def test_folding():
"""FP Folding"""
# Upper bound
assert_array_equal(fold([MAX_HASH_VALUE], 1024), [1023])
assert_array_equal(fold([MAX_HASH_VALUE], 1234567890), [1234567889])
assert_array_equal(fold([MAX_HASH_VALUE], MAX_HASH_VALUE / 2),
[MAX_HASH_VALUE / 2 - 1])
assert_array_equal(fold([MAX_HASH_VALUE], MAX_HASH_VALUE - 1),
[MAX_HASH_VALUE - 2])
# Lower bound
assert_array_equal(fold([MIN_HASH_VALUE], 1024), [0])
assert_array_equal(fold([MIN_HASH_VALUE], 1234567890), [0])
assert_array_equal(fold([MIN_HASH_VALUE], MAX_HASH_VALUE / 2), [0])
assert_array_equal(fold([MIN_HASH_VALUE], MAX_HASH_VALUE - 1), [0])
# Range check
fp = np.arange(1, MAX_HASH_VALUE, 1e6, dtype=int)
assert_array_equal(fold(fp, MAX_HASH_VALUE), fp - 1)
def test_folding():
"""FP Folding"""
# Upper bound
assert_array_equal(fold([MAX_HASH_VALUE], 1024), [1023])
assert_array_equal(fold([MAX_HASH_VALUE], 1234567890), [1234567889])
assert_array_equal(fold([MAX_HASH_VALUE], MAX_HASH_VALUE / 2),
[MAX_HASH_VALUE / 2 - 1])
assert_array_equal(fold([MAX_HASH_VALUE], MAX_HASH_VALUE - 1),
[MAX_HASH_VALUE - 2])
# Lower bound
assert_array_equal(fold([MIN_HASH_VALUE], 1024), [0])
assert_array_equal(fold([MIN_HASH_VALUE], 1234567890), [0])
assert_array_equal(fold([MIN_HASH_VALUE], MAX_HASH_VALUE / 2), [0])
assert_array_equal(fold([MIN_HASH_VALUE], MAX_HASH_VALUE - 1), [0])
# Range check
fp = np.arange(1, MAX_HASH_VALUE, 1e6, dtype=int)
assert_array_equal(fold(fp, MAX_HASH_VALUE), fp - 1)
def _load_pdbbind_desc(self, desc_path, pdbbind_version=2016,
train_set='refined', test_set='core',
train_blacklist=None, fold_size=None):
"""
TODO: write the docs
"""
df = pd.read_csv(desc_path, index_col='pdbid')
# generate dense representation of sparse descriptor in CSV
cols = list(map(str, range(len(self.descriptor_generator))))
if 'sparse' in df.columns:
# convert strings to np.arrays
df['sparse'] = df['sparse'].map(
lambda x: np.fromstring(x[1:-1], dtype=np.uint64, sep=','))
cols = 'sparse' # sparse array will have one column
# fold only if necessary
if fold_size:
df['sparse'] = df['sparse'].map(lambda x: fold(x, fold_size))
# convert to sparse csr_matrix
df['sparse'] = df['sparse'].map(
partial(sparse_to_csr_matrix,
size=len(self.descriptor_generator)))
if isinstance(train_set, six.string_types):
train_idx = df['%i_%s' % (pdbbind_version, train_set)]
else:
train_idx = df[['%i_%s' % (pdbbind_version, s)
for s in train_set]].any(axis=1)
if train_blacklist:
train_idx &= ~df.index.isin(train_blacklist)
train_idx &= ~df['%i_%s' % (pdbbind_version, test_set)]
# load sparse matrices as training is usually faster on them
if 'sparse' in df.columns:
self.train_descs = sparse_vstack(df.loc[train_idx, cols].values,
format='csr')
else:
self.train_descs = df.loc[train_idx, cols].values
self.train_target = df.loc[train_idx, 'act'].values
test_idx = df['%i_%s' % (pdbbind_version, test_set)]
if 'sparse' in df.columns:
self.test_descs = sparse_vstack(df.loc[test_idx, cols].values,
format='csr')
else:
self.test_descs = df.loc[test_idx, cols].values
self.test_target = df.loc[test_idx, 'act'].values