Pin intake to <v2 (#651)

intake · Feb 6, 2024 · 14d069c · 14d069c
1 parent b2c0fa1
commit 14d069c
Show file tree

Hide file tree

Showing 8 changed files with 50 additions and 43 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -15,14 +15,10 @@ repos:
       - id: mixed-line-ending
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.1.9"
+    rev: "v0.2.1"
     hooks:
       - id: ruff
         args: ["--fix"]
-
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.9
-    hooks:
       - id: ruff-format
 
   - repo: https://github.com/pre-commit/mirrors-prettier

diff --git a/ci/environment-docs.yml b/ci/environment-docs.yml
@@ -8,7 +8,7 @@ dependencies:
   - ecgtools >=2022.10.7
   - fsspec>=2023.05
   - gcsfs >=2023.05
-  - intake>=0.7
+  - intake<2.0
   - jupyterlab
   - matplotlib
   - myst-nb

diff --git a/ci/environment.yml b/ci/environment.yml
@@ -9,7 +9,7 @@ dependencies:
   - fsspec>=2022.11.0
   - gcsfs >=2022.11.0
   - h5netcdf>=0.8.1
-  - intake>=0.6.6
+  - intake<2.0
   - ipython
   - matplotlib
   - netcdf4>=1.5.5

diff --git a/intake_esm/core.py b/intake_esm/core.py
@@ -60,7 +60,7 @@ class esm_datastore(Catalog):
     can be accessed with `intake.open_esm_datastore()`:
 
     >>> import intake
-    >>> url = "https://storage.googleapis.com/cmip6/pangeo-cmip6.json"
+    >>> url = 'https://storage.googleapis.com/cmip6/pangeo-cmip6.json'
     >>> cat = intake.open_esm_datastore(url)
     >>> cat.df.head()
     activity_id institution_id source_id experiment_id  ... variable_id grid_label                                             zstore dcpp_init_year
@@ -155,7 +155,7 @@ def keys_info(self) -> pd.DataFrame:
         --------
 
         >>> import intake
-        >>> cat = intake.open_esm_datastore("./tests/sample-catalogs/cesm1-lens-netcdf.json")
+        >>> cat = intake.open_esm_datastore('./tests/sample-catalogs/cesm1-lens-netcdf.json')
         >>> cat.keys_info()
                         component experiment stream
         key
@@ -233,8 +233,8 @@ def __getitem__(self, key: str) -> ESMDataSource:
 
         Examples
         --------
-        >>> cat = intake.open_esm_datastore("mycatalog.json")
-        >>> data_source = cat["AerChemMIP.BCC.BCC-ESM1.piClim-control.AERmon.gn"]
+        >>> cat = intake.open_esm_datastore('mycatalog.json')
+        >>> data_source = cat['AerChemMIP.BCC.BCC-ESM1.piClim-control.AERmon.gn']
         """
         # The canonical unique key is the key of a compatible group of assets
         try:
@@ -354,19 +354,19 @@ def search(
         Examples
         --------
         >>> import intake
-        >>> cat = intake.open_esm_datastore("pangeo-cmip6.json")
+        >>> cat = intake.open_esm_datastore('pangeo-cmip6.json')
         >>> cat.df.head(3)
         activity_id institution_id source_id  ... grid_label                                             zstore dcpp_init_year
         0  AerChemMIP            BCC  BCC-ESM1  ...         gn  gs://cmip6/AerChemMIP/BCC/BCC-ESM1/ssp370/r1i1...            NaN
         1  AerChemMIP            BCC  BCC-ESM1  ...         gn  gs://cmip6/AerChemMIP/BCC/BCC-ESM1/ssp370/r1i1...            NaN
         2  AerChemMIP            BCC  BCC-ESM1  ...         gn  gs://cmip6/AerChemMIP/BCC/BCC-ESM1/ssp370/r1i1...            NaN
 
         >>> sub_cat = cat.search(
-        ...     source_id=["BCC-CSM2-MR", "CNRM-CM6-1", "CNRM-ESM2-1"],
-        ...     experiment_id=["historical", "ssp585"],
-        ...     variable_id="pr",
-        ...     table_id="Amon",
-        ...     grid_label="gn",
+        ...     source_id=['BCC-CSM2-MR', 'CNRM-CM6-1', 'CNRM-ESM2-1'],
+        ...     experiment_id=['historical', 'ssp585'],
+        ...     variable_id='pr',
+        ...     table_id='Amon',
+        ...     grid_label='gn',
         ... )
         >>> sub_cat.df.head(3)
             activity_id institution_id    source_id  ... grid_label                                             zstore dcpp_init_year
@@ -379,7 +379,7 @@ def search(
 
         >>> import re
         >>> # Let's search for variables containing "Frac" in their name
-        >>> pat = re.compile(r"Frac")  # Define a regular expression
+        >>> pat = re.compile(r'Frac')  # Define a regular expression
         >>> cat.search(variable_id=pat)
         >>> cat.df.head().variable_id
         0     residualFrac
@@ -479,14 +479,14 @@ def serialize(
         Examples
         --------
         >>> import intake
-        >>> cat = intake.open_esm_datastore("pangeo-cmip6.json")
+        >>> cat = intake.open_esm_datastore('pangeo-cmip6.json')
         >>> cat_subset = cat.search(
-        ...     source_id="BCC-ESM1",
-        ...     grid_label="gn",
-        ...     table_id="Amon",
-        ...     experiment_id="historical",
+        ...     source_id='BCC-ESM1',
+        ...     grid_label='gn',
+        ...     table_id='Amon',
+        ...     experiment_id='historical',
         ... )
-        >>> cat_subset.serialize(name="cmip6_bcc_esm1", catalog_type="file")
+        >>> cat_subset.serialize(name='cmip6_bcc_esm1', catalog_type='file')
         """
 
         self.esmcat.save(
@@ -505,7 +505,7 @@ def nunique(self) -> pd.Series:
         Examples
         --------
         >>> import intake
-        >>> cat = intake.open_esm_datastore("pangeo-cmip6.json")
+        >>> cat = intake.open_esm_datastore('pangeo-cmip6.json')
         >>> cat.nunique()
         activity_id          10
         institution_id       23
@@ -583,18 +583,18 @@ def to_dataset_dict(
         Examples
         --------
         >>> import intake
-        >>> cat = intake.open_esm_datastore("glade-cmip6.json")
+        >>> cat = intake.open_esm_datastore('glade-cmip6.json')
         >>> sub_cat = cat.search(
-        ...     source_id=["BCC-CSM2-MR", "CNRM-CM6-1", "CNRM-ESM2-1"],
-        ...     experiment_id=["historical", "ssp585"],
-        ...     variable_id="pr",
-        ...     table_id="Amon",
-        ...     grid_label="gn",
+        ...     source_id=['BCC-CSM2-MR', 'CNRM-CM6-1', 'CNRM-ESM2-1'],
+        ...     experiment_id=['historical', 'ssp585'],
+        ...     variable_id='pr',
+        ...     table_id='Amon',
+        ...     grid_label='gn',
         ... )
         >>> dsets = sub_cat.to_dataset_dict()
         >>> dsets.keys()
         dict_keys(['CMIP.BCC.BCC-CSM2-MR.historical.Amon.gn', 'ScenarioMIP.BCC.BCC-CSM2-MR.ssp585.Amon.gn'])
-        >>> dsets["CMIP.BCC.BCC-CSM2-MR.historical.Amon.gn"]
+        >>> dsets['CMIP.BCC.BCC-CSM2-MR.historical.Amon.gn']
         <xarray.Dataset>
         Dimensions:    (bnds: 2, lat: 160, lon: 320, member_id: 3, time: 1980)
         Coordinates:
@@ -733,16 +733,16 @@ def to_datatree(
         Examples
         --------
         >>> import intake
-        >>> cat = intake.open_esm_datastore("glade-cmip6.json")
+        >>> cat = intake.open_esm_datastore('glade-cmip6.json')
         >>> sub_cat = cat.search(
-        ...     source_id=["BCC-CSM2-MR", "CNRM-CM6-1", "CNRM-ESM2-1"],
-        ...     experiment_id=["historical", "ssp585"],
-        ...     variable_id="pr",
-        ...     table_id="Amon",
-        ...     grid_label="gn",
+        ...     source_id=['BCC-CSM2-MR', 'CNRM-CM6-1', 'CNRM-ESM2-1'],
+        ...     experiment_id=['historical', 'ssp585'],
+        ...     variable_id='pr',
+        ...     table_id='Amon',
+        ...     grid_label='gn',
         ... )
         >>> dsets = sub_cat.to_datatree()
-        >>> dsets["CMIP/BCC.BCC-CSM2-MR/historical/Amon/gn"].ds
+        >>> dsets['CMIP/BCC.BCC-CSM2-MR/historical/Amon/gn'].ds
         <xarray.Dataset>
         Dimensions:    (bnds: 2, lat: 160, lon: 320, member_id: 3, time: 1980)
         Coordinates:

diff --git a/intake_esm/derived.py b/intake_esm/derived.py
@@ -75,9 +75,9 @@ def load(cls, name: str, package: str = None) -> 'DerivedVariableRegistry':
         $PYTHONPATH before calling this function.
 
         >>> import sys
-        >>> sys.path.insert(0, "/home/foo/pythonfiles")
+        >>> sys.path.insert(0, '/home/foo/pythonfiles')
         >>> from intake_esm.derived import DerivedVariableRegistry
-        >>> registsry = DerivedVariableRegistry.load("registry")
+        >>> registsry = DerivedVariableRegistry.load('registry')
         """
         modname = importlib.import_module(name, package=package)
         candidates = inspect.getmembers(modname, lambda x: isinstance(x, DerivedVariableRegistry))

diff --git a/intake_esm/utils.py b/intake_esm/utils.py
@@ -85,7 +85,6 @@ class set_options:
     >>> cat = intake.open_esm_datastore('catalog.json')
     >>> with intake_esm.set_options(attrs_prefix='cat'):
     ...     out = cat.to_dataset_dict()
-    ...
 
     Or to set global options:
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -16,29 +16,40 @@ markers = "network: tests requiring a network connection"
 [tool.ruff]
 line-length = 100
 target-version = "py39"
+extend-include = ["*.ipynb"]
+
+
 builtins = ["ellipsis"]
 # Exclude a variety of commonly ignored directories.
 exclude = [
     ".bzr",
     ".direnv",
     ".eggs",
     ".git",
+    ".git-rewrite",
     ".hg",
+    ".ipynb_checkpoints",
     ".mypy_cache",
     ".nox",
     ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
     ".ruff_cache",
     ".svn",
     ".tox",
     ".venv",
+    ".vscode",
     "__pypackages__",
     "_build",
     "buck-out",
     "build",
     "dist",
     "node_modules",
+    "site-packages",
     "venv",
 ]
+[tool.ruff.lint]
 per-file-ignores = {}
 ignore = [
     "E721", # Comparing types instead of isinstance
@@ -67,6 +78,7 @@ combine-as-imports = true
 
 [tool.ruff.format]
 quote-style = "single"
+docstring-code-format = true
 
 [tool.ruff.lint.pydocstyle]
 convention = "numpy"
diff --git a/requirements.txt b/requirements.txt
@@ -1,7 +1,7 @@
 dask[complete]>=2022.02.0
 fastprogress>=1.0.0
 fsspec>=2022.11.0
-intake>=0.6.6
+intake>=0.6.6,<2
 netCDF4>=1.5.5
 pandas>=2.1.0
 requests>=2.24.0