Enforce mypy compliance in CI (#3197)

* Enforce mypy compliance in CI

* Fix mypy errors

* black

* docstrings

* Update doc/whats-new.rst

Co-Authored-By: Maximilian Roos <5635139+max-sixty@users.noreply.github.com>

* typo

* Pre-commit hook

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,5 +2,5 @@
 
  - [ ] Closes #xxxx
  - [ ] Tests added
- - [ ] Passes `black .` & `flake8`
+ - [ ] Passes `black . && mypy . && flake8`
  - [ ] Fully documented, including `whats-new.rst` for all changes and `api.rst` for new API

.pre-commit-config.yaml

@@ -10,6 +10,10 @@ repos:
     rev: v2.2.3
     hooks:
       - id: flake8
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.720
+    hooks:
+    -   id: mypy
   # run these occasionally, ref discussion https://github.com/pydata/xarray/pull/3194
   # - repo: https://github.com/asottile/pyupgrade
   #   rev: v1.22.1

azure-pipelines.yml

@@ -75,7 +75,7 @@ jobs:
   - template: ci/azure/install.yml
   - bash: |
       source activate xarray-tests
-      mypy . || exit 0
+      mypy .
     displayName: mypy type checks
 
 - job: Docs

doc/whats-new.rst

@@ -29,8 +29,8 @@ New functions/methods
   <http://github.com/DavidMertz>`_.
 
 - The xarray package is now discoverably by mypy (although typing hints
-  coverage is not complete yet). mypy users can now remove from their setup.cfg
-  the lines::
+  coverage is not complete yet). mypy type checking is now enforced by CI.
+  Libraries that depend on xarray and use mypy can now remove from their setup.cfg the lines::
 
     [mypy-xarray]
     ignore_missing_imports = True

xarray/core/common.py

@@ -46,12 +46,7 @@ def wrapped_func(self, dim=None, axis=None, skipna=None, **kwargs):
 
         else:
 
-            def wrapped_func(
-                self,
-                dim=None,
-                axis=None,  # type: ignore
-                **kwargs
-            ):
+            def wrapped_func(self, dim=None, axis=None, **kwargs):  # type: ignore
                 return self.reduce(func, dim, axis, allow_lazy=True, **kwargs)
 
         return wrapped_func

xarray/core/dataset.py

@@ -408,17 +408,9 @@ def __init__(
         self,
         # could make a VariableArgs to use more generally, and refine these
         # categories
-        data_vars: Mapping[
-            Hashable,
-            Union[
-                "DataArray",
-                Variable,
-                Tuple[Hashable, Any],
-                Tuple[Sequence[Hashable], Any],
-            ],
-        ] = None,
+        data_vars: Mapping[Hashable, Any] = None,
         coords: Mapping[Hashable, Any] = None,
-        attrs: Mapping = None,
+        attrs: Mapping[Hashable, Any] = None,
         compat=None,
     ):
         """To load data from a file or file-like object, use the `open_dataset`
@@ -439,6 +431,8 @@ def __init__(
             - mapping {var name: Variable}
             - mapping {var name: (dimension name, array-like)}
             - mapping {var name: (tuple of dimension names, array-like)}
+            - mapping {dimension name: array-like}
+              (it will be automatically moved to coords, see below)
 
             Each dimension must have the same length in all variables in which
             it appears.
@@ -460,6 +454,7 @@ def __init__(
             - mapping {coord name: (dimension name, array-like)}
             - mapping {coord name: (tuple of dimension names, array-like)}
             - mapping {dimension name: array-like}
+              (the dimension name is implicitly set to be the same as the coord name)
 
             The last notation implies that the coord name is the same as the
             dimension name.
@@ -2052,17 +2047,13 @@ def relevant_keys(mapping):
             ]
 
         coords = relevant_keys(self.coords)
-        indexers = [
-            (k, np.asarray(v))  # type: ignore
-            for k, v in indexers.items()
-        ]
-        indexers_dict = dict(indexers)
+        indexers = {k: np.asarray(v) for k, v in indexers.items()}
         non_indexed_dims = set(self.dims) - indexer_dims
         non_indexed_coords = set(self.coords) - set(coords)
 
         # All the indexers should be iterables
         # Check that indexers are valid dims, integers, and 1D
-        for k, v in indexers:
+        for k, v in indexers.items():
             if k not in self.dims:
                 raise ValueError("dimension %s does not exist" % k)
             if v.dtype.kind != "i":  # type: ignore
@@ -2071,7 +2062,7 @@ def relevant_keys(mapping):
                 raise ValueError("Indexers must be 1 dimensional")
 
         # all the indexers should have the same length
-        lengths = {len(v) for k, v in indexers}
+        lengths = {len(v) for k, v in indexers.items()}
         if len(lengths) > 1:
             raise ValueError("All indexers must be the same length")
 
@@ -2109,12 +2100,9 @@ def relevant_keys(mapping):
         variables = OrderedDict()  # type: ignore
 
         for name, var in reordered.variables.items():
-            if name in indexers_dict or any(d in indexer_dims for d in var.dims):
+            if name in indexers or any(d in indexer_dims for d in var.dims):
                 # slice if var is an indexer or depends on an indexed dim
-                slc = [
-                    indexers_dict[k] if k in indexers_dict else slice(None)
-                    for k in var.dims
-                ]
+                slc = [indexers.get(k, slice(None)) for k in var.dims]
 
                 var_dims = [dim_name] + [d for d in var.dims if d in non_indexed_dims]
                 selection = take(var, tuple(slc))

xarray/core/groupby.py

@@ -775,12 +775,8 @@ def wrapped_func(
 
         else:
 
-            def wrapped_func(
-                self,
-                dim=DEFAULT_DIMS,
-                axis=None,  # type: ignore
-                keep_attrs=None,
-                **kwargs
+            def wrapped_func(  # type: ignore
+                self, dim=DEFAULT_DIMS, axis=None, keep_attrs=None, **kwargs
             ):
                 return self.reduce(
                     func, dim, axis, keep_attrs=keep_attrs, allow_lazy=True, **kwargs
@@ -912,11 +908,7 @@ def wrapped_func(self, dim=DEFAULT_DIMS, skipna=None, **kwargs):
 
         else:
 
-            def wrapped_func(
-                self,
-                dim=DEFAULT_DIMS,  # type: ignore
-                **kwargs
-            ):
+            def wrapped_func(self, dim=DEFAULT_DIMS, **kwargs):  # type: ignore
                 return self.reduce(
                     func, dim, numeric_only=numeric_only, allow_lazy=True, **kwargs
                 )