normalize: set number_of_decimals=3 when centering data

Author: pavlin-policar

Orange/data/variable.py

@@ -586,6 +586,12 @@ def repr_val(self, val):
                 and abs(round(val, self._number_of_decimals) - val) \
                 > self._max_round_diff:
             return f"{val:.{self._number_of_decimals + 2}f}"
+
+        # Sometimes, -1e-16 will be rounded to 0, and displayed as -0.00. This
+        # ensures that there are never negative signs in front of zeros
+        if float(self._format_str % val) == 0:
+            val = 0.0
+
         return self._format_str % val
 
     str_val = repr_val
@@ -602,6 +608,7 @@ def copy(self, compute_value=None, *, name=None, **kwargs):
             var._max_round_diff = self._max_round_diff
             var.adjust_decimals = self.adjust_decimals
             var.format_str = self._format_str
+
         return var
 
 

Orange/preprocess/normalize.py

@@ -1,6 +1,6 @@
 import numpy as np
 
-from Orange.data import Domain
+from Orange.data import Domain, ContinuousVariable
 from Orange.statistics import distribution
 from Orange.util import Reprable
 from .preprocess import Normalize
@@ -42,26 +42,30 @@ def normalize(self, dist, var):
             var = self.normalize_by_sd(dist, var)
         elif self.norm_type == Normalize.NormalizeBySpan:
             var = self.normalize_by_span(dist, var)
-        var.number_of_decimals = None
         return var
 
-    def normalize_by_sd(self, dist, var):
+    def normalize_by_sd(self, dist, var: ContinuousVariable) -> ContinuousVariable:
         avg, sd = (dist.mean(), dist.standard_deviation()) if dist.size else (0, 1)
         if sd == 0:
             sd = 1
         if self.center:
             compute_val = Norm(var, avg, 1 / sd)
+            num_decimals = 3
         else:
             compute_val = Norm(var, 0, 1 / sd)
-        return var.copy(compute_value=compute_val)
+            num_decimals = None
+        num_decimals += int(-np.floor(np.log10(sd)))
+        return var.copy(compute_value=compute_val, number_of_decimals=num_decimals)
 
-    def normalize_by_span(self, dist, var):
+    def normalize_by_span(self, dist, var: ContinuousVariable) -> ContinuousVariable:
         dma, dmi = (dist.max(), dist.min()) if dist.shape[1] else (np.nan, np.nan)
         diff = dma - dmi
         if diff < 1e-15:
             diff = 1
         if self.zero_based:
             compute_val = Norm(var, dmi, 1 / diff)
+            num_decimals = 3
         else:
             compute_val = Norm(var, (dma + dmi) / 2, 2 / diff)
-        return var.copy(compute_value=compute_val)
+            num_decimals = None
+        return var.copy(compute_value=compute_val, number_of_decimals=num_decimals)