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

Implemented Pagerank

Browse Source
This commit is contained in:
Dominik Moritz Roth 2022-01-31 13:45:26 +01:00
parent 96258ae19b
commit 33ba27e2d0
1 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
caliGraph.py
View File

@ -407,6 +407,8 @@ def scoreUnread(G, globMu, globStd):
if len(feedbacks): if len(feedbacks):
node['mean'], node['std'] = norm.fit(feedbacks) node['mean'], node['std'] = norm.fit(feedbacks)
node['se'] = globStd / math.sqrt(len(feedbacks)) node['se'] = globStd / math.sqrt(len(feedbacks))
feedbacks.append(node['pagerank_score'])
ws.append(['pagerank'])
feedbacks.append(node['std']) feedbacks.append(node['std'])
ws.append(['sigma']) ws.append(['sigma'])
feedbacks.append(node['se']) feedbacks.append(node['se'])
@ -477,6 +479,15 @@ def getKeywords(txt,rake):
return k return k
return [] 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): def buildBookGraph(books, darkMode=False, extractKeywords=True, mergeTags=True):
G = nx.Graph() G = nx.Graph()
if extractKeywords: if extractKeywords:
@ -622,6 +633,7 @@ def buildFullGraph(darkMode=False):
graphAddTopLists(G, books, darkMode=darkMode) graphAddTopLists(G, books, darkMode=darkMode)
graphAddSeries(G, books, darkMode=darkMode) graphAddSeries(G, books, darkMode=darkMode)
graphAddTags(G, books, darkMode=darkMode) graphAddTags(G, books, darkMode=darkMode)
runPagerank(G)
return G, books return G, books
@ -898,6 +910,7 @@ def evaluateFitness(books, debugPrint=False):
graphAddTopLists(G, books) graphAddTopLists(G, books)
graphAddSeries(G, books) graphAddSeries(G, books)
graphAddTags(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] ratedBooks = [n for n in list(G.nodes) if 'rating' in G.nodes[n] and G.nodes[n]['rating'] != None]
boundsLoss = 0 boundsLoss = 0
@ -932,8 +945,8 @@ def evaluateFitness(books, debugPrint=False):
for g in gradient: for g in gradient:
gradient[g] /= len(errSq) gradient[g] /= len(errSq)
if debugPrint: if debugPrint:
print(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) + 0.005*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 return fit, gradient
def train(initGamma, full=True): def train(initGamma, full=True):