From 9a473edfdc7487730f054d777c85751a280853bc Mon Sep 17 00:00:00 2001
From: Dominik Roth <dominik.roth.dev@gmail.com>
Date: Sat, 19 Nov 2022 16:18:58 +0100
Subject: [PATCH] Allow configurable curiosity and bug fixes

---
 caliGraph.py | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/caliGraph.py b/caliGraph.py
index dd1cfff..4a148dc 100755
--- a/caliGraph.py
+++ b/caliGraph.py
@@ -138,7 +138,7 @@ def removeWhitepapers(G):
     for n in list(G.nodes):
         node = G.nodes[n]
         if node['t'] == 'book':
-            if 'whitepaper' in node['tags']:
+            if 'whitepaper' in node['tags'] or 'Lernzettel' in node['tags']:
                 G.remove_node(n)
 
 
@@ -198,7 +198,7 @@ def removeTags(G):
             G.remove_node(n)
 
 
-def pruneTags(G, minCons=2):
+def pruneTags(G, minCons=2, forceKeepLabels=[]):
     for n in sorted(list(G.nodes), key=lambda i: G.nodes[i]['score'] + len(G.nodes[i]['feedbacks'])/5 if 'score' in G.nodes[i] and 'feedbacks' in G.nodes[i] else 0):
         node = G.nodes[n]
         if node['t'] == 'tag':
@@ -213,7 +213,7 @@ def pruneTags(G, minCons=2):
                             foundCon += 0.25
                         else:
                             foundCon += 1
-            if foundCon > minCons:
+            if foundCon > minCons and node['label'] not in forceKeepLabels:
                 G.remove_node(n)
 
 
@@ -288,11 +288,11 @@ def pruneAuthorCons(G, maxCons=3):
                                 G.remove_node(m)
 
 
-def removeHighSpanTags(G, maxCons=5):
+def removeHighSpanTags(G, maxCons=5, forceKeepLabels=[]):
     for n in list(G.nodes):
         node = G.nodes[n]
         if node['t'] == 'tag':
-            if len(G.adj[n]) > maxCons:
+            if len(G.adj[n]) > maxCons and not node['label'] in forceKeepLabels:
                 G.remove_node(n)
 
 
@@ -395,6 +395,16 @@ def removeUselessTags(G, minUnread=1):
                 G.remove_node(n)
 
 
+def curiosityReward(G, coeff=1, dTan=True):
+    for n in list(G.nodes):
+        node = G.nodes[n]
+        if 'score' in node and 'se' in node:
+            delta = node['se'] * coeff
+            if dTan:
+                delta *= (1- math.tanh((node['score']/10-0.5)*7)**2)
+            new = max(0.0, min(10.0, node['score'] + delta))
+            node['score'] = new
+
 def removeUselessSeries(G, minSco=0):
     for n in list(G.nodes):
         node = G.nodes[n]
@@ -814,7 +824,7 @@ def scaleOpinionsByRating(G):
 def addScoreToLabels(G):
     for n in list(G.nodes):
         node = G.nodes[n]
-        if node['t'] not in ['tag', 'newBook']:
+        if node['t'] not in []: #['tag', 'newBook']:
             if 'rating' in node and node['rating'] != None:
                 node['label'] += " ("+str(node['rating'])+")"
             else:
@@ -1185,7 +1195,7 @@ def analyze(G, books, mu, type_name, name, dist=2.1):
             G.remove_node(n)
     if dist >= 2:
         removeThinRecs(G, 2)
-    removeHighSpanTags(G, 12)
+    removeHighSpanTags(G, 12, forceKeepLabels=[match['label']])
     if dist > 1:
         removeDangling(G, True)
 
@@ -1530,6 +1540,8 @@ def cliInterface(imgDef=False):
     parser.add_argument('--keep-top-lists', action="store_true")
     parser.add_argument('--keep-useless-recommenders', action="store_true")
     parser.add_argument('--dark', action="store_true")
+    parser.add_argument('--curiosity', type=float, default=0.0,
+                       help='curiosity coefficient (higher = more speculative)')
     parser.add_argument('--v3d', action="store_true")
     if imgDef:
         parser.add_argument('--no-imgs', action="store_true")
@@ -1634,6 +1646,8 @@ def mainCLI(args):
     G, books = buildFullGraph(darkMode=args.dark)
     mu, std = genScores(G, books)
 
+    curiosityReward(G, args.curiosity)
+
     if not args.keep_whitepapers:
         removeWhitepapers(G)