Skip to content

Intersection query for relevant_pages #509

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
norvig merged 2 commits into from
May 24, 2017
Merged

Intersection query for relevant_pages #509

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
25df9a2
Modified relevant_pages()
Chipe1 Apr 18, 2017
0429539
Additional tests for relevant_pages()
Chipe1 Apr 18, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 11 additions & 9 deletions nlp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,15 +301,17 @@ def expand_pages(pages):


def relevant_pages(query):
"""Relevant pages are pages that contain the query in its entireity.
If a page's content contains the query it is returned by the function."""
relevant = {}
print("pagesContent in function: ", pagesContent)
for addr, page in pagesIndex.items():
if query.lower() in pagesContent[addr].lower():
relevant[addr] = page
return relevant

"""Relevant pages are pages that contain all of the query words. They are obtained by
intersecting the hit lists of the query words."""
hit_intersection = {addr for addr in pagesIndex}
query_words = query.split()
for query_word in query_words:
hit_list = set()
for addr in pagesIndex:
if query_word.lower() in pagesContent[addr].lower():
hit_list.add(addr)
hit_intersection = hit_intersection.intersection(hit_list)
return {addr: pagesIndex[addr] for addr in hit_intersection}

def normalize(pages):
"""From the pseudocode: Normalize divides each page's score by the sum of
Expand Down
10 changes: 7 additions & 3 deletions tests/test_nlp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ def test_lexicon():
href="https://google.com.au"
< href="/wiki/TestThing" > href="/wiki/TestBoy"
href="/wiki/TestLiving" href="/wiki/TestMan" >"""
testHTML2 = "Nothing"
testHTML2 = "a mom and a dad"
testHTML3 = """
<!DOCTYPE html>
<html>
Expand Down Expand Up @@ -106,9 +106,13 @@ def test_expand_pages():


def test_relevant_pages():
pages = relevant_pages("male")
assert all((x in pages.keys()) for x in ['A', 'C', 'E'])
pages = relevant_pages("his dad")
assert all((x in pages) for x in ['A', 'C', 'E'])
assert all((x not in pages) for x in ['B', 'D', 'F'])
pages = relevant_pages("mom and dad")
assert all((x in pages) for x in ['A', 'B', 'C', 'D', 'E', 'F'])
pages = relevant_pages("philosophy")
assert all((x not in pages) for x in ['A', 'B', 'C', 'D', 'E', 'F'])


def test_normalize():
Expand Down