Update pre-commit

.pre-commit-config.yaml

@@ -1,43 +1,43 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.2.0
+    rev: v4.1.0
     hooks:
       - id: check-merge-conflict
       - id: debug-statements
       - id: mixed-line-ending
       - id: check-case-conflict
       - id: check-yaml
   - repo: https://github.com/benjeffery/pre-commit-clang-format
-    rev: '1.0'
+    rev: c21a74d089aaeb86c2c19df371c7e7bf40c07207
     hooks:
     - id: clang-format
       exclude: avl
       verbose: true
   - repo: https://github.com/asottile/reorder_python_imports
-    rev: v2.3.5
+    rev: v3.0.1
     hooks:
       - id: reorder-python-imports
         args: [ --unclassifiable-application-module=_tsinfer ]
   - repo: https://github.com/asottile/pyupgrade
-    rev: v2.7.2
+    rev: v2.31.1
     hooks:
       - id: pyupgrade
-        args: [ --py3-plus, --py36-plus ]
+        args: [ --py3-plus, --py37-plus ]
   - repo: https://github.com/psf/black
-    rev: 20.8b1
+    rev: 22.3.0
     hooks:
       - id: black
         language_version: python3
   - repo: https://github.com/asottile/blacken-docs
-    rev: v1.8.0
+    rev: v1.12.1
     hooks:
       - id: blacken-docs
         args: [--skip-errors]
-        additional_dependencies: [black==20.8b1]
+        additional_dependencies: [black==22.3.0]
         language_version: python3
   - repo: https://gitlab.com/pycqa/flake8
-    rev: 3.8.3
+    rev: 3.9.2
     hooks:
       - id: flake8
         args: [--config=.flake8]
-        additional_dependencies: ["flake8-bugbear==20.1.4", "flake8-builtins==1.5.2"]
+        additional_dependencies: ["flake8-bugbear==22.3.23", "flake8-builtins==1.5.3"]

dev.py

@@ -67,13 +67,13 @@ def tsinfer_dev(
 
     np.random.seed(seed)
     random.seed(seed)
-    L_megabases = int(L * 10 ** 6)
+    L_megabases = int(L * 10**6)
 
     # daiquiri.setup(level=log_level)
 
     source_ts = msprime.simulate(
         n,
-        Ne=10 ** 4,
+        Ne=10**4,
         length=L_megabases,
         recombination_rate=recombination_rate,
         mutation_rate=1e-8,
@@ -211,7 +211,7 @@ def dump_provenance(ts):
 
 
 def build_profile_inputs(n, num_megabases):
-    L = num_megabases * 10 ** 6
+    L = num_megabases * 10**6
     input_file = "tmp__NOBACKUP__/profile-n={}-m={}.input.trees".format(
         n, num_megabases
     )
@@ -221,7 +221,7 @@ def build_profile_inputs(n, num_megabases):
         ts = msprime.simulate(
             n,
             length=L,
-            Ne=10 ** 4,
+            Ne=10**4,
             recombination_rate=1e-8,
             mutation_rate=1e-8,
             random_seed=10,
@@ -281,10 +281,10 @@ def tutorial_samples():
 
     ts = msprime.simulate(
         sample_size=10000,
-        Ne=10 ** 4,
+        Ne=10**4,
         recombination_rate=1e-8,
         mutation_rate=1e-8,
-        length=10 * 10 ** 6,
+        length=10 * 10**6,
         random_seed=42,
     )
     ts.dump("tmp__NOBACKUP__/simulation-source.trees")

docs/simulation-example.py

@@ -10,10 +10,10 @@
 if True:
     ts = msprime.simulate(
         sample_size=10000,
-        Ne=10 ** 4,
+        Ne=10**4,
         recombination_rate=1e-8,
         mutation_rate=1e-8,
-        length=10 * 10 ** 6,
+        length=10 * 10**6,
         random_seed=42,
     )
     ts.dump("simulation-source.trees")

docs/tutorial.rst

@@ -130,10 +130,10 @@ data under the coalescent with recombination, using `msprime
 
     ts = msprime.simulate(
         sample_size=10000,
-        Ne=10 ** 4,
+        Ne=10**4,
         recombination_rate=1e-8,
         mutation_rate=1e-8,
-        length=10 * 10 ** 6,
+        length=10 * 10**6,
         random_seed=42,
     )
     ts.dump("simulation-source.trees")

evaluation.py

@@ -237,7 +237,7 @@ def edges_performance_worker(args):
 
 def run_edges_performance(args):
     num_lengths = 10
-    MB = 10 ** 6
+    MB = 10**6
 
     work = []
     rng = random.Random()
@@ -251,7 +251,7 @@ def run_edges_performance(args):
                 "mutation_rate": args.mutation_rate,
                 "Ne": args.Ne,
                 "model": "smc_prime",
-                "random_seed": rng.randint(1, 2 ** 30),
+                "random_seed": rng.randint(1, 2**30),
             }
             work.append((sim_args, args.compute_tree_metrics, args.engine))
 
@@ -423,7 +423,7 @@ def unrank(samples, n):
 
 def edge_plot(ts, filename):
     n = ts.num_samples
-    pallete = sns.color_palette("husl", 2 ** n - 1)
+    pallete = sns.color_palette("husl", 2**n - 1)
     lines = []
     colours = []
     for tree in ts.trees():
@@ -445,7 +445,7 @@ def edge_plot(ts, filename):
 
 
 def run_hotspot_analysis(args):
-    MB = 10 ** 6
+    MB = 10**6
     L = args.length * MB
 
     rng = random.Random()
@@ -467,7 +467,7 @@ def run_hotspot_analysis(args):
         "recombination_map": recomb_map,
         "mutation_rate": args.mutation_rate,
         "Ne": args.Ne,
-        "random_seed": rng.randint(1, 2 ** 30),
+        "random_seed": rng.randint(1, 2**30),
     }
     ts = msprime.simulate(**sim_args)
     print("simulated ", ts.num_trees, "trees and", ts.num_sites, "sites")
@@ -562,7 +562,7 @@ def ancestor_properties_worker(args):
 
 def run_ancestor_properties(args):
     num_lengths = 10
-    MB = 10 ** 6
+    MB = 10**6
 
     work = []
     rng = random.Random()
@@ -577,7 +577,7 @@ def run_ancestor_properties(args):
                 "mutation_rate": args.mutation_rate,
                 "Ne": args.Ne,
                 "model": "smc_prime",
-                "random_seed": rng.randint(1, 2 ** 30),
+                "random_seed": rng.randint(1, 2**30),
             }
             work.append((sim_args, not args.skip_exact))
 
@@ -702,7 +702,7 @@ def imputation_accuracy_worker(args):
 
 
 def run_imputation_accuracy(args):
-    MB = 10 ** 6
+    MB = 10**6
 
     work = []
     rng = random.Random()
@@ -716,7 +716,7 @@ def run_imputation_accuracy(args):
                 "recombination_rate": args.recombination_rate,
                 "mutation_rate": args.mutation_rate,
                 "Ne": args.Ne,
-                "random_seed": rng.randint(1, 2 ** 30),
+                "random_seed": rng.randint(1, 2**30),
             }
             work.append((sim_args, missing_proportion))
             # imputation_accuracy_worker((sim_args, missing_proportion))
@@ -802,7 +802,7 @@ def sim_true_and_inferred_ancestors(args):
     Run a simulation under args and return the samples, plus the true and the inferred
     ancestors
     """
-    MB = 10 ** 6
+    MB = 10**6
     rng = random.Random(args.random_seed)
     np.random.seed(args.random_seed)
     sim_args = {
@@ -812,7 +812,7 @@ def sim_true_and_inferred_ancestors(args):
         "mutation_rate": args.mutation_rate,
         "Ne": args.Ne,
         "model": "smc_prime",
-        "random_seed": rng.randint(1, 2 ** 30),
+        "random_seed": rng.randint(1, 2**30),
     }
     ts = msprime.simulate(**sim_args)
 
@@ -1342,7 +1342,7 @@ def run_ancestor_quality(args):
                 print(" " * (olap_start_exact - offset1), end="")
                 print(" " * (olap_start_estim - offset2), end="")
             elif args.print_bad_ancestors == "inferred":
-                print("{:<5}".format(int(freq[focal_pos])), end="")
+                print(f"{int(freq[focal_pos]):<5}", end="")
             k = 0
             mask = estim_sites_mask[olap_start_estim:olap_end_estim]
             for j, (bit, curr_pos) in enumerate(
@@ -1526,7 +1526,7 @@ def run_ancestor_quality(args):
             color="k",
             markeredgewidth=0.5,
             markerfacecolor="w",
-            markersize=1 ** 0.5,
+            markersize=1**0.5,
         ),
         mp.lines.Line2D(
             [],
@@ -1537,7 +1537,7 @@ def run_ancestor_quality(args):
             color="k",
             markeredgewidth=0.5,
             markerfacecolor="w",
-            markersize=10 ** 0.5,
+            markersize=10**0.5,
         ),
         mp.lines.Line2D(
             [],
@@ -1548,7 +1548,7 @@ def run_ancestor_quality(args):
             color="k",
             markeredgewidth=0.5,
             markerfacecolor="w",
-            markersize=100 ** 0.5,
+            markersize=100**0.5,
         ),
     ]
     name = "quality-by-freq-with-bias"
@@ -1704,7 +1704,7 @@ def get_node_degree_by_depth(ts):
 
 
 def run_node_degree(args):
-    MB = 10 ** 6
+    MB = 10**6
     rng = random.Random()
     if args.random_seed is not None:
         rng.seed(args.random_seed)
@@ -1715,7 +1715,7 @@ def run_node_degree(args):
         "mutation_rate": args.mutation_rate,
         "Ne": args.Ne,
         "model": "smc_prime",
-        "random_seed": rng.randint(1, 2 ** 30),
+        "random_seed": rng.randint(1, 2**30),
     }
     smc_ts = msprime.simulate(**sim_args)
 
@@ -1804,11 +1804,11 @@ def run_perfect_inference(args):
     rng = random.Random()
     rng.seed(args.random_seed)
     for _ in range(args.num_replicates):
-        seed = rng.randint(1, 2 ** 30)
+        seed = rng.randint(1, 2**30)
         base_ts = msprime.simulate(
             args.sample_size,
             Ne=args.Ne,
-            length=args.length * 10 ** 6,
+            length=args.length * 10**6,
             recombination_rate=1e-8,
             random_seed=seed,
             model=model,
@@ -1867,7 +1867,7 @@ def add_standard_arguments(
 ):
     parser.add_argument("--destination-dir", "-d", default="")
     parser.add_argument("--sample-size", "-n", type=int, default=sample_size)
-    parser.add_argument("--Ne", "-N", type=int, default=10 ** 4)
+    parser.add_argument("--Ne", "-N", type=int, default=10**4)
     parser.add_argument(
         "--length", "-l", type=float, default=length, help="Sequence length in MB"
     )

tests/test_formats.py

@@ -238,7 +238,7 @@ def test_too_small_max_file_size_init(self):
 
     def test_too_small_max_file_size_add(self):
         with tempfile.TemporaryDirectory(prefix="tsinf_format_test") as tempdir:
-            base_size = 2 ** 16  # Big enough to allow the initial file to be created
+            base_size = 2**16  # Big enough to allow the initial file to be created
             # Fail during adding a large amount of data
             with pytest.raises(lmdb.MapFullError):
                 filename = os.path.join(tempdir, "samples.tmp")
@@ -257,8 +257,8 @@ def test_acceptable_max_file_size(self):
         with tempfile.TemporaryDirectory(prefix="tsinf_format_test") as tempdir:
             # set a reasonably large number of sites and samples, and check we
             # don't bomb out
-            n_samples = 2 ** 10
-            n_sites = 2 ** 12
+            n_samples = 2**10
+            n_sites = 2**12
             np.random.seed(123)
             filename = os.path.join(tempdir, "samples.tmp")
             with formats.SampleData(
@@ -331,7 +331,7 @@ def test_from_tree_sequence_bad_times(self):
         tables = ts.dump_tables()
         # Associate nodes at different times with a single individual
         nodes_time = tables.nodes.time
-        min_time = min([n.time for n in ts.nodes() if not n.is_sample()])
+        min_time = min(n.time for n in ts.nodes() if not n.is_sample())
         nodes_time[ts.samples()] = np.linspace(0, min_time, n_individuals * ploidy)
         tables.nodes.time = nodes_time
         # Zap out the mutation times to avoid conflicts.
@@ -2324,7 +2324,9 @@ def test_ancestors_truncated_length(self):
         assert np.array_equal(
             trunc_lengths[time < upper_limit], original_lengths[time < upper_limit]
         )
-        for orig_anc, trunc_anc in zip(ancestors.ancestors(), trunc_anc.ancestors()):
+        for orig_anc, trunc_anc in zip(  # noqa: B020
+            ancestors.ancestors(), trunc_anc.ancestors()
+        ):
             assert orig_anc.time == trunc_anc.time
             assert np.array_equal(orig_anc.focal_sites, trunc_anc.focal_sites)
             if orig_anc.time >= upper_limit:
@@ -2348,7 +2350,9 @@ def test_truncate_extreme_interval(self):
         ancestors = tsinfer.generate_ancestors(sample_data)
         time = ancestors.ancestors_time[:]
         trunc_anc = ancestors.truncate_ancestors(np.min(time), np.max(time), 1)
-        for orig_anc, trunc_anc in zip(ancestors.ancestors(), trunc_anc.ancestors()):
+        for orig_anc, trunc_anc in zip(  # noqa: B020
+            ancestors.ancestors(), trunc_anc.ancestors()
+        ):
             assert orig_anc.start == trunc_anc.start
             assert orig_anc.end == trunc_anc.end
             assert orig_anc.time == trunc_anc.time
@@ -2359,7 +2363,9 @@ def test_truncate_extreme_interval(self):
         ancestors = tsinfer.generate_ancestors(sample_data)
         time = ancestors.ancestors_time[:]
         trunc_anc = ancestors.truncate_ancestors(0, 1, 1)
-        for orig_anc, trunc_anc in zip(ancestors.ancestors(), trunc_anc.ancestors()):
+        for orig_anc, trunc_anc in zip(  # noqa: B020
+            ancestors.ancestors(), trunc_anc.ancestors()
+        ):
             assert orig_anc.start == trunc_anc.start
             assert orig_anc.end == trunc_anc.end
             assert orig_anc.time == trunc_anc.time
@@ -2374,7 +2380,9 @@ def test_one_haplotype_truncated(self):
         oldest_site = np.max(sites_time)
         midpoint = np.median(sites_time)
         trunc_anc = ancestors.truncate_ancestors(midpoint, oldest_site, 1)
-        for orig_anc, trunc_anc in zip(ancestors.ancestors(), trunc_anc.ancestors()):
+        for orig_anc, trunc_anc in zip(  # noqa: B020
+            ancestors.ancestors(), trunc_anc.ancestors()
+        ):
             assert orig_anc.time == trunc_anc.time
             assert np.array_equal(orig_anc.focal_sites, trunc_anc.focal_sites)