geometallurgy 0.4.13__py3-none-any.whl → 0.4.15__py3-none-any.whl

elphick/geomet/validate.py.hide

@@ -1,176 +1,176 @@
-"""
-Classes to support validation of block model files.
-"""
-
-import logging
-import tempfile
-from abc import ABC, abstractmethod
-from concurrent.futures import ThreadPoolExecutor
-from concurrent.futures import as_completed
-from pathlib import Path
-from typing import Optional
-
-import pandas as pd
-
-from elphick.geomet.readers import ParquetFileReader, OMFFileReader
-from elphick.geomet.utils.components import is_compositional
-
-
-#
-# class FileValidator(ABC):
-#     def __init__(self, file_path: Path, schema_path: Optional[Path] = None,
-#                  lazy_validation: bool = True,
-#                  negative_to_nan_threshold: float = 0):
-#         if not file_path.exists():
-#             raise ValueError(f"File does not exist: {file_path}")
-#         self._logger = logging.getLogger(self.__class__.__name__)
-#         self.file_path = file_path
-#         self.schema_path = schema_path
-#         self.schema: DataFrameSchema = DataFrameSchema({}) if schema_path is None else pandera.io.from_yaml(schema_path)
-#         self.lazy_validation = lazy_validation
-#         self.negative_to_nan_threshold = negative_to_nan_threshold
-#
-#         self.report: Optional[dict] = None
-#
-#     @abstractmethod
-#     def validate(self):
-#         pass
-#
-#     def create_schema_file(self, schema_output_path: Path):
-#         """
-#         Create an inferred schema file from the file being validated
-#         Args:
-#             schema_output_path: The output path for the schema file
-#
-#         Returns:
-#
-#         """
-#
-#         df = self.read_column()
-#
-#         with open(schema_output_path, 'w') as f:
-#             yaml.dump(self.schema.to_yaml(), f)
-
-
-class BaseProcessor(ABC):
-    """
-    To support columnar processing of large datasets, the BaseProcessor class provides a framework for processing
-    data by column. The process method will process the data by column if a file_path is provided, or the entire
-    dataset if data is provided.
-    """
-
-    def __init__(self, file_path: Optional[Path] = None, data: Optional[pd.DataFrame] = None, **kwargs):
-        self.logger = logging.getLogger(self.__class__.__name__)
-        if file_path is None and data is None:
-            raise ValueError("Either file_path or data must be provided.")
-        self.file_path = file_path
-        self.data = data
-        self.temp_files = []
-
-        if self.file_path.suffix == '.parquet':
-            self.reader: ParquetFileReader = ParquetFileReader(self.file_path)
-        elif self.file_path.suffix == '.omf':
-            self.reader: OMFFileReader = OMFFileReader(self.file_path, **kwargs)
-        else:
-            raise ValueError(f"Unsupported file format: {self.file_path.suffix}")
-
-    @property
-    def composition_variables(self) -> list[str]:
-        """
-        Detect columns that contain composition data
-
-        Returns:
-            A list of column names that contain composition data
-        """
-        res = None
-        if self.reader.variables_in_file:
-            res = list(is_compositional(self.reader.variables_in_file, strict=False).keys())
-        return res
-
-    def process(self, num_workers: Optional[int] = 1, **kwargs):
-        if self.data is None:
-            with ThreadPoolExecutor(max_workers=num_workers, thread_name_prefix='geomet-processor') as executor:
-                futures = {executor.submit(self._process_variable, variable, **kwargs): variable for variable in
-                           self.reader.variables_in_file}
-                results = {}
-                for future in as_completed(futures):
-                    variable = futures[future]
-                    try:
-                        results[variable] = future.result()
-                    except Exception as exc:
-                        print(f'{variable} generated an exception: {exc}')
-        else:
-            results = self._process_data()
-        return results
-
-    @abstractmethod
-    def _process_variable(self, column, **kwargs):
-        pass
-
-    @abstractmethod
-    def _process_data(self):
-        pass
-
-
-class PreProcessor(BaseProcessor):
-    def __init__(self, file_path: Optional[Path] = None, data: Optional[pd.DataFrame] = None, **kwargs):
-        """
-        Preprocess data before validation.
-        For large datasets where memory may be constrained, file_path will provide processing by columns.
-        If data is provided, the entire dataset already in memory will be processed.
-        Args:
-            file_path: The optional path to the file to be preprocessed.
-            data: The optional DataFrame to be preprocessed.
-        """
-
-        super().__init__(file_path, data, **kwargs)
-
-    def process(self, negative_to_nan_threshold: Optional[float] = -1,
-                not_detected_assays_threshold: Optional[float] = 0.5,
-                max_workers=1):
-        super().process(max_workers=max_workers, negative_to_nan_threshold=negative_to_nan_threshold,
-                        not_detected_assays_threshold=not_detected_assays_threshold)
-
-    def _process_variable(self, column, **kwargs):
-        data = pd.read_parquet(self.file_path, columns=[column])
-        processed_data = self._process_data(data)
-        temp_file = tempfile.NamedTemporaryFile(delete=False)
-        processed_data.to_parquet(temp_file.name)
-        self.temp_files.append(temp_file)
-
-    def _process_data(self) -> pd.DataFrame:
-        # Preprocessing logic here
-        return data
-
-
-class Validator(BaseProcessor):
-    def __init__(self, file_path: Optional[Path] = None, data: Optional[pd.DataFrame] = None, **kwargs):
-        """
-        Validate the data using a pandera schema.
-        For large datasets where memory may be constrained file_path will provide processing by columns.
-        If data is provided, the entire dataset already in memory will be processed.
-        Args:
-            file_path: The optional path to the file to be preprocessed.
-            data: The optional DataFrame to be preprocessed.
-        """
-        super().__init__(file_path, data, **kwargs)
-
-    def process(self):
-        if self.data is None:
-            columns = get_parquet_columns(self.file_path)
-            with ThreadPoolExecutor() as executor:
-                for column in columns:
-                    executor.submit(self._process_variable, column)
-        else:
-            self._process_data()
-
-    def _process_variable(self, column):
-        data = pd.read_parquet(self.file_path, columns=[column])
-        processed_data = self._process_data(data)
-        temp_file = tempfile.NamedTemporaryFile(delete=False)
-        processed_data.to_parquet(temp_file.name)
-        self.temp_files.append(temp_file)
-
-    def _process_data(self, data):
-        # Validation logic here
-        return data
+"""
+Classes to support validation of block model files.
+"""
+
+import logging
+import tempfile
+from abc import ABC, abstractmethod
+from concurrent.futures import ThreadPoolExecutor
+from concurrent.futures import as_completed
+from pathlib import Path
+from typing import Optional
+
+import pandas as pd
+
+from elphick.geomet.readers import ParquetFileReader, OMFFileReader
+from elphick.geomet.utils.components import is_compositional
+
+
+#
+# class FileValidator(ABC):
+#     def __init__(self, file_path: Path, schema_path: Optional[Path] = None,
+#                  lazy_validation: bool = True,
+#                  negative_to_nan_threshold: float = 0):
+#         if not file_path.exists():
+#             raise ValueError(f"File does not exist: {file_path}")
+#         self._logger = logging.getLogger(self.__class__.__name__)
+#         self.file_path = file_path
+#         self.schema_path = schema_path
+#         self.schema: DataFrameSchema = DataFrameSchema({}) if schema_path is None else pandera.io.from_yaml(schema_path)
+#         self.lazy_validation = lazy_validation
+#         self.negative_to_nan_threshold = negative_to_nan_threshold
+#
+#         self.report: Optional[dict] = None
+#
+#     @abstractmethod
+#     def validate(self):
+#         pass
+#
+#     def create_schema_file(self, schema_output_path: Path):
+#         """
+#         Create an inferred schema file from the file being validated
+#         Args:
+#             schema_output_path: The output path for the schema file
+#
+#         Returns:
+#
+#         """
+#
+#         df = self.read_column()
+#
+#         with open(schema_output_path, 'w') as f:
+#             yaml.dump(self.schema.to_yaml(), f)
+
+
+class BaseProcessor(ABC):
+    """
+    To support columnar processing of large datasets, the BaseProcessor class provides a framework for processing
+    data by column. The process method will process the data by column if a file_path is provided, or the entire
+    dataset if data is provided.
+    """
+
+    def __init__(self, file_path: Optional[Path] = None, data: Optional[pd.DataFrame] = None, **kwargs):
+        self.logger = logging.getLogger(self.__class__.__name__)
+        if file_path is None and data is None:
+            raise ValueError("Either file_path or data must be provided.")
+        self.file_path = file_path
+        self.data = data
+        self.temp_files = []
+
+        if self.file_path.suffix == '.parquet':
+            self.reader: ParquetFileReader = ParquetFileReader(self.file_path)
+        elif self.file_path.suffix == '.omf':
+            self.reader: OMFFileReader = OMFFileReader(self.file_path, **kwargs)
+        else:
+            raise ValueError(f"Unsupported file format: {self.file_path.suffix}")
+
+    @property
+    def composition_variables(self) -> list[str]:
+        """
+        Detect columns that contain composition data
+
+        Returns:
+            A list of column names that contain composition data
+        """
+        res = None
+        if self.reader.variables_in_file:
+            res = list(is_compositional(self.reader.variables_in_file, strict=False).keys())
+        return res
+
+    def process(self, num_workers: Optional[int] = 1, **kwargs):
+        if self.data is None:
+            with ThreadPoolExecutor(max_workers=num_workers, thread_name_prefix='geomet-processor') as executor:
+                futures = {executor.submit(self._process_variable, variable, **kwargs): variable for variable in
+                           self.reader.variables_in_file}
+                results = {}
+                for future in as_completed(futures):
+                    variable = futures[future]
+                    try:
+                        results[variable] = future.result()
+                    except Exception as exc:
+                        print(f'{variable} generated an exception: {exc}')
+        else:
+            results = self._process_data()
+        return results
+
+    @abstractmethod
+    def _process_variable(self, column, **kwargs):
+        pass
+
+    @abstractmethod
+    def _process_data(self):
+        pass
+
+
+class PreProcessor(BaseProcessor):
+    def __init__(self, file_path: Optional[Path] = None, data: Optional[pd.DataFrame] = None, **kwargs):
+        """
+        Preprocess data before validation.
+        For large datasets where memory may be constrained, file_path will provide processing by columns.
+        If data is provided, the entire dataset already in memory will be processed.
+        Args:
+            file_path: The optional path to the file to be preprocessed.
+            data: The optional DataFrame to be preprocessed.
+        """
+
+        super().__init__(file_path, data, **kwargs)
+
+    def process(self, negative_to_nan_threshold: Optional[float] = -1,
+                not_detected_assays_threshold: Optional[float] = 0.5,
+                max_workers=1):
+        super().process(max_workers=max_workers, negative_to_nan_threshold=negative_to_nan_threshold,
+                        not_detected_assays_threshold=not_detected_assays_threshold)
+
+    def _process_variable(self, column, **kwargs):
+        data = pd.read_parquet(self.file_path, columns=[column])
+        processed_data = self._process_data(data)
+        temp_file = tempfile.NamedTemporaryFile(delete=False)
+        processed_data.to_parquet(temp_file.name)
+        self.temp_files.append(temp_file)
+
+    def _process_data(self) -> pd.DataFrame:
+        # Preprocessing logic here
+        return data
+
+
+class Validator(BaseProcessor):
+    def __init__(self, file_path: Optional[Path] = None, data: Optional[pd.DataFrame] = None, **kwargs):
+        """
+        Validate the data using a pandera schema.
+        For large datasets where memory may be constrained file_path will provide processing by columns.
+        If data is provided, the entire dataset already in memory will be processed.
+        Args:
+            file_path: The optional path to the file to be preprocessed.
+            data: The optional DataFrame to be preprocessed.
+        """
+        super().__init__(file_path, data, **kwargs)
+
+    def process(self):
+        if self.data is None:
+            columns = get_parquet_columns(self.file_path)
+            with ThreadPoolExecutor() as executor:
+                for column in columns:
+                    executor.submit(self._process_variable, column)
+        else:
+            self._process_data()
+
+    def _process_variable(self, column):
+        data = pd.read_parquet(self.file_path, columns=[column])
+        processed_data = self._process_data(data)
+        temp_file = tempfile.NamedTemporaryFile(delete=False)
+        processed_data.to_parquet(temp_file.name)
+        self.temp_files.append(temp_file)
+
+    def _process_data(self, data):
+        # Validation logic here
+        return data

{geometallurgy-0.4.13.dist-info → geometallurgy-0.4.15.dist-info}/LICENSE

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2024 Greg Elphick
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+MIT License
+
+Copyright (c) 2024 Greg Elphick
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{geometallurgy-0.4.13.dist-info → geometallurgy-0.4.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geometallurgy
-Version: 0.4.13
+Version: 0.4.15
 Summary: Tools for the geometallurgist
 Home-page: https://github.com/elphick/geometallurgy
 Author: Greg
@@ -9,13 +9,12 @@ Requires-Python: >=3.10,<3.13
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Provides-Extra: all
 Provides-Extra: blockmodel
 Provides-Extra: spatial
 Provides-Extra: validation
 Requires-Dist: folium (>=0.16.0,<0.17.0) ; extra == "spatial"
-Requires-Dist: omfpandas (>=0.8.1,<0.9.0) ; extra == "blockmodel"
+Requires-Dist: omfpandas (>=0.8.1) ; extra == "blockmodel"
 Requires-Dist: omfvista (>=0.3.0) ; extra == "blockmodel"
 Requires-Dist: pandas (>=1.0)
 Requires-Dist: pandera[io] (>=0.19.3,<0.21.0) ; extra == "validation"

geometallurgy-0.4.15.dist-info/RECORD

@@ -0,0 +1,48 @@
+elphick/geomet/__init__.py,sha256=gcaArz-agLsm_Tf9KNvmGznw4Jml2QTjj_CxKUC1Ejg,274
+elphick/geomet/base.py,sha256=vp0C7DEAAUDGhTdQ8_Hz9WmqZRjNGn7m5CqEGy3L_98,50603
+elphick/geomet/block_model.py,sha256=E-krPZfjQVIjTgxdDgp0RbvDTJJLFJbUMELE6dh7Jlk,12937
+elphick/geomet/config/__init__.py,sha256=F94hbxN3KzSaljbElIGVhdEwX0FKmHxST4jJ7rNohxY,35
+elphick/geomet/config/config_read.py,sha256=frRwfRwUXpgxwMNCiBVFUw1-yPbBHs3h2KjmzXImvxY,1396
+elphick/geomet/config/flowsheet_example_partition.yaml,sha256=85vrhOotQHhaKkYN-0QQA7ed03EMRkyaKZc-GtXMKro,716
+elphick/geomet/config/flowsheet_example_simple.yaml,sha256=u4sM2gkyyHXnOlqW3TvwBjRdl4x34zGeZS7YGNmdfC4,428
+elphick/geomet/config/mc_config.yml,sha256=6eUGCJlU5Aw9M5Rn6Xuezf8_bShxwxZ1g5XB8P5iLWc,913
+elphick/geomet/data/downloader.py,sha256=x_107mTNCaG9YwEO54mBx7l3KaqOavCi93uZjPdC5GU,1621
+elphick/geomet/data/register.csv,sha256=-N3F6L0097C-I79axINi_ewFAxiqbT_SOSW3-XtPkI4,3046
+elphick/geomet/datasets/__init__.py,sha256=7CX648YFMv39FchI1_oEF28zF52v4gX0lnqomPwkcvU,59
+elphick/geomet/datasets/datasets.py,sha256=RUqQWXZTWEA3R4S5RRdjwlosQZFy2PaMX8x329eP9mo,1882
+elphick/geomet/datasets/downloader.py,sha256=JXHQfwQYbe1X-tIfajx4kGbqkcWh0U2k5R03ur2J6E4,1622
+elphick/geomet/datasets/register.csv,sha256=-N3F6L0097C-I79axINi_ewFAxiqbT_SOSW3-XtPkI4,3046
+elphick/geomet/datasets/sample_data.py,sha256=jt5DWxdMmPbZGDuon2s8Q2wlX3cEegB0dSmRKF4pz4I,7684
+elphick/geomet/extras.py,sha256=UMkAYp72X-30ckaZ-2ENffUUZ7k7JBTdtgsVdgxxYAk,1164
+elphick/geomet/flowsheet/__init__.py,sha256=-lxSLPZNQfiLXKZ2qqS5XbbhrZA2ABi3ppx0LaHnNEI,33
+elphick/geomet/flowsheet/flowsheet.py,sha256=__kgowBIyWfvXcdPWCFihoEUdOqTj7KszSbKGF1AkBo,52032
+elphick/geomet/flowsheet/loader.py,sha256=8nd9Vqbg1de35iuoc4mdRFxrUsIBZed0ivXIAu80jBk,4756
+elphick/geomet/flowsheet/operation.py,sha256=f8k0-Gr_Uy2SlEp8bwAaG4yeBa3DU0HoPn9wyWhYipE,9720
+elphick/geomet/flowsheet/stream.py,sha256=NOXcYeZLSmOSoSRFc7M36Jc8c1ARgjiCvtRuixYfuqA,1370
+elphick/geomet/interval_sample.py,sha256=fhcWBTA01TqvCBsJv7dzWZHRBpw_4W2Ahawks5SPj28,31320
+elphick/geomet/io.py,sha256=tZsX_getGxL07dPlF3Ozyzvt2tFHE5OdgPM5pc5xL68,15709
+elphick/geomet/plot.py,sha256=e9uz8L3QZ23CW4OYm78NhdZl01i0DxHfC4r1kigz7Ss,5732
+elphick/geomet/profile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+elphick/geomet/sample.py,sha256=cbkqkSbCu7IU09IOlEp_Wfx0-tYT6hfaOqUy30gMctM,1223
+elphick/geomet/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+elphick/geomet/utils/amenability.py,sha256=wZ4eIAmcJRfWUp0ZwzfVPUaHEe0g9N2LBaoNv1fZ61E,1874
+elphick/geomet/utils/block_model_converter.py,sha256=REYbS4cu-8z0IzCpuU9ISlPnAvxs9nyX4Bm4yo9mBC8,3364
+elphick/geomet/utils/components.py,sha256=oDR8w7aFKRP38u98yfHp-8MtOaG-c0YcGtwNjgrhGWA,3546
+elphick/geomet/utils/data.py,sha256=AnQ3JXEt2M-T5doGljM_fvdX1CvGbMr6wwjxqcw0fjs,1983
+elphick/geomet/utils/estimates.py,sha256=-x6KDQb-04IrxN8yO38Fx93F6_SGG67koagCtYBtW3c,4892
+elphick/geomet/utils/interp.py,sha256=9lb2sEFfAWYzFECybLPD4nF0S85Xo37nNkxU1DG__A4,10679
+elphick/geomet/utils/interp2.py,sha256=ybuQBNTQOdVzmVYOhQDx2LkGKpl8yxgbQPz_hwS8ClQ,6633
+elphick/geomet/utils/layout.py,sha256=-c1EF-G0qGRQbLrrTS-LsbII-lnvw71y97iUBLd02do,2080
+elphick/geomet/utils/moisture.py,sha256=t9WMwADyz-QAMW-cdah1tIlzTDrhooSoKOPdIlVQHvU,2192
+elphick/geomet/utils/pandas.py,sha256=6sKl3WUjXLR7qFmqBzuCjnfCoUsLRapwZk2nO5BfzYI,17397
+elphick/geomet/utils/parallel.py,sha256=l38JBTkCmdqKHQkS8njoA-sBN9XQGkhF59XtAhWShgs,842
+elphick/geomet/utils/partition.py,sha256=U0jFpvdvZJVdutfB6RzUzKfO9NWCGtBkeySx-QbP-l4,1534
+elphick/geomet/utils/size.py,sha256=EmV_sv2bOImQN3s7TWCniU_y83HNJEPtZH7fMMkYTcc,2272
+elphick/geomet/utils/timer.py,sha256=8WNKLFcINRsZ3IsKtOIZ77YbKtqczyOOTEWY9h9Uxxw,3112
+elphick/geomet/utils/viz.py,sha256=M0CnfDXBHtYb8aak1Sfz6XLvRSmkzX3ybIDllEmDR8A,1718
+elphick/geomet/validate.py.hide,sha256=qAWJlgq0jp19UakVV0dEU_AsqV_JctUn1QTHn8cCRw0,6738
+geometallurgy-0.4.15.dist-info/LICENSE,sha256=GrSVdcGtNbGvAYC_tIjLHBrIVPyg-Ksfe7ZGr087yCI,1069
+geometallurgy-0.4.15.dist-info/METADATA,sha256=YW9b1XuvYaxff2WQK1NcydFmPXSQf2VTNgxn0sav2Iw,4469
+geometallurgy-0.4.15.dist-info/WHEEL,sha256=WGfLGfLX43Ei_YORXSnT54hxFygu34kMpcQdmgmEwCQ,88
+geometallurgy-0.4.15.dist-info/entry_points.txt,sha256=aQI-8kmaba_c9ZGOFkJgWl0MWBke5BQLNyPSVcbS7EU,58
+geometallurgy-0.4.15.dist-info/RECORD,,

{geometallurgy-0.4.13.dist-info → geometallurgy-0.4.15.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: poetry-core 1.6.0
 Root-Is-Purelib: true
 Tag: py3-none-any