From 06a0461e937b26e2802c66138c3abf097e27dd60 Mon Sep 17 00:00:00 2001
From: Dominik Roth <dominik.roth.dev@gmail.com>
Date: Sun, 26 Sep 2021 16:51:17 +0200
Subject: [PATCH] Better pruning of tags and recommenders

---
 caliGraph.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/caliGraph.py b/caliGraph.py
index c69c4e1..0df48d8 100755
--- a/caliGraph.py
+++ b/caliGraph.py
@@ -169,7 +169,7 @@ def removeTags(G):
 
 
 def pruneTags(G, minCons=2):
-    for n in list(G.nodes):
+    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':
             foundCon = 0
@@ -188,7 +188,7 @@ def pruneTags(G, minCons=2):
 
 
 def pruneRecommenders(G, minCons=2):
-    for n in list(G.nodes):
+    for n in sorted(list(G.nodes), key=lambda i: G.nodes[i]['score'] if 'score' in G.nodes[i] else 0):
         node = G.nodes[n]
         if node['t'] == 'recommender':
             foundCon = 0
@@ -638,11 +638,12 @@ def recommendNBooksTagBased(G, mu, std, n, removeTopListsB=True):
 
 def recommendNBooks(G, mu, std, n, removeTopListsB=True, removeUselessRecommenders=True):
     removeRestOfSeries(G)
-    removeBad(G, mu-std-1)
+    removeBad(G, mu-std-0.5)
+    removeBad(G, mu+std/2, groups=['recommender'])
     removeKeepBest(G, int(n*2) + 5, maxDistForRead=2)
     removeEdge(G)
-    removeHighSpanTags(G, 12)
-    removeHighSpanReadBooks(G, 6)
+    removeHighSpanTags(G, 10)
+    removeHighSpanReadBooks(G, 10)
     removeDangling(G, alsoBooks=False)
     pruneRecommenders(G, 13)
     pruneTags(G, 13)