subsurface-terra 2025.1.0rc14__py3-none-any.whl → 2025.1.0rc16__py3-none-any.whl

subsurface/modules/reader/wells/read_borehole_interface.py

@@ -1,148 +1,148 @@
-import numpy as np
-import warnings
-
-from subsurface.core.reader_helpers.readers_data import GenericReaderFilesHelper
-import pandas as pd
-
-from subsurface.modules.reader.wells._read_to_df import check_format_and_read_to_df
-from subsurface.modules.reader.wells.wells_utils import add_tops_from_base_and_altitude_in_place
-
-
-def read_collar(reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
-    if reader_helper.index_col is False: reader_helper.index_col = 0
-
-    # Check file_or_buffer type
-    data_df: pd.DataFrame = check_format_and_read_to_df(reader_helper)
-    _map_rows_and_cols_inplace(data_df, reader_helper)
-
-    # Remove duplicates
-    data_df = data_df[~data_df.index.duplicated(keep='first')]
-
-    return data_df
-
-
-def read_survey(reader_helper: GenericReaderFilesHelper, validate_survey: bool = True) -> pd.DataFrame:
-    if reader_helper.index_col is False: reader_helper.index_col = 0
-
-    d = check_format_and_read_to_df(reader_helper)
-    _map_rows_and_cols_inplace(d, reader_helper)
-
-    if validate_survey:
-        d_no_singles = _validate_survey_data(d)
-    else:
-        d_no_singles = d
-
-    return d_no_singles
-
-
-def read_lith(reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
-    return read_attributes(reader_helper, is_lith=True)
-
-
-def read_attributes(reader_helper: GenericReaderFilesHelper, is_lith: bool = False, validate_attr: bool = True) -> pd.DataFrame:
-    if reader_helper.index_col is False:
-        reader_helper.index_col = 0
-        
-    d = check_format_and_read_to_df(reader_helper)
-
-    _map_rows_and_cols_inplace(d, reader_helper)
-    if validate_attr is False:
-        return d
-    
-    if is_lith:
-        d = _validate_lith_data(d, reader_helper)
-    else:
-        _validate_attr_data(d)
-    return d
-
-
-def _map_rows_and_cols_inplace(d: pd.DataFrame, reader_helper: GenericReaderFilesHelper):
-    if reader_helper.index_map is not None:
-        d.rename(reader_helper.index_map, axis="index", inplace=True)  # d.index = d.index.map(reader_helper.index_map)
-    if reader_helper.columns_map is not None:
-        d.rename(reader_helper.columns_map, axis="columns", inplace=True)
-
-
-def _validate_survey_data(d):
-    # Check for essential column 'md'
-    if 'md' not in d.columns:
-        raise AttributeError(
-            'md, inc, and azi columns must be present in the file. Use columns_map to assign column names to these fields.')
-
-    # Check if 'dip' column exists and convert it to 'inc'
-    if 'dip' in d.columns:
-        # Convert dip to inclination (90 - dip)
-        d['inc'] = 90 - d['dip']
-        # Optionally, drop the 'dip' column if it's no longer needed
-        d.drop(columns=['dip'], inplace=True)
-
-    # Handle if inclination ('inc') or azimuth ('azi') columns are missing
-    if not np.isin(['inc', 'azi'], d.columns).all():
-        warnings.warn(
-            'inc and/or azi columns are not present in the file. The boreholes will be straight.')
-        d['inc'] = 180
-        d['azi'] = 0
-
-    # Drop wells that contain only one value, ensuring that we keep rows only when there are duplicates
-    d_no_singles = d[d.index.duplicated(keep=False)]
-
-    return d_no_singles
-
-
-def _validate_attr_data(d):
-    assert d.columns.isin(['base']).any(), ('base column must be present in the file. '
-                                            'Use columns_map to assign column names to these fields.')
-
-
-def _validate_lith_data(d: pd.DataFrame, reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
-    # Check component lith in column
-    if 'component lith' not in d.columns:
-        raise AttributeError('If wells attributes represent lithology, `component lith` column must be present in the file. '
-                             'Use columns_map to assign column names to these fields. Maybe you are marking as lithology'
-                             'the wrong file?')
-    else:
-        # TODO: Add categories to reader helper
-        categories = sorted(d['component lith'].dropna().unique())
-        d['component lith'] = pd.Categorical(
-            d['component lith'],
-            categories=categories,
-            ordered=True
-        )
-        
-        d['lith_ids'] = d['component lith'].cat.codes + 1
-
-    given_top = np.isin(['top', 'base'], d.columns).all()
-    given_altitude_and_base = np.isin(['altitude', 'base'], d.columns).all()
-    given_only_base = np.isin(['base'], d.columns).all()
-    if given_altitude_and_base and not given_top:
-        warnings.warn('top column is not present in the file. The tops will be calculated from the base and altitude')
-        d = add_tops_from_base_and_altitude_in_place(
-            data=d,
-            col_well_name=reader_helper.index_col,
-            col_base='base',
-            col_altitude='altitude'
-        )
-    elif given_only_base and not given_top:
-        warnings.warn('top column is not present in the file. The tops will be calculated from the base assuming altitude=0')
-        # add a top column with 0 and call add_tops_from_base_and_altitude_in_place
-        d['altitude'] = 0
-        d = add_tops_from_base_and_altitude_in_place(
-            data=d,
-            col_well_name=reader_helper.index_col,
-            col_base='base',
-            col_altitude='altitude'
-        )
-
-
-    elif not given_top and not given_altitude_and_base:
-        raise ValueError('top column or base and altitude columns must be present in the file. '
-                         'Use columns_map to assign column names to these fields. Maybe you are marking as lithology'
-                         'the wrong file?')
-
-    lith_df = d[['top', 'base', 'component lith']]
-
-    # * Make sure values are positive
-    lith_df['top'] = np.abs(lith_df['top'])
-    lith_df['base'] = np.abs(lith_df['base'])
-
-    return lith_df
+import numpy as np
+import warnings
+
+from subsurface.core.reader_helpers.readers_data import GenericReaderFilesHelper
+import pandas as pd
+
+from subsurface.modules.reader.wells._read_to_df import check_format_and_read_to_df
+from subsurface.modules.reader.wells.wells_utils import add_tops_from_base_and_altitude_in_place
+
+
+def read_collar(reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
+    if reader_helper.index_col is False: reader_helper.index_col = 0
+
+    # Check file_or_buffer type
+    data_df: pd.DataFrame = check_format_and_read_to_df(reader_helper)
+    _map_rows_and_cols_inplace(data_df, reader_helper)
+
+    # Remove duplicates
+    data_df = data_df[~data_df.index.duplicated(keep='first')]
+
+    return data_df
+
+
+def read_survey(reader_helper: GenericReaderFilesHelper, validate_survey: bool = True) -> pd.DataFrame:
+    if reader_helper.index_col is False: reader_helper.index_col = 0
+
+    d = check_format_and_read_to_df(reader_helper)
+    _map_rows_and_cols_inplace(d, reader_helper)
+
+    if validate_survey:
+        d_no_singles = _validate_survey_data(d)
+    else:
+        d_no_singles = d
+
+    return d_no_singles
+
+
+def read_lith(reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
+    return read_attributes(reader_helper, is_lith=True)
+
+
+def read_attributes(reader_helper: GenericReaderFilesHelper, is_lith: bool = False, validate_attr: bool = True) -> pd.DataFrame:
+    if reader_helper.index_col is False:
+        reader_helper.index_col = 0
+        
+    d = check_format_and_read_to_df(reader_helper)
+
+    _map_rows_and_cols_inplace(d, reader_helper)
+    if validate_attr is False:
+        return d
+    
+    if is_lith:
+        d = _validate_lith_data(d, reader_helper)
+    else:
+        _validate_attr_data(d)
+    return d
+
+
+def _map_rows_and_cols_inplace(d: pd.DataFrame, reader_helper: GenericReaderFilesHelper):
+    if reader_helper.index_map is not None:
+        d.rename(reader_helper.index_map, axis="index", inplace=True)  # d.index = d.index.map(reader_helper.index_map)
+    if reader_helper.columns_map is not None:
+        d.rename(reader_helper.columns_map, axis="columns", inplace=True)
+
+
+def _validate_survey_data(d):
+    # Check for essential column 'md'
+    if 'md' not in d.columns:
+        raise AttributeError(
+            'md, inc, and azi columns must be present in the file. Use columns_map to assign column names to these fields.')
+
+    # Check if 'dip' column exists and convert it to 'inc'
+    if 'dip' in d.columns:
+        # Convert dip to inclination (90 - dip)
+        d['inc'] = 90 - d['dip']
+        # Optionally, drop the 'dip' column if it's no longer needed
+        d.drop(columns=['dip'], inplace=True)
+
+    # Handle if inclination ('inc') or azimuth ('azi') columns are missing
+    if not np.isin(['inc', 'azi'], d.columns).all():
+        warnings.warn(
+            'inc and/or azi columns are not present in the file. The boreholes will be straight.')
+        d['inc'] = 180
+        d['azi'] = 0
+
+    # Drop wells that contain only one value, ensuring that we keep rows only when there are duplicates
+    d_no_singles = d[d.index.duplicated(keep=False)]
+
+    return d_no_singles
+
+
+def _validate_attr_data(d):
+    assert d.columns.isin(['base']).any(), ('base column must be present in the file. '
+                                            'Use columns_map to assign column names to these fields.')
+
+
+def _validate_lith_data(d: pd.DataFrame, reader_helper: GenericReaderFilesHelper) -> pd.DataFrame:
+    # Check component lith in column
+    if 'component lith' not in d.columns:
+        raise AttributeError('If wells attributes represent lithology, `component lith` column must be present in the file. '
+                             'Use columns_map to assign column names to these fields. Maybe you are marking as lithology'
+                             'the wrong file?')
+    else:
+        # TODO: Add categories to reader helper
+        categories = sorted(d['component lith'].dropna().unique())
+        d['component lith'] = pd.Categorical(
+            d['component lith'],
+            categories=categories,
+            ordered=True
+        )
+        
+        d['lith_ids'] = d['component lith'].cat.codes + 1
+
+    given_top = np.isin(['top', 'base'], d.columns).all()
+    given_altitude_and_base = np.isin(['altitude', 'base'], d.columns).all()
+    given_only_base = np.isin(['base'], d.columns).all()
+    if given_altitude_and_base and not given_top:
+        warnings.warn('top column is not present in the file. The tops will be calculated from the base and altitude')
+        d = add_tops_from_base_and_altitude_in_place(
+            data=d,
+            col_well_name=reader_helper.index_col,
+            col_base='base',
+            col_altitude='altitude'
+        )
+    elif given_only_base and not given_top:
+        warnings.warn('top column is not present in the file. The tops will be calculated from the base assuming altitude=0')
+        # add a top column with 0 and call add_tops_from_base_and_altitude_in_place
+        d['altitude'] = 0
+        d = add_tops_from_base_and_altitude_in_place(
+            data=d,
+            col_well_name=reader_helper.index_col,
+            col_base='base',
+            col_altitude='altitude'
+        )
+
+
+    elif not given_top and not given_altitude_and_base:
+        raise ValueError('top column or base and altitude columns must be present in the file. '
+                         'Use columns_map to assign column names to these fields. Maybe you are marking as lithology'
+                         'the wrong file?')
+
+    lith_df = d[['top', 'base', 'component lith']]
+
+    # * Make sure values are positive
+    lith_df['top'] = np.abs(lith_df['top'])
+    lith_df['base'] = np.abs(lith_df['base'])
+
+    return lith_df

subsurface/modules/reader/wells/wells_utils.py

@@ -1,68 +1,68 @@
-from typing import List
-
-import pandas as pd
-
-
-__all__ = ['add_tops_from_base_and_altitude_in_place',
-           'fix_wells_higher_base_than_top_inplace', 'map_attr_to_segments',
-           'pivot_wells_df_into_segment_per_row']
-
-
-def add_tops_from_base_and_altitude_in_place(data: pd.DataFrame, col_well_name: str, col_base: str,
-                                             col_altitude: str) -> pd.DataFrame:
-    d = data
-    d = _remove_repeated_rows(d)
-    _create_base_col(col_altitude, col_base, d)
-    _create_top_col(col_altitude, col_well_name, d)
-    _add_md_col_if_missing(d)
-    return d
-
-
-def fix_wells_higher_base_than_top_inplace(df_fixed) -> pd.DataFrame:
-    top_base_error = df_fixed["top"] > df_fixed["base"]
-    df_fixed["base"][top_base_error] = df_fixed["top"] + 0.01
-    return df_fixed
-
-
-def map_attr_to_segments(df, attr_per_segment: List, n_wells: int) -> pd.DataFrame:
-    tiled_formations = pd.np.tile(attr_per_segment, (n_wells))
-    df['formation'] = tiled_formations
-    return df
-
-
-def pivot_wells_df_into_segment_per_row(df: pd.DataFrame, start_segment_cols: int, n_segments_per_well: int) -> pd.DataFrame:
-    # Repeat fixed rows (collar name and so)
-    df_fixed = df.iloc[:, :start_segment_cols]
-    df_fixed = df_fixed.loc[df_fixed.index.repeat(n_segments_per_well)]
-
-    df_bottoms = df.iloc[:, start_segment_cols:start_segment_cols + n_segments_per_well]
-    df_fixed['base'] = df_bottoms.values.reshape(-1, 1, order='C')
-
-    return df_fixed
-
-
-def _add_md_col_if_missing(d):
-    if "md" not in d.columns:
-        d.loc[:, 'md'] = d['top']
-
-
-def _create_top_col(col_altitude, col_well_name, d):
-    Z_shift = d.groupby(col_well_name)['base'].shift(1)
-    Z_0 = Z_shift.fillna(0)
-    v = Z_0 + d[col_altitude]
-    d.loc[:, 'top'] = Z_0
-    d.loc[:, '_top_abs'] = v
-
-
-def _create_base_col(col_altitude, col_base, d):
-    d.loc[:, 'base'] = d[col_altitude] - d[col_base]
-
-
-def _remove_repeated_rows(d):
-    repeated_rows = _mark_repeated_rows(d['base'])
-    d = d[~repeated_rows]  # removed repeated rows
-    return d
-
-
-def _mark_repeated_rows(series: pd.Series):
-    return series.shift(1) == series
+from typing import List
+
+import pandas as pd
+
+
+__all__ = ['add_tops_from_base_and_altitude_in_place',
+           'fix_wells_higher_base_than_top_inplace', 'map_attr_to_segments',
+           'pivot_wells_df_into_segment_per_row']
+
+
+def add_tops_from_base_and_altitude_in_place(data: pd.DataFrame, col_well_name: str, col_base: str,
+                                             col_altitude: str) -> pd.DataFrame:
+    d = data
+    d = _remove_repeated_rows(d)
+    _create_base_col(col_altitude, col_base, d)
+    _create_top_col(col_altitude, col_well_name, d)
+    _add_md_col_if_missing(d)
+    return d
+
+
+def fix_wells_higher_base_than_top_inplace(df_fixed) -> pd.DataFrame:
+    top_base_error = df_fixed["top"] > df_fixed["base"]
+    df_fixed["base"][top_base_error] = df_fixed["top"] + 0.01
+    return df_fixed
+
+
+def map_attr_to_segments(df, attr_per_segment: List, n_wells: int) -> pd.DataFrame:
+    tiled_formations = pd.np.tile(attr_per_segment, (n_wells))
+    df['formation'] = tiled_formations
+    return df
+
+
+def pivot_wells_df_into_segment_per_row(df: pd.DataFrame, start_segment_cols: int, n_segments_per_well: int) -> pd.DataFrame:
+    # Repeat fixed rows (collar name and so)
+    df_fixed = df.iloc[:, :start_segment_cols]
+    df_fixed = df_fixed.loc[df_fixed.index.repeat(n_segments_per_well)]
+
+    df_bottoms = df.iloc[:, start_segment_cols:start_segment_cols + n_segments_per_well]
+    df_fixed['base'] = df_bottoms.values.reshape(-1, 1, order='C')
+
+    return df_fixed
+
+
+def _add_md_col_if_missing(d):
+    if "md" not in d.columns:
+        d.loc[:, 'md'] = d['top']
+
+
+def _create_top_col(col_altitude, col_well_name, d):
+    Z_shift = d.groupby(col_well_name)['base'].shift(1)
+    Z_0 = Z_shift.fillna(0)
+    v = Z_0 + d[col_altitude]
+    d.loc[:, 'top'] = Z_0
+    d.loc[:, '_top_abs'] = v
+
+
+def _create_base_col(col_altitude, col_base, d):
+    d.loc[:, 'base'] = d[col_altitude] - d[col_base]
+
+
+def _remove_repeated_rows(d):
+    repeated_rows = _mark_repeated_rows(d['base'])
+    d = d[~repeated_rows]  # removed repeated rows
+    return d
+
+
+def _mark_repeated_rows(series: pd.Series):
+    return series.shift(1) == series

subsurface/modules/tools/mocking_aux.py

@@ -1,104 +1,104 @@
-import numpy as np
-import pyvista as pv
-
-
-def transform_gaussian_blur(grid, sigma=20.0):
-    """
-    Applies a Gaussian blur to the 'model_name' field of the structured grid.
-
-    Parameters:
-        grid - PyVista grid with 'model_name' field
-        sigma - Standard deviation for the Gaussian kernel
-    """
-    from scipy.ndimage import gaussian_filter
-
-    # Get the original dimensions of the grid
-    dims = grid.dimensions
-
-    # Reshape the data to 3D array matching grid dimensions
-    values = np.array(grid['model_name'])
-    values_3d = values.reshape(dims[2] - 1, dims[1] - 1, dims[0] - 1).transpose(2, 1, 0)
-
-    # Apply Gaussian filter
-    blurred_values = gaussian_filter(values_3d, sigma=sigma, axes=(2,))
-
-    # Reshape back to 1D array
-    grid['model_name'] = blurred_values.transpose(2, 1, 0).flatten()
-    return grid
-
-
-def transform_sinusoidal(values, amplitude=1.0, frequency=0.01, phase=0):
-    """
-    Apply a sinusoidal transformation to the values.
-    """
-    return values + amplitude * np.sin(frequency * values + phase)
-
-
-def obfuscate_model_name(grid, transform_functions, attr):
-    """
-    Applies transformation functions to the 'model_name' field.
-    Functions can operate on either the grid or the values array.
-    """
-    for func in transform_functions:
-        if 'grid' in func.__code__.co_varnames:
-            # Function expects the full grid
-            grid = func(grid)
-        else:
-            # Function expects just the values array
-            values = np.array(grid[attr])
-            grid[attr] = func(values)
-
-    return grid
-
-
-# pyvista_struct = transform_xy_to_z_propagation(pyvista_struct, z_factor=0.3, noise_level=0.1)
-def transform_subtract_mean(values):
-    """
-    Subtract the mean of the array from each element.
-    """
-    return values - np.mean(values)
-
-
-def transform_scale(values, scale_factor=0.003):
-    """
-    Multiply each value by scale_factor.
-    """
-    return values * scale_factor
-
-
-
-
-def update_extent(pyvista_grid, new_extent):
-    # new_extent: array-like with 6 elements [xmin, xmax, ymin, ymax, zmin, zmax]
-    old_bounds = np.array(pyvista_grid.bounds)  # [xmin, xmax, ymin, ymax, zmin, zmax]
-
-    # Check for valid extents
-    if any(new_extent[i] >= new_extent[i + 1] for i in range(0, 6, 2)):
-        raise ValueError("Each min value must be less than the corresponding max value in the new extent.")
-
-    # Compute old ranges and new ranges for each axis
-    old_ranges = old_bounds[1::2] - old_bounds[0::2]  # [x_range, y_range, z_range]
-    new_ranges = np.array([new_extent[1] - new_extent[0],
-                           new_extent[3] - new_extent[2],
-                           new_extent[5] - new_extent[4]])
-
-    # Avoid division by zero if any old range is zero
-    if np.any(old_ranges == 0):
-        raise ValueError("One of the dimensions in the current grid has zero length.")
-
-    # Get the old points and reshape for easier manipulation
-    old_points = pyvista_grid.points  # shape (N, 3)
-
-    # Compute normalized coordinates within the old extent
-    norm_points = (old_points - old_bounds[0::2]) / old_ranges
-
-    # Compute new points based on new extent
-    new_mins = np.array([new_extent[0], new_extent[2], new_extent[4]])
-    new_points = new_mins + norm_points * new_ranges
-
-    # Update the grid's points
-    pyvista_grid.points = new_points
-
-    # Updating bounds is implicit once the points are modified.
-    pyvista_grid.Modified()
-    return pyvista_grid
+import numpy as np
+import pyvista as pv
+
+
+def transform_gaussian_blur(grid, sigma=20.0):
+    """
+    Applies a Gaussian blur to the 'model_name' field of the structured grid.
+
+    Parameters:
+        grid - PyVista grid with 'model_name' field
+        sigma - Standard deviation for the Gaussian kernel
+    """
+    from scipy.ndimage import gaussian_filter
+
+    # Get the original dimensions of the grid
+    dims = grid.dimensions
+
+    # Reshape the data to 3D array matching grid dimensions
+    values = np.array(grid['model_name'])
+    values_3d = values.reshape(dims[2] - 1, dims[1] - 1, dims[0] - 1).transpose(2, 1, 0)
+
+    # Apply Gaussian filter
+    blurred_values = gaussian_filter(values_3d, sigma=sigma, axes=(2,))
+
+    # Reshape back to 1D array
+    grid['model_name'] = blurred_values.transpose(2, 1, 0).flatten()
+    return grid
+
+
+def transform_sinusoidal(values, amplitude=1.0, frequency=0.01, phase=0):
+    """
+    Apply a sinusoidal transformation to the values.
+    """
+    return values + amplitude * np.sin(frequency * values + phase)
+
+
+def obfuscate_model_name(grid, transform_functions, attr):
+    """
+    Applies transformation functions to the 'model_name' field.
+    Functions can operate on either the grid or the values array.
+    """
+    for func in transform_functions:
+        if 'grid' in func.__code__.co_varnames:
+            # Function expects the full grid
+            grid = func(grid)
+        else:
+            # Function expects just the values array
+            values = np.array(grid[attr])
+            grid[attr] = func(values)
+
+    return grid
+
+
+# pyvista_struct = transform_xy_to_z_propagation(pyvista_struct, z_factor=0.3, noise_level=0.1)
+def transform_subtract_mean(values):
+    """
+    Subtract the mean of the array from each element.
+    """
+    return values - np.mean(values)
+
+
+def transform_scale(values, scale_factor=0.003):
+    """
+    Multiply each value by scale_factor.
+    """
+    return values * scale_factor
+
+
+
+
+def update_extent(pyvista_grid, new_extent):
+    # new_extent: array-like with 6 elements [xmin, xmax, ymin, ymax, zmin, zmax]
+    old_bounds = np.array(pyvista_grid.bounds)  # [xmin, xmax, ymin, ymax, zmin, zmax]
+
+    # Check for valid extents
+    if any(new_extent[i] >= new_extent[i + 1] for i in range(0, 6, 2)):
+        raise ValueError("Each min value must be less than the corresponding max value in the new extent.")
+
+    # Compute old ranges and new ranges for each axis
+    old_ranges = old_bounds[1::2] - old_bounds[0::2]  # [x_range, y_range, z_range]
+    new_ranges = np.array([new_extent[1] - new_extent[0],
+                           new_extent[3] - new_extent[2],
+                           new_extent[5] - new_extent[4]])
+
+    # Avoid division by zero if any old range is zero
+    if np.any(old_ranges == 0):
+        raise ValueError("One of the dimensions in the current grid has zero length.")
+
+    # Get the old points and reshape for easier manipulation
+    old_points = pyvista_grid.points  # shape (N, 3)
+
+    # Compute normalized coordinates within the old extent
+    norm_points = (old_points - old_bounds[0::2]) / old_ranges
+
+    # Compute new points based on new extent
+    new_mins = np.array([new_extent[0], new_extent[2], new_extent[4]])
+    new_points = new_mins + norm_points * new_ranges
+
+    # Update the grid's points
+    pyvista_grid.points = new_points
+
+    # Updating bounds is implicit once the points are modified.
+    pyvista_grid.Modified()
+    return pyvista_grid

subsurface/modules/visualization/__init__.py

@@ -1,2 +1,2 @@
-from .to_pyvista import *
-from .to_pyvista import init_plotter
+from .to_pyvista import *
+from .to_pyvista import init_plotter