From 33ba27e2d04922776bcdb25cfcb73856c1fdcbc5 Mon Sep 17 00:00:00 2001
From: Dominik Roth <dominik.roth.dev@gmail.com>
Date: Mon, 31 Jan 2022 13:45:26 +0100
Subject: [PATCH] Implemented Pagerank

---
 caliGraph.py | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/caliGraph.py b/caliGraph.py
index 4c2577b..51a68bf 100755
--- a/caliGraph.py
+++ b/caliGraph.py
@@ -407,6 +407,8 @@ def scoreUnread(G, globMu, globStd):
                 if len(feedbacks):
                     node['mean'], node['std'] = norm.fit(feedbacks)
                     node['se'] = globStd / math.sqrt(len(feedbacks))
+                    feedbacks.append(node['pagerank_score'])
+                    ws.append(['pagerank'])
                     feedbacks.append(node['std'])
                     ws.append(['sigma'])
                     feedbacks.append(node['se'])
@@ -477,6 +479,15 @@ def getKeywords(txt,rake):
         return k
     return []
 
+def runPagerank(G):
+    try:
+        scores = nx.pagerank(G=G)
+    except nx.exception.PowerIterationFailedConvergence:
+        print('[!] Could not calculate pagerank-scores: power iteration of the eigenvector calculation did not converge')
+        scores = {}
+    for n in list(G.nodes):
+        G.nodes[n]['pagerank_score'] = scores[n] if n in scores else 0
+
 def buildBookGraph(books, darkMode=False, extractKeywords=True, mergeTags=True):
     G = nx.Graph()
     if extractKeywords:
@@ -622,6 +633,7 @@ def buildFullGraph(darkMode=False):
     graphAddTopLists(G, books, darkMode=darkMode)
     graphAddSeries(G, books, darkMode=darkMode)
     graphAddTags(G, books, darkMode=darkMode)
+    runPagerank(G)
     return G, books
 
 
@@ -898,6 +910,7 @@ def evaluateFitness(books, debugPrint=False):
     graphAddTopLists(G, books)
     graphAddSeries(G, books)
     graphAddTags(G, books)
+    runPagerank(G)
 
     ratedBooks = [n for n in list(G.nodes) if 'rating' in G.nodes[n] and G.nodes[n]['rating'] != None]
     boundsLoss = 0
@@ -932,8 +945,8 @@ def evaluateFitness(books, debugPrint=False):
     for g in gradient:
         gradient[g] /= len(errSq)
     if debugPrint:
-        print(sum(errSq)/len(errSq), 0.005*regressionLoss, 0.2*boundsLoss/len(ratedBooks), 1.0*sum(linSepLoss)/len(linSepLoss))
-    fit = sum(errSq)/len(errSq) + 0.005*regressionLoss + 0.2*boundsLoss/len(ratedBooks) - 1.0*sum(linSepLoss)/len(linSepLoss)
+        print(sum(errSq)/len(errSq), 0.003*regressionLoss, 0.2*boundsLoss/len(ratedBooks), 1.0*sum(linSepLoss)/len(linSepLoss))
+    fit = sum(errSq)/len(errSq) + 0.003*regressionLoss + 0.2*boundsLoss/len(ratedBooks) - 1.0*sum(linSepLoss)/len(linSepLoss)
     return fit, gradient
 
 def train(initGamma, full=True):