Merge pull request #150 from martinfleis/categorical_align_bug

BUG: support custom index in area_interpolate

Author: knaaptime

Diff for: tobler/area_weighted/area_interpolate.py

@@ -129,7 +129,10 @@ def _area_tables_binning_parallel(source_df, target_df, n_jobs=-1):
 
     # Build DOK table
     table = coo_matrix(
-        (areas, (ids_src, ids_tgt),),
+        (
+            areas,
+            (ids_src, ids_tgt),
+        ),
         shape=(df1.shape[0], df2.shape[0]),
         dtype=np.float32,
     )
@@ -190,7 +193,10 @@ def _area_tables_binning(source_df, target_df, spatial_index):
     areas = df1.geometry.values[ids_src].intersection(df2.geometry.values[ids_tgt]).area
 
     table = coo_matrix(
-        (areas, (ids_src, ids_tgt),),
+        (
+            areas,
+            (ids_src, ids_tgt),
+        ),
         shape=(df1.shape[0], df2.shape[0]),
         dtype=np.float32,
     )
@@ -359,7 +365,7 @@ def _area_interpolate_binning(
         else:
             table = _area_tables_binning_parallel(source_df, target_df, n_jobs=n_jobs)
 
-    den = source_df[source_df.geometry.name].area.values
+    den = source_df.area.values
     if allocate_total:
         den = np.asarray(table.sum(axis=1))
     den = den + (den == 0)
@@ -415,7 +421,7 @@ def _area_interpolate_binning(
                 )[0]
 
         categorical = pd.DataFrame(categorical)
-        categorical = categorical.div(target_df.area, axis="rows")
+        categorical = categorical.div(target_df.area.values, axis="rows")
 
     if extensive_variables:
         dfs.append(extensive)

Diff for: tobler/tests/test_dasymetric.py

@@ -59,6 +59,28 @@ def test_area_interpolate():
     assert_almost_equal(area.animal_capybara.sum(), 20, decimal=0)
 
 
+@pytest.mark.skipif(QUILTMISSING, reason="quilt3 not available.")
+def test_area_interpolate_custom_index():
+    sac1, sac2 = datasets()
+    sac1.index = sac1.index * 2
+    sac2.index = sac2.index * 13
+    area = area_interpolate(
+        source_df=sac1,
+        target_df=sac2,
+        extensive_variables=["TOT_POP"],
+        intensive_variables=["pct_poverty"],
+        categorical_variables=["animal"],
+    )
+    assert_almost_equal(area.TOT_POP.sum(), 1796856, decimal=0)
+    assert_almost_equal(area.pct_poverty.sum(), 2140, decimal=0)
+    assert_almost_equal(area.animal_cat.sum(), 32, decimal=0)
+    assert_almost_equal(area.animal_dog.sum(), 19, decimal=0)
+    assert_almost_equal(area.animal_donkey.sum(), 22, decimal=0)
+    assert_almost_equal(area.animal_wombat.sum(), 23, decimal=0)
+    assert_almost_equal(area.animal_capybara.sum(), 20, decimal=0)
+    assert not area.isna().any().any()
+
+
 @pytest.mark.skipif(QUILTMISSING, reason="quilt3 not available.")
 def test_masked_area_interpolate():
     sac1, sac2 = datasets()