Bugfixes in MVFTS and DEHO

pyFTS/hyperparam/mvfts.py

@@ -75,9 +75,14 @@ def random_genotype(**kwargs):
     explanatory_params = []
 
     for v in explanatory_variables:
+        var = vars[v]
+        if var['type'] == 'common':
+            npart = random.randint(7, 50)
+        else:
+            npart = var['npart']
         param = {
             'mf': random.randint(1, 4),
-            'npart': random.randint(10, 50),
+            'npart': npart,
             'partitioner': 1, #random.randint(1, 2),
             'alpha': random.uniform(0, .5)
         }
@@ -85,7 +90,7 @@ def random_genotype(**kwargs):
 
     target_params = {
             'mf': random.randint(1, 4),
-            'npart': random.randint(10, 50),
+            'npart': random.randint(7, 50),
             'partitioner': 1, #random.randint(1, 2),
             'alpha': random.uniform(0, .5)
         }
@@ -133,6 +138,8 @@ def phenotype(individual, train, fts_method, parameters={}, **kwargs):
                                    partitioner_specific={'mf': mf}, npart=tparams['npart'], alpha_cut=tparams['alpha'],
                                     data=train)
 
+    explanatory_vars.append(target_var)
+
     model = fts_method(explanatory_variables=explanatory_vars, target_variable=target_var, **parameters)
     model.fit(train, **parameters)
 
@@ -171,6 +178,7 @@ def evaluate(dataset, individual, **kwargs):
     :param parameters: dict with model specific arguments for fit method.
     :return: a tuple (len_lags, rmse) with the parsimony fitness value and the accuracy fitness value
     """
+    import logging
     from pyFTS.models import hofts, ifts, pwfts
     from pyFTS.common import Util
     from pyFTS.benchmarks import Measures

pyFTS/partitioners/partitioner.py

@@ -2,7 +2,7 @@ from pyFTS.common import FuzzySet, Membership
 import numpy as np
 from scipy.spatial import KDTree
 import matplotlib.pylab as plt
-
+import logging
 
 class Partitioner(object):
     """
@@ -154,7 +154,6 @@ class Partitioner(object):
         method = kwargs.get('method', 'fuzzy')
 
         nearest = self.search(data, type='index')
-
         mv = np.zeros(self.partitions)
 
         for ix in nearest:
@@ -317,16 +316,20 @@ class Partitioner(object):
         it represents the fuzzy set name.
         :return: the fuzzy set
         """
-        if isinstance(item, (int, np.int, np.int8, np.int16, np.int32, np.int64)):
-            if item < 0 or item >= self.partitions:
-                raise ValueError("The fuzzy set index must be between 0 and {}.".format(self.partitions))
-            return self.sets[self.ordered_sets[item]]
-        elif isinstance(item, str):
-            if item not in self.sets:
-                raise ValueError("The fuzzy set with name {} does not exist.".format(item))
-            return self.sets[item]
-        else:
-            raise ValueError("The parameter 'item' must be an integer or a string and the value informed was {} of type {}!".format(item, type(item)))
+        try:
+            if isinstance(item, (int, np.int, np.int8, np.int16, np.int32, np.int64)):
+                if item < 0 or item >= self.partitions:
+                    raise ValueError("The fuzzy set index must be between 0 and {}.".format(self.partitions))
+                return self.sets[self.ordered_sets[item]]
+            elif isinstance(item, str):
+                if item not in self.sets:
+                    raise ValueError("The fuzzy set with name {} does not exist.".format(item))
+                return self.sets[item]
+            else:
+                raise ValueError("The parameter 'item' must be an integer or a string and the value informed was {} of type {}!".format(item, type(item)))
+        except Exception as ex:
+            logging.exception("Error")
+
 
     def __iter__(self):
         """

pyFTS/tests/hyperparam.py

@@ -17,7 +17,7 @@ def get_dataset():
     data['time'] = pd.to_datetime(data["time"], format='%m/%d/%y %I:%M %p')
 
     #return 'SONDA.ws_10m', data
-    return 'Malaysia', data.iloc[:5000] #train, test
+    return 'Malaysia', data.iloc[:2000] #train, test
     #return 'Malaysia.temperature', data  # train, test
 
 '''
@@ -47,7 +47,6 @@ datsetname, dataset  = get_dataset()
 #                   window_size=10000, train_rate=.9, increment_rate=1,)
 
 explanatory_variables =[
-    {'name': 'Load', 'data_label': 'load', 'type': 'common'},
     {'name': 'Temperature', 'data_label': 'temperature', 'type': 'common'},
     {'name': 'Daily', 'data_label': 'time', 'type': 'seasonal', 'seasonality': DateTime.minute_of_day, 'npart': 24 },
     {'name': 'Weekly', 'data_label': 'time', 'type': 'seasonal', 'seasonality': DateTime.day_of_week, 'npart': 7 },
@@ -59,13 +58,13 @@ target_variable = {'name': 'Load', 'data_label': 'load', 'type': 'common'}
 nodes=['192.168.28.38']
 deho_mv.execute(datsetname, dataset,
               ngen=10, npop=10,psel=0.6, pcross=.5, pmut=.3,
-              window_size=5000, train_rate=.9, increment_rate=1,
+              window_size=2000, train_rate=.9, increment_rate=1,
               experiments=1,
               fts_method=wmvfts.WeightedMVFTS,
               variables=explanatory_variables,
               target_variable=target_variable,
-              distributed='dispy', nodes=nodes,
-              #parameters=dict(num_batches=5)
+              #distributed='dispy', nodes=nodes,
+              parameters=dict(num_batches=5)
               #parameters=dict(distributed='dispy', nodes=nodes, num_batches=5)
               )
 

pyFTS/tests/multivariate.py

@@ -23,8 +23,8 @@ from pyFTS.data import Malaysia, Enrollments
 df = Malaysia.get_dataframe()
 df['time'] = pd.to_datetime(df["time"], format='%m/%d/%y %I:%M %p')
 
-train_mv = df.iloc[:4500]
-test_mv = df.iloc[4500:5000]
+train_mv = df.iloc[:1800]
+test_mv = df.iloc[1800:2000]
 
 del(df)