def tfidf_profile(self, items_repository, size, content_filter,
time_context=0):
"""
Return the most relevant tags for the user list of packages based on
the sublinear tfidf weight of packages' tags.
"""
docs = data.axi_search_pkgs(items_repository, self.pkg_profile)
# weights = data.tfidf_plus(items_repository,docs,content_filter)
weights = data.tfidf_weighting(items_repository, docs, content_filter,
time_context=time_context)
# Eliminate duplicated stemmed term
profile = self._eliminate_duplicated([w[0] for w in weights], size)
return profile
def eset_profile(self, items_repository, size, content_filter):
"""
Return most relevant tags for a list of packages.
"""
# Store package documents in a relevant set
enquire = xapian.Enquire(items_repository)
docs = data.axi_search_pkgs(items_repository, self.pkg_profile)
rset_packages = xapian.RSet()
for d in docs:
rset_packages.add_document(d.docid)
# Get expanded query terms (statistically good differentiators)
eset_tags = enquire.get_eset(size * 2, rset_packages,
xapian.Enquire.INCLUDE_QUERY_TERMS,
1, content_filter)
# Eliminate duplicated stemmed term
profile = self._eliminate_duplicated([res.term for res in eset_tags],
size)
return profile
def eset_profile(self, items_repository, size, content_filter):
"""
Return most relevant tags for a list of packages.
"""
# Store package documents in a relevant set
enquire = xapian.Enquire(items_repository)
docs = data.axi_search_pkgs(items_repository, self.pkg_profile)
rset_packages = xapian.RSet()
for d in docs:
rset_packages.add_document(d.docid)
# Get expanded query terms (statistically good differentiators)
eset_tags = enquire.get_eset(size * 2, rset_packages,
xapian.Enquire.INCLUDE_QUERY_TERMS, 1,
content_filter)
# Eliminate duplicated stemmed term
profile = self._eliminate_duplicated([res.term for res in eset_tags],
size)
return profile
def tfidf_profile(self,
items_repository,
size,
content_filter,
time_context=0):
"""
Return the most relevant tags for the user list of packages based on
the sublinear tfidf weight of packages' tags.
"""
docs = data.axi_search_pkgs(items_repository, self.pkg_profile)
# weights = data.tfidf_plus(items_repository,docs,content_filter)
weights = data.tfidf_weighting(items_repository,
docs,
content_filter,
time_context=time_context)
# Eliminate duplicated stemmed term
profile = self._eliminate_duplicated([w[0] for w in weights], size)
return profile