Approximate Pagerank while training (+performance) and implemented

batch-training (disabled do to non-convergence)

caliGraph.py

@@ -640,9 +640,10 @@ def buildFullGraph(darkMode=False):
     return G, books
 
 
-def genScores(G, books):
+def genScores(G, books, calcPagerank=True):
     globMu, globStd = calcRecDist(G, books)
-    runPagerank(G)
+    if calcPagerank:
+        runPagerank(G)
     scoreOpinions(G, globMu, globStd)
     scoreUnread(G, globMu, globStd)
     return globMu, globStd
@@ -906,7 +907,10 @@ def shell(G, books, mu, std):
     from ptpython.repl import embed
     embed(globals(), locals())
 
-def evaluateFitness(books, debugPrint=False):
+# while batchSize is implemented, we only get a good gonvergence when we disable it (batchSize=-1)
+# but might be necessary to enable later for a larger libary for better training performance...
+# maybe try again for 128 books?
+def evaluateFitness(books, batchSize=-1, debugPrint=False):
     global weights
     G = buildBookGraph(books)
     graphAddAuthors(G, books)
@@ -914,6 +918,7 @@ 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
@@ -924,10 +929,11 @@ def evaluateFitness(books, debugPrint=False):
         gradient[wt] = 0
     mu, sigma = genScores(G, books)
     for b in G.nodes:
-        if b in ratedBooks:
+        batch = random.sample(ratedBooks, batchSize) if batchSize!=-1 and len(ratedBooks) > batchSize else ratedBooks
+        if b in batch:
             rating = G.nodes[b]['rating']
             G.nodes[b]['rating'] = None
-            _, _ = genScores(G, books)
+            _, _ = genScores(G, books, calcPagerank=False)
             if G.nodes[b]['score'] > rating: # over estimated
                 errSq.append(((rating - G.nodes[b]['score'])**2)*2)
             else:

neuralWeights.json

@@ -1 +1 @@
-{"topList": 0.6242390366079424, "recommender": 0.19944547091869327, "author": 0.5538234948661109, "series": 0.3459804141050738, "tag": 0.014690671910647879, "pagerank": 0.19122234015715153, "mu": 0.6727738107799146, "sigma": 0.6261661745577459, "bias": 0.10501847188587837}
+{"topList": 0.5830829472833505, "recommender": 0.1853397829569056, "author": 0.68263573164139, "series": 0.3041545091933662, "tag": 0.007576290358844896, "pagerank": 0.07216203473617633, "mu": 0.8203785554750931, "sigma": 0.5483459224046601, "bias": 0.1280901837325877}