def __init__(self, initial_query, initial_ranked_docs, patent_info):
self.initial_query = initial_query
self.initial_ranked_docs = initial_ranked_docs
self.terms_dictionary = self.initial_query.terms_dictionary
self.patent_info = patent_info
self.terms = self.get_expanded_terms()
self.terms_dist = util.getFreqDist(self.terms)
self.tf_weights = util.get_tf_weights(self.terms_dist)
def __init__(self, query_file, terms_dictionary, patent_info):
self.terms_dictionary = self.get_terms_dictionary(terms_dictionary)
self.patent_info = patent_info
self.corpus_size = len(patent_info) - 1
self.avg_doc_length = self.get_avg_doc_length(patent_info)
self.title, self.desc = Query.parse(query_file)
self.terms = self.get_terms()
self.terms_dist = util.getFreqDist(self.terms)
self.tf_weights = util.get_tf_weights(self.terms_dist)
self.docterm_matrix = self.get_docterms_matrix()
def __init__(self, doc_file):
# Raw fields extracted from XML file
self.fields = self.parse(doc_file)
# Initialization of fields
self.id = self.fields["patent number"]
self.abstract = self.get_abstract()
self.terms = self.get_terms()
self.cites = self.get_cited_patents()
self.cited_by = []
self.related = self.get_related_patents()
self.ipc = self.get_IPC_groups()
self.upc = self.get_UPC_groups()
self.terms_dist = util.getFreqDist(self.terms)
self.tf_weights = util.get_tf_weights(self.terms_dist)