def BKing(file_name, query_string, return_count = 10):
# set idx file and dict file path
idx_file = file_name + ".index"
# error detection
if not os.path.isfile(idx_file):
print "Error: index dictionary file inverted index file (.index) not found. Please Run:\
python corpusParser.py -f %s -s %s" % (file_name, 'stopword')
exit(1)
# read dict file to dict
dicts = decompress_dict(idx_file)
(N, docsyID, docsByName) = getCorpusDoc(file_name)
# docs's parameter table
docs_table = {}
# docs score hash, use cosine similarity score with weight use tf-idf
docs_score = {}
# stem the query string
query_string = stem_query(query_string)
(query_table, docs_set, term_index) = query_weight(query_string, dicts, idx_file, N)
docs_table = docs_weight(docs_set, term_index, query_string, query_table)
docs_score = cos_vector_space_model(query_table, docs_table)
print "Query terms:", query_string
print "Top", return_count, "results:"
print "doc#\tscore"
count = return_count
for i in sorted(docs_score, key=docs_score.get, reverse=True):
count -= 1
if count < 0:
break
print "%d\t%.6f" % (int(i), docs_score[i])
if count >= 0:
print "Only have found %d relevant documents." % (return_count - count)
print '\n*****************Some information about corpus*************************'
print "The query string in corups information:"
for i in term_index:
if term_index[i].df > 0:
term_index[i].output()
print '\n*****************Some information about corpus*************************'
for doc in docsByName.values():
print doc[1], " docID:", doc[0], " docLength:", doc[2]
def query(file_name, query_string, return_count=10):
# set idx file and dict file path
idx_file = file_name + ".index"
# error detection
if not os.path.isfile(idx_file):
print "Error: index dictionary file(.index.dict or inverted index file (.index.idx) not found."
exit(1)
# read dict file to dict
dicts = decompress_dict(idx_file)
# docs's parameter table
docs_table = {}
# docs score hash, use cosine similarity score with weight use tf-idf
docs_score = {}
# stem the query string
query_string = stem_query(query_string)
(query_table, docs_set, term_index) = query_weight(query_string, dicts,
idx_file)
docs_table = docs_weight(docs_set, term_index, query_string, query_table)
docs_score = cos_vector_space_model(query_table, docs_table)
print "Query terms:", query_string
print "Top", return_count, "results:"
print "doc#\tscore"
for i in sorted(docs_score, key=docs_score.get, reverse=True):
return_count -= 1
if return_count < 0:
break
print "%d\t%.3f" % (int(i), docs_score[i])
def query(file_name, query_string, return_count = 10):
# set idx file and dict file path
idx_file = file_name + ".index"
# error detection
if not os.path.isfile(idx_file):
print "Error: index dictionary file(.index.dict or inverted index file (.index.idx) not found."
exit(1)
# read dict file to dict
dicts = decompress_dict(idx_file)
# docs's parameter table
docs_table = {}
# docs score hash, use cosine similarity score with weight use tf-idf
docs_score = {}
# stem the query string
query_string = stem_query(query_string)
(query_table, docs_set, term_index) = query_weight(query_string, dicts, idx_file)
docs_table = docs_weight(docs_set, term_index, query_string, query_table)
docs_score = cos_vector_space_model(query_table, docs_table)
print "Query terms:", query_string
print "Top", return_count, "results:"
print "doc#\tscore"
for i in sorted(docs_score, key=docs_score.get, reverse=True):
return_count -= 1
if return_count < 0:
break
print "%d\t%.3f" % (int(i), docs_score[i])
