Merge branch 'master' into release1.7

pyFTS/common/transformations/roi.py

@@ -1,4 +1,5 @@
 from pyFTS.common.transformations.transformation import Transformation 
+import numpy as np
 
 
 class ROI(Transformation):

pyFTS/common/transformations/som.py

@@ -6,14 +6,14 @@ import pandas as pd
 from typing import Tuple
 from typing import List
 from pyFTS.common.transformations.transformation import Transformation 
-import SimpSOM as sps
+
 
 class SOMTransformation(Transformation):
     def __init__(self,
                  grid_dimension: Tuple,
                  **kwargs):
 
-        
+        import SimpSOM as sps
         
         # SOM attributes
         self.load_file = kwargs.get('loadFile')

pyFTS/common/transformations/trend.py

@@ -1,4 +1,8 @@
 from pyFTS.common.transformations.transformation import Transformation 
+from pandas import datetime
+from sklearn.linear_model import LinearRegression
+import numpy as np
+import pandas as pd
 
 
 class LinearTrend(Transformation):
@@ -24,8 +28,6 @@ class LinearTrend(Transformation):
         '''Regression model'''
 
     def train(self, data, **kwargs):
-        from pandas import datetime
-        from sklearn.linear_model import LinearRegression
 
         x = data[self.index_field].values
 

pyFTS/models/multivariate/variable.py

@@ -47,11 +47,11 @@ class Variable:
         :param kwargs:
         :return:
         """
-        fs = kwargs.get('partitioner', Grid.GridPartitioner)
-        mf = kwargs.get('func', Membership.trimf)
-        np = kwargs.get('npart', 10)
+        fs = kwargs.pop('partitioner', Grid.GridPartitioner)
+        mf = kwargs.pop('func', Membership.trimf)
+        np = kwargs.pop('npart', 10)
         data = kwargs.get('data', None)
-        kw = kwargs.get('partitioner_specific', {})
+        kw = kwargs.pop('partitioner_specific', {})
         self.partitioner = fs(data=data[self.data_label].values, npart=np, func=mf,
                               transformation=self.transformation, prefix=self.alias,
                               variable=self.name, **kw)

pyFTS/models/pwfts.py

@@ -661,16 +661,13 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
         return tmp
 
 
-def visualize_distributions(model, **kwargs):
-    import matplotlib.pyplot as plt
-    from matplotlib import gridspec
-    import seaborn as sns
-
+def highorder_fuzzy_markov_chain(model):
     ordered_sets = model.partitioner.ordered_sets
+    
     ftpg_keys = sorted(model.flrgs.keys(), key=lambda x: model.flrgs[x].get_midpoint(model.sets))
     
-    lhs_probs = [model.flrg_lhs_unconditional_probability(model.flrgs[k])
-                 for k in ftpg_keys]
+    lhs_probs = np.array([model.flrg_lhs_unconditional_probability(model.flrgs[k])
+                 for k in ftpg_keys])
 
     mat = np.zeros((len(ftpg_keys), len(ordered_sets)))
     for row, w in enumerate(ftpg_keys):
@@ -678,6 +675,16 @@ def visualize_distributions(model, **kwargs):
             if k in model.flrgs[w].RHS:
                 mat[row, col] = model.flrgs[w].rhs_unconditional_probability(k)
                 
+    return ftpg_keys, ordered_sets, lhs_probs, mat
+
+    
+def visualize_distributions(model, **kwargs):
+    import matplotlib.pyplot as plt
+    from matplotlib import gridspec
+    import seaborn as sns
+    
+    ftpg_keys, ordered_sets, lhs_probs, mat = highorder_fuzzy_markov_chain(model)
+
     size = kwargs.get('size', (5,10))
 
     fig = plt.figure(figsize=size)
@@ -695,3 +702,5 @@ def visualize_distributions(model, **kwargs):
     ax.set_xticklabels(ordered_sets)
     ax.grid(True)
     ax.xaxis.set_tick_params(rotation=90)
+    
+