Lint

pyproject.toml

@@ -34,7 +34,7 @@ requires = ["setuptools ~= 63.0", "Cython ~= 0.29.5"]
 build-backend = "setuptools.build_meta"
 
 [tool.ruff]
-ignore = ["E501"]
+ignore = ["E722", "E501"]
 
 # pyproject.toml
 [tool.pytest.ini_options]

test/test_encode.py

@@ -151,12 +151,6 @@ def test_bad_args(self):
         with self.assertRaises(ValueError):
             vamb.encode.VAE(5, dropout=-0.001)
 
-    def test_samples_too_small(self):
-        vae = vamb.encode.VAE(self.rpkm.shape[1])
-        r = self.rpkm.copy()
-        t = self.tnfs.copy()
-        l = self.lens.copy()
-
     def test_loss_falls(self):
         vae = vamb.encode.VAE(self.rpkm.shape[1])
         rpkm_copy = self.rpkm.copy()

test/test_semisupervised_encode.py

@@ -1,6 +1,5 @@
 import unittest
 import numpy as np
-import torch
 import tempfile
 import io
 

vamb/__main__.py

@@ -16,7 +16,6 @@
 from pathlib import Path
 from collections.abc import Sequence
 from collections import defaultdict
-from functools import reduce
 from torch.utils.data import DataLoader
 import pandas as pd
 
@@ -1080,7 +1079,7 @@ def parse_mmseqs_taxonomy(
 
     if list(df_mmseq[0]) != list(contignames):
         raise AssertionError(
-            f"The contig names of taxonomy entries are not the same as in the contigs metadata"
+            "The contig names of taxonomy entries are not the same as in the contigs metadata"
         )
 
     return graph_column
@@ -1180,7 +1179,7 @@ def predict_taxonomy(
             while table_parent[label] != -1:
                 pred_labels.append(table_parent[label])
                 label = table_parent[label]
-            pred_labels = ";".join([nodes_ar[l] for l in pred_labels][::-1])
+            pred_labels = ";".join([nodes_ar[label] for label in pred_labels][::-1])
             threshold_mask = (
                 predicted_vector[i] > predictor_training_options.softmax_threshold
             )

vamb/h_loss.py

@@ -18,7 +18,6 @@
 import torch.nn.functional as F
 from torch.utils.data.dataset import TensorDataset as _TensorDataset
 from torch.utils.data import DataLoader as _DataLoader
-from torch.optim import Adam as _Adam
 from torch import Tensor
 
 import vamb.semisupervised_encode as _semisupervised_encode

vamb/parsecontigs.py

@@ -9,7 +9,7 @@
 import numpy as _np
 import vamb.vambtools as _vambtools
 from collections.abc import Iterable, Sequence
-from typing import IO, Union, TypeVar, Optional, IO
+from typing import IO, Union, TypeVar, Optional
 from pathlib import Path
 import warnings
 

vamb/reclustering.py

@@ -5,7 +5,6 @@
 
 import os
 import subprocess
-import tempfile
 import sys
 import contextlib
 from typing import IO
@@ -16,6 +15,7 @@
 from sklearn.cluster import DBSCAN
 from sklearn.metrics import pairwise_distances
 import gzip
+import lzma
 
 
 def log(string: str, logfile: IO[str], indent: int = 0):
@@ -92,16 +92,12 @@ def op(f, _):
             return f
 
     elif fname.endswith(".gz"):
-        import gzip
-
         op = gzip.open
     elif fname.endswith(".bz2"):
         import bz2
 
         op = bz2.open
     elif fname.endswith(".xz"):
-        import lzma
-
         op = lzma.open
     else:
         op = open