Improvements of FCM_FTS

pyFTS/fcm/GA.py

@@ -4,7 +4,6 @@ import math
 import time
 from functools import reduce
 from operator import itemgetter
-import dispy
 
 import random
 from pyFTS.common import Util
@@ -13,7 +12,6 @@ from pyFTS.partitioners import Grid, Entropy  # , Huarng
 from pyFTS.models import hofts
 from pyFTS.common import Membership
 from pyFTS.hyperparam import Util as hUtil
-from pyFTS.distributed import dispy as dUtil
 
 from pyFTS.fcm import common, fts
 
@@ -267,6 +265,8 @@ def GeneticAlgorithm(dataset, **kwargs):
             ret = evaluate(dataset, individual, **kwargs)
             individual['rmse'] = ret['rmse']
     elif distributed=='dispy':
+        import dispy
+        from pyFTS.distributed import dispy as dUtil
         jobs = []
         for ct, individual in enumerate(population):
             job = cluster.submit(dataset, individual, **kwargs)
@@ -396,13 +396,17 @@ def log_result(conn, datasetname, result):
 
 
 def execute(datasetname, dataset, **kwargs):
-    conn = hUtil.open_hyperparam_db('hyperparam.db')
+    file = kwargs.get('file', 'hyperparam.db')
+
+    conn = hUtil.open_hyperparam_db(file)
 
     experiments = kwargs.get('experiments', 30)
 
     distributed = kwargs.get('distributed', False)
 
     if distributed == 'dispy':
+        import dispy
+        from pyFTS.distributed import dispy as dUtil
         nodes = kwargs.get('nodes', ['127.0.0.1'])
         cluster, http_server = dUtil.start_dispy_cluster(evaluate, nodes=nodes)
         kwargs['cluster'] = cluster

pyFTS/fcm/fts.py

@@ -1,6 +1,6 @@
 from pyFTS.common import fts
 from pyFTS.models import hofts
-from pyFTS.fcm import common
+from pyFTS.fcm import common, GA, Activations
 import numpy as np
 
 
@@ -10,6 +10,10 @@ class FCM_FTS(hofts.HighOrderFTS):
         super(FCM_FTS, self).__init__(**kwargs)
         self.fcm = common.FuzzyCognitiveMap(**kwargs)
 
+    def train(self, data, **kwargs):
+        ret = GA.execute(data, **kwargs)
+        self.fcm.weights = ret['weights']
+
     def forecast(self, ndata, **kwargs):
         ret = []
 

pyFTS/hyperparam/Evolutionary.py

@@ -562,7 +562,7 @@ def execute(datasetname, dataset, **kwargs):
 
     :param datasetname:
     :param dataset: The time series to optimize the FTS
-    :keyword database_file:
+    :keyword file:
     :keyword experiments:
     :keyword distributed:
     :keyword ngen: An integer value with the maximum number of generations, default value: 30
@@ -591,7 +591,7 @@ def execute(datasetname, dataset, **kwargs):
     :return: the best genotype
     """
 
-    file = kwargs.get('database_file', 'hyperparam.db')
+    file = kwargs.get('file', 'hyperparam.db')
 
     conn = hUtil.open_hyperparam_db(file)
 

pyFTS/hyperparam/GridSearch.py

@@ -127,7 +127,9 @@ def execute(hyperparams, datasetname, dataset, **kwargs):
     print("Evaluation values: \n {}".format(hp_values))
     
     cluster, http_server = dUtil.start_dispy_cluster(cluster_method, nodes=nodes)
-    conn = hUtil.open_hyperparam_db('hyperparam.db')
+    file = kwargs.get('file', 'hyperparam.db')
+
+    conn = hUtil.open_hyperparam_db(file)
 
     for instance in product(*hp_values):
         partitions = instance[index['partitions']]