board

CONTRIBUTIONS.md

@@ -46,7 +46,7 @@ Many thanks to these additional authors:
 * "bale-go" for development and continued work on the 'calibrated rank' AI and rank estimation algorithm.
 * "Dontbtme" for detailed feedback and early testing of v1.0+.
 * "nowoowoo" for a fix to the parser for SGF files with extra line breaks.
-* "nimets123" for the timer sound effects and stone graphics.
+* "nimets123" for the timer sound effects and board/stone graphics.
 * Jordan Seaward for the stone sound effects.
 * "fohristiwhirl" for the Gibo format parsing code.
 

README.md

@@ -99,6 +99,8 @@ Further technical details and discussion on these AIs can be found on [this](htt
 
 ## <a name="analysis"></a> Analysis
 
+Analysis options in KaTrain allow you to explore variations and request more in-depth analysis from the engine at any point in the game.
+
 Keyboard shortcuts are shown with **[key]**.
 
 * **[Tab]**: Switch between analysis and play modes.
@@ -123,6 +125,12 @@ Keyboard shortcuts are shown with **[key]**.
     * **[spacebar]**: Turn continuous analysis on/off. 
     * **[enter]** AI move. Makes the AI move for the current player regardless of current player selection.
 
+### Rank Estimation
+
+A new feature in v1.3 is the rank estimation panel. This adds an extra graph which uses a statistical model to estimate the playing strength
+of both players for every 80 move segment. It can be used for determining which part of your game needs extra attention,
+but keep in mind the estimation is based purely on how well moves correspond to the 'shape sense' of KataGo and can be very inaccurate at times.
+
 ## <a name="keyboard"></a> Keyboard and mouse shortcuts
 
 In addition to shortcuts mentioned above and those shown in the main menu:
@@ -158,7 +166,7 @@ In addition to shortcuts mentioned above and those shown in the main menu:
 [![GitHub issues](https://img.shields.io/github/issues/sanderland/katrain)](https://github.com/sanderland/katrain/issues)
 [![Contributors](https://img.shields.io/static/v1?label=contributors&message=16&color=dcb424)](CONTRIBUTIONS.md)
 [![Liberapay patrons](https://img.shields.io/liberapay/patrons/sanderbaduk)](https://liberapay.com/sanderbaduk/)
-[![Github sponsors](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=dcb424&link=https://github.com/sponsors/sanderland/)](https://github.com/sponsors/sanderland)
+[![Github sponsors](https://img.shields.io/static/v1?label=Sponsor&message=2&logo=GitHub&color=dcb424&link=https://github.com/sponsors/sanderland/)](https://github.com/sponsors/sanderland)
 
  * Ideas, feedback, and contributions to code or translations are all very welcome.
     * For suggestions and planned improvements, see [open issues](https://github.com/sanderland/katrain/issues) on github to check if the functionality is already planned.

katrain/core/ai.py

@@ -197,7 +197,9 @@ def generate_ai_move(game: Game, ai_mode: str, ai_settings: Dict) -> Tuple[Move,
                 ai_thoughts += f"Top policy move has weight > {override:.1%}, so overriding other strategies."
             elif policy_moves[0][0] + policy_moves[1][0] > overridetwo:
                 aimove = top_policy_move
-                ai_thoughts += f"Top two policy moves have cumulative weight > {overridetwo:.1%}, so overriding other strategies."
+                ai_thoughts += (
+                    f"Top two policy moves have cumulative weight > {overridetwo:.1%}, so overriding other strategies."
+                )
             elif ai_mode == AI_WEIGHTED:
                 aimove, ai_thoughts = policy_weighted_move(
                     policy_moves, ai_settings["lower_bound"], ai_settings["weaken_fac"]

katrain/core/game_node.py

@@ -230,7 +230,13 @@ class GameNode(SGFNode):
             polmoves = self.policy_ranking
             top_polmove = polmoves[0][1] if polmoves else Move(None)  # if no info at all, pass
             return [
-                {**self.analysis["root"], "pointsLost": 0, "order": 0, "move": top_polmove.gtp(),"pv":[top_polmove.gtp()]}
+                {
+                    **self.analysis["root"],
+                    "pointsLost": 0,
+                    "order": 0,
+                    "move": top_polmove.gtp(),
+                    "pv": [top_polmove.gtp()],
+                }
             ]  # single visit -> go by policy/root
 
         root_score = self.analysis["root"]["scoreLead"]

katrain/gui/badukpan.py

@@ -148,9 +148,11 @@ class BadukPanWidget(Widget):
             eval_radius = math.sqrt(evalscale)  # scale area by evalscale
             evalsize = self.stone_size * (EVAL_DOT_MIN_SIZE + eval_radius * (EVAL_DOT_MAX_SIZE - EVAL_DOT_MIN_SIZE))
             Color(*evalcol)
-            Rectangle(  pos=(self.gridpos_x[x] - evalsize, self.gridpos_y[y] - evalsize),
+            Rectangle(
+                pos=(self.gridpos_x[x] - evalsize, self.gridpos_y[y] - evalsize),
                 size=(2 * evalsize, 2 * evalsize),
-                        source=f"img/dot.png")
+                source=f"img/dot.png",
+            )
         if innercol:
             Color(*innercol)
             inner_size = stone_size * 0.8
@@ -194,10 +196,11 @@ class BadukPanWidget(Widget):
                 for i in range(board_size_y)
             ]
 
-            Color(*BOARD_COLOR)
+            Color(1, 0.95, 0.8, 1)  # image is a bit too light
             Rectangle(
                 pos=(self.gridpos_x[0] - self.grid_size * 1.5, self.gridpos_y[0] - self.grid_size * 1.5),
                 size=(self.grid_size * x_grid_spaces, self.grid_size * y_grid_spaces),
+                source="img/board.png",
             )
 
             Color(*LINE_COLOR)