Merge pull request #22 from kthyng/main

get axes/coords use regex matching too

cf_pandas/accessor.py

@@ -3,6 +3,7 @@
 """
 
 import itertools
+from collections import ChainMap
 from typing import (
     Any,
     Callable,
@@ -25,9 +26,14 @@
 
 import cf_pandas as cfp
 
-from .criteria import coordinate_criteria
+from .criteria import coordinate_criteria, guess_regex
 from .options import OPTIONS
-from .utils import always_iterable, match_criteria_key, set_up_criteria
+from .utils import (
+    _is_datetime_like,
+    always_iterable,
+    match_criteria_key,
+    set_up_criteria,
+)
 from .vocab import Vocab
 
 #:  `axis` names understood by cf_xarray
@@ -195,7 +201,6 @@ def axes(self) -> Dict[str, List[str]]:
         """
         # vardict = {key: self.__getitem__(key) for key in _AXIS_NAMES}
         vardict = {key: _get_all(self._obj, key) for key in _AXIS_NAMES}
-
         return {k: sorted(v) for k, v in vardict.items() if v}
 
     @property
@@ -275,23 +280,28 @@ def standard_names(self):
 
 def _get_axis_coord(obj: Union[DataFrame, Series], key: str) -> list:
     """
-    Translate from axis or coord name to variable name
+    Translate from axis or coord name to variable name. After matching based on coordinate_criteria,
+    if there are no matches for key, then guess_regex is used to search for matches.
+
     Parameters
     ----------
     obj : DataArray, Dataset
         DataArray belonging to the coordinate to be checked
     key : str, ["X", "Y", "Z", "T", "longitude", "latitude", "vertical", "time"]
         key to check for.
+
     Returns
     -------
     List[str], Variable name(s) in parent xarray object that matches axis or coordinate `key`
+
     Notes
     -----
     This functions checks for the following attributes in order
     - `standard_name` (CF option)
     - `_CoordinateAxisType` (from THREDDS)
     - `axis` (CF option)
     - `positive` (CF standard for non-pressure vertical coordinate)
+
     References
     ----------
     MetPy's parse_cf
@@ -340,6 +350,18 @@ def _get_axis_coord(obj: Union[DataFrame, Series], key: str) -> list:
                     #     units = getattr(col.data, "units", None)
                     #     if units in expected:
                     #         results.update((col,))
+
+        # also use the guess_regex approach by default, but only if no results so far
+        # this takes the logic from cf-xarray guess_coord_axis
+        if len(results) == 0:
+            if obj[col].ndim == 1 and _is_datetime_like(obj[col]):
+                results.update((col,))
+                continue  # prevent second detection
+
+            pattern = guess_regex[key]
+            if pattern.match(col.lower()):
+                results.update((col,))
+
     return list(results)
 
 

cf_pandas/utils.py

@@ -5,8 +5,10 @@
 from collections import ChainMap
 from typing import Any, Iterable, Optional, Union
 
+import numpy as np
 import pandas as pd
 import regex
+from pandas import Series
 
 from .options import OPTIONS
 
@@ -152,3 +154,12 @@ def standard_names():
     standard_names = [entry.get("id") for entry in soup.find_all("entry")]
 
     return standard_names
+
+
+def _is_datetime_like(da: Series) -> bool:
+    if np.issubdtype(da.dtype, np.datetime64) or np.issubdtype(
+        da.dtype, np.timedelta64
+    ):
+        return True
+
+    return False

tests/test_accessor.py

@@ -121,3 +121,10 @@ def test_set_item():
         assert all(df.cf["temp"].values == np.arange(8))
         df.cf["longitude"] = np.arange(8)
         assert all(df.cf["longitude"].values == np.arange(8))
+
+
+def test_get_by_guess_regex():
+    df = pd.DataFrame(columns=["lon", "lat", "min"])
+    assert df.cf["longitude"].name == "lon"
+    assert df.cf["latitude"].name == "lat"
+    assert df.cf["time"].name == "min"

tests/test_utils.py

@@ -2,6 +2,7 @@
 
 from unittest import mock
 
+import pandas as pd
 import requests
 
 import cf_pandas as cfp
@@ -49,3 +50,14 @@ def test_standard_names(mock_requests):
     mock_requests.return_value = resp
     names = cfp.standard_names()
     assert "wind_speed" in names
+
+
+def test__is_datetime_like():
+    df = pd.DataFrame()
+    df["time"] = pd.date_range(start="2001-1-1", end="2001-1-5", freq="1D")
+    assert cfp.utils._is_datetime_like(df["time"])
+
+    df = pd.DataFrame()
+    df["time"] = ["2001-1-1", "2001-1-2", "2001-1-3"]
+    assert not cfp.utils._is_datetime_like(df["time"])
+    assert cfp.utils._is_datetime_like(pd.to_datetime(df["time"]))