Flake8

decoupler/method_aucell.py

@@ -7,7 +7,6 @@
 import pandas as pd
 from scipy.sparse import csr_matrix
 
-from numpy.random import default_rng
 from tqdm.auto import tqdm
 
 from .pre import extract, rename_net, filt_min_n, return_data, break_ties

decoupler/method_gsva.py

@@ -6,9 +6,7 @@
 import numpy as np
 import pandas as pd
 
-from scipy.stats import norm
 from scipy.sparse import csr_matrix
-from numpy.random import default_rng
 import math
 
 from .pre import extract, rename_net, filt_min_n, return_data, break_ties
@@ -36,6 +34,7 @@ def erf(x):
     y = 1.0 - (((((a5 * t + a4) * t + a3) * t + a2) * t + a1) * t * np.exp(-abs_x * abs_x))
     return sign * y
 
+
 @nb.njit(nb.f8[:](nb.f8[:], nb.f8, nb.f8), cache=True)
 def norm_cdf(x, mu=0.0, sigma=1.0):
     e = erf((x - mu) / (sigma * np.sqrt(2.0)))

decoupler/method_ora.py

@@ -6,7 +6,6 @@
 import numpy as np
 import pandas as pd
 
-from numpy.random import default_rng
 from scipy.sparse import csr_matrix
 
 from scipy.stats import rankdata

decoupler/method_udt.py

@@ -11,6 +11,7 @@
 
 from tqdm.auto import tqdm
 
+
 def check_if_sklearn():
     try:
         import sklearn as sk

decoupler/method_zscore.py

@@ -25,13 +25,13 @@ def zscore(m, net, flavor='RoKAI', verbose=False):
 
 
 def run_zscore(mat, net, source='source', target='target', weight='weight', batch_size=10000, flavor='RoKAI',
-             min_n=5, verbose=False, use_raw=True):
+               min_n=5, verbose=False, use_raw=True):
     """
     z-score.
 
-    Calculates regulatory activities using a z-score as descibed in KSEA or RoKAI. The z-score calculates the mean of the molecular features of the 
-    known targets for each regulator and adjusts it for the number of identified targets for the regulator, the standard deviation of all molecular 
-    features (RoKAI), as well as the mean of all moleculare features (KSEA).
+    Calculates regulatory activities using a z-score as descibed in KSEA or RoKAI. The z-score calculates the mean of the
+    molecular features of the known targets for each regulator and adjusts it for the number of identified targets for the
+    regulator, the standard deviation of all molecular features (RoKAI), as well as the mean of all moleculare features (KSEA).
 
     Parameters
     ----------
@@ -74,7 +74,8 @@ def run_zscore(mat, net, source='source', target='target', weight='weight', batc
     net = match(c, targets, net)
 
     if verbose:
-        print('Running zscore on mat with {0} samples and {1} targets for {2} sources.'.format(m.shape[0], len(c), net.shape[1]))
+        print('Running zscore on mat with {0} samples and {1} targets for {2} sources.'.format(
+            m.shape[0], len(c), net.shape[1]))
 
     # Run ULM
     estimate, pvals = zscore(m, net, flavor=flavor)

decoupler/pre.py

@@ -307,4 +307,3 @@ def break_ties(m, c, seed):
     idx = rng.choice(idx, c.size, replace=False)
     m, c = m[:, idx], c[idx]
     return m, c
-

decoupler/tests/test_gsva.py

@@ -42,7 +42,8 @@ def test_ppois():
 
 
 def test_norm_cdf():
-    assert np.isclose(norm_cdf(np.array([1, 2, 3], dtype=float), mu=0.0, sigma=1.0), np.array([0.8413447, 0.9772499, 0.9986501])).all()
+    assert np.isclose(norm_cdf(np.array([1, 2, 3], dtype=float), mu=0.0, sigma=1.0),
+                      np.array([0.8413447, 0.9772499, 0.9986501])).all()
     assert np.isclose(norm_cdf(np.array([0, 9, 1], dtype=float), mu=0.0, sigma=1.0), np.array([0.5, 1., 0.8413447])).all()
 
 

decoupler/tests/test_zscore.py

@@ -3,8 +3,10 @@
 from anndata import AnnData
 from ..method_zscore import zscore, run_zscore
 
+
 def test_zscore():
-    m = np.array([[-7., -1., 1., 1.], [-4., -2., 1., 2.], [1., 2., 5., 1.], [1., 1., 6., 2.], [-8., -7., 1., 1.]], dtype=np.float32)
+    m = np.array([[-7., -1., 1., 1.], [-4., -2., 1., 2.], [1., 2., 5., 1.],
+                  [1., 1., 6., 2.], [-8., -7., 1., 1.]], dtype=np.float32)
     net = np.array([[1., 0.], [1, 0.], [0., -1.], [0., -1.]], dtype=np.float32)
     act, pvl = zscore(m, net)
     assert act[0, 0] < 0
@@ -13,7 +15,7 @@ def test_zscore():
     assert act[3, 0] > 0
     assert act[4, 0] < 0
     assert np.all((0. <= pvl) * (pvl <= 1.))
-    
+
     act2, pvl2 = zscore(m, net, flavor='KSEA')
     assert act2[0, 0] < 0
     assert act2[1, 0] < 0
@@ -22,6 +24,7 @@ def test_zscore():
     assert act2[4, 0] < 0
     assert np.all((0. <= pvl2) * (pvl2 <= 1.))
 
+
 def test_run_zscore():
     m = np.array([[-7., -1., 1., 1.], [-4., -2., 1., 2.], [1., 2., 5., 1.], [1., 1., -6., -8.], [-8., -7., 1., 1.]])
     r = np.array(['S1', 'S2', 'S3', 'S4', 'S5'])
@@ -36,14 +39,14 @@ def test_run_zscore():
     assert res[0].loc['S4', 'T2'] > 0
     assert res[0].loc['S5', 'T2'] < 0
     assert res[1].map(lambda x: 0 <= x <= 1).all().all()
-    
+
     res2 = run_zscore(df, net, verbose=True, use_raw=False, min_n=0, flavor='KSEA')
     assert res2[0].loc['S1', 'T2'] > 0
     assert res2[0].loc['S2', 'T2'] < 0
     assert res2[0].loc['S3', 'T2'] < 0
     assert res2[0].loc['S4', 'T2'] > 0
     assert res2[0].loc['S5', 'T2'] > 0
     assert res2[1].map(lambda x: 0 <= x <= 1).all().all()
-    
+
     adata = AnnData(df.astype(np.float32))
-    run_zscore(adata, net, verbose=True, use_raw=False, min_n=0)
+    run_zscore(adata, net, verbose=True, use_raw=False, min_n=0)