Minor bugfixes

pyFTS/benchmarks/Measures.py

@@ -294,19 +294,24 @@ def get_point_statistics(data, model, **kwargs):
     if indexer is not None:
         ndata = np.array(indexer.get_data(data))
     else:
-        ndata = np.array(data[model.order:])
+        ndata = np.array(data)
 
     ret = list()
 
     if steps_ahead == 1:
-        forecasts = model.predict(data, **kwargs)
+        forecasts = model.predict(ndata, **kwargs)
+
+        if not isinstance(forecasts, (list, np.ndarray)):
+            forecasts = [forecasts]
+
         if model.has_seasonality:
             nforecasts = np.array(forecasts)
         else:
             nforecasts = np.array(forecasts[:-1])
-        ret.append(np.round(rmse(ndata, nforecasts), 2))
+
-        ret.append(np.round(smape(ndata, nforecasts), 2))
+        ret.append(np.round(rmse(ndata[model.order:], nforecasts), 2))
-        ret.append(np.round(UStatistic(ndata, nforecasts), 2))
+        ret.append(np.round(smape(ndata[model.order:], nforecasts), 2))
+        ret.append(np.round(UStatistic(ndata[model.order:], nforecasts), 2))
     else:
         steps_ahead_sampler = kwargs.get('steps_ahead_sampler', 1)
         nforecasts = []

pyFTS/benchmarks/Util.py

@@ -47,14 +47,17 @@ def insert_benchmark(data, conn):
 
 def process_common_data(dataset, tag, type, job):
     model = job["obj"]
-    if not model.benchmark_only:
+    if model.benchmark_only:
+        data = [dataset, tag, type, model.shortname,
+                str(model.transformations[0]) if len(model.transformations) > 0 else None,
+                model.order, None, None,
+                None, job['steps'], job['method']]
+    else:
         data = [dataset, tag, type, model.shortname,
                 str(model.partitioner.transformation) if model.partitioner.transformation is not None else None,
                 model.order, model.partitioner.name, str(model.partitioner.partitions),
                 len(model), job['steps'], job['method']]
-    else:
+
-        data = [tag, type, model.shortname, None, model.order, None, None,
-                None, job['steps'], job['method']]
     return data
 
 

pyFTS/benchmarks/arima.py

@@ -31,20 +31,27 @@ class ARIMA(fts.FTS):
         self.min_order = 1
         self.alpha = kwargs.get("alpha", 0.05)
         self.shortname += str(self.alpha)
+        self._decompose_order(self.order)
 
-    def train(self, data, sets, order, parameters=None):
+    def _decompose_order(self, order):
+        if isinstance(order, (tuple, set, list)):
             self.p = order[0]
             self.d = order[1]
             self.q = order[2]
-        self.order = self.p + self.q
+            self.order = self.p + self.q + (self.q - 1 if self.q > 0 else 0)
+            self.d = len(self.transformations)
             self.shortname = "ARIMA(" + str(self.p) + "," + str(self.d) + "," + str(self.q) + ") - " + str(self.alpha)
 
+    def train(self, data, **kwargs):
+        if kwargs.get('order', None) is not None:
+            order = kwargs.get('order', (1,0,0))
+            self._decompose_order(order)
+
         if self.indexer is not None:
             data = self.indexer.get_data(data)
 
-        data = self.apply_transformations(data, updateUoD=True)
+        #data = self.apply_transformations(data, updateUoD=True)
 
-        old_fit = self.model_fit
         try:
             self.model =  stats_arima(data, order=(self.p, self.d, self.q))
             self.model_fit = self.model.fit(disp=0)
@@ -58,34 +65,32 @@ class ARIMA(fts.FTS):
     def ma(self, data):
         return data.dot(self.model_fit.maparams)
 
-    def forecast(self, data, **kwargs):
+    def forecast(self, ndata, **kwargs):
         if self.model_fit is None:
             return np.nan
 
-        if self.indexer is not None and isinstance(data, pd.DataFrame):
+        if self.indexer is not None and isinstance(ndata, pd.DataFrame):
-            data = self.indexer.get_data(data)
+            data = self.indexer.get_data(ndata)
 
-        ndata = np.array(self.apply_transformations(data))
+        ndata = np.array(ndata)
 
         l = len(ndata)
 
         ret = []
 
-        if self.d == 0:
         ar = np.array([self.ar(ndata[k - self.p: k]) for k in np.arange(self.p, l+1)]) #+1 to forecast one step ahead given all available lags
-        else:
-            ar = np.array([ndata[k] + self.ar(ndata[k - self.p: k]) for k in np.arange(self.p, l+1)])
 
         if self.q > 0:
-            residuals = np.array([ndata[k] - ar[k - self.p] for k in np.arange(self.p, l)])
+            residuals = ndata[self.p-1:] - ar
 
-            ma = np.array([self.ma(residuals[k - self.q: k]) for k in np.arange(self.q, len(residuals)+1)])
+            ma = np.array([self.ma(residuals[k - self.q: k]) for k in np.arange(self.q, len(residuals) + 1)])
 
-            ret = ar[self.q:] + ma
+            ret = ar[self.q - 1:] + ma
+            ret = ret[self.q:]
         else:
             ret = ar
 
-        ret = self.apply_inverse_transformations(ret, params=[data[self.order - 1:]])
+        #ret = self.apply_inverse_transformations(ret, params=[data[self.order - 1:]])        nforecasts = np.array(forecasts)
 
         return ret
 
@@ -121,7 +126,7 @@ class ARIMA(fts.FTS):
 
         return ret
 
-    def forecast_ahead_interval(self, data, steps, **kwargs):
+    def forecast_ahead_interval(self, ndata, steps, **kwargs):
         if self.model_fit is None:
             return np.nan
 
@@ -129,7 +134,7 @@ class ARIMA(fts.FTS):
 
         sigma = np.sqrt(self.model_fit.sigma2)
 
-        ndata = np.array(self.apply_transformations(data))
+        #ndata = np.array(self.apply_transformations(data))
 
         l = len(ndata)
 
@@ -147,13 +152,10 @@ class ARIMA(fts.FTS):
 
             ret.append(tmp)
 
-        ret = self.apply_inverse_transformations(ret, params=[[data[-1] for a in np.arange(0, steps)]], interval=True)
+        #ret = self.apply_inverse_transformations(ret, params=[[data[-1] for a in np.arange(0, steps)]], interval=True)
 
         return ret
 
-    def empty_grid(self, resolution):
-        return self.get_empty_grid(-(self.original_max*2), self.original_max*2, resolution)
-
     def forecast_distribution(self, data, **kwargs):
 
         if self.indexer is not None and isinstance(data, pd.DataFrame):

pyFTS/benchmarks/benchmarks.py

@@ -151,7 +151,7 @@ def sliding_window_benchmarks(data, windowsize, train=0.8, **kwargs):
             elif type == 'distribution':
                 benchmark_methods = get_benchmark_probabilistic_methods()
 
-        if benchmark_models is not None:
+        if isinstance(benchmark_models, list) :
             pool.extend(benchmark_models)
         elif benchmark_methods is not None:
             for count, model in enumerate(benchmark_methods, start=0):
@@ -342,6 +342,7 @@ def run_point(mfts, partitioner, train_data, test_data, window_key=None, **kwarg
 
     if mfts.benchmark_only:
         _key = mfts.shortname + str(mfts.order if mfts.order is not None else "")
+        mfts.append_transformation(partitioner.transformation)
     else:
         pttr = str(partitioner.__module__).split('.')[-1]
         _key = mfts.shortname + " n = " + str(mfts.order) + " " + pttr + " q = " + str(partitioner.partitions)
@@ -356,6 +357,7 @@ def run_point(mfts, partitioner, train_data, test_data, window_key=None, **kwarg
     _end = time.time()
     times = _end - _start
 
+
     _start = time.time()
     _rmse, _smape, _u = Measures.get_point_statistics(test_data, mfts, **kwargs)
     _end = time.time()

pyFTS/common/FuzzySet.py

@@ -147,10 +147,18 @@ def fuzzyfy_series(data, fuzzySets, method='maximum'):
     return fts
 
 
+def grant_bounds(data, sets, ordered_sets):
+    if data < sets[ordered_sets[0]].lower:
+        return sets[ordered_sets[0]].lower
+    elif data > sets[ordered_sets[-1]].upper:
+        return sets[ordered_sets[-1]].upper
+    else:
+        return data
+
 def check_bounds(data, sets, ordered_sets):
-    if data < sets[ordered_sets[0]].get_lower():
+    if data < sets[ordered_sets[0]].lower:
         return sets[ordered_sets[0]]
-    elif data > sets[ordered_sets[-1]].get_upper():
+    elif data > sets[ordered_sets[-1]].upper:
         return sets[ordered_sets[-1]]
 
 

pyFTS/models/hofts.py

@@ -46,6 +46,7 @@ class HighOrderFTS(fts.FTS):
         self.order = kwargs.get('order',1)
         self.setsDict = {}
         self.is_high_order = True
+        self.min_order = 2
 
     def generate_lhs_flrg(self, sample):
         lags = {}

pyFTS/models/hwang.py

@@ -20,6 +20,10 @@ class HighOrderFTS(fts.FTS):
 
     def forecast(self, ndata, **kwargs):
 
+        if self.sets == None:
+            self.sets = self.partitioner.sets
+            ordered_sets = self.partitioner.ordered_sets
+        else:
             ordered_sets = FuzzySet.set_ordered(self.sets)
 
         l = len(self.sets)
@@ -35,9 +39,9 @@ class HighOrderFTS(fts.FTS):
 
             for ix in range(l):
                 s = ordered_sets[ix]
-                cn[ix] = self.sets[s].membership(ndata[t])
+                cn[ix] = self.sets[s].membership( FuzzySet.grant_bounds(ndata[t], self.sets, ordered_sets))
                 for w in range(self.order - 1):
-                    ow[w, ix] = self.sets[s].membership(ndata[t - w])
+                    ow[w, ix] = self.sets[s].membership(FuzzySet.grant_bounds(ndata[t - w], self.sets, ordered_sets))
                     rn[w, ix] = ow[w, ix] * cn[ix]
                     ft[ix] = max(ft[ix], rn[w, ix])
             mft = max(ft)
@@ -55,4 +59,7 @@ class HighOrderFTS(fts.FTS):
     def train(self, data, **kwargs):
         if kwargs.get('sets', None) is not None:
             self.sets = kwargs.get('sets', None)
-        self.order = kwargs.get('order', 1)
+        else:
+            self.sets = self.partitioner.sets
+
+        self.order = kwargs.get('order', 2)

pyFTS/tests/general.py

@@ -17,7 +17,7 @@ dataset = TAIEX.get_data()
 
 from pyFTS.benchmarks import benchmarks as bchmk, Util as bUtil, Measures
 
-from pyFTS.models import pwfts
+from pyFTS.models import pwfts, song
 '''
 from pyFTS.partitioners import Grid, Util as pUtil
 partitioner = Grid.GridPartitioner(data=dataset[:800], npart=10, transformation=tdiff)
@@ -32,12 +32,19 @@ print(Measures.get_distribution_statistics(dataset[800:1000], model, steps_ahead
 '''
 
 #'''
+
+from pyFTS.benchmarks import arima, naive, quantreg
+
 bchmk.sliding_window_benchmarks(dataset[:1000], 1000, train=0.8, inc=0.2,
-                                #methods=[pwfts.ProbabilisticWeightedFTS],
+                                #methods=[song.ConventionalFTS], #[pwfts.ProbabilisticWeightedFTS],
-                                benchmark_models=False,
+                                benchmark_models=True,
-                                #transformations=[tdiff],
+                                benchmark_methods=[naive.Naive, arima.ARIMA,arima.ARIMA], #arima.ARIMA,arima.ARIMA],
-                                orders=[1], #[1, 2, 3],
+                                #benchmark_methods=[arima.ARIMA],
-                                partitions=[20], #np.arange(10, 100, 5),
+                                benchmark_methods_parameters=[1,(1,0,0),(1,0,1)], #(2,0,1),(2,0,2)],
+                                #benchmark_methods_parameters=[(1,0,0)],
+                                transformations=[None, tdiff],
+                                orders=[1, 2, 3],
+                                partitions=[35], #np.arange(10, 100, 5),
                                 progress=True, type='point',
                                 #steps_ahead=[1,4,7,10], #steps_ahead=[1]
                                 #distributed=True, nodes=['192.168.0.110', '192.168.0.105','192.168.0.106'],