def Save(self):
print "Loading Data"
training_queries = queryClass.load_queries(self.testQueries,
self.feature_count)
ranker = pickle.load(open(self.rankerPath))
max = 100 #max number of docs in the ranking
#print clusterData.queryToCluster.keys()
#print training_queries.keys()
BestRanker = queryFeatures()
print "Loading training objects"
i = 0
for query in training_queries:
#print str(i*100/len(training_queries))+"%"
i = i + 1
#query = training_queries.get_query(qid)
ranker.init_ranking(query)
docIds = ranker.get_ranking()
iter = 0
for docId in docIds:
if iter > max:
break
iter = iter + 1
features = query.get_feature_vector(docId)
BestRanker.add(query.get_qid(), features)
#print features
#BestRanker.addFeaturesToQid([float(i) for i in features],query.get_qid())
pickle.dump(BestRanker,
open("QueryData/" + self.dataset + ".data", "wb"))
def Train(self):
print "Loading Data"
clusterData=pickle.load(open( self.clusterDataPath, "rb" ) )
feature_count=len(clusterData.clusterToRanker[0][0])
training_queries = queryClass.load_queries(self.testQueries, feature_count)
ranker=pickle.load( open( self.rankerPath ) )
"""
testWeights=str(clusterData.clusterToRanker[0][0])
testWeights=testWeights.replace("[", "")
testWeights=testWeights.replace("]", "")
weights = np.array([float(num) for num in testWeights.split(",")])
ranker_tie="random"
ranker_args="3"
sample_send="sample_unit_sphere"
ranker=rankerClass.ProbabilisticRankingFunction(ranker_args,
ranker_tie,
feature_count,
sample=sample_send,
init=testWeights)
"""
X=[]
Y=[]
max=100 #max number of docs in the ranking
#print clusterData.queryToCluster.keys()
#print training_queries.keys()
print "Loading training objects"
for qid in clusterData.queryToCluster:
query = training_queries.get_query(qid)
ranker.init_ranking(query)
docIds=ranker.get_ranking()
iter=0
for docId in docIds:
if iter>max:
break
features=query.get_feature_vector(docId)
X.append(features)
Y.append(clusterData.queryToCluster[qid][0])
iter=iter+1
#X = [[0, 0], [1, 1]]
#y = [0, 1]
X=np.array(X)
Y=np.array(Y)
print "Training"
clf = svm.SVC()
clf.fit(X, Y)
if not os.path.exists("Classifier"):
os.makedirs("Classifier")
paths=self.clusterDataPath.split('/')
name=paths[len(paths)-1]
parts=name.split('.')
name=parts[0]
pickle.dump(clf, open( "Classifier/"+name+".data", "wb" ) )
