From cc6606f468201d1875c09ba20219e4022bd781af Mon Sep 17 00:00:00 2001
From: Dominik Roth <dominik.roth.dev@gmail.com>
Date: Wed, 23 Jun 2021 15:45:32 +0200
Subject: [PATCH] Better Tag-Pruning (keep more good tags)

---
 caliGraph.py | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/caliGraph.py b/caliGraph.py
index 6a07968..74f4276 100755
--- a/caliGraph.py
+++ b/caliGraph.py
@@ -28,11 +28,13 @@ def getRecommenders(book):
     for tag in book['tags']:
         if tag.find(" Recommendation") != -1:
             yield tag.replace(" Recommendation", "")
+        elif tag.find("s Literature Club") != -1:
+            yield tag.replace("s Literature Club", "")
 
 
 def getTags(book):
     for tag in book['tags']:
-        if tag.find(" Recommendation") == -1 and tag.find(" Top ") == -1:
+        if tag.find(" Recommendation") == -1 and tag.find("s Literature Club") == -1 and tag.find(" Top ") == -1:
             yield tag
 
 
@@ -166,8 +168,14 @@ def pruneTags(G, minCons=2):
             foundCon = 0
             for book in G.adj[n]:
                 for con in G.adj[book]:
-                    if G.nodes[con]['t'] not in ['tag', 'topList', 'series']:
-                        foundCon += 1
+                    conType = G.nodes[con]['t']
+                    if conType not in ['topList']:
+                        if conType in ['recommender']:
+                            foundCon += 0.5
+                        elif conType in ['tag', 'series']:
+                            foundCon += 0.25
+                        else:
+                            foundCon += 1
             if foundCon > minCons:
                 G.remove_node(n)
 
@@ -483,9 +491,9 @@ def recommendNBooks(G, mu, std, n):
     removeEdge(G)
     removeHighSpanTags(G, 9)
     removeDangling(G, alsoBooks=False)
-    pruneTags(G, 4)
+    pruneTags(G, 6)
     removeBad(G, mu, groups=['book'])
-    pruneTags(G, 3)
+    pruneTags(G, 4.25)
     pruneRecommenderCons(G, int(n/7)+1)
     pruneAuthorCons(G, int(n/15))
     removeTopLists(G)
@@ -544,7 +552,7 @@ def analyze(G, type_name, name, dist=2.7):
         print("Best Match: "+match['label'])
 
     menge = set()
-    pruneDist(G, match, n, dist, menge)
+    waveFlow(G, match, n, dist, menge)
     for n in list(G.nodes):
         if n not in menge:
             G.remove_node(n)
@@ -560,7 +568,7 @@ def analyze(G, type_name, name, dist=2.7):
     addScoreToLabels(G)
     match['label'] = "*"+match['label']+"*"
 
-def pruneDist(G, node, n, dist, menge, firstEdge=False):
+def waveFlow(G, node, n, dist, menge, firstEdge=False):
     if dist <= 0:
         return
     dist -= 1
@@ -600,7 +608,7 @@ def pruneDist(G, node, n, dist, menge, firstEdge=False):
     for m in list(G.adj[n]):
         node = G.nodes[m]
         if node in bestlist or node in keeplist:
-            pruneDist(G, node, m, dist, menge, firstEdge=firstEdge)
+            waveFlow(G, node, m, dist, menge, firstEdge=firstEdge)
 
 def cliInterface():
     import argparse