def get_similarity_for_tag(self, tag):
# a = db.session.query(func.unnest(func.string_to_array(strings_tags, ';')).label('value')).cte('param')
result = db.session.query(
Tag.id, Tag.value, Tag.word, Tag.meaning,
func.similarity(Tag.value, tag).label('similarity')).filter(
func.similarity(Tag.value, tag) > 0.6).order_by(
desc(func.similarity(
Tag.value, tag).label('similarity'))).limit(2).all()
return result
def auto_movie(self, q):
orig_q = q
q = q.lstrip().lower().split(' ')
full_words, q = q[:-1], q[-1]
if 'the' in full_words:
full_words.remove('the')
target = literal(' ').op('||')(Movie.title)
filters = []
for word in full_words:
filters.append(target.ilike('%% %s %%' % word))
filters.append(target.ilike('%% %s%%' % q))
if len(filters) > 1:
filters = and_(*filters)
else:
filters = filters[0]
res = self.session.query(Movie.id, Movie.title, Rating.rating)\
.outerjoin((Rating, and_(Rating.movie_id == Movie.id,
Rating.user == self.user)))\
.filter(filters)\
.order_by(func.similarity(func.lower(target), orig_q).desc())\
.limit(7).all()
self.return_json(res)
def fetch_all_by_trgm_sim(self, smiles, *expr, **kwargs):
"""
Returns all fragments that are similar to the given SMILES string
using trigam similarity (similar to LINGO).
Parameters
----------
threshold : float, default=0.6
Similarity threshold that will be used for searching.
limit : int, default=25
Maximum number of hits that will be returned.
Returns
-------
resultset : list
List of tuples (Fragment, similarity) containing the chemical components
and the calculated trigram similarity.
Queried Entities
----------------
Fragment
Examples
--------
>>>> FragmentAdaptor().fetch_all_by_trgm_sim('Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)CN5CC[NH+](CC5)C')
[(<Fragment(STI)>, 0.883721), (<Fragment(NIL)>, 0.73913),
(<Fragment(PRC)>, 0.738095), (<Fragment(406)>, 0.666667),
(<Fragment(J07)>, 0.604167), (<Fragment(AD5)>, 0.6),
(<Fragment(AAX)>, 0.6), (<Fragment(VX6)>, 0.6)]
Requires
--------
.. important:: `pg_trgm <http://www.postgresql.org/docs/current/static/pgtrgm.html>`_ PostgreSQL extension.
"""
session = Session()
threshold = kwargs.get('threshold', 0.6)
# SET THE SIMILARITY THRESHOLD FOR THE INDEX
session.execute(
text("SELECT set_limit(:threshold)").execution_options(
autocommit=True).params(threshold=threshold))
similarity = func.similarity(Fragment.ism, smiles).label('similarity')
sim_thresh = func.show_limit().label('sim_thresh')
query = self.query.add_columns(similarity, sim_thresh)
query = query.filter(and_(Fragment.like(smiles), *expr))
# KNN-GIST
query = query.order_by(Fragment.ism.op('<->')(smiles))
if kwargs.get('limit'):
query = query.limit(kwargs['limit'])
results = query.all()
#session.close()
return results #query
def fetch_all_by_trgm_sim(self, smiles, *expressions, **kwargs):
'''
Returns all molecules that are similar to the given SMILES string using
trigam similarity (similar to LINGO).
By far the quickest way to get similar molecules!
Parameters
----------
threshold : float, default=0.6
Similarity threshold that will be used for searching.
limit : int, default=25
Maximum number of hits that will be returned.
Returns
-------
resultset : list
List of tuples (Emolecule, similarity) containing the chemical components
and the calculated trigram similarity.
Queried Entities
----------------
Emolecule
Examples
--------
Requires
--------
.. important:: `pg_trgm <http://www.postgresql.org/docs/current/static/pgtrgm.html>`_ PostgreSQL extension.
Notes
-----
Will make use of the KNNGIST operator <-> in 9.1.
'''
threshold = kwargs.get('threshold', 0.6)
limit = kwargs.get('limit', 25)
# SET THE SIMILARITY THRESHOLD FOR THE INDEX
session.execute(
text("SELECT set_limit(:threshold)").execution_options(
autocommit=True).params(threshold=threshold))
similarity = func.similarity(Emolecule.smiles,
smiles).label('similarity')
query = session.query(Emolecule, similarity)
query = query.filter(and_(Emolecule.like(smiles), *expressions))
query = query.order_by(similarity.desc()).limit(limit)
return query.all()
def get_similarity_query(self, query):
return (func.coalesce(func.similarity(self.column, query),
0).label('first_name_rank') * self.rank)
def get_similarity(self, value):
return db.session.query(TagerTag.id).filter(
func.similarity(TagerTag.value, value) > 0.3).first()
def get_similarity(self, value):
return db.session.query(
TagerColor.id
# TagerColor.name
).filter(func.similarity(TagerColor.name, value) > 0.3).first()