def fill_lower_triangle(results):
"""Duplicate each entry of `results` to its transpose
This is used after the symmetric threshold search to turn the
upper-triangle results into a full matrix.
"""
_chemfp.fill_lower_triangle(results, len(results))
def fill_lower_triangle(results):
"""Duplicate each entry of `results` to its transpose
This is used after the symmetric threshold search to turn the
upper-triangle results into a full matrix.
"""
_chemfp.fill_lower_triangle(results, len(results))
def threshold_tanimoto_search_symmetric(arena,
threshold=0.7,
include_lower_triangle=True,
batch_size=100):
"""Search for the hits in the `arena` at least `threshold` similar to the fingerprints in the arena
When `include_lower_triangle` is True, compute the upper-triangle
similarities, then copy the results to get the full set of
results. When `include_lower_triangle` is False, only compute the
upper triangle.
The computation can take a long time. Python won't check check for
a ^C until the function finishes. This can be irritating. Instead,
process only `batch_size` rows at a time before checking for a ^C.
The hits in the returned `SearchResults` are in arbitrary order.
Example::
arena = chemfp.load_fingerprints("queries.fps")
full_result = chemfp.search.threshold_tanimoto_search_symmetric(arena, threshold=0.2)
upper_triangle = chemfp.search.threshold_tanimoto_search_symmetric(
arena, threshold=0.2, include_lower_triangle=False)
assert sum(map(len, full_result)) == sum(map(len, upper_triangle))*2
:param arena: the set of fingerprints
:type arena: a FingerprintArena
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:param include_lower_triangle:
if False, compute only the upper triangle, otherwise use symmetry to compute the full matrix
:type include_lower_triangle: boolean
:param batch_size: the number of rows to process before checking for a ^C
:type batch_size: integer
:returns: a SearchResults instance
"""
if batch_size <= 0:
raise ValueError("batch_size must be positive")
N = len(arena)
results = SearchResults(N, arena.arena_ids)
if N:
# Break it up into batch_size groups in order to let Python's
# interrupt handler check for a ^C, which is otherwise
# suppressed until the function finishes.
for query_start in xrange(0, N, batch_size):
query_end = min(query_start + batch_size, N)
_chemfp.threshold_tanimoto_arena_symmetric(
threshold, arena.num_bits, arena.start_padding,
arena.end_padding, arena.storage_size, arena.arena,
query_start, query_end, 0, N, arena.popcount_indices, results)
if include_lower_triangle:
_chemfp.fill_lower_triangle(results, N)
return results
def threshold_tanimoto_search_symmetric(arena, threshold=0.7, include_lower_triangle=True, batch_size=100):
"""Search for the hits in the `arena` at least `threshold` similar to the fingerprints in the arena
When `include_lower_triangle` is True, compute the upper-triangle
similarities, then copy the results to get the full set of
results. When `include_lower_triangle` is False, only compute the
upper triangle.
The computation can take a long time. Python won't check check for
a ^C until the function finishes. This can be irritating. Instead,
process only `batch_size` rows at a time before checking for a ^C.
The hits in the returned `SearchResults` are in arbitrary order.
Example::
arena = chemfp.load_fingerprints("queries.fps")
full_result = chemfp.search.threshold_tanimoto_search_symmetric(arena, threshold=0.2)
upper_triangle = chemfp.search.threshold_tanimoto_search_symmetric(
arena, threshold=0.2, include_lower_triangle=False)
assert sum(map(len, full_result)) == sum(map(len, upper_triangle))*2
:param arena: the set of fingerprints
:type arena: a FingerprintArena
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:param include_lower_triangle:
if False, compute only the upper triangle, otherwise use symmetry to compute the full matrix
:type include_lower_triangle: boolean
:param batch_size: the number of rows to process before checking for a ^C
:type batch_size: integer
:returns: a SearchResults instance
"""
if batch_size <= 0:
raise ValueError("batch_size must be positive")
N = len(arena)
results = SearchResults(N, arena.arena_ids)
if N:
# Break it up into batch_size groups in order to let Python's
# interrupt handler check for a ^C, which is otherwise
# suppressed until the function finishes.
for query_start in xrange(0, N, batch_size):
query_end = min(query_start + batch_size, N)
_chemfp.threshold_tanimoto_arena_symmetric(
threshold, arena.num_bits,
arena.start_padding, arena.end_padding, arena.storage_size, arena.arena,
query_start, query_end, 0, N,
arena.popcount_indices,
results)
if include_lower_triangle:
_chemfp.fill_lower_triangle(results, N)
return results
def threshold_tanimoto_search_symmetric(arena,
threshold,
include_lower_triangle=True):
assert arena.popcount_indices
N = len(arena)
results = SearchResults(N, arena.ids)
if N:
_chemfp.threshold_tanimoto_arena_symmetric(
threshold, arena.num_bits, arena.start_padding, arena.end_padding,
arena.storage_size, arena.arena, 0, N, 0, N,
arena.popcount_indices, results)
if include_lower_triangle:
_chemfp.fill_lower_triangle(results, N)
return results
def fill_lower_triangle(results):
_chemfp.fill_lower_triangle(results, len(results))
