Fix overlap problem and update numpy recs

.github/workflows/tests.yaml

@@ -7,7 +7,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: [3.8, 3.9, '3.10', 3.11]
+        python-version: [3.9, '3.10', 3.11]
         os: [ubuntu-latest, macOS-latest]
 
     steps:

.readthedocs.yaml

@@ -9,7 +9,7 @@ version: 2
 build:
   os: ubuntu-22.04
   tools:
-    python: "3.8"
+    python: "3.9"
 
 
 # Build documentation in the docs/ directory with Sphinx

docs/requirements.txt

@@ -163,54 +163,61 @@ munch==2.5.0; python_version >= "3.6" \
 myst-parser==0.15.0; python_version >= "3.6" \
     --hash=sha256:3bddfbc8d8afb8dfbd4a6d4b626633585f2ef3480f2ac17eb0e771f96dd743ba \
     --hash=sha256:dd9d5ab06bc7cd047f672785b44f2d172988e63452ef67dbefe0a9a38e6a4a41
-numpy==1.20.3; python_version >= "3.7" \
-    --hash=sha256:70eb5808127284c4e5c9e836208e09d685a7978b6a216db85960b1a112eeace8 \
-    --hash=sha256:6ca2b85a5997dabc38301a22ee43c82adcb53ff660b89ee88dded6b33687e1d8 \
-    --hash=sha256:c5bf0e132acf7557fc9bb8ded8b53bbbbea8892f3c9a1738205878ca9434206a \
-    --hash=sha256:db250fd3e90117e0312b611574cd1b3f78bec046783195075cbd7ba9c3d73f16 \
-    --hash=sha256:637d827248f447e63585ca3f4a7d2dfaa882e094df6cfa177cc9cf9cd6cdf6d2 \
-    --hash=sha256:8b7bb4b9280da3b2856cb1fc425932f46fba609819ee1c62256f61799e6a51d2 \
-    --hash=sha256:67d44acb72c31a97a3d5d33d103ab06d8ac20770e1c5ad81bdb3f0c086a56cf6 \
-    --hash=sha256:43909c8bb289c382170e0282158a38cf306a8ad2ff6dfadc447e90f9961bef43 \
-    --hash=sha256:f1452578d0516283c87608a5a5548b0cdde15b99650efdfd85182102ef7a7c17 \
-    --hash=sha256:6e51534e78d14b4a009a062641f465cfaba4fdcb046c3ac0b1f61dd97c861b1b \
-    --hash=sha256:e515c9a93aebe27166ec9593411c58494fa98e5fcc219e47260d9ab8a1cc7f9f \
-    --hash=sha256:c1c09247ccea742525bdb5f4b5ceeacb34f95731647fe55774aa36557dbb5fa4 \
-    --hash=sha256:66fbc6fed94a13b9801fb70b96ff30605ab0a123e775a5e7a26938b717c5d71a \
-    --hash=sha256:ea9cff01e75a956dbee133fa8e5b68f2f92175233de2f88de3a682dd94deda65 \
-    --hash=sha256:f39a995e47cb8649673cfa0579fbdd1cdd33ea497d1728a6cb194d6252268e48 \
-    --hash=sha256:1676b0a292dd3c99e49305a16d7a9f42a4ab60ec522eac0d3dd20cdf362ac010 \
-    --hash=sha256:830b044f4e64a76ba71448fce6e604c0fc47a0e54d8f6467be23749ac2cbd2fb \
-    --hash=sha256:55b745fca0a5ab738647d0e4db099bd0a23279c32b31a783ad2ccea729e632df \
-    --hash=sha256:5d050e1e4bc9ddb8656d7b4f414557720ddcca23a5b88dd7cff65e847864c400 \
-    --hash=sha256:a9c65473ebc342715cb2d7926ff1e202c26376c0dcaaee85a1fd4b8d8c1d3b2f \
-    --hash=sha256:16f221035e8bd19b9dc9a57159e38d2dd060b48e93e1d843c49cb370b0f415fd \
-    --hash=sha256:6690080810f77485667bfbff4f69d717c3be25e5b11bb2073e76bb3f578d99b4 \
-    --hash=sha256:4e465afc3b96dbc80cf4a5273e5e2b1e3451286361b4af70ce1adb2984d392f9 \
-    --hash=sha256:e55185e51b18d788e49fe8305fd73ef4470596b33fc2c1ceb304566b99c71a69
+numpy==1.23.0; python_version >= "3.9" \
+    --hash=sha256:092f5e6025813e64ad6d1b52b519165d08c730d099c114a9247c9bb635a2a450 \
+    --hash=sha256:196cd074c3f97c4121601790955f915187736f9cf458d3ee1f1b46aff2b1ade0 \
+    --hash=sha256:1c29b44905af288b3919803aceb6ec7fec77406d8b08aaa2e8b9e63d0fe2f160 \
+    --hash=sha256:2b2da66582f3a69c8ce25ed7921dcd8010d05e59ac8d89d126a299be60421171 \
+    --hash=sha256:5043bcd71fcc458dfb8a0fc5509bbc979da0131b9d08e3d5f50fb0bbb36f169a \
+    --hash=sha256:58bfd40eb478f54ff7a5710dd61c8097e169bc36cc68333d00a9bcd8def53b38 \
+    --hash=sha256:79a506cacf2be3a74ead5467aee97b81fca00c9c4c8b3ba16dbab488cd99ba10 \
+    --hash=sha256:94b170b4fa0168cd6be4becf37cb5b127bd12a795123984385b8cd4aca9857e5 \
+    --hash=sha256:97a76604d9b0e79f59baeca16593c711fddb44936e40310f78bfef79ee9a835f \
+    --hash=sha256:98e8e0d8d69ff4d3fa63e6c61e8cfe2d03c29b16b58dbef1f9baa175bbed7860 \
+    --hash=sha256:ac86f407873b952679f5f9e6c0612687e51547af0e14ddea1eedfcb22466babd \
+    --hash=sha256:ae8adff4172692ce56233db04b7ce5792186f179c415c37d539c25de7298d25d \
+    --hash=sha256:bd3fa4fe2e38533d5336e1272fc4e765cabbbde144309ccee8675509d5cd7b05 \
+    --hash=sha256:d0d2094e8f4d760500394d77b383a1b06d3663e8892cdf5df3c592f55f3bff66 \
+    --hash=sha256:d54b3b828d618a19779a84c3ad952e96e2c2311b16384e973e671aa5be1f6187 \
+    --hash=sha256:d6ca8dabe696c2785d0c8c9b0d8a9b6e5fdbe4f922bde70d57fa1a2848134f95 \
+    --hash=sha256:d8cc87bed09de55477dba9da370c1679bd534df9baa171dd01accbb09687dac3 \
+    --hash=sha256:f0f18804df7370571fb65db9b98bf1378172bd4e962482b857e612d1fec0f53e \
+    --hash=sha256:f1d88ef79e0a7fa631bb2c3dda1ea46b32b1fe614e10fedd611d3d5398447f2f \
+    --hash=sha256:f9c3fc2adf67762c9fe1849c859942d23f8d3e0bee7b5ed3d4a9c3eeb50a2f07 \
+    --hash=sha256:fc431493df245f3c627c0c05c2bd134535e7929dbe2e602b80e42bf52ff760bc \
+    --hash=sha256:fe8b9683eb26d2c4d5db32cd29b38fdcf8381324ab48313b5b69088e0e355379
 numpydoc==1.1.0; python_version >= "3.5" \
     --hash=sha256:c53d6311190b9e3b9285bc979390ba0257ba9acde5eca1a7065fc8dfca9d46e8 \
     --hash=sha256:c36fd6cb7ffdc9b4e165a43f67bf6271a7b024d0bb6b00ac468c9e2bfc76448e
 packaging==20.9; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6" \
     --hash=sha256:67714da7f7bc052e064859c05c595155bd1ee9f69f76557e21f051443c20947a \
     --hash=sha256:5b327ac1320dc863dca72f4514ecc086f31186744b84a230374cc1fd776feae5
-pandas==1.2.4; python_full_version >= "3.7.1" \
-    --hash=sha256:c601c6fdebc729df4438ec1f62275d6136a0dd14d332fc0e8ce3f7d2aadb4dd6 \
-    --hash=sha256:8d4c74177c26aadcfb4fd1de6c1c43c2bf822b3e0fc7a9b409eeaf84b3e92aaa \
-    --hash=sha256:b730add5267f873b3383c18cac4df2527ac4f0f0eed1c6cf37fcb437e25cf558 \
-    --hash=sha256:2cb7e8f4f152f27dc93f30b5c7a98f6c748601ea65da359af734dd0cf3fa733f \
-    --hash=sha256:2111c25e69fa9365ba80bbf4f959400054b2771ac5d041ed19415a8b488dc70a \
-    --hash=sha256:167693a80abc8eb28051fbd184c1b7afd13ce2c727a5af47b048f1ea3afefff4 \
-    --hash=sha256:612add929bf3ba9d27b436cc8853f5acc337242d6b584203f207e364bb46cb12 \
-    --hash=sha256:971e2a414fce20cc5331fe791153513d076814d30a60cd7348466943e6e909e4 \
-    --hash=sha256:68d7baa80c74aaacbed597265ca2308f017859123231542ff8a5266d489e1858 \
-    --hash=sha256:bd659c11a4578af740782288cac141a322057a2e36920016e0fc7b25c5a4b686 \
-    --hash=sha256:9db70ffa8b280bb4de83f9739d514cd0735825e79eef3a61d312420b9f16b758 \
-    --hash=sha256:298f0553fd3ba8e002c4070a723a59cdb28eda579f3e243bc2ee397773f5398b \
-    --hash=sha256:52d2472acbb8a56819a87aafdb8b5b6d2b3386e15c95bde56b281882529a7ded \
-    --hash=sha256:d0877407359811f7b853b548a614aacd7dea83b0c0c84620a9a643f180060950 \
-    --hash=sha256:2b063d41803b6a19703b845609c0b700913593de067b552a8b24dd8eeb8c9895 \
-    --hash=sha256:649ecab692fade3cbfcf967ff936496b0cfba0af00a55dfaacd82bdda5cb2279
+pandas==2.1.2 \
+    --hash=sha256:021f09c15e1381e202d95d4a21ece8e7f2bf1388b6d7e9cae09dfe27bd2043d1 \
+    --hash=sha256:02954e285e8e2f4006b6f22be6f0df1f1c3c97adbb7ed211c6b483426f20d5c8 \
+    --hash=sha256:08d287b68fd28906a94564f15118a7ca8c242e50ae7f8bd91130c362b2108a81 \
+    --hash=sha256:24057459f19db9ebb02984c6fdd164a970b31a95f38e4a49cf7615b36a1b532c \
+    --hash=sha256:25c9976c17311388fcd953cb3d0697999b2205333f4e11e669d90ff8d830d429 \
+    --hash=sha256:3223f997b6d2ebf9c010260cf3d889848a93f5d22bb4d14cd32638b3d8bba7ad \
+    --hash=sha256:3f76280ce8ec216dde336e55b2b82e883401cf466da0fe3be317c03fb8ee7c7d \
+    --hash=sha256:52867d69a54e71666cd184b04e839cff7dfc8ed0cd6b936995117fdae8790b69 \
+    --hash=sha256:52897edc2774d2779fbeb6880d2cfb305daa0b1a29c16b91f531a18918a6e0f3 \
+    --hash=sha256:5aa6b86802e8cf7716bf4b4b5a3c99b12d34e9c6a9d06dad254447a620437931 \
+    --hash=sha256:5b40c9f494e1f27588c369b9e4a6ca19cd924b3a0e1ef9ef1a8e30a07a438f43 \
+    --hash=sha256:65177d1c519b55e5b7f094c660ed357bb7d86e799686bb71653b8a4803d8ff0d \
+    --hash=sha256:6ae6ffbd9d614c20d028c7117ee911fc4e266b4dca2065d5c5909e401f8ff683 \
+    --hash=sha256:7ad20d24acf3a0042512b7e8d8fdc2e827126ed519d6bd1ed8e6c14ec8a2c813 \
+    --hash=sha256:83c166b9bb27c1715bed94495d9598a7f02950b4749dba9349c1dd2cbf10729d \
+    --hash=sha256:851b5afbb0d62f6129ae891b533aa508cc357d5892c240c91933d945fff15731 \
+    --hash=sha256:8d0382645ede2fde352da2a885aac28ec37d38587864c0689b4b2361d17b1d4c \
+    --hash=sha256:a6cf8fcc8a63d333970b950a7331a30544cf59b1a97baf0a7409e09eafc1ac38 \
+    --hash=sha256:bbd98dcdcd32f408947afdb3f7434fade6edd408c3077bbce7bd840d654d92c6 \
+    --hash=sha256:d594e2ce51b8e0b4074e6644758865dc2bb13fd654450c1eae51201260a539f1 \
+    --hash=sha256:e78507adcc730533619de07bfdd1c62b2918a68cd4419ea386e28abf7f6a1e5c \
+    --hash=sha256:e7f12b2de0060b0b858cfec0016e7d980ae5bae455a1746bfcc70929100ee633 \
+    --hash=sha256:e90c95abb3285d06f6e4feedafc134306a8eced93cb78e08cf50e224d5ce22e2 \
+    --hash=sha256:eff794eeb7883c5aefb1ed572e7ff533ae779f6c6277849eab9e77986e352688 \
+    --hash=sha256:fc4944dc004ca6cc701dfa19afb8bdb26ad36b9bed5bcec617d2a11e9cae6902
 pluggy==0.13.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6" \
     --hash=sha256:966c145cd83c96502c3c3868f50408687b38434af77734af1e9ca461a4081d2d \
     --hash=sha256:15b2acde666561e1298d71b523007ed7364de07029219b604cf808bfa1c765b0
@@ -252,9 +259,9 @@ pytest-cov==2.12.1; (python_version >= "2.7" and python_full_version < "3.0.0")
 pytest==6.2.4; python_version >= "3.6" \
     --hash=sha256:91ef2131a9bd6be8f76f1f08eac5c5317221d6ad1e143ae03894b862e8976890 \
     --hash=sha256:50bcad0a0b9c5a72c8e4e7c9855a3ad496ca6a881a3641b4260605450772c54b
-python-dateutil==2.8.1; python_full_version >= "3.7.1" and python_version >= "3.6" \
-    --hash=sha256:73ebfe9dbf22e832286dafa60473e4cd239f8592f699aa5adaf10050e6e1823c \
-    --hash=sha256:75bb3f31ea686f1197762692a9ee6a7550b59fc6ca3a1f4b5d7e32fb98e2da2a
+python-dateutil==2.8.2; python_full_version >= "3.7.1" and python_version >= "3.6" \
+    --hash=sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86 \
+    --hash=sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9
 pytz==2021.1; python_full_version >= "3.7.1" and python_version >= "3.6" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6") \
     --hash=sha256:eb10ce3e7736052ed3623d49975ce333bcd712c7bb19a58b9e2089d4057d0798 \
     --hash=sha256:83a4a90894bf38e243cf052c8b58f381bfe9a7a483f6a9cab140bc7f702ac4da
@@ -373,6 +380,9 @@ typing-extensions==3.10.0.0; python_version < "3.8" and python_version >= "3.6"
     --hash=sha256:0ac0f89795dd19de6b97debb0c6af1c70987fd80a2d62d1958f7e56fcc31b497 \
     --hash=sha256:779383f6086d90c99ae41cf0ff39aac8a7937a9283ce0a414e5dd782f4c94a84 \
     --hash=sha256:50b6f157849174217d0656f99dc82fe932884fb250826c18350e159ec6cdf342
+tzdata==2023.1 \
+    --hash=sha256:027ebdafcf386857fc2ce00f3a9e58b7a721d0e8237da60a7abce6d8bbd608a5 \
+    --hash=sha256:b9bb4b0aa169012eb77f19beef072437767ff07cafd20910c4def7c801c70791
 urllib3==1.26.5; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version < "4" and python_version >= "3.6" \
     --hash=sha256:753a0374df26658f99d826cfe40394a686d05985786d946fbe4165b5148f5a7c \
     --hash=sha256:a7acd0977125325f516bda9735fa7142b909a8d01e8b2e4c8108d0984e6e0098

maup/indexed_geometries.py

@@ -1,6 +1,8 @@
 import pandas
 import geopandas
+# Added numpy import to handle output of STRtree query
 import numpy
+import warnings
 
 from shapely.prepared import prep
 from shapely.strtree import STRtree
@@ -21,17 +23,20 @@ def __init__(self, geometries):
 
 
     def query(self, geometry):  
+        # IMPORTANT: When "geometry" is multi-part, this query will return a
+        # (2 x n) array instead of a (1 x n) array, so it's safest to flatten the query
+        # output before proceeding.
         relevant_index_array = self.spatial_index.query(geometry)
         relevant_indices = [*set(numpy.ndarray.flatten(relevant_index_array))]
         relevant_geometries = self.geometries.iloc[relevant_indices]
         return relevant_geometries
 
-    def intersections(self, geometry):
+    def intersections(self, geometry):  
         relevant_geometries = self.query(geometry)  
         intersections = relevant_geometries.intersection(geometry)
         return intersections[-(intersections.is_empty | intersections.isna())]
 
-    def covered_by(self, container):
+    def covered_by(self, container):   
         relevant_geometries = self.query(container)
         prepared_container = prep(container)
 
@@ -41,7 +46,7 @@ def covered_by(self, container):
             selected_geometries = relevant_geometries.apply(prepared_container.covers)
             return relevant_geometries[selected_geometries]
 
-    def assign(self, targets):
+    def assign(self, targets):  
         target_geometries = get_geometries(targets)
         groups = [
             self.covered_by(container).apply(lambda x: container_index)
@@ -50,7 +55,20 @@ def assign(self, targets):
             )
         ]
         if groups:
-            return pandas.concat(groups).reindex(self.index)
+            groups = [group for group in groups if len(group) > 0]
+            groups_concat = pandas.concat(groups)
+            # No reindexing allowed with a non-unique Index,
+            # so we need to find and remove repetitions.  (This only happens when the
+            # targets have overlaps and some source is completely covered by more
+            # than one target.)
+            # Any that get removed here will be randomly assigned to one of the 
+            # covering units at the assign_by_area step by maup.assign.
+            groups_concat_index_list = list(groups_concat.index)
+            seen = set()
+            bad_indices = list(set([x for x in groups_concat_index_list if x in seen or seen.add(x)]))             
+            if len(bad_indices)>0:
+                groups_concat = groups_concat.drop(bad_indices)
+            return groups_concat.reindex(self.index)
         else:
             return geopandas.GeoSeries()