replacing the deprecated append method with the concat method in pandas

.gitignore

@@ -0,0 +1,57 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/

MANIFEST

@@ -104,7 +104,7 @@ pyFTS/models/seasonal/common.py
 pyFTS/models/seasonal/msfts.py
 pyFTS/models/seasonal/partitioner.py
 pyFTS/models/seasonal/sfts.py
-pyFTS/partitioners/CMeans.py
+pyFTS/partitioners/KMeans.py
 pyFTS/partitioners/Entropy.py
 pyFTS/partitioners/FCM.py
 pyFTS/partitioners/Grid.py

README.md

@@ -38,7 +38,7 @@ Fuzzy Time Series (FTS) are non parametric methods for time series forecasting b
 2. **Universe of Discourse Partitioning**: This is the most important step. Here, the range of values of the numerical time series *Y(t)* will be splited in overlapped intervals and for each interval will be created a Fuzzy Set. This step is performed by pyFTS.partition module and its classes (for instance GridPartitioner, EntropyPartitioner, etc). The main parameters are:
  - the number of intervals
  - which fuzzy membership function (on [pyFTS.common.Membership](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/common/Membership.py))
- - partition scheme ([GridPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py), [EntropyPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py)[3], [FCMPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py), [CMeansPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/CMeans.py), [HuarngPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py)[4])
+ - partition scheme ([GridPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py), [EntropyPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py)[3], [FCMPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py), [KMeansPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/KMeans.py), [HuarngPartitioner](https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py)[4])
  
  Check out the jupyter notebook on [notebooks/Partitioners.ipynb](https://github.com/PYFTS/notebooks/blob/master/Partitioners.ipynb) for sample codes.
  

docs/pyFTS.partitioners.rst

@@ -28,10 +28,10 @@ pyFTS.partitioners.Class module
     :undoc-members:
     :show-inheritance:
 
-pyFTS.partitioners.CMeans module
+pyFTS.partitioners.KMeans module
 --------------------------------
 
-.. automodule:: pyFTS.partitioners.CMeans
+.. automodule:: pyFTS.partitioners.KMeans
     :members:
     :undoc-members:
     :show-inheritance:

pyFTS/common/transformations/trend.py

@@ -1,5 +1,5 @@
 from pyFTS.common.transformations.transformation import Transformation 
-from pandas import datetime
+# from pandas import datetime
 from sklearn.linear_model import LinearRegression
 import numpy as np
 import pandas as pd

pyFTS/models/multivariate/cmvfts.py

@@ -146,7 +146,7 @@ class ClusteredMVFTS(mvfts.MVFTS):
 
             new_data_point[self.target_variable.data_label] = tmp.expected_value()
 
-            sample = sample.append(new_data_point, ignore_index=True)
+            sample = pd.concat([sample, pd.DataFrame([new_data_point])], ignore_index=True)
 
         return ret[-steps:]
 
@@ -199,7 +199,7 @@ class ClusteredMVFTS(mvfts.MVFTS):
         for k in np.arange(0, steps):
             sample = ret.iloc[k:self.order+k]
             tmp = self.forecast_multivariate(sample, **kwargs)
-            ret = ret.append(tmp, ignore_index=True)
+            ret = pd.concat([ret, pd.DataFrame([tmp])], ignore_index=True)
 
         return ret
 

pyFTS/models/multivariate/mvfts.py

@@ -211,7 +211,7 @@ class MVFTS(fts.FTS):
 
             new_data_point[self.target_variable.data_label] = tmp
 
-            ndata = ndata.append(new_data_point, ignore_index=True)
+            ndata = pd.concat([ndata, pd.DataFrame([new_data_point])], ignore_index=True)
 
         return ret[-steps:]
 
@@ -307,8 +307,8 @@ class MVFTS(fts.FTS):
             new_data_point_lo[self.target_variable.data_label] = min(tmp_lo)
             new_data_point_up[self.target_variable.data_label] = max(tmp_up)
 
-            lo = lo.append(new_data_point_lo, ignore_index=True)
-            up = up.append(new_data_point_up, ignore_index=True)
+            lo = pd.concat([lo, pd.DataFrame([new_data_point_lo])], ignore_index=True)
+            up = pd.concat([up, pd.DataFrame([new_data_point_up])], ignore_index=True)
 
         return ret[-steps:]
 

pyFTS/models/multivariate/wmvfts.py

@@ -69,7 +69,7 @@ class WeightedMVFTS(mvfts.MVFTS):
         self.shortname = "WeightedMVFTS"
         self.name = "Weighted Multivariate FTS"
         self.has_classification = True
-        self.class_weigths : dict = kwargs.get("class_weights", {})
+        self.class_weights : dict = kwargs.get("class_weights", {})
         
 
     def generate_flrg(self, flrs):
@@ -102,7 +102,7 @@ class WeightedMVFTS(mvfts.MVFTS):
                     for k,v in _flrg.RHS.items():
                         classification[k] += (v / _flrg.count) * mb
                 
-            classification = activation(classification, self.class_weigths)
+            classification = activation(classification, self.class_weights)
 
             ret.append(classification)
 

pyFTS/partitioners/FCM.py

@@ -36,7 +36,7 @@ def fuzzy_cmeans(k, data, size, m, deltadist=0.001):
     centroids = [data[rnd.randint(0, data_length - 1)] for kk in range(0, k)]
 
     # Membership table
-    membership_table = np.zeros((k, data_length)) #[[0 for kk in range(0, k)] for xx in range(0, data_length)]
+    membership_table = np.zeros((data_length, k))
 
     mean_change = 1000
 
@@ -50,12 +50,12 @@ def fuzzy_cmeans(k, data, size, m, deltadist=0.001):
         inst_count = 0
         for instance in data:
 
-            dist_groups = np.zeros(k) #[0 for xx in range(0, k)]
+            dist_groups = np.zeros(k)
 
             for group_count, group in enumerate(centroids):
                 dist_groups[group_count] = fuzzy_distance(group, instance)
 
-            dist_groups_total = functools.reduce(operator.add, [xk for xk in dist_groups])
+            # dist_groups_total = functools.reduce(operator.add, [xk for xk in dist_groups])
 
             for grp in range(0, k):
                 if dist_groups[grp] == 0:

pyFTS/partitioners/Huarng.py

@@ -19,13 +19,13 @@ class HuarngPartitioner(partitioner.Partitioner):
     def build(self, data):
         diff = Transformations.Differential(1)
         data2 = diff.apply(data)
-        davg = np.abs( np.mean(data2) / 2 )
+        divs = np.abs( np.mean(data2) / 2 )
 
-        if davg <= 1.0:
+        if divs <= 1.0:
             base = 0.1
-        elif 1 < davg <= 10:
+        elif 1 < divs <= 10:
             base = 1.0
-        elif 10 < davg <= 100:
+        elif 10 < divs <= 100:
             base = 10
         else:
             base = 100

pyFTS/partitioners/KMeans.py

@@ -14,15 +14,15 @@ def distance(x, y):
     return math.sqrt(tmp)
 
 
-def c_means(k, dados, tam):
-    # Inicializa as centróides escolhendo elementos aleatórios dos conjuntos
+def k_means(k, dados, tam):
+    # Инициализирует центроиды, выбирая случайные элементы из множества
     centroides = [dados[rnd.randint(0, len(dados)-1)] for kk in range(0, k)]
 
     grupos = [-1 for x in range(0, len(dados))]
 
     it_semmodificacao = 0
 
-    # para cada instância
+    # для каждого экземпляра
     iteracoes = 0
     while iteracoes < 1000 and it_semmodificacao < 10:
         inst_count = 0
@@ -31,7 +31,7 @@ def c_means(k, dados, tam):
 
         for instancia in dados:
 
-            # verifica a distância para cada centroide
+            # проверяет расстояние до каждого центроида
             grupo_count = 0
             dist = 10000
 
@@ -41,7 +41,7 @@ def c_means(k, dados, tam):
                 tmp = distance(instancia, grupo)
                 if tmp < dist:
                     dist = tmp
-                    # associa a a centroide de menor distância à instância
+                    # ассоциирует центроид с наименьшим расстоянием до экземпляра
                     grupos[inst_count] = grupo_count
                 grupo_count = grupo_count + 1
 
@@ -55,7 +55,7 @@ def c_means(k, dados, tam):
         else:
             it_semmodificacao = 0
 
-        # atualiza cada centroide com base nos valores médios de todas as instâncias à ela associadas
+        # обновляет каждый центроид на основе средних значений всех связанных с ним экземпляров
         grupo_count = 0
         for grupo in centroides:
             total_inst = functools.reduce(operator.add, [1 for xx in grupos if xx == grupo_count], 0)
@@ -77,21 +77,21 @@ def c_means(k, dados, tam):
     return centroides
 
 
-class CMeansPartitioner(partitioner.Partitioner):
+class KMeansPartitioner(partitioner.Partitioner):
     def __init__(self, **kwargs):
-        super(CMeansPartitioner, self).__init__(name="CMeans", **kwargs)
+        super(KMeansPartitioner, self).__init__(name="KMeans", **kwargs)
 
     def build(self, data):
         sets = {}
 
         kwargs = {'type': self.type, 'variable': self.variable}
 
-        centroides = c_means(self.partitions, data, 1)
+        centroides = k_means(self.partitions, data, 1)
         centroides.append(self.max)
         centroides.append(self.min)
         centroides = list(set(centroides))
         centroides.sort()
-        for c in np.arange(1, len(centroides) - 1):
+        for c in range(1, len(centroides) - 1):
             _name = self.get_name(c)
             sets[_name] = FuzzySet.FuzzySet(_name, Membership.trimf,
                                  [round(centroides[c - 1], 3), round(centroides[c], 3), round(centroides[c + 1], 3)],

pyFTS/partitioners/Util.py

@@ -18,19 +18,20 @@ all_methods = [Grid.GridPartitioner, Entropy.EntropyPartitioner, FCM.FCMPartitio
 mfs = [Membership.trimf, Membership.gaussmf, Membership.trapmf]
 
 
-def plot_sets(data, sets: dict, titles : list, size=[12, 10], save=False, file=None, axis=None):
+def plot_sets(sets: dict, titles : list, size=[12, 10], save=False, file=None, axis=None):
     """
     Plot all fuzzy sets in a Partitioner
     
     """
     num = len(sets)
+    num_cols_plot = 1
 
     if axis is None:
-        fig, axes = plt.subplots(nrows=num, ncols=1,figsize=size)
-    for k in np.arange(0,num):
+        fig, axes = plt.subplots(nrows=num, ncols=num_cols_plot, figsize=size, squeeze=False)
+    for k in range(num):
         ticks = []
         x = []
-        ax = axes[k] if axis is None else axis
+        ax = axes[k, num_cols_plot-1] if axis is None else axis
         ax.set_title(titles[k])
         ax.set_ylim([0, 1.1])
         for key in sets[k].keys():
@@ -54,7 +55,7 @@ def plot_sets(data, sets: dict, titles : list, size=[12, 10], save=False, file=N
         Util.show_and_save_image(fig, file, save)
 
 
-def plot_partitioners(data, objs, tam=[12, 10], save=False, file=None, axis=None):
+def plot_partitioners(objs, tam=[12, 10], save=False, file=None, axis=None):
     sets = [k.sets for k in objs]
     titles = [k.name for k in objs]
     plot_sets(sets, titles, tam, save, file, axis)

pyFTS/partitioners/partitioner.py

@@ -1,6 +1,7 @@
 from pyFTS.common import FuzzySet, Membership
 import numpy as np
 from scipy.spatial import KDTree
+import warnings
 
 
 class Partitioner(object):
@@ -45,6 +46,9 @@ class Partitioner(object):
         if kwargs.get('preprocess',True):
 
             data = kwargs.get('data',[None])
+            
+            if isinstance(data, np.ndarray) and len(data.shape) > 1:
+                warnings.warn(f"An ndarray of dimension greater than 1 is used. shape.len(): {len(data.shape)}")
 
             if self.indexer is not None:
                 ndata = self.indexer.get_data(data)

pyFTS/tests/cmsfts.py

@@ -11,7 +11,7 @@ from mpl_toolkits.mplot3d import Axes3D
 import datetime
 
 import pandas as pd
-from pyFTS.partitioners import Grid, CMeans, FCM, Entropy
+from pyFTS.partitioners import Grid, KMeans, FCM, Entropy
 from pyFTS.common import FLR, FuzzySet, Membership, Transformations, Util, fts
 from pyFTS import sfts
 from pyFTS.models import msfts

setup.py

@@ -26,6 +26,7 @@ setuptools.setup(
         'Programming Language :: Python :: 3.6',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.10',
+        'Programming Language :: Python :: 3.11',
         'Intended Audience :: Science/Research',
         'Intended Audience :: Developers',
         'Intended Audience :: Education',