3.3.0

.github/workflows/conda.yml

@@ -33,7 +33,7 @@ jobs:
           conda install -c conda-forge conda-build scikit-build-core numpy anaconda-client conda-libmamba-solver -y
           conda config --set solver libmamba
           conda build --output-folder conda conda  --python ${{matrix.python-version}}
-          anaconda upload --label main conda/*/*.tar.bz2
+          anaconda upload --label main conda/*/*.conda
 
       - name: upload artifacts
         uses: actions/upload-artifact@v4

.github/workflows/linting_and_testing.yml

@@ -48,28 +48,33 @@ jobs:
         with:
             python-version: ${{ matrix.python-version }}
             conda-remove-defaults: "true"
-
-
-      - name: Install dependencies for windows python 3.10
-        if: ${{ matrix.os == 'windows-latest' && matrix.python-version == '3.10' }}
+
+      - name: Install dependencies for windows python 3.9 and 3.10
+        if: ${{ matrix.os == 'windows-latest' && (matrix.python-version == '3.9' || matrix.python-version == '3.10') }}
         run: |
             conda run -n test conda info
             conda run -n test conda install -c loop3d -c conda-forge "gdal=3.4.3" python=${{ matrix.python-version }} -y
             conda run -n test conda install -c loop3d -c conda-forge --file dependencies.txt python=${{ matrix.python-version }} -y
             conda run -n test conda install pytest python=${{ matrix.python-version }} -y
 
-      - name: Install dependencies for other environments
-        if: ${{ matrix.os != 'windows-latest' || matrix.python-version != '3.10' }}
+      - name: Install dependencies for windows python 3.11
+        if: ${{ matrix.os == 'windows-latest' && matrix.python-version == '3.11' }}
         run: |
             conda run -n test conda info
-            conda run -n test conda install -c loop3d -c conda-forge gdal python=${{ matrix.python-version }} -y
+            conda run -n test conda install -c loop3d -c conda-forge gdal "netcdf4=*=nompi_py311*" python=${{ matrix.python-version }} -y
             conda run -n test conda install -c loop3d -c conda-forge --file dependencies.txt python=${{ matrix.python-version }} -y
             conda run -n test conda install pytest python=${{ matrix.python-version }} -y
+
+      - name: Install dependencies for other environments
+        if: ${{ !(matrix.os == 'windows-latest' && (matrix.python-version == '3.9' || matrix.python-version == '3.10' || matrix.python-version == '3.11')) }}
+        run: |
+            conda run -n test conda info
+            conda run -n test conda install -c loop3d -c conda-forge python=${{ matrix.python-version }} gdal pytest --file dependencies.txt -y
 
       - name: Install map2loop
         run: |
             conda run -n test python -m pip install .
 
       - name: Run tests
         run: |
-            conda run -n test  pytest
+            conda run -n test  pytest -v

map2loop/contact_extractor.py

@@ -0,0 +1,96 @@
+import geopandas
+import pandas
+import shapely
+from .logging import getLogger
+from typing import Optional
+
+logger = getLogger(__name__)
+
+class ContactExtractor:
+    def __init__(self, geology: geopandas.GeoDataFrame, faults: Optional[geopandas.GeoDataFrame] = None):
+        self.geology = geology
+        self.faults = faults
+        self.contacts = None
+        self.basal_contacts = None
+        self.all_basal_contacts = None
+
+    def extract_all_contacts(self, save_contacts: bool = True) -> geopandas.GeoDataFrame:
+        logger.info("Extracting contacts")
+        geology = self.geology.copy()
+        geology = geology.dissolve(by="UNITNAME", as_index=False)
+        geology = geology[~geology["INTRUSIVE"]]
+        geology = geology[~geology["SILL"]]
+        if self.faults is not None:
+            faults = self.faults.copy()
+            faults["geometry"] = faults.buffer(50)
+            geology = geopandas.overlay(geology, faults, how="difference", keep_geom_type=False)
+        units = geology["UNITNAME"].unique().tolist()
+        column_names = ["UNITNAME_1", "UNITNAME_2", "geometry"]
+        contacts = geopandas.GeoDataFrame(crs=geology.crs, columns=column_names, data=None)
+        while len(units) > 1:
+            unit1 = units[0]
+            units = units[1:]
+            for unit2 in units:
+                if unit1 != unit2:
+                    join = geopandas.overlay(
+                        geology[geology["UNITNAME"] == unit1],
+                        geology[geology["UNITNAME"] == unit2],
+                        keep_geom_type=False,
+                    )[column_names]
+                    join["geometry"] = join.buffer(1)
+                    buffered = geology[geology["UNITNAME"] == unit2][["geometry"]].copy()
+                    buffered["geometry"] = buffered.boundary
+                    end = geopandas.overlay(buffered, join, keep_geom_type=False)
+                    if len(end):
+                        contacts = pandas.concat([contacts, end], ignore_index=True)
+        contacts["length"] = [row.length for row in contacts["geometry"]]
+        if save_contacts:
+            self.contacts = contacts
+        return contacts
+
+    def extract_basal_contacts(self, 
+                               stratigraphic_column: list, 
+                               save_contacts: bool = True) -> geopandas.GeoDataFrame:
+
+        logger.info("Extracting basal contacts")
+        units = stratigraphic_column
+
+        if self.contacts is None:
+            self.extract_all_contacts(save_contacts=True)
+            basal_contacts = self.contacts.copy()
+        else:
+            basal_contacts = self.contacts.copy()
+        if any(unit not in units for unit in basal_contacts["UNITNAME_1"].unique()):
+            missing_units = (
+                basal_contacts[~basal_contacts["UNITNAME_1"].isin(units)]["UNITNAME_1"]
+                .unique()
+                .tolist()
+            )
+            logger.error(
+                "There are units in the Geology dataset, but not in the stratigraphic column: "
+                + ", ".join(missing_units)
+                + ". Please readjust the stratigraphic column if this is a user defined column."
+            )
+            raise ValueError(
+                "There are units in stratigraphic column, but not in the Geology dataset: "
+                + ", ".join(missing_units)
+                + ". Please readjust the stratigraphic column if this is a user defined column."
+            )
+        basal_contacts["ID"] = basal_contacts.apply(
+            lambda row: min(units.index(row["UNITNAME_1"]), units.index(row["UNITNAME_2"])), axis=1
+        )
+        basal_contacts["basal_unit"] = basal_contacts.apply(lambda row: units[row["ID"]], axis=1)
+        basal_contacts["stratigraphic_distance"] = basal_contacts.apply(
+            lambda row: abs(units.index(row["UNITNAME_1"]) - units.index(row["UNITNAME_2"])), axis=1
+        )
+        basal_contacts["type"] = basal_contacts.apply(
+            lambda row: "ABNORMAL" if abs(row["stratigraphic_distance"]) > 1 else "BASAL", axis=1
+        )
+        basal_contacts = basal_contacts[["ID", "basal_unit", "type", "geometry"]]
+        basal_contacts["geometry"] = [
+            shapely.line_merge(shapely.snap(geo, geo, 1)) for geo in basal_contacts["geometry"]
+        ]
+        if save_contacts:
+            self.all_basal_contacts = basal_contacts
+            self.basal_contacts = basal_contacts[basal_contacts["type"] == "BASAL"]
+        return basal_contacts

map2loop/data_checks.py

@@ -471,11 +471,13 @@ def check_keys(d: dict, parent_key=""):
         "fault": {
             "structtype_column",  "fault_text",  "dip_null_value",
             "dipdir_flag", "dipdir_column",  "dip_column",  "orientation_type",
-            "dipestimate_column",  "dipestimate_text",  "name_column",
-            "objectid_column", "minimum_fault_length", "ignore_fault_codes",
+            "dipestimate_column",  "dipestimate_text","displacement_column", 
+            "displacement_text",  "name_column","objectid_column", "featureid_column", "minimum_fault_length",
+            "fault_length_column", "fault_length_text", "ignore_fault_codes",
         },
         "fold": {
-            "structtype_column", "fold_text", "description_column",
+            "structtype_column", "fold_text", "axial_plane_dipdir_column", 
+            "axial_plane_dip_column","tightness_column", "description_column",
             "synform_text", "foldname_column","objectid_column",
         },
     }
@@ -853,6 +855,7 @@ def validate_structtype_column(
     if text_keys:
         for text_key, config_key in text_keys.items():
             text_value = config.get(config_key, None)
+            text_pattern = '|'.join(text_value) if text_value else None
             if text_value:
                 if not isinstance(text_value, str):
                     error_msg = (
@@ -862,7 +865,7 @@ def validate_structtype_column(
                     logger.error(error_msg)
                     return (True, error_msg)
 
-                if not geodata[structtype_column].str.contains(text_value, na=False).any():
+                if not geodata[structtype_column].str.contains(text_pattern, case=False, regex=True, na=False).any():
                     if text_key == "synform_text":
                         warning_msg = (
                             f"Datatype {datatype_name.upper()}: The '{text_key}' value '{text_value}' is not found in column '{structtype_column}'. "