Fix some typos and lints (#6300)

* Use `a not in b` instead of `not a in b`
* Remove unnecessary imports
* Fix a warning raising
* Remove unnecessary f string
* Add missing traceback import
* Fix typo
* Use new-style typing annotations, not comments

Author: Armavica

docs/source/conf.py

@@ -17,7 +17,6 @@
 # serve to show the default.
 
 import os
-import sys
 from pathlib import Path
 
 import pymc  # isort:skip

pymc/backends/arviz.py

@@ -26,14 +26,11 @@
 import pymc
 
 from pymc.aesaraf import extract_obs_data
-from pymc.model import modelcontext
+from pymc.model import Model, modelcontext
 from pymc.util import get_default_varnames
 
 if TYPE_CHECKING:
-    from typing import Set  # pylint: disable=ungrouped-imports
-
     from pymc.backends.base import MultiTrace  # pylint: disable=invalid-name
-    from pymc.model import Model
 
 ___all__ = [""]
 
@@ -145,12 +142,10 @@ def insert(self, k: str, v, idx: int):
 class InferenceDataConverter:  # pylint: disable=too-many-instance-attributes
     """Encapsulate InferenceData specific logic."""
 
-    model = None  # type: Optional[Model]
-    nchains = None  # type: int
-    ndraws = None  # type: int
-    posterior_predictive = None  # Type: Optional[Mapping[str, np.ndarray]]
-    predictions = None  # Type: Optional[Mapping[str, np.ndarray]]
-    prior = None  # Type: Optional[Mapping[str, np.ndarray]]
+    model: Optional[Model] = None
+    posterior_predictive: Optional[Mapping[str, np.ndarray]] = None
+    predictions: Optional[Mapping[str, np.ndarray]] = None
+    prior: Optional[Mapping[str, np.ndarray]] = None
 
     def __init__(
         self,

pymc/backends/ndarray.py

@@ -85,7 +85,7 @@ def setup(self, draws, chain, sampler_vars=None) -> None:
         if self._stats is None:
             self._stats = []
             for sampler in sampler_vars:
-                data = dict()  # type: Dict[str, np.ndarray]
+                data: Dict[str, np.ndarray] = dict()
                 self._stats.append(data)
                 for varname, dtype in sampler.items():
                     data[varname] = np.zeros(draws, dtype=dtype)

pymc/data.py

@@ -301,7 +301,7 @@ class Minibatch(TensorVariable):
         >>> assert x.eval().shape == (2, 20, 20, 40, 10)
     """
 
-    RNG = collections.defaultdict(list)  # type: Dict[str, List[Any]]
+    RNG: Dict[str, List[Any]] = collections.defaultdict(list)
 
     @aesara.config.change_flags(compute_test_value="raise")
     def __init__(
@@ -708,7 +708,7 @@ def Data(
             xshape = x.shape
         # Register new dimension lengths
         for d, dname in enumerate(dims):
-            if not dname in model.dim_lengths:
+            if dname not in model.dim_lengths:
                 model.add_coord(
                     name=dname,
                     # Note: Coordinate values can't be taken from

pymc/distributions/distribution.py

@@ -63,9 +63,9 @@
 
 DIST_PARAMETER_TYPES: TypeAlias = Union[np.ndarray, int, float, TensorVariable]
 
-vectorized_ppc = contextvars.ContextVar(
+vectorized_ppc: contextvars.ContextVar[Optional[Callable]] = contextvars.ContextVar(
     "vectorized_ppc", default=None
-)  # type: contextvars.ContextVar[Optional[Callable]]
+)
 
 PLATFORM = sys.platform
 

pymc/gp/util.py

@@ -136,7 +136,7 @@ def kmeans_inducing_points(n_inducing, X, **kmeans_kwargs):
     Xw = X / scaling
 
     if "k_or_guess" in kmeans_kwargs:
-        warn.UserWarning("Use `n_inducing` to set the `k_or_guess` parameter instead.")
+        warnings.warn("Use `n_inducing` to set the `k_or_guess` parameter instead.")
 
     Xu, distortion = kmeans(Xw, k_or_guess=n_inducing, **kmeans_kwargs)
     return Xu * scaling

pymc/model.py

@@ -188,7 +188,7 @@ def get_context(cls, error_if_none=True) -> Optional[T]:
         on the stack, or ``None``. If ``error_if_none`` is True (default),
         raise a ``TypeError`` instead of returning ``None``."""
         try:
-            candidate = cls.get_contexts()[-1]  # type: Optional[T]
+            candidate: Optional[T] = cls.get_contexts()[-1]
         except IndexError as e:
             # Calling code expects to get a TypeError if the entity
             # is unfound, and there's too much to fix.
@@ -1093,7 +1093,7 @@ def set_dim(self, name: str, new_length: int, coord_values: Optional[Sequence] =
             len_cvals = len(coord_values)
             if len_cvals != new_length:
                 raise ShapeError(
-                    f"Length of new coordinate values does not match the new dimension length.",
+                    "Length of new coordinate values does not match the new dimension length.",
                     actual=len_cvals,
                     expected=new_length,
                 )
@@ -1292,7 +1292,7 @@ def register_rv(
         # the length of the corresponding RV dimension.
         if dims is not None:
             for d, dname in enumerate(dims):
-                if not dname in self.dim_lengths:
+                if dname not in self.dim_lengths:
                     self.add_coord(dname, values=None, length=rv_var.shape[d])
 
         if data is None:

pymc/model_graph.py

@@ -355,7 +355,7 @@ def model_to_networkx(
 
         model_to_networkx(schools)
     """
-    if not "plain" in formatting:
+    if "plain" not in formatting:
 
         raise ValueError(f"Unsupported formatting for graph nodes: '{formatting}'. See docstring.")
 
@@ -419,7 +419,7 @@ def model_to_graphviz(
 
         model_to_graphviz(schools)
     """
-    if not "plain" in formatting:
+    if "plain" not in formatting:
         raise ValueError(f"Unsupported formatting for graph nodes: '{formatting}'. See docstring.")
     if formatting != "plain":
         warnings.warn(

pymc/tests/distributions/test_discrete.py

@@ -69,7 +69,7 @@ def categorical_logpdf(value, p):
     if value >= 0 and value <= len(p):
         return floatX(np.log(np.moveaxis(p, -1, 0)[value]))
     else:
-        return -inf
+        return -np.inf
 
 
 def invlogit(x, eps=sys.float_info.epsilon):

pymc/tests/test_model.py

@@ -13,6 +13,7 @@
 #   limitations under the License.
 import pickle
 import threading
+import traceback
 import unittest
 import warnings
 
@@ -406,7 +407,7 @@ def test_multiple_observed_rv():
     assert not model["x"] == model["mu"]
     assert model["x"] == model["x"]
     assert model["x"] in model.observed_RVs
-    assert not model["x"] in model.value_vars
+    assert model["x"] not in model.value_vars
 
 
 def test_tempered_logp_dlogp():

pymc/tests/tuning/test_starting.py

@@ -42,7 +42,7 @@ def test_mle_jacobian(bounded):
 def test_tune_not_inplace():
     orig_scaling = np.array([0.001, 0.1])
     returned_scaling = tune(orig_scaling, acc_rate=0.6)
-    assert not returned_scaling is orig_scaling
+    assert returned_scaling is not orig_scaling
     assert np.all(orig_scaling == np.array([0.001, 0.1]))
 
 

pymc/variational/inference.py

@@ -258,7 +258,7 @@ def _infmean(input_array):
                 )
         else:
             if n == 0:
-                logger.info(f"Initialization only")
+                logger.info("Initialization only")
             elif n < 10:
                 logger.info(f"Finished [100%]: Loss = {scores[-1]:,.5g}")
             else:

pymc/variational/opvi.py

@@ -1482,7 +1482,7 @@ def sample(
 
         if random_seed is not None:
             (random_seed,) = _get_seeds_per_chain(random_seed, 1)
-        samples = self.sample_dict_fn(draws, random_seed=random_seed)  # type: dict
+        samples: dict = self.sample_dict_fn(draws, random_seed=random_seed)
         points = ({name: records[i] for name, records in samples.items()} for i in range(draws))
 
         trace = NDArray(

scripts/run_mypy.py

@@ -144,7 +144,7 @@ def check_no_unexpected_results(mypy_lines: Iterator[str]):
     all_files = {
         str(fp).replace(str(DP_ROOT), "").strip(os.sep).replace(os.sep, "/")
         for fp in DP_ROOT.glob("pymc/**/*.py")
-        if not "tests" in str(fp)
+        if "tests" not in str(fp)
     }
     failing = set(df.reset_index().file.str.replace(os.sep, "/", regex=False))
     if not failing.issubset(all_files):

setup.py

@@ -12,7 +12,6 @@
 #   See the License for the specific language governing permissions and
 #   limitations under the License.
 
-import re
 
 from codecs import open
 from os.path import dirname, join, realpath

setupegg.py

@@ -17,7 +17,6 @@
 A setup.py script to use setuptools, which gives egg goodness, etc.
 """
 
-from setuptools import setup
 
 with open("setup.py") as s:
     exec(s.read())