From ad38e3e2a2410b8faab2de61966e015d826853bb Mon Sep 17 00:00:00 2001
From: Dominik Roth <dominik.roth.dev@gmail.com>
Date: Tue, 15 Jun 2021 13:52:41 +0200
Subject: [PATCH] Added pruning of connections from recommenders (above maximum
 threshold) and tweaked some params

---
 main.py | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/main.py b/main.py
index c3f8653..1b80617 100644
--- a/main.py
+++ b/main.py
@@ -170,6 +170,31 @@ def pruneTags(G, minCons=2):
             if foundCon > minCons:
                 G.remove_node(n)
 
+def pruneRecommenderCons(G, maxCons=5):
+    for n in list(G.nodes):
+        node = G.nodes[n]
+        if node['t'] == 'recommender':
+            if len(G.adj[n]) > maxCons:
+                bestlist = []
+                for m in list(G.adj[n]):
+                    book = G.nodes[m]
+                    if book['t'] == 'book':
+                        if 'score' in book and book['score'] != None:
+                            bestlist.append(book)
+                bestlist.sort(key=lambda node: node['score'], reverse=True)
+                bestlist = bestlist[:maxCons]
+
+                for m in list(G.adj[n]):
+                    book = G.nodes[m]
+                    if book['t'] == 'book' and book not in bestlist or 'score' in book and book['score'] == None:
+                        if not 'rating' in book or book['rating'] == None:
+                            foundCon = 0
+                            for con in G.adj[m]:
+                                if G.nodes[con]['t'] not in ['topList']:
+                                    foundCon += 1
+                            if foundCon < 2:
+                                G.remove_node(m)
+
 
 def removeHighSpanTags(G, maxCons=5):
     for n in list(G.nodes):
@@ -202,7 +227,7 @@ def removeRestOfSeries(G):
                     G.remove_node(adj)
 
 
-def scoreOpinions(G, globMu, globStd, errorFac=1.2):
+def scoreOpinions(G, globMu, globStd, errorFac=0.7):
     for n in list(G.nodes):
         node = G.nodes[n]
         feedbacks = []
@@ -217,14 +242,14 @@ def scoreOpinions(G, globMu, globStd, errorFac=1.2):
                 node['se'] = globStd / math.sqrt(len(feedbacks))
                 ratio = len(feedbacks) / len(adjacens)
                 node['score'] = node['mean'] - errorFac * \
-                    node['se']*(9/10 + (1-ratio)/10) + 0.001 * \
+                    node['se']*(6/7 + (1-ratio)/7) + 0.001 * \
                     (node['t'] == 'recommender')
                 node['feedbacks'] = feedbacks
             else:
                 node['score'] = None
 
 
-def scoreUnread(G, globMu, globStd, errorFac=1):
+def scoreUnread(G, globMu, globStd, errorFac=0.6):
     for n in list(G.nodes):
         feedbacks = []
         deepFeedbacks = []
@@ -440,6 +465,7 @@ def recommendNBooks(n):
     pruneTags(G, 4)
     removeBad(G, mu, groups=['book'])
     pruneTags(G, 3)
+    pruneRecommenderCons(G, 5)
     removeTopLists(G)
     removeDangling(G, alsoBooks=True)
     removeKeepBest(G, n, maxDistForRead=0.75)
@@ -451,7 +477,7 @@ def recommendNBooks(n):
     addScoreToLabels(G)
 
     printBestList(G, num=n)
-    genAndShowHTML(G)
+    genAndShowHTML(G, True)
 
 
 def fullGraph():
@@ -495,4 +521,4 @@ def readBooksAnalysis():
 
 
 if __name__ == "__main__":
-    recommendNBooks(30)
+    recommendNBooks(35)