removeUselessSeries and stronger linear seperation

caliGraph.py

@@ -344,6 +344,12 @@ def removeUselessTags(G, minUnread=1):
             if foundUnread < minUnread:
                 G.remove_node(n)
 
+def removeUselessSeries(G, minSco=0):
+    for n in list(G.nodes):
+        node = G.nodes[n]
+        if node['t'] == 'series':
+            if len(G.adj[n]) < 2 or node['score'] < minSco:
+                G.remove_node(n)
 
 def scoreOpinions(G, globMu, globStd):
     for n in list(G.nodes):
@@ -386,7 +392,8 @@ def scoreUnread(G, globMu, globStd):
                     ws.append(getWeightForType('sigma'))
                     feedbacks.append(node['se'])
                     ws.append(getWeightForType('se'))
-                    #node['score'] = sum([fb*w for fb, w in zip(feedbacks, weights)])/len(feedbacks)
+                    feedbacks.append(globMu)
+                    ws.append(getWeightForType('bias'))
                     node['score'] = sum([fb*w for fb, w in zip(feedbacks, ws)])/sum(ws)
                 else:
                     node['score'] = globMu + errorFac*globStd + len(feedbacks)*0.0000000001
@@ -644,13 +651,17 @@ def recommendNBooks(G, mu, std, n, removeTopListsB=True, removeUselessRecommende
     pruneTags(G, 12)
     pruneAuthorCons(G, int(n/5))
     pruneRecommenders(G, 12 - min(5, n/20))
+    removeUselessSeries(G, mu)
     removeUselessTags(G)
     if removeTopListsB:
         removeTopLists(G)
     removeDangling(G, alsoBooks=True)
     removeKeepBest(G, n+math.ceil(n/20)+3, maxDistForRead=1.5)
-    removeUselessReadBooks(G)
     removeEdge(G)
+    removeKeepBest(G, n+1, maxDistForRead=1.25)
+    removeUselessSeries(G, mu)
+    removeUselessTags(G)
+    removeUselessReadBooks(G)
     removeKeepBest(G, n, maxDistForRead=1.25)
 
     scaleBooksByRating(G)
@@ -775,6 +786,7 @@ def evaluateFitness(books):
 
     ratedBooks = [n for n in list(G.nodes) if 'rating' in G.nodes[n] and G.nodes[n]['rating'] != None]
     boundsLoss = 0
+    linSepLoss = []
     errSq = []
     mu, sigma = genScores(G, books)
     for b in G.nodes:
@@ -794,9 +806,10 @@ def evaluateFitness(books):
             elif score < 0.0:
                 boundsLoss += (score)**2
             # reward seperation linearly
-            boundsLoss -= abs(score - mu)/10
+            linSepLoss.append(abs(score - mu))
     regressionLoss = sum([(1-w)**2 for w in weights.values()])
-    return sum(errSq)/len(errSq) + regressionLoss/100 + boundsLoss/100
+    print(sum(errSq)/len(errSq), 0.005*regressionLoss, 0.2*boundsLoss/len(ratedBooks), 0.5*sum(linSepLoss)/len(linSepLoss))
+    return sum(errSq)/len(errSq) + 0.005*regressionLoss + 0.2*boundsLoss/len(ratedBooks) - 0.5*sum(linSepLoss)/len(linSepLoss)
 
 def train(gamma = 1):
     global weights