ruff & black

quadram-institute-bioscience · Jul 2, 2024 · 7341946 · 7341946
1 parent ab4dc63
commit 7341946
Show file tree

Hide file tree

Showing 14 changed files with 271 additions and 231 deletions.
diff --git a/Makefile b/Makefile
@@ -9,7 +9,7 @@ lint:
 	flake8
 
 test: all
-	py.test
+	py.test -vvv
 
 install: all
 	pip install .

diff --git a/q2_usearch/__init__.py b/q2_usearch/__init__.py
@@ -13,4 +13,5 @@
 del get_versions
 
 from . import _version
-__version__ = _version.get_versions()['version']
+
+__version__ = _version.get_versions()["version"]
diff --git a/q2_usearch/_chimera.py b/q2_usearch/_chimera.py
@@ -12,71 +12,87 @@
 from q2_types.feature_data import DNAFASTAFormat
 
 from ._utils import run_command, _fasta_with_sizes
+
 # from ._cluster_features import _fasta_with_sizes, run_command
 # from ._format import UchimeStatsFmt
 
 
-_uchime_defaults = {'dn': 1.4,
-                    'mindiffs': 3,
-                    'mindiv': 0.8,
-                    'minh': 0.28,
-                    'xn': 8.0}
-
-
-def uchime_ref(sequences: DNAFASTAFormat,
-               table: biom.Table,
-               reference_sequences: DNAFASTAFormat,
-               dn: float = _uchime_defaults['dn'],
-               mindiffs: int = _uchime_defaults['mindiffs'],
-               mindiv: float = _uchime_defaults['mindiv'],
-               minh: float = _uchime_defaults['minh'],
-               xn: float = _uchime_defaults['xn'],
-               threads: int = 1) \
-               -> (DNAFASTAFormat, DNAFASTAFormat, UchimeStatsFmt):
-    cmd, chimeras, nonchimeras, uchime_stats = \
-        _uchime_ref(sequences, table, reference_sequences, dn, mindiffs,
-                    mindiv, minh, xn, threads)
+_uchime_defaults = {"dn": 1.4, "mindiffs": 3, "mindiv": 0.8, "minh": 0.28, "xn": 8.0}
+
+
+def uchime_ref(
+    sequences: DNAFASTAFormat,
+    table: biom.Table,
+    reference_sequences: DNAFASTAFormat,
+    dn: float = _uchime_defaults["dn"],
+    mindiffs: int = _uchime_defaults["mindiffs"],
+    mindiv: float = _uchime_defaults["mindiv"],
+    minh: float = _uchime_defaults["minh"],
+    xn: float = _uchime_defaults["xn"],
+    threads: int = 1,
+) -> (DNAFASTAFormat, DNAFASTAFormat, UchimeStatsFmt):
+    cmd, chimeras, nonchimeras, uchime_stats = _uchime_ref(
+        sequences, table, reference_sequences, dn, mindiffs, mindiv, minh, xn, threads
+    )
     return chimeras, nonchimeras, uchime_stats
 
 
-def _uchime_ref(sequences, table, reference_sequences, dn, mindiffs,
-                mindiv, minh, xn, threads):
+def _uchime_ref(
+    sequences, table, reference_sequences, dn, mindiffs, mindiv, minh, xn, threads
+):
     # this function only exists to simplify testing
     chimeras = DNAFASTAFormat()
     nonchimeras = DNAFASTAFormat()
     uchime_stats = UchimeStatsFmt()
     with tempfile.NamedTemporaryFile() as fasta_with_sizes:
         _fasta_with_sizes(str(sequences), fasta_with_sizes.name, table)
-        cmd = ['vsearch',
-               '--uchime_ref', fasta_with_sizes.name,
-               '--uchimeout', str(uchime_stats),
-               '--nonchimeras', str(nonchimeras),
-               '--chimeras', str(chimeras),
-               '--dn', str(dn),
-               '--mindiffs', str(mindiffs),
-               '--mindiv', str(mindiv),
-               '--minh', str(minh),
-               '--xn', str(xn),
-               '--db', str(reference_sequences),
-               '--qmask', 'none',  # ensures no lowercase DNA chars
-               '--xsize',
-               '--threads', str(threads),
-               '--fasta_width', '0']
+        cmd = [
+            "vsearch",
+            "--uchime_ref",
+            fasta_with_sizes.name,
+            "--uchimeout",
+            str(uchime_stats),
+            "--nonchimeras",
+            str(nonchimeras),
+            "--chimeras",
+            str(chimeras),
+            "--dn",
+            str(dn),
+            "--mindiffs",
+            str(mindiffs),
+            "--mindiv",
+            str(mindiv),
+            "--minh",
+            str(minh),
+            "--xn",
+            str(xn),
+            "--db",
+            str(reference_sequences),
+            "--qmask",
+            "none",  # ensures no lowercase DNA chars
+            "--xsize",
+            "--threads",
+            str(threads),
+            "--fasta_width",
+            "0",
+        ]
         run_command(cmd)
 
     return cmd, chimeras, nonchimeras, uchime_stats
 
 
-def uchime3_denovo(sequences: DNAFASTAFormat,
-                  table: biom.Table,
-                  dn: float = _uchime_defaults['dn'],
-                  mindiffs: int = _uchime_defaults['mindiffs'],
-                  mindiv: float = _uchime_defaults['mindiv'],
-                  minh: float = _uchime_defaults['minh'],
-                  xn: float = _uchime_defaults['xn']) \
-                  -> (DNAFASTAFormat, DNAFASTAFormat, UchimeStatsFmt):
-    cmd, chimeras, nonchimeras, uchime_stats = \
-        _uchime_denovo(sequences, table, dn, mindiffs, mindiv, minh, xn)
+def uchime3_denovo(
+    sequences: DNAFASTAFormat,
+    table: biom.Table,
+    dn: float = _uchime_defaults["dn"],
+    mindiffs: int = _uchime_defaults["mindiffs"],
+    mindiv: float = _uchime_defaults["mindiv"],
+    minh: float = _uchime_defaults["minh"],
+    xn: float = _uchime_defaults["xn"],
+) -> (DNAFASTAFormat, DNAFASTAFormat, UchimeStatsFmt):
+    cmd, chimeras, nonchimeras, uchime_stats = _uchime_denovo(
+        sequences, table, dn, mindiffs, mindiv, minh, xn
+    )
     return chimeras, nonchimeras, uchime_stats
 
 
@@ -87,19 +103,32 @@ def _uchime3_denovo(sequences, table, dn, mindiffs, mindiv, minh, xn):
     uchime_stats = UchimeStatsFmt()
     with tempfile.NamedTemporaryFile() as fasta_with_sizes:
         _fasta_with_sizes(str(sequences), fasta_with_sizes.name, table)
-        cmd = ['usearch',
-               '-uchime3_denovo', fasta_with_sizes.name,
-               '-uchimeout', str(uchime_stats),
-               '--nonchimeras', str(nonchimeras),
-               '--chimeras', str(chimeras),
-               '--dn', str(dn),
-               '--mindiffs', str(mindiffs),
-               '--mindiv', str(mindiv),
-               '--minh', str(minh),
-               '--xn', str(xn),
-               '--qmask', 'none',  # ensures no lowercase DNA chars
-               '--xsize',
-               '--fasta_width', '0']
+        cmd = [
+            "usearch",
+            "-uchime3_denovo",
+            fasta_with_sizes.name,
+            "-uchimeout",
+            str(uchime_stats),
+            "--nonchimeras",
+            str(nonchimeras),
+            "--chimeras",
+            str(chimeras),
+            "--dn",
+            str(dn),
+            "--mindiffs",
+            str(mindiffs),
+            "--mindiv",
+            str(mindiv),
+            "--minh",
+            str(minh),
+            "--xn",
+            str(xn),
+            "--qmask",
+            "none",  # ensures no lowercase DNA chars
+            "--xsize",
+            "--fasta_width",
+            "0",
+        ]
         run_command(cmd)
 
     return cmd, chimeras, nonchimeras, uchime_stats
diff --git a/q2_usearch/_cluster.py b/q2_usearch/_cluster.py
@@ -7,20 +7,14 @@
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
 
-import os
-import tempfile
-import sqlite3
-
-import biom
-import skbio
-import pandas as pd
-from qiime2 import Metadata
+
 from q2_types.feature_data import DNAFASTAFormat
-from ._utils import run_command, validate_params, USearchError
+from ._utils import run_command, validate_params
 import shlex
 
 from ._format import USEARCHTextFile
 
+
 def cluster_otus(
     sequences: DNAFASTAFormat,
     minsize: int = 2,
@@ -29,21 +23,24 @@ def cluster_otus(
 ) -> (DNAFASTAFormat, USEARCHTextFile):  # type: ignore
     otus_seqs = DNAFASTAFormat()
     uparse_out = USEARCHTextFile()
-    
+
     validate_params([minsize, threads])
-  
+
     _relabel = f"-relabel {relabel}"
     _minsize = f"-minsize {minsize}"
     _cmd = f"usearch -cluster_otus {sequences} -otus {otus_seqs} -uparseout {uparse_out} {_relabel} {_minsize} -threads {threads}".strip()
     cmd = shlex.split(_cmd)
     run_command(cmd)
     return otus_seqs, uparse_out
 
+
 def cluster_fast():
     pass
 
+
 def cluster_smallmem():
     pass
 
+
 def cluster_mt():
-    pass
+    pass