subsurface-terra 2025.1.0rc15__py3-none-any.whl → 2025.1.0rc16__py3-none-any.whl

subsurface/modules/reader/wells/DEP/pandas_to_welly.py

@@ -1,212 +1,212 @@
-from typing import Iterable, Union, List
-
-import numpy as np
-import pandas as pd
-
-try:
-    import welly
-    from welly import Well, Location, Project, Curve
-    from striplog import Striplog, Component
-
-    welly_imported = True
-except ImportError:
-    welly_imported = False
-
-__all__ = ['WellyToSubsurfaceHelper', ]
-
-
-class WellyToSubsurfaceHelper:
-    def __init__(
-            self,
-            collar_df: pd.DataFrame = None,
-            survey_df: pd.DataFrame = None,
-            lith_df: pd.DataFrame = None,
-            attrib_dfs: List[pd.DataFrame] = None
-    ):
-        """ Class that wraps `welly` to read borehole data - las files (upcoming)
-         and deviations, csv, excel - and converts it into a
-         `subsurface.UnstructuredData`
-
-        This class is only meant to be extended with all the necessary functionality
-         to load borehole data. For extensive manipulations of the data
-         it should be done in `welly` itself.
-
-        A borehole has:
-
-            -  Datum (XYZ location)
-
-            -  Deviation
-
-            - Lithology: For this we are going to need striplog
-
-            - Logs
-
-        Everything would be a LineSet with a bunch of properties
-
-        """
-
-        if welly_imported is False:
-            raise ImportError('You need to install welly to read well data.')
-
-        self.welly_project = Project([])
-        self._well_names = set()
-        self._unique_formations = None
-
-        if collar_df is not None: self.add_datum(collar_df)
-        if survey_df is not None: self.add_deviation(survey_df)
-        if lith_df is not None:  self.add_striplog(lith_df)
-
-        # First check if is just a path or list
-        if attrib_dfs is not None:
-            for e, attrib in enumerate(attrib_dfs):
-                self.add_assays(attrib, basis='basis')
-
-    def __repr__(self):
-        return self.p.__repr__()
-
-    @property
-    def p(self):
-        """Project Alias"""
-        return self.welly_project
-
-    @p.setter
-    def p(self, p):
-        self.welly_project = p
-
-    @property
-    def lith_component_table(self):
-        return [Component({'lith': l}) for l in self._unique_formations]
-
-    @lith_component_table.setter
-    def lith_component_table(self, unique_formations):
-        self._unique_formations = unique_formations
-
-    def add_wells(self, well_names: Iterable):
-        new_boreholes = set(well_names).difference(self._well_names)
-
-        self._well_names = self._well_names.union(well_names)
-        for b in new_boreholes:
-            # TODO: Name and uwi should be different
-            if welly.__version__ < '0.5':
-                w = Well(params={'header': {'name': b, 'uwi': b}})
-            else:
-                w = Well()
-                w.uwi = b
-                w.name = b
-            # w.location = Location(params={'kb': 100})
-            self.p += w
-        return self.p
-
-    def add_datum(self, data: pd.DataFrame):
-        self.add_wells(
-            well_names=np.unique(data.index)
-        )
-
-        for b in np.unique(data.index):
-            w = self.welly_project.get_well(b)
-            datum = data.loc[[b]]
-            assert datum.shape[1] == 3, 'datum must be XYZ coord'
-
-            w.location.position = datum.values[0]
-
-        return self.welly_project
-
-    def add_collar(self, data: pd.DataFrame):
-        """Alias for add_datum"""
-        return self.add_datum(data=data)
-
-    def add_striplog(self, data: pd.DataFrame):
-        unique_borehole = np.unique(data.index)
-        self.add_wells(unique_borehole)
-        self.lith_component_table = data['component lith'].unique()
-        missed_borehole = []
-        for b in unique_borehole:
-            w = self.p.get_well(b)
-            data_dict = data.loc[[b]].to_dict('list')
-            data_csv = data.loc[[b]].to_csv()
-            # s = Striplog.from_dict_advanced(data_dict, points=True)
-            # s = Striplog.from_dict(data_dict)
-            s = Striplog.from_csv(text=data_csv)
-
-            try:
-                n_basis = w.location.md.shape[0]
-            except TypeError:
-                n_basis = 2
-            try:
-                start, stop, step_size = self._calculate_basis_parameters(
-                    w,
-                    n_basis)
-                s_log, basis, table = s.to_log(step_size, start, stop,
-                                               return_meta=True)
-
-                w.data['lith'] = s
-                w.data['lith_log'] = Curve(s_log, basis)
-            except TypeError:
-                missed_borehole.append(b)
-                continue
-
-        print('The following striplog failed being processed: ', missed_borehole)
-
-        return self.p
-
-    def add_assays(self, data: pd.DataFrame, basis: Union[str, Iterable]):
-        unique_borehole = np.unique(data.index)
-        self.add_wells(unique_borehole)
-        assay_attributes = data.columns
-
-        if type(basis) == str:
-            assay_attributes = assay_attributes.drop(basis)
-            basis = data[basis]
-        elif type(basis) == Iterable:
-            pass
-        else:
-            raise AttributeError('basis must be either a string with the column name'
-                                 'or a array like object')
-
-        for b in unique_borehole:
-            for a in assay_attributes:
-                w = self.p.get_well(b)
-                w.data[a] = Curve(
-                    data=data[a],
-                    basis=basis
-                )
-
-        return self.p
-
-    @staticmethod
-    def _calculate_basis_parameters(well, n_points):
-
-        max_ = well.location.md.max()
-        min_ = well.location.md.min()
-        step_size = (max_ - min_) / n_points
-        return min_ + step_size / 2, max_ - step_size / 2, step_size + 1e-12
-
-    def add_deviation(
-            self,
-            deviations: pd.DataFrame,
-            td=None,
-            method='mc',
-            update_deviation=True,
-            azimuth_datum=0
-    ):
-        """ Add a deviation survey to this instance, and try to compute a position
-         log from it.
-
-        """
-        unique_borehole = np.unique(deviations.index)
-        self.add_wells(unique_borehole)
-
-        for b in unique_borehole:
-            w = self.p.get_well(b)
-            deviations_df: pd.DataFrame = deviations.loc[[b], ['md', 'inc', 'azi']]
-            deviations_df.fillna(0, inplace=True)
-            w.location.add_deviation(
-                deviation=deviations_df,
-                td=td,
-                method=method,
-                update_deviation=update_deviation,
-                azimuth_datum=azimuth_datum)
-            if w.location.position is None:
-                raise ValueError('Deviations could not be calculated.')
-
-        return self.p
+from typing import Iterable, Union, List
+
+import numpy as np
+import pandas as pd
+
+try:
+    import welly
+    from welly import Well, Location, Project, Curve
+    from striplog import Striplog, Component
+
+    welly_imported = True
+except ImportError:
+    welly_imported = False
+
+__all__ = ['WellyToSubsurfaceHelper', ]
+
+
+class WellyToSubsurfaceHelper:
+    def __init__(
+            self,
+            collar_df: pd.DataFrame = None,
+            survey_df: pd.DataFrame = None,
+            lith_df: pd.DataFrame = None,
+            attrib_dfs: List[pd.DataFrame] = None
+    ):
+        """ Class that wraps `welly` to read borehole data - las files (upcoming)
+         and deviations, csv, excel - and converts it into a
+         `subsurface.UnstructuredData`
+
+        This class is only meant to be extended with all the necessary functionality
+         to load borehole data. For extensive manipulations of the data
+         it should be done in `welly` itself.
+
+        A borehole has:
+
+            -  Datum (XYZ location)
+
+            -  Deviation
+
+            - Lithology: For this we are going to need striplog
+
+            - Logs
+
+        Everything would be a LineSet with a bunch of properties
+
+        """
+
+        if welly_imported is False:
+            raise ImportError('You need to install welly to read well data.')
+
+        self.welly_project = Project([])
+        self._well_names = set()
+        self._unique_formations = None
+
+        if collar_df is not None: self.add_datum(collar_df)
+        if survey_df is not None: self.add_deviation(survey_df)
+        if lith_df is not None:  self.add_striplog(lith_df)
+
+        # First check if is just a path or list
+        if attrib_dfs is not None:
+            for e, attrib in enumerate(attrib_dfs):
+                self.add_assays(attrib, basis='basis')
+
+    def __repr__(self):
+        return self.p.__repr__()
+
+    @property
+    def p(self):
+        """Project Alias"""
+        return self.welly_project
+
+    @p.setter
+    def p(self, p):
+        self.welly_project = p
+
+    @property
+    def lith_component_table(self):
+        return [Component({'lith': l}) for l in self._unique_formations]
+
+    @lith_component_table.setter
+    def lith_component_table(self, unique_formations):
+        self._unique_formations = unique_formations
+
+    def add_wells(self, well_names: Iterable):
+        new_boreholes = set(well_names).difference(self._well_names)
+
+        self._well_names = self._well_names.union(well_names)
+        for b in new_boreholes:
+            # TODO: Name and uwi should be different
+            if welly.__version__ < '0.5':
+                w = Well(params={'header': {'name': b, 'uwi': b}})
+            else:
+                w = Well()
+                w.uwi = b
+                w.name = b
+            # w.location = Location(params={'kb': 100})
+            self.p += w
+        return self.p
+
+    def add_datum(self, data: pd.DataFrame):
+        self.add_wells(
+            well_names=np.unique(data.index)
+        )
+
+        for b in np.unique(data.index):
+            w = self.welly_project.get_well(b)
+            datum = data.loc[[b]]
+            assert datum.shape[1] == 3, 'datum must be XYZ coord'
+
+            w.location.position = datum.values[0]
+
+        return self.welly_project
+
+    def add_collar(self, data: pd.DataFrame):
+        """Alias for add_datum"""
+        return self.add_datum(data=data)
+
+    def add_striplog(self, data: pd.DataFrame):
+        unique_borehole = np.unique(data.index)
+        self.add_wells(unique_borehole)
+        self.lith_component_table = data['component lith'].unique()
+        missed_borehole = []
+        for b in unique_borehole:
+            w = self.p.get_well(b)
+            data_dict = data.loc[[b]].to_dict('list')
+            data_csv = data.loc[[b]].to_csv()
+            # s = Striplog.from_dict_advanced(data_dict, points=True)
+            # s = Striplog.from_dict(data_dict)
+            s = Striplog.from_csv(text=data_csv)
+
+            try:
+                n_basis = w.location.md.shape[0]
+            except TypeError:
+                n_basis = 2
+            try:
+                start, stop, step_size = self._calculate_basis_parameters(
+                    w,
+                    n_basis)
+                s_log, basis, table = s.to_log(step_size, start, stop,
+                                               return_meta=True)
+
+                w.data['lith'] = s
+                w.data['lith_log'] = Curve(s_log, basis)
+            except TypeError:
+                missed_borehole.append(b)
+                continue
+
+        print('The following striplog failed being processed: ', missed_borehole)
+
+        return self.p
+
+    def add_assays(self, data: pd.DataFrame, basis: Union[str, Iterable]):
+        unique_borehole = np.unique(data.index)
+        self.add_wells(unique_borehole)
+        assay_attributes = data.columns
+
+        if type(basis) == str:
+            assay_attributes = assay_attributes.drop(basis)
+            basis = data[basis]
+        elif type(basis) == Iterable:
+            pass
+        else:
+            raise AttributeError('basis must be either a string with the column name'
+                                 'or a array like object')
+
+        for b in unique_borehole:
+            for a in assay_attributes:
+                w = self.p.get_well(b)
+                w.data[a] = Curve(
+                    data=data[a],
+                    basis=basis
+                )
+
+        return self.p
+
+    @staticmethod
+    def _calculate_basis_parameters(well, n_points):
+
+        max_ = well.location.md.max()
+        min_ = well.location.md.min()
+        step_size = (max_ - min_) / n_points
+        return min_ + step_size / 2, max_ - step_size / 2, step_size + 1e-12
+
+    def add_deviation(
+            self,
+            deviations: pd.DataFrame,
+            td=None,
+            method='mc',
+            update_deviation=True,
+            azimuth_datum=0
+    ):
+        """ Add a deviation survey to this instance, and try to compute a position
+         log from it.
+
+        """
+        unique_borehole = np.unique(deviations.index)
+        self.add_wells(unique_borehole)
+
+        for b in unique_borehole:
+            w = self.p.get_well(b)
+            deviations_df: pd.DataFrame = deviations.loc[[b], ['md', 'inc', 'azi']]
+            deviations_df.fillna(0, inplace=True)
+            w.location.add_deviation(
+                deviation=deviations_df,
+                td=td,
+                method=method,
+                update_deviation=update_deviation,
+                azimuth_datum=azimuth_datum)
+            if w.location.position is None:
+                raise ValueError('Deviations could not be calculated.')
+
+        return self.p

subsurface/modules/reader/wells/_read_to_df.py

@@ -1,57 +1,57 @@
-import io
-import pathlib
-from typing import Callable
-
-from subsurface.core.reader_helpers.readers_data import GenericReaderFilesHelper, SupportedFormats
-import pandas as pd
-
-
-def check_format_and_read_to_df(reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
-    # ? This swithch is veeery confusing
-    match (reader_helper.file_or_buffer, reader_helper.format):
-        case _, SupportedFormats.JSON | ".json":
-            d = pd.read_json(reader_helper.file_or_buffer, orient='split')
-        case str() | pathlib.Path(), _:
-            reader: Callable = _get_reader(reader_helper.format)
-            d = reader(
-                filepath_or_buffer=reader_helper.file_or_buffer,
-                sep=reader_helper.separator,
-                **reader_helper.pandas_reader_kwargs
-            )
-        case (bytes() | io.BytesIO() | io.StringIO() | io.TextIOWrapper()), _:
-            reader = _get_reader(reader_helper.format)
-            d = reader(reader_helper.file_or_buffer, **reader_helper.pandas_reader_kwargs)
-        case dict(), _:
-            reader = _get_reader('dict')
-            d = reader(reader_helper.file_or_buffer)
-        case _:
-            raise AttributeError('file_or_buffer must be either a path or a dict')
-            
-    if type(d.columns) is str:  d.columns = d.columns.str.strip()  # Remove spaces at the beginning and end
-    if type(d.index) is str: d.index = d.index.str.strip()  # Remove spaces at the beginning and end
-    return d
-
-
-
-
-def _get_reader(file_format) -> Callable:
-    def _dict_reader(dict_):
-        return pd.DataFrame(
-            data=dict_['data'],
-            columns=dict_['columns'],
-            index=dict_['index']
-        )
-
-    match file_format:
-        case SupportedFormats.XLXS:
-            raise NotImplemented("Pandas changed the backend for reading excel files and needs to be re-implemented")
-            reader = pd.read_excel
-        case 'dict':
-            reader = _dict_reader
-        case SupportedFormats.CSV:
-            reader = pd.read_csv
-        case SupportedFormats.JSON:
-            reader = _dict_reader
-        case _:
-            raise ValueError(f"Subsurface is not able to read the following extension: {file_format}")
-    return reader
+import io
+import pathlib
+from typing import Callable
+
+from subsurface.core.reader_helpers.readers_data import GenericReaderFilesHelper, SupportedFormats
+import pandas as pd
+
+
+def check_format_and_read_to_df(reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
+    # ? This swithch is veeery confusing
+    match (reader_helper.file_or_buffer, reader_helper.format):
+        case _, SupportedFormats.JSON | ".json":
+            d = pd.read_json(reader_helper.file_or_buffer, orient='split')
+        case str() | pathlib.Path(), _:
+            reader: Callable = _get_reader(reader_helper.format)
+            d = reader(
+                filepath_or_buffer=reader_helper.file_or_buffer,
+                sep=reader_helper.separator,
+                **reader_helper.pandas_reader_kwargs
+            )
+        case (bytes() | io.BytesIO() | io.StringIO() | io.TextIOWrapper()), _:
+            reader = _get_reader(reader_helper.format)
+            d = reader(reader_helper.file_or_buffer, **reader_helper.pandas_reader_kwargs)
+        case dict(), _:
+            reader = _get_reader('dict')
+            d = reader(reader_helper.file_or_buffer)
+        case _:
+            raise AttributeError('file_or_buffer must be either a path or a dict')
+            
+    if type(d.columns) is str:  d.columns = d.columns.str.strip()  # Remove spaces at the beginning and end
+    if type(d.index) is str: d.index = d.index.str.strip()  # Remove spaces at the beginning and end
+    return d
+
+
+
+
+def _get_reader(file_format) -> Callable:
+    def _dict_reader(dict_):
+        return pd.DataFrame(
+            data=dict_['data'],
+            columns=dict_['columns'],
+            index=dict_['index']
+        )
+
+    match file_format:
+        case SupportedFormats.XLXS:
+            raise NotImplemented("Pandas changed the backend for reading excel files and needs to be re-implemented")
+            reader = pd.read_excel
+        case 'dict':
+            reader = _dict_reader
+        case SupportedFormats.CSV:
+            reader = pd.read_csv
+        case SupportedFormats.JSON:
+            reader = _dict_reader
+        case _:
+            raise ValueError(f"Subsurface is not able to read the following extension: {file_format}")
+    return reader