Spaces:
Sleeping
Sleeping
Fanwang Meng
commited on
Commit
·
ba3d577
1
Parent(s):
fff07bd
Clean up following pre-commit
Browse files- .bandit.yml +4 -4
- selector/__init__.py +0 -2
- selector/converter.py +1 -3
- selector/diversity.py +1 -2
- selector/methods/__init__.py +0 -1
- selector/methods/base.py +2 -3
- selector/methods/distance.py +0 -2
- selector/methods/partition.py +1 -3
- selector/methods/similarity.py +2 -3
- selector/methods/tests/__init__.py +0 -1
- selector/methods/tests/common.py +2 -4
- selector/methods/tests/test_distance.py +3 -3
- selector/methods/tests/test_partition.py +2 -6
- selector/methods/utils.py +0 -2
- selector/similarity.py +1 -3
- selector/tests/__init__.py +0 -1
- selector/tests/common.py +0 -1
- selector/tests/test_converter.py +1 -2
- selector/tests/test_diversity.py +5 -6
- selector/tests/test_similarity.py +4 -4
.bandit.yml
CHANGED
@@ -3,9 +3,9 @@ skips:
|
|
3 |
- B101
|
4 |
# Standard pseudo-random generators are not suitable for security/cryptographic purposes
|
5 |
- B311
|
6 |
-
# Ignore warnings about importing subprocess
|
7 |
-
- B404
|
8 |
# Ignore warnings about calling subprocess
|
9 |
-
- B603
|
10 |
# Ignore warnings about calling subprocess
|
11 |
-
- B607
|
|
|
3 |
- B101
|
4 |
# Standard pseudo-random generators are not suitable for security/cryptographic purposes
|
5 |
- B311
|
6 |
+
# Ignore warnings about importing subprocess
|
7 |
+
- B404
|
8 |
# Ignore warnings about calling subprocess
|
9 |
+
- B603
|
10 |
# Ignore warnings about calling subprocess
|
11 |
+
- B607
|
selector/__init__.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -24,4 +23,3 @@
|
|
24 |
"""Selector Package."""
|
25 |
|
26 |
from selector.methods import *
|
27 |
-
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
23 |
"""Selector Package."""
|
24 |
|
25 |
from selector.methods import *
|
|
selector/converter.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -22,10 +21,9 @@
|
|
22 |
# --
|
23 |
"""Module for converting similarity measures to distance/dissimilarity measures."""
|
24 |
|
25 |
-
import numpy as np
|
26 |
-
|
27 |
from typing import Union
|
28 |
|
|
|
29 |
|
30 |
__all__ = [
|
31 |
"sim_to_dist",
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
21 |
# --
|
22 |
"""Module for converting similarity measures to distance/dissimilarity measures."""
|
23 |
|
|
|
|
|
24 |
from typing import Union
|
25 |
|
26 |
+
import numpy as np
|
27 |
|
28 |
__all__ = [
|
29 |
"sim_to_dist",
|
selector/diversity.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -26,8 +25,8 @@
|
|
26 |
import warnings
|
27 |
|
28 |
import numpy as np
|
29 |
-
from selector.similarity import tanimoto
|
30 |
|
|
|
31 |
|
32 |
__all__ = [
|
33 |
"compute_diversity",
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
25 |
import warnings
|
26 |
|
27 |
import numpy as np
|
|
|
28 |
|
29 |
+
from selector.similarity import tanimoto
|
30 |
|
31 |
__all__ = [
|
32 |
"compute_diversity",
|
selector/methods/__init__.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
selector/methods/base.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -22,11 +21,11 @@
|
|
22 |
# --
|
23 |
"""Base class for diversity based subset selection."""
|
24 |
|
25 |
-
import numpy as np
|
26 |
import warnings
|
27 |
-
|
28 |
from abc import ABC, abstractmethod
|
29 |
|
|
|
|
|
30 |
__all__ = ["SelectionBase"]
|
31 |
|
32 |
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
21 |
# --
|
22 |
"""Base class for diversity based subset selection."""
|
23 |
|
|
|
24 |
import warnings
|
|
|
25 |
from abc import ABC, abstractmethod
|
26 |
|
27 |
+
import numpy as np
|
28 |
+
|
29 |
__all__ = ["SelectionBase"]
|
30 |
|
31 |
|
selector/methods/distance.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -29,7 +28,6 @@ import scipy
|
|
29 |
from selector.methods.base import SelectionBase
|
30 |
from selector.methods.utils import optimize_radius
|
31 |
|
32 |
-
|
33 |
__all__ = [
|
34 |
"MaxMin",
|
35 |
"MaxSum",
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
28 |
from selector.methods.base import SelectionBase
|
29 |
from selector.methods.utils import optimize_radius
|
30 |
|
|
|
31 |
__all__ = [
|
32 |
"MaxMin",
|
33 |
"MaxSum",
|
selector/methods/partition.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -29,9 +28,8 @@ import bitarray
|
|
29 |
import numpy as np
|
30 |
import scipy
|
31 |
|
32 |
-
from selector.methods.base import SelectionBase
|
33 |
from selector.diversity import compute_diversity
|
34 |
-
|
35 |
|
36 |
__all__ = [
|
37 |
"GridPartition",
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
28 |
import numpy as np
|
29 |
import scipy
|
30 |
|
|
|
31 |
from selector.diversity import compute_diversity
|
32 |
+
from selector.methods.base import SelectionBase
|
33 |
|
34 |
__all__ = [
|
35 |
"GridPartition",
|
selector/methods/similarity.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -36,13 +35,13 @@ The ideas behind the similarity-based selection methods are described in the fol
|
|
36 |
"""
|
37 |
|
38 |
import math
|
39 |
-
from math import log
|
40 |
import random
|
|
|
41 |
from typing import List, Optional, Union
|
42 |
|
43 |
-
from selector.methods.base import SelectionBase
|
44 |
import numpy as np
|
45 |
|
|
|
46 |
|
47 |
__all__ = ["NSimilarity", "SimilarityIndex"]
|
48 |
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
35 |
"""
|
36 |
|
37 |
import math
|
|
|
38 |
import random
|
39 |
+
from math import log
|
40 |
from typing import List, Optional, Union
|
41 |
|
|
|
42 |
import numpy as np
|
43 |
|
44 |
+
from selector.methods.base import SelectionBase
|
45 |
|
46 |
__all__ = ["NSimilarity", "SimilarityIndex"]
|
47 |
|
selector/methods/tests/__init__.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
selector/methods/tests/common.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -22,12 +21,11 @@
|
|
22 |
# --
|
23 |
"""Common functions for test module."""
|
24 |
|
25 |
-
import
|
26 |
|
|
|
27 |
from sklearn.datasets import make_blobs
|
28 |
from sklearn.metrics import pairwise_distances
|
29 |
-
from typing import Any, Tuple, Union
|
30 |
-
|
31 |
|
32 |
__all__ = [
|
33 |
"generate_synthetic_data",
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
21 |
# --
|
22 |
"""Common functions for test module."""
|
23 |
|
24 |
+
from typing import Any, Tuple, Union
|
25 |
|
26 |
+
import numpy as np
|
27 |
from sklearn.datasets import make_blobs
|
28 |
from sklearn.metrics import pairwise_distances
|
|
|
|
|
29 |
|
30 |
__all__ = [
|
31 |
"generate_synthetic_data",
|
selector/methods/tests/test_distance.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -23,12 +22,13 @@
|
|
23 |
"""Test selector/methods/distance.py."""
|
24 |
|
25 |
|
26 |
-
from selector.methods.distance import MaxMin, MaxSum, OptiSim, DISE
|
27 |
import numpy as np
|
|
|
28 |
from numpy.testing import assert_equal, assert_raises
|
29 |
from sklearn.metrics import pairwise_distances
|
|
|
|
|
30 |
from selector.methods.tests.common import generate_synthetic_data
|
31 |
-
import pytest
|
32 |
|
33 |
|
34 |
def test_maxmin():
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
22 |
"""Test selector/methods/distance.py."""
|
23 |
|
24 |
|
|
|
25 |
import numpy as np
|
26 |
+
import pytest
|
27 |
from numpy.testing import assert_equal, assert_raises
|
28 |
from sklearn.metrics import pairwise_distances
|
29 |
+
|
30 |
+
from selector.methods.distance import DISE, MaxMin, MaxSum, OptiSim
|
31 |
from selector.methods.tests.common import generate_synthetic_data
|
|
|
32 |
|
33 |
|
34 |
def test_maxmin():
|
selector/methods/tests/test_partition.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -23,13 +22,10 @@
|
|
23 |
"""Test Partition-Based Selection Methods."""
|
24 |
|
25 |
import numpy as np
|
26 |
-
from numpy.testing import assert_equal, assert_raises
|
27 |
import pytest
|
|
|
28 |
|
29 |
-
from selector.methods.partition import
|
30 |
-
GridPartition,
|
31 |
-
Medoid,
|
32 |
-
)
|
33 |
from selector.methods.tests.common import generate_synthetic_data
|
34 |
|
35 |
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
22 |
"""Test Partition-Based Selection Methods."""
|
23 |
|
24 |
import numpy as np
|
|
|
25 |
import pytest
|
26 |
+
from numpy.testing import assert_equal, assert_raises
|
27 |
|
28 |
+
from selector.methods.partition import GridPartition, Medoid
|
|
|
|
|
|
|
29 |
from selector.methods.tests.common import generate_synthetic_data
|
30 |
|
31 |
|
selector/methods/utils.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -26,7 +25,6 @@ import warnings
|
|
26 |
|
27 |
import numpy as np
|
28 |
|
29 |
-
|
30 |
__all__ = [
|
31 |
"optimize_radius",
|
32 |
]
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
25 |
|
26 |
import numpy as np
|
27 |
|
|
|
28 |
__all__ = [
|
29 |
"optimize_radius",
|
30 |
]
|
selector/similarity.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -22,10 +21,9 @@
|
|
22 |
# --
|
23 |
"""Similarity Module."""
|
24 |
|
25 |
-
import numpy as np
|
26 |
-
|
27 |
from itertools import combinations_with_replacement
|
28 |
|
|
|
29 |
|
30 |
__all__ = ["pairwise_similarity_bit", "tanimoto", "modified_tanimoto"]
|
31 |
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
21 |
# --
|
22 |
"""Similarity Module."""
|
23 |
|
|
|
|
|
24 |
from itertools import combinations_with_replacement
|
25 |
|
26 |
+
import numpy as np
|
27 |
|
28 |
__all__ = ["pairwise_similarity_bit", "tanimoto", "modified_tanimoto"]
|
29 |
|
selector/tests/__init__.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
selector/tests/common.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
selector/tests/test_converter.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -22,10 +21,10 @@
|
|
22 |
# --
|
23 |
"""Test Converter Module."""
|
24 |
|
25 |
-
import selector.converter as cv
|
26 |
import numpy as np
|
27 |
from numpy.testing import assert_almost_equal, assert_equal, assert_raises
|
28 |
|
|
|
29 |
|
30 |
# Tests for variations on input `x` for sim_to_dist()
|
31 |
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
21 |
# --
|
22 |
"""Test Converter Module."""
|
23 |
|
|
|
24 |
import numpy as np
|
25 |
from numpy.testing import assert_almost_equal, assert_equal, assert_raises
|
26 |
|
27 |
+
import selector.converter as cv
|
28 |
|
29 |
# Tests for variations on input `x` for sim_to_dist()
|
30 |
|
selector/tests/test_diversity.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -23,21 +22,21 @@
|
|
23 |
|
24 |
"""Test Diversity Module."""
|
25 |
|
26 |
-
import pytest
|
27 |
import numpy as np
|
|
|
28 |
from numpy.testing import assert_almost_equal, assert_equal, assert_raises, assert_warns
|
|
|
29 |
from selector.diversity import (
|
30 |
compute_diversity,
|
31 |
-
gini_coefficient,
|
32 |
explicit_diversity_index,
|
|
|
|
|
33 |
logdet,
|
|
|
34 |
shannon_entropy,
|
35 |
-
hypersphere_overlap_of_subset,
|
36 |
wdud,
|
37 |
-
nearest_average_tanimoto,
|
38 |
)
|
39 |
|
40 |
-
|
41 |
# each row is a feature and each column is a molecule
|
42 |
sample1 = np.array([[4, 2, 6], [4, 9, 6], [2, 5, 0], [2, 0, 9], [5, 3, 0]])
|
43 |
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
22 |
|
23 |
"""Test Diversity Module."""
|
24 |
|
|
|
25 |
import numpy as np
|
26 |
+
import pytest
|
27 |
from numpy.testing import assert_almost_equal, assert_equal, assert_raises, assert_warns
|
28 |
+
|
29 |
from selector.diversity import (
|
30 |
compute_diversity,
|
|
|
31 |
explicit_diversity_index,
|
32 |
+
gini_coefficient,
|
33 |
+
hypersphere_overlap_of_subset,
|
34 |
logdet,
|
35 |
+
nearest_average_tanimoto,
|
36 |
shannon_entropy,
|
|
|
37 |
wdud,
|
|
|
38 |
)
|
39 |
|
|
|
40 |
# each row is a feature and each column is a molecule
|
41 |
sample1 = np.array([[4, 2, 6], [4, 9, 6], [2, 5, 0], [2, 0, 9], [5, 3, 0]])
|
42 |
|
selector/tests/test_similarity.py
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
# The Selector library provides a set of tools for selecting a
|
3 |
# subset of the dataset and computing diversity.
|
4 |
#
|
@@ -26,11 +25,12 @@ import ast
|
|
26 |
import csv
|
27 |
|
28 |
import numpy as np
|
29 |
-
from numpy.testing import assert_almost_equal, assert_equal, assert_raises
|
30 |
import pkg_resources
|
31 |
import pytest
|
32 |
-
from
|
|
|
33 |
from selector.methods.similarity import NSimilarity, SimilarityIndex
|
|
|
34 |
|
35 |
|
36 |
def test_pairwise_similarity_bit_raises():
|
@@ -1284,7 +1284,7 @@ def _get_selections_ref_dict():
|
|
1284 |
"""
|
1285 |
|
1286 |
file_path = get_data_file_path("ref_similarity_data.csv")
|
1287 |
-
with open(file_path,
|
1288 |
reader = csv.reader(file, delimiter=";")
|
1289 |
next(reader) # skip header
|
1290 |
# initialize the dictionary
|
|
|
|
|
1 |
# The Selector library provides a set of tools for selecting a
|
2 |
# subset of the dataset and computing diversity.
|
3 |
#
|
|
|
25 |
import csv
|
26 |
|
27 |
import numpy as np
|
|
|
28 |
import pkg_resources
|
29 |
import pytest
|
30 |
+
from numpy.testing import assert_almost_equal, assert_equal, assert_raises
|
31 |
+
|
32 |
from selector.methods.similarity import NSimilarity, SimilarityIndex
|
33 |
+
from selector.similarity import modified_tanimoto, pairwise_similarity_bit, tanimoto
|
34 |
|
35 |
|
36 |
def test_pairwise_similarity_bit_raises():
|
|
|
1284 |
"""
|
1285 |
|
1286 |
file_path = get_data_file_path("ref_similarity_data.csv")
|
1287 |
+
with open(file_path, encoding="utf-8") as file:
|
1288 |
reader = csv.reader(file, delimiter=";")
|
1289 |
next(reader) # skip header
|
1290 |
# initialize the dictionary
|