
+            return np.mean(num)
 
     def check_bounds(self, data):
         """

pyFTS/probabilistic/ProbabilityDistribution.py

@@ -5,6 +5,19 @@ from pyFTS.common import FuzzySet,SortedCollection,tree
 from pyFTS.probabilistic import kde
 
 
+def from_point(x,**kwargs):
+    """
+    Create a probability distribution from a scalar value
+
+    :param x: scalar value
+    :param kwargs: common parameters of the distribution
+    :return: the ProbabilityDistribution object
+    """
+    tmp = ProbabilityDistribution(**kwargs)
+    tmp.set(x, 1.0)
+    return tmp
+
+
 class ProbabilityDistribution(object):
     """
     Represents a discrete or continous probability distribution

pyFTS/tests/pwfts.py

@@ -47,12 +47,28 @@ model = granular.GranularWMVFTS(explanatory_variables=[vhour, vtemp, vload], tar
 
 model.fit(train_mv)
 
-print(model)
+
+temp_generator = pwfts.ProbabilisticWeightedFTS(partitioner=vtemp.partitioner, order=2)
+temp_generator.fit(train_mv['temperature'].values)
+
+#print(model)
+
+time_generator = lambda x : pd.to_datetime(x) + pd.to_timedelta(1, unit='h')
+#temp_generator = lambda x : x
+
+generators = {'time': time_generator, 'temperature': temp_generator}
+
+#print(model.predict(test_mv.iloc[:10], type='point', steps_ahead=10, generators=generators))
+#print(model.predict(test_mv.iloc[:10], type='interval', steps_ahead=10, generators=generators))
+print(model.predict(test_mv.iloc[:10], type='distribution', steps_ahead=10, generators=generators))
 
 
-print(model.predict(test_mv.iloc[:10], type='point'))
+#
-print(model.predict(test_mv.iloc[:10], type='interval'))
+
-print(model.predict(test_mv.iloc[:10], type='distribution'))
+#forecasts1 = model.predict(test_mv, type='multivariate')
+#forecasts2 = model.predict(test, type='multivariate', generators={'date': time_generator},
+#                           steps_ahead=200)
+
 
 '''
 from pyFTS.data import Enrollments