Bugfixes and improvements on benchmark methods

pyFTS/benchmarks/BSTS.py

@@ -21,6 +21,7 @@ class ARIMA(fts.FTS):
         self.has_point_forecasting = True
         self.has_interval_forecasting = True
         self.has_probability_forecasting = True
+        self.uod_clip = False
         self.model = None
         self.model_fit = None
         self.trained_data = None

pyFTS/benchmarks/arima.py

@@ -21,6 +21,7 @@ class ARIMA(fts.FTS):
         self.has_point_forecasting = True
         self.has_interval_forecasting = True
         self.has_probability_forecasting = True
+        self.uod_clip = False
         self.model = None
         self.model_fit = None
         self.trained_data = None
@@ -96,6 +97,11 @@ class ARIMA(fts.FTS):
         if self.model_fit is None:
             return np.nan
 
+        if 'alpha' in kwargs:
+            alpha = kwargs.get('alpha',0.05)
+        else:
+            alpha = self.alpha
+
         sigma = np.sqrt(self.model_fit.sigma2)
 
         l = len(data)
@@ -112,8 +118,8 @@ class ARIMA(fts.FTS):
             if isinstance(mean,(list, np.ndarray)):
                 mean = mean[0]
 
-            tmp.append(mean + st.norm.ppf(self.alpha) * sigma)
+            tmp.append(mean + st.norm.ppf(alpha) * sigma)
-            tmp.append(mean + st.norm.ppf(1 - self.alpha) * sigma)
+            tmp.append(mean + st.norm.ppf(1 - alpha) * sigma)
 
             ret.append(tmp)
 
@@ -123,6 +129,11 @@ class ARIMA(fts.FTS):
         if self.model_fit is None:
             return np.nan
 
+        if 'alpha' in kwargs:
+            alpha = kwargs.get('alpha',0.05)
+        else:
+            alpha = self.alpha
+
         smoothing = kwargs.get("smoothing",0.5)
 
         sigma = np.sqrt(self.model_fit.sigma2)
@@ -138,8 +149,8 @@ class ARIMA(fts.FTS):
 
             hsigma = (1 + k*smoothing)*sigma
 
-            tmp.append(nmeans[k] + st.norm.ppf(self.alpha) * hsigma)
+            tmp.append(nmeans[k] + st.norm.ppf(alpha) * hsigma)
-            tmp.append(nmeans[k] + st.norm.ppf(1 - self.alpha) * hsigma)
+            tmp.append(nmeans[k] + st.norm.ppf(1 - alpha) * hsigma)
 
             ret.append(tmp)
 
@@ -207,3 +218,4 @@ class ARIMA(fts.FTS):
             ret.append(dist)
 
         return ret
+

pyFTS/benchmarks/quantreg.py

@@ -19,6 +19,7 @@ class QuantileRegression(fts.FTS):
         self.has_point_forecasting = True
         self.has_interval_forecasting = True
         self.has_probability_forecasting = True
+        self.uod_clip = False
         self.benchmark_only = True
         self.min_order = 1
         self.alpha = kwargs.get("alpha", 0.05)
@@ -96,7 +97,7 @@ class QuantileRegression(fts.FTS):
 
     def forecast_ahead_interval(self, ndata, steps, **kwargs):
 
-        smoothing = kwargs.get("smoothing", 0.9)
+        smoothing = kwargs.get("smoothing", 0.1)
 
         l = len(ndata)
 
@@ -110,7 +111,9 @@ class QuantileRegression(fts.FTS):
         for k in np.arange(self.order, steps+self.order):
             intl = self.point_to_interval(nmeans[k - self.order: k], self.lower_qt, self.upper_qt)
 
-            ret.append([intl[0]*(1 + k*smoothing), intl[1]*(1 + k*smoothing)])
+            tmpk = k-self.order
+
+            ret.append([intl[0]*(1 + (tmpk*smoothing)), intl[1]*(1 + (tmpk*smoothing))])
 
         return ret[-steps:]
 
@@ -136,7 +139,7 @@ class QuantileRegression(fts.FTS):
         return ret
 
     def forecast_ahead_distribution(self, ndata, steps, **kwargs):
-        smoothing = kwargs.get("smoothing", 0.9)
+        smoothing = kwargs.get("smoothing", 0.1)
 
         l = len(ndata)
 
@@ -154,7 +157,8 @@ class QuantileRegression(fts.FTS):
             intervals = [[nmeans[self.order], nmeans[self.order]]]
             for qt in self.dist_qt:
                 intl1 = self.point_to_interval(nmeans[k - self.order: k], qt[0], qt[1])
-                intl2 = [intl1[0] * (1 + k * smoothing), intl1[1] * (1 + k * smoothing)]
+                tmpk = k - self.order
+                intl2 = [intl1[0] * (1 + (tmpk * smoothing)), intl1[1] * (1 + (tmpk * smoothing))]
                 intervals.append(intl2)
             dist.append_interval(intervals)
 

pyFTS/common/Util.py

@@ -244,7 +244,7 @@ def plot_interval(axis, intervals, order, label, color='red', typeonlegend=False
     upper = [kk[1] for kk in intervals]
     mi = min(lower) * 0.95
     ma = max(upper) * 1.05
-    for k in np.arange(0, order):
+    for k in np.arange(0, order+1):
         lower.insert(0, None)
         upper.insert(0, None)
     if typeonlegend: label += " (Interval)"
@@ -253,6 +253,53 @@ def plot_interval(axis, intervals, order, label, color='red', typeonlegend=False
     return [mi, ma]
 
 
+def plot_interval2(intervals, data, **kwargs):
+    '''
+    Plot forecasted intervals on matplotlib
+
+    :param intervals: list of forecasted intervals
+    :param data: the original test sample
+    :keyword start_at: the time index (inside of data) to start to plot the intervals
+    :keyword label: figure label
+    :keyword color: matplotlib color name
+    :keyword typeonlegend:
+    :keyword ls: matplotlib line style
+    :keyword linewidth: matplotlib width
+    :return: a list [lower, upper] with the minimum and maximum bounds of the intervals
+    '''
+
+    l = len(intervals)
+
+    start_at = kwargs.get('start_at', 1)
+
+    ax = kwargs.get('ax', None)
+    if ax is None:
+        fig, ax = plt.subplots(nrows=1, ncols=1, figsize=[15, 5])
+
+    for k in np.arange(0, start_at-1):
+        intervals.insert(0, [None,None])
+
+    intervals.insert(start_at, [data[start_at], data[start_at]])
+
+    lower = [kk[0] for kk in intervals]
+    upper = [kk[1] for kk in intervals]
+    mi = min(lower) * 0.95
+    ma = max(upper) * 1.05
+
+    typeonlegend = kwargs.get('typeonlegend', False)
+    color = kwargs.get('color', 'red')
+    label = kwargs.get('label','')
+    linewidth = kwargs.get('linewidth', 1)
+
+    ls = kwargs.get('ls','-')
+
+    if typeonlegend: label += " (Interval)"
+    ax.plot(lower, color=color, label=label, ls=ls,linewidth=linewidth)
+    ax.plot(upper, color=color, ls=ls,linewidth=linewidth)
+    return [mi, ma]
+
+
+
 def plot_rules(model, size=[5, 5], axis=None, rules_by_axis=None, columns=1):
     '''
     Plot the FLRG rules of a FTS model on a matplotlib axis

pyFTS/tests/general.py

@@ -13,20 +13,34 @@ from pyFTS.partitioners import Grid, Entropy, Util as pUtil, Simple
 from pyFTS.benchmarks import benchmarks as bchmk, Measures
 from pyFTS.models import chen, yu, cheng, ismailefendi, hofts, pwfts, tsaur, song, sadaei
 from pyFTS.common import Transformations, Membership
-
+from pyFTS.benchmarks import arima, quantreg, BSTS
 from pyFTS.fcm import fts, common, GA
 
 from pyFTS.data import Enrollments, TAIEX
 
-x = [k for k in np.arange(-2*np.pi, 2*np.pi, 0.15)]
+data = TAIEX.get_data()
-y = [np.sin(k) for k in x]
 
-from pyFTS.probabilistic import ProbabilityDistribution
+train = data[:500]
+test = data[500:1000]
 
-pd = ProbabilityDistribution.ProbabilityDistribution(type='histogram', data=y, num_bins=30)
+model = quantreg.QuantileRegression(order=1, dist=True)
+model.fit(train)
 
-print(pd.quantile([.5]))
+horizon=5
-print(pd.cdf)
+
+#points  = model.predict(test[:10], type='point', steps_ahead=horizon)
+
+intervals = model.predict(test[:10], type='interval', alpha=.05, smoothing=0.01, steps_ahead=horizon)
+print(test[:10])
+print(intervals)
+distributions = model.predict(test[:10], type='distribution', steps_ahead=horizon, num_bins=100)
+
+
+fig, ax = plt.subplots(nrows=1, ncols=1,figsize=[15,5])
+
+ax.plot(test[:10], label='Original',color='black')
+cUtil.plot_interval(ax, intervals, model.order, label='ensemble')
+cUtil.plot_distribution2(distributions, test[:10], start_at=2, ax=ax, cmap="Blues")
 
 '''
 model = fts.FCM_FTS(partitioner=fs, order=1)