STY: ruff applied to paper scripts and notebooks

paper/nbks/benchmark_ctree.py

@@ -1,12 +1,14 @@
+import itertools
 from pathlib import Path
+
 import cogent3
-import itertools
-from diverse_seq import cli as dvs_cli
-from diverse_seq import util as dvs_util
-from click.testing import CliRunner
 from benchmark import TempWorkingDir, TimeIt
+from click.testing import CliRunner
 from rich import progress as rich_progress
 
+from diverse_seq import cli as dvs_cli
+from diverse_seq import util as dvs_util
+
 RUNNER = CliRunner()
 
 
@@ -29,15 +31,18 @@ def main():
             repeats = progress.add_task("Doing reps", total=len(reps))
             for _ in reps:
                 combo = progress.add_task(
-                    "Doing k x num_seq", total=len(num_seqs) * len(kmer_sizes)
+                    "Doing k x num_seq",
+                    total=len(num_seqs) * len(kmer_sizes),
                 )
                 for k, num_seq in itertools.product(kmer_sizes, num_seqs):
                     with TempWorkingDir() as temp_dir:
                         out_tree_file = temp_dir / f"{in_file.name}.tre"
                         args = f"-s {in_file} -o {out_tree_file} -k {k} --distance mash --sketch-size 3000 -hp --limit {num_seq}".split()
                         with TimeIt() as timer:
                             r = RUNNER.invoke(
-                                dvs_cli.ctree, args, catch_exceptions=False
+                                dvs_cli.ctree,
+                                args,
+                                catch_exceptions=False,
                             )
                             assert r.exit_code == 0, r.output
                         results["time(s)"].append(timer.get_elapsed_time())

paper/nbks/ctree.ipynb

@@ -6,9 +6,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import project_path\n",
     "import cogent3\n",
     "import plotly.express as px\n",
+    "import project_path\n",
     "\n",
     "color_discrete_sequence = px.colors.sequential.Rainbow\n",
     "\n",
@@ -22,15 +22,16 @@
     "\n",
     "    inpath = project_path.PAPER_DIR / \"nbks\" / \"ctree\" / \"out\" / fname\n",
     "    lines = [l.split(\"\\t\") for l in inpath.read_text().splitlines()]\n",
-    "    data = dict(zip(header, zip(*lines)))\n",
+    "    data = dict(zip(header, zip(*lines, strict=False), strict=False))\n",
     "    for name, vals in data.items():\n",
     "        data[name] = cast_str_to_array(vals)\n",
     "    return cogent3.make_table(header=header, data=data)\n",
     "\n",
     "\n",
     "def get_plot_for(*, x_axis, limit_to, colour, legend_title, log_x):\n",
     "    table = load_table(\n",
-    "        \"results_with_ls.tsv\", [\"k\", \"ss\", \"cpus\", \"time\", \"lnL\", \"tree\"]\n",
+    "        \"results_with_ls.tsv\",\n",
+    "        [\"k\", \"ss\", \"cpus\", \"time\", \"lnL\", \"tree\"],\n",
     "    )\n",
     "    table = table.get_columns([c for c in table.header if c != \"tree\"])\n",
     "    table = table.filtered(lambda x: int(x) in limit_to, columns=colour)\n",

paper/nbks/ctree/experiment.py

@@ -4,6 +4,7 @@
 from pathlib import Path
 
 from cogent3 import load_aligned_seqs, make_aligned_seqs
+
 from diverse_seq.cluster import dvs_par_ctree
 
 MAMMALS_PATH = Path("data/mammals-aligned")
@@ -30,7 +31,8 @@
 
 def load_alignment(directory: Path):
     fasta_files = filter(
-        lambda file_name: file_name.endswith(".fa"), os.listdir(directory)
+        lambda file_name: file_name.endswith(".fa"),
+        os.listdir(directory),
     )
 
     seqs = {}

paper/nbks/ctree/iq_experiment.py

@@ -1,9 +1,9 @@
 import os
-from pathlib import Path
 import time
-from piqtree2 import build_tree
+from pathlib import Path
 
 from cogent3 import load_aligned_seqs, make_aligned_seqs
+from piqtree2 import build_tree
 
 MAMMALS_PATH = Path("data/mammals-aligned")
 
@@ -13,7 +13,8 @@
 
 def load_alignment(directory: Path):
     fasta_files = filter(
-        lambda file_name: file_name.endswith(".fa"), os.listdir(directory)
+        lambda file_name: file_name.endswith(".fa"),
+        os.listdir(directory),
     )
 
     seqs = {}

paper/nbks/ctree/likelihoods.py

@@ -1,8 +1,8 @@
 import os
 from pathlib import Path
-from piqtree2 import fit_tree
 
 from cogent3 import load_aligned_seqs, make_aligned_seqs, make_tree
+from piqtree2 import fit_tree
 
 MAMMALS_PATH = Path("data/mammals-aligned")
 
@@ -15,7 +15,8 @@
 
 def load_alignment(directory: Path):
     fasta_files = filter(
-        lambda file_name: file_name.endswith(".fa"), os.listdir(directory)
+        lambda file_name: file_name.endswith(".fa"),
+        os.listdir(directory),
     )
 
     seqs = {}
@@ -53,7 +54,7 @@ def do_likelihoods():
             likelihood = tree.params["lnL"]
             with OUT_FILE.open("a") as f:
                 f.write(
-                    "\t".join([k, ss, cpus, time, str(likelihood), str(tree)]) + "\n"
+                    "\t".join([k, ss, cpus, time, str(likelihood), str(tree)]) + "\n",
                 )
     with IQ_FILE.open() as f:
         for line in f:

paper/nbks/get_data_sets.py

@@ -1,16 +1,17 @@
+import pathlib
 import re
 import sys
-import pathlib
+import zipfile
+
 import requests
 from rich import progress as rich_progress
-import zipfile
 
 DATA_DIR = pathlib.Path(__file__).parent.parent / "data"
 
 if not DATA_DIR.exists():
     if DATA_DIR.parent.name != "paper":
         print(
-            f"cannot find the data directory {DATA_DIR}, this file belongs in the `paper/nbks` directory"
+            f"cannot find the data directory {DATA_DIR}, this file belongs in the `paper/nbks` directory",
         )
         sys.exit(1)
     else:

paper/nbks/jsd_v_dist.ipynb

@@ -202,7 +202,10 @@
     "\n",
     "fig.update_yaxes(title_text=\"<b>Significant %</b>\", row=1, col=1, title_font=titlefont)\n",
     "fig.update_yaxes(\n",
-    "    title_text=\"<b>Mean Number Selected</b>\", row=2, col=1, title_font=titlefont\n",
+    "    title_text=\"<b>Mean Number Selected</b>\",\n",
+    "    row=2,\n",
+    "    col=1,\n",
+    "    title_font=titlefont,\n",
     ")\n",
     "fig.update_xaxes(title_text=\"<b><i>k</i></b>\", row=2, col=1, title_font=titlefont)\n",
     "fig.update_layout(legend=legend, width=1600, height=1200)\n",

paper/nbks/jsd_v_dist.py

@@ -10,6 +10,7 @@
 from numpy.random import choice
 from rich.progress import track
 from scipy import special
+
 from diverse_seq import util as dvs_utils
 from diverse_seq.records import dvs_max, dvs_nmost
 

paper/nbks/plugin_demo.ipynb

@@ -96,7 +96,9 @@
     "from cogent3 import get_app, open_data_store\n",
     "\n",
     "in_data = open_data_store(\n",
-    "    project_path.DATA_DIR / \"mammals-aligned.zip\", suffix=\"fa\", mode=\"r\"\n",
+    "    project_path.DATA_DIR / \"mammals-aligned.zip\",\n",
+    "    suffix=\"fa\",\n",
+    "    mode=\"r\",\n",
     ")\n",
     "loader = get_app(\"load_aligned\", moltype=\"dna\")\n",
     "aln = loader(in_data[64])"

paper/nbks/project_path.py

@@ -1,5 +1,6 @@
 import pathlib
 import time
+
 from plotly.io import write_image
 
 PAPER_DIR = pathlib.Path(__file__).parent.parent

paper/nbks/synthetic_known.py

@@ -1,12 +1,13 @@
 from itertools import product
 
+import project_path
 from cogent3 import make_table, make_unaligned_seqs
 from cogent3.app import typing as c3_types
 from cogent3.app.composable import NotCompleted, define_app
 from numpy import array
 from numpy.random import choice, shuffle
 from rich.progress import track
-import project_path
+
 from diverse_seq import util as dvs_utils
 from diverse_seq.record import KmerSeq, SeqArray, seqarray_to_kmerseq
 from diverse_seq.records import max_divergent