Bugfixes and improvements on pwfts and multivariate.granular

pyFTS/benchmarks/Measures.py

@@ -300,6 +300,9 @@ def crps(targets, densities):
         targets = [targets]
 
     n = len(densities)
+    if n == 0:
+        return np.nan
+
     for ct, df in enumerate(densities):
         _crps += np.nansum([(df.cumulative(bin) - (1 if bin >= targets[ct] else 0)) ** 2 for bin in df.bins])
 

pyFTS/common/Util.py

@@ -216,7 +216,7 @@ def plot_distribution2(probabilitydist, data, **kwargs):
     if kwargs.get('median',True):
         y = [data[start_at]]
         for pd in probabilitydist:
-            qts = pd.quantile(.5)
+            qts = pd.quantile([.5])
             y.append(qts[0])
 
         ax.plot(x, y, color='red', label='Median')

pyFTS/hyperparam/Evolutionary.py

@@ -139,24 +139,33 @@ def evaluate(dataset, individual, **kwargs):
 
     for count, train, test in Util.sliding_window(dataset, window_size, train=train_rate, inc=increment_rate):
 
-        model = phenotype(individual, train, fts_method=fts_method, parameters=parameters)
+        try:
 
-        forecasts = model.predict(test)
+            model = phenotype(individual, train, fts_method=fts_method, parameters=parameters)
 
-        rmse = Measures.rmse(test[model.max_lag:], forecasts[:-1])
+            forecasts = model.predict(test)
-        lengths.append(len(model))
 
-        errors.append(rmse)
+            rmse = Measures.rmse(test[model.max_lag:], forecasts[:-1])
+            lengths.append(len(model))
 
-    _lags = sum(model.lags) * 100
+            errors.append(rmse)
 
-    _rmse = np.nanmean(errors)
+        except:
-    _len = np.nanmean(lengths)
+            lengths.append(np.nan)
+            errors.append(np.nan)
 
-    f1 = np.nansum([.6 * _rmse, .4 * np.nanstd(errors)])
+    try:
-    f2 = np.nansum([.4 * _len, .6 * _lags])
+        _lags = sum(model.lags) * 100
 
-    return {'f1': f1, 'f2': f2, 'rmse': _rmse, 'size': _len }
+        _rmse = np.nanmean(errors)
+        _len = np.nanmean(lengths)
+
+        f1 = np.nansum([.6 * _rmse, .4 * np.nanstd(errors)])
+        f2 = np.nansum([.4 * _len, .6 * _lags])
+
+        return {'f1': f1, 'f2': f2, 'rmse': _rmse, 'size': _len }
+    except:
+        return {'f1': np.inf, 'f2': np.inf, 'rmse': np.inf, 'size': np.inf}
 
 
 def tournament(population, objective, **kwargs):

pyFTS/models/multivariate/granular.py

@@ -15,8 +15,8 @@ class GranularWMVFTS(cmvfts.ClusteredMVFTS):
         """The most recent trained model"""
         self.knn = kwargs.get('knn', 2)
         self.order = kwargs.get("order", 2)
-        self.shortname = "GranularWMVFTS"
+        self.shortname = "FIG-FTS"
-        self.name = "Granular Weighted Multivariate FTS"
+        self.name = "Fuzzy Information Granular FTS"
         self.mode = kwargs.get('mode','sets')
 
     def train(self, data, **kwargs):

pyFTS/models/pwfts.py

@@ -165,8 +165,8 @@ class ProbabilisticWeightedFTS(ifts.IntervalFTS):
 
     def pwflrg_lhs_memberhip_fuzzyfied(self, flrg, sample):
         vals = []
-        for ct, fuzz in enumerate(sample):
+        for ct in range(len(flrg.LHS)): # fuzz in enumerate(sample):
-            vals.append([mv for fset, mv in fuzz if fset == flrg.LHS[ct]])
+            vals.append([mv for fset, mv in sample[ct] if fset == flrg.LHS[ct]])
 
         return np.nanprod(vals)
 

pyFTS/probabilistic/ProbabilityDistribution.py

@@ -217,7 +217,7 @@ class ProbabilityDistribution(object):
         else:
             try:
                 k = self.bin_index.find_ge(values)
-                return self.cdf[values]
+                return self.cdf[k]
             except:
                 return np.nan
 

pyFTS/tests/multivariate.py

@@ -19,9 +19,33 @@ from pyFTS.common import Membership
 
 
 import os
+'''
+def sample_by_hour(data):
+    return [np.nanmean(data[k:k+60]) for k in np.arange(0,len(data),60)]
+
+def sample_date_by_hour(data):
+    return [data[k] for k in np.arange(0,len(data),60)]
+
+from pyFTS.data import SONDA
+
+sonda = SONDA.get_dataframe()[['datahora','glo_avg','ws_10m']]
+
+sonda = sonda.drop(sonda.index[np.where(sonda["ws_10m"] <= 0.01)])
+sonda = sonda.drop(sonda.index[np.where(sonda["glo_avg"] <= 0.01)])
+sonda = sonda.dropna()
+sonda['datahora'] = pd.to_datetime(sonda["datahora"], format='%Y-%m-%d %H:%M:%S')
 
 
-from pyFTS.data import SONDA, Malaysia
+var = {
+    'datahora': sample_date_by_hour(sonda['datahora'].values),
+    'glo_avg': sample_by_hour(sonda['glo_avg'].values),
+    'ws_10m': sample_by_hour(sonda['ws_10m'].values)
+}
+
+df = pd.DataFrame(var)
+'''
+
+from pyFTS.data import Malaysia
 
 df = Malaysia.get_dataframe()
 df['time'] = pd.to_datetime(df["time"], format='%m/%d/%y %I:%M %p')
@@ -39,11 +63,10 @@ variables = {
                          alpha_cut=.25)
 }
 
-methods = [mvfts.MVFTS, wmvfts.WeightedMVFTS, granular.GranularWMVFTS]
+
-#methods = [granular.GranularWMVFTS]
+methods = [granular.GranularWMVFTS]
 
 parameters = [
-    {},{},
     dict(fts_method=pwfts.ProbabilisticWeightedFTS, fuzzyfy_mode='both',
                 order=1, knn=1)
 ]
@@ -52,16 +75,16 @@ bchmk.multivariate_sliding_window_benchmarks2(df, 10000, train=0.9, inc=0.25,
                                               methods=methods,
                                               methods_parameters=parameters,
                                               variables=variables,
-                                              target_variable='Load',
+                                              target_variable='Temperature',
-                                              type='interval',
+                                              type='distribution',
                                               steps_ahead=[1],
-                                              distributed=False,
+                                              file="experiments.db", dataset='Malaysia.temperature',
-                                              nodes=['192.168.0.110', '192.168.0.107', '192.168.0.106'],
-                                              file="experiments.db", dataset='Malaysia',
                                               tag="experiments"
                                               )
 
 
+
+
 '''
 from pyFTS.data import lorentz
 df = lorentz.get_dataframe(iterations=5000)

pyFTS/tests/pwfts.py

@@ -19,63 +19,18 @@ from pyFTS.models.seasonal import partitioner as seasonal
 from pyFTS.models.seasonal.common import DateTime
 from pyFTS.common import Membership
 
-def sample_by_hour(data):
-    return [np.nanmean(data[k:k+60]) for k in np.arange(0,len(data),60)]
-
-def sample_date_by_hour(data):
-    return [data[k] for k in np.arange(0,len(data),60)]
-
 from pyFTS.data import SONDA
 
-sonda = SONDA.get_dataframe()[['datahora','glo_avg','ws_10m']]
+data = [k for k in SONDA.get_data('ws_10m') if k > 0.1 and k != np.nan and k is not None]
+data = [np.nanmean(data[k:k+60]) for k in np.arange(0,len(data),60)]
 
-sonda = sonda.drop(sonda.index[np.where(sonda["ws_10m"] <= 0.01)])
+train = data[:9000]
-sonda = sonda.drop(sonda.index[np.where(sonda["glo_avg"] <= 0.01)])
+test = data[9000:10000]
-sonda = sonda.dropna()
-sonda['datahora'] = pd.to_datetime(sonda["datahora"], format='%Y-%m-%d %H:%M:%S')
 
+fs = Grid.GridPartitioner(data=train, npart=95)
 
-var = {
+model = pwfts.ProbabilisticWeightedFTS(partitioner=fs, order=3)
-    'datahora': sample_date_by_hour(sonda['datahora'].values),
-    'glo_avg': sample_by_hour(sonda['glo_avg'].values),
-    'ws_10m': sample_by_hour(sonda['ws_10m'].values),
-}
 
-df = pd.DataFrame(var)
+model.fit(train)
-
-train_mv = df.iloc[:9000]
-test_mv = df.iloc[9000:10000]
-
-fig, ax = plt.subplots(nrows=2, ncols=1, figsize=[10,3])
-
-sp = {'seasonality': DateTime.month, 'names': ['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']}
-
-vmonth = variable.Variable("Month", data_label="datahora", partitioner=seasonal.TimeGridPartitioner, npart=12,
-                          data=train_mv, partitioner_specific=sp, alpha_cut=.3)
-
-vmonth.partitioner.plot(ax[0])
-
-vwin = variable.Variable("Wind", data_label="ws_10m", alias='wind',
-                         partitioner=Grid.GridPartitioner, npart=15, func=Membership.gaussmf,
-                         data=train_mv, alpha_cut=.25)
-
-vwin.partitioner.plot(ax[1])
-
-plt.tight_layout()
-
-order = 3
-knn = 2
-
-model = granular.GranularWMVFTS(explanatory_variables=[vmonth, vwin], target_variable=vwin,
-                                fts_method=pwfts.ProbabilisticWeightedFTS, fuzzyfy_mode='both',
-                                order=order, knn=knn)
-
-model.fit(train_mv)
-
-fig, ax = plt.subplots(nrows=1, ncols=1, figsize=[15,3])
-ax.plot(test_mv['ws_10m'].values[:100], label='original')
-
-forecasts = model.predict(test_mv.iloc[:100], type='distribution')
-
-Util.plot_distribution2(forecasts, test_mv['ws_10m'].values[:100], start_at=model.order-1, ax=ax)
 
+model.predict(test)