Nomogram: Speedups

Author: nikicc

Orange/widgets/visualize/ownomogram.py

@@ -1,5 +1,6 @@
 import time
 from enum import IntEnum
+from collections import OrderedDict
 
 import numpy as np
 
@@ -868,11 +869,13 @@ def calculate_log_reg_coefficients(self):
         self.log_reg_coeffs = [coeffs[:, ranges[i]] for i in range(len(attrs))]
         self.log_reg_coeffs_orig = self.log_reg_coeffs.copy()
 
-        for i in range(len(self.log_reg_coeffs)):
+        min_values = nanmin(self.data.X, axis=0)
+        max_values = nanmax(self.data.X, axis=0)
+
+        for i, min_t, max_t in zip(range(len(self.log_reg_coeffs)),
+                                   min_values, max_values):
             if self.log_reg_coeffs[i].shape[1] == 1:
                 coef = self.log_reg_coeffs[i]
-                min_t = nanmin(self.data.X, axis=0)[i]
-                max_t = nanmax(self.data.X, axis=0)[i]
                 self.log_reg_coeffs[i] = np.hstack((coef * min_t, coef * max_t))
                 self.log_reg_cont_data_extremes.append(
                     [sorted([min_t, max_t], reverse=(c < 0)) for c in coef])
@@ -1109,13 +1112,15 @@ def send_report(self):
 
     @staticmethod
     def reconstruct_domain(original, preprocessed):
-        attrs = []
+        # abuse dict to make "in" comparisons faster
+        attrs = OrderedDict()
         for attr in preprocessed.attributes:
             cv = attr._compute_value.variable._compute_value
             var = cv.variable if cv else original[attr.name]
-            if var in attrs:
+            if var in attrs:    # the reason for OrderedDict
                 continue
-            attrs.append(var)
+            attrs[var] = None   # we only need keys
+        attrs = list(attrs.keys())
         return Domain(attrs, original.class_var, original.metas)
 
     @staticmethod