Improve pandas and xarray conversion

Oscar Gustafsson · oscargus · commit 1e27b8a88c0e · 2022-02-28T12:06:16.000+01:00
diff --git a/environment.yml b/environment.yml
@@ -56,3 +56,4 @@ dependencies:
   - pytest-xdist
   - tornado
   - pytz
+  - xarray
diff --git a/lib/matplotlib/axes/_axes.py b/lib/matplotlib/axes/_axes.py
@@ -7907,8 +7907,8 @@ def violinplot(self, dataset, positions=None, vert=True, widths=0.5,
         """
 
         def _kde_method(X, coords):
-            if hasattr(X, 'values'):  # support pandas.Series
-                X = X.values
+            # Unpack in case of e.g. Pandas or xarray object
+            X = cbook._unpack_to_numpy(X)
             # fallback gracefully if the vector contains only one value
             if np.all(X[0] == X):
                 return (X[0] == coords).astype(float)
diff --git a/lib/matplotlib/cbook/__init__.py b/lib/matplotlib/cbook/__init__.py
@@ -1377,15 +1377,8 @@ def _reshape_2D(X, name):
     *name* is used to generate the error message for invalid inputs.
     """
 
-    # unpack if we have a values or to_numpy method.
-    try:
-        X = X.to_numpy()
-    except AttributeError:
-        try:
-            if isinstance(X.values, np.ndarray):
-                X = X.values
-        except AttributeError:
-            pass
+    # Unpack in case of e.g. Pandas or xarray object
+    X = _unpack_to_numpy(X)
 
     # Iterate over columns for ndarrays.
     if isinstance(X, np.ndarray):
@@ -2276,3 +2269,20 @@ def _picklable_class_constructor(mixin_class, fmt, attr_name, base_class):
     factory = _make_class_factory(mixin_class, fmt, attr_name)
     cls = factory(base_class)
     return cls.__new__(cls)
+
+
+def _unpack_to_numpy(x):
+    """Internal helper to extract data from e.g. pandas and xarray objects."""
+    if isinstance(x, np.ndarray):
+        # If numpy, return directly
+        return x
+    if hasattr(x, 'to_numpy'):
+        # Assume that any function to_numpy() do actually return a numpy array
+        return x.to_numpy()
+    if hasattr(x, 'values'):
+        xtmp = x.values
+        # For example a dict has a 'values' attribute, but it is not a property
+        # so in this case we do not want to return a function
+        if isinstance(xtmp, np.ndarray):
+            return xtmp
+    return x
diff --git a/lib/matplotlib/dates.py b/lib/matplotlib/dates.py
@@ -437,9 +437,8 @@ def date2num(d):
     The Gregorian calendar is assumed; this is not universal practice.
     For details see the module docstring.
     """
-    if hasattr(d, "values"):
-        # this unpacks pandas series or dataframes...
-        d = d.values
+    # Unpack in case of e.g. Pandas or xarray object
+    d = cbook._unpack_to_numpy(d)
 
     # make an iterable, but save state to unpack later:
     iterable = np.iterable(d)
diff --git a/lib/matplotlib/testing/conftest.py b/lib/matplotlib/testing/conftest.py
@@ -125,3 +125,10 @@ def pd():
     except ImportError:
         pass
     return pd
+
+
+@pytest.fixture
+def xr():
+    """Fixture to import xarray."""
+    xr = pytest.importorskip('xarray')
+    return xr
diff --git a/lib/matplotlib/tests/conftest.py b/lib/matplotlib/tests/conftest.py
@@ -1,3 +1,3 @@
 from matplotlib.testing.conftest import (mpl_test_settings,
                                          pytest_configure, pytest_unconfigure,
-                                         pd)
+                                         pd, xr)
diff --git a/lib/matplotlib/tests/test_cbook.py b/lib/matplotlib/tests/test_cbook.py
@@ -681,8 +681,11 @@ def test_reshape2d_pandas(pd):
     for x, xnew in zip(X.T, Xnew):
         np.testing.assert_array_equal(x, xnew)
 
+
+def test_reshape2d_xarray(xr):
+    # separate to allow the rest of the tests to run if no pandas...
     X = np.arange(30).reshape(10, 3)
-    x = pd.DataFrame(X, columns=["a", "b", "c"])
+    x = xr.DataArray(X, dims=["x", "y"])
     Xnew = cbook._reshape_2D(x, 'x')
     # Need to check each row because _reshape_2D returns a list of arrays:
     for x, xnew in zip(X.T, Xnew):
diff --git a/lib/matplotlib/units.py b/lib/matplotlib/units.py
@@ -180,8 +180,9 @@ class Registry(dict):
 
     def get_converter(self, x):
         """Get the converter interface instance for *x*, or None."""
-        if hasattr(x, "values"):
-            x = x.values  # Unpack pandas Series and DataFrames.
+        # Unpack in case of e.g. Pandas or xarray object
+        x = cbook._unpack_to_numpy(x)
+
         if isinstance(x, np.ndarray):
             # In case x in a masked array, access the underlying data (only its
             # type matters).  If x is a regular ndarray, getdata() just returns
diff --git a/requirements/testing/extra.txt b/requirements/testing/extra.txt
@@ -7,3 +7,4 @@ pandas!=0.25.0
 pikepdf
 pytz
 pywin32; sys.platform == 'win32'
+xarray

-Original file line number
+Diff line change
   - pytest-xdist
   - tornado
   - pytz
 +  - xarray