def test_symmetric(self):
# query[i] always matches target[i] so x[i] will always contain element[i]
x = search.knearest_tanimoto_search_arena(fps, fps, 31, 0.9)
# This only processes the upper-triangle, and not the diagonal
y = search.knearest_tanimoto_search_symmetric(fps, 30, 0.9)
for i, (x_row, y_row) in enumerate(zip(x, y)):
x_row = x_row.get_indices_and_scores()
y_row = y_row.get_indices_and_scores()
y_row.append((i, 1.0))
x_row.sort()
y_row.sort()
self.assertEquals(x_row, y_row, "Problem in %d" % i)
def test_symmetric(self):
# query[i] always matches target[i] so x[i] will always contain element[i]
x = search.knearest_tanimoto_search_arena(fps, fps, 31, 0.9)
# This only processes the upper-triangle, and not the diagonal
y = search.knearest_tanimoto_search_symmetric(fps, 30, 0.9)
for i, (x_row, y_row) in enumerate(zip(x, y)):
x_row = x_row.get_indices_and_scores()
y_row = y_row.get_indices_and_scores()
y_row.append((i, 1.0))
x_row.sort()
y_row.sort()
self.assertEquals(x_row, y_row, "Problem in %d" % i)
def knearest_tanimoto_search_arena(self, queries, k=3, threshold=0.7):
"""Find the k-nearest fingerprint which are similar to each of the query fingerprints
DEPRECATED: Use `chemfp.search.knearest_tanimoto_search_arena`_ or
`chemfp.search.knearest_tanimoto_search_symmetric`_ instead.
For each fingerprint in the `query_arena`, find the `k`
fingerprints in this arena which are most similar and which
are at least `threshold` similar to the query fingerprint.
The hits are returned as a SearchResult where the hits are
sorted with the highest similarity first. Ties are broken
arbitrarily.
:param query_arena: query arena
:type query_arena: FingerprintArena
:param k: number of nearest neighbors to find (default: 3)
:type k: positive integer
:param threshold: minimum similarity threshold (default: 0.7)
:type threshold: float between 0.0 and 1.0, inclusive
:returns: SearchResult
"""
return search.knearest_tanimoto_search_arena(queries, self, k, threshold)