Use base-e (not-10) in expected_win_probability

Change `expected_win_probability` to use base-e (instead of base-10), to match
Glicko-2.  `v5_glicko2_update` was already (correctly) using base-e.

This follow-up to 87c3fa8 gets handles the
math domain error from tallying results on large small board handicaps. The
base-10 bug made the expected win rate 1.0 (100%).

Of course, it's still possible to skip large handicap games when tallying
results... but no longer necessary.

goratings/math/glicko2.py

@@ -72,15 +72,9 @@ def g(rd: float) -> float:
                 return 1 / sqrt(1 + 3 * q ** 2 * (self.deviation ** 2) / pi ** 2)
 
         E = 1 / (
-            1
-            + (
-                10
-                ** (
-                    -g(sqrt(self.deviation ** 2 + white.deviation ** 2))
+            1 + exp(-g(sqrt(self.deviation ** 2 + white.deviation ** 2))
                     * (self.rating + handicap_adjustment - white.rating)
-                    / 400
-                )
-            )
+                    / 400)
         )
         return E