dodox/CaliGraph
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Added pruning of connections from recommenders (above maximum threshold)

Browse Source 
and tweaked some params
This commit is contained in:
Dominik Moritz Roth 2021-06-15 13:52:41 +02:00
parent a5352dd794
commit ad38e3e2a2
1 changed files with 31 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
main.py
View File

@ -170,6 +170,31 @@ def pruneTags(G, minCons=2):
if foundCon > minCons: if foundCon > minCons:
G.remove_node(n) 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): def removeHighSpanTags(G, maxCons=5):
for n in list(G.nodes): for n in list(G.nodes):
@ -202,7 +227,7 @@ def removeRestOfSeries(G):
G.remove_node(adj) 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): for n in list(G.nodes):
node = G.nodes[n] node = G.nodes[n]
feedbacks = [] feedbacks = []
@ -217,14 +242,14 @@ def scoreOpinions(G, globMu, globStd, errorFac=1.2):
node['se'] = globStd / math.sqrt(len(feedbacks)) node['se'] = globStd / math.sqrt(len(feedbacks))
ratio = len(feedbacks) / len(adjacens) ratio = len(feedbacks) / len(adjacens)
node['score'] = node['mean'] - errorFac * \ 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['t'] == 'recommender')
node['feedbacks'] = feedbacks node['feedbacks'] = feedbacks
else: else:
node['score'] = None node['score'] = None
def scoreUnread(G, globMu, globStd, errorFac=1): def scoreUnread(G, globMu, globStd, errorFac=0.6):
for n in list(G.nodes): for n in list(G.nodes):
feedbacks = [] feedbacks = []
deepFeedbacks = [] deepFeedbacks = []
@ -440,6 +465,7 @@ def recommendNBooks(n):
pruneTags(G, 4) pruneTags(G, 4)
removeBad(G, mu, groups=['book']) removeBad(G, mu, groups=['book'])
pruneTags(G, 3) pruneTags(G, 3)
pruneRecommenderCons(G, 5)
removeTopLists(G) removeTopLists(G)
removeDangling(G, alsoBooks=True) removeDangling(G, alsoBooks=True)
removeKeepBest(G, n, maxDistForRead=0.75) removeKeepBest(G, n, maxDistForRead=0.75)
@ -451,7 +477,7 @@ def recommendNBooks(n):
addScoreToLabels(G) addScoreToLabels(G)
printBestList(G, num=n) printBestList(G, num=n)
genAndShowHTML(G) genAndShowHTML(G, True)
def fullGraph(): def fullGraph():
@ -495,4 +521,4 @@ def readBooksAnalysis():
if __name__ == "__main__": if __name__ == "__main__":
recommendNBooks(30) recommendNBooks(35)