def sample_sim_index():
# Create an in-memory index and query it
print()
print("Creating in-memory index of university homepages")
sim_index = MemorySimIndex()
sim_index.index_urls('http://www.stanford.edu/',
'http://www.berkeley.edu',
'http://www.ucla.edu',
'http://www.mit.edu')
print("Postings list for 'university':")
pprint(sim_index.postings_list('university'))
print("Pages containing terms 'university' and 'california'")
pprint(list(sim_index.docnames_with_terms('university', 'california')))
# Issue some similarity queries
print()
print("Similarity search for query 'stanford university' (simple scorer)")
sim_index.set_query_scorer('simple_count')
pprint(list(sim_index.query("stanford university")))
print()
print("Similarity search for query 'stanford university' (tf.idf scorer)")
sim_index.set_query_scorer('tfidf')
pprint(list(sim_index.query("stanford university")))
# Save the index to disk, then load it back in
print()
print("Saving index to disk")
with open("myindex.idx", "w") as index_file:
sim_index.save(index_file)
print()
print("Loading index from disk")
with open("myindex.idx", "r") as index_file:
sim_index2 = MemorySimIndex.load(index_file)
print()
print("Pages containing terms 'university' and 'california' in loaded index")
pprint(list(sim_index2.docnames_with_terms('university', 'california')))
def sample_sim_index():
# Create an in-memory index and query it
print()
print("Creating in-memory index of university homepages")
sim_index = MemorySimIndex()
sim_index.index_urls('http://www.stanford.edu/', 'http://www.berkeley.edu',
'http://www.ucla.edu', 'http://www.mit.edu')
print("Postings list for 'university':")
pprint(sim_index.postings_list('university'))
print("Pages containing terms 'university' and 'california'")
pprint(list(sim_index.docnames_with_terms('university', 'california')))
# Issue some similarity queries
print()
print("Similarity search for query 'stanford university' (simple scorer)")
sim_index.set_query_scorer('simple_count')
pprint(list(sim_index.query("stanford university")))
print()
print("Similarity search for query 'stanford university' (tf.idf scorer)")
sim_index.set_query_scorer('tfidf')
pprint(list(sim_index.query("stanford university")))
# Save the index to disk, then load it back in
print()
print("Saving index to disk")
with open("myindex.idx", "w") as index_file:
sim_index.save(index_file)
print()
print("Loading index from disk")
with open("myindex.idx", "r") as index_file:
sim_index2 = MemorySimIndex.load(index_file)
print()
print(
"Pages containing terms 'university' and 'california' in loaded index")
pprint(list(sim_index2.docnames_with_terms('university', 'california')))
