-
Notifications
You must be signed in to change notification settings - Fork 8
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #416 from GispoCoding/415-coda-fixes
415 coda fixes
- Loading branch information
Showing
9 changed files
with
667 additions
and
695 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,88 +1,88 @@ | ||
| from numbers import Number | ||
|
|
||
| import numpy as np | ||
| import pandas as pd | ||
| from beartype import beartype | ||
| from beartype.typing import Optional, Sequence | ||
|
|
||
| from eis_toolkit.exceptions import InvalidColumnException, NumericValueSignException | ||
| from eis_toolkit.utilities.aitchison_geometry import _closure | ||
| from eis_toolkit.utilities.checks.compositional import check_in_simplex_sample_space | ||
| from eis_toolkit.utilities.miscellaneous import rename_columns_by_pattern | ||
|
|
||
|
|
||
| @beartype | ||
| def _alr_transform(df: pd.DataFrame, columns: Sequence[str], denominator_column: str) -> pd.DataFrame: | ||
|
|
||
| ratios = df[columns].div(df[denominator_column], axis=0) | ||
| return np.log(ratios) | ||
|
|
||
|
|
||
| @beartype | ||
| def alr_transform( | ||
| df: pd.DataFrame, column: Optional[str] = None, keep_denominator_column: bool = False | ||
| ) -> pd.DataFrame: | ||
| """ | ||
| Perform an additive logratio transformation on the data. | ||
| Args: | ||
| df: A dataframe of compositional data. | ||
| column: The name of the column to be used as the denominator column. | ||
| keep_denominator_column: Whether to include the denominator column in the result. If True, the returned | ||
| dataframe retains its original shape. | ||
| Returns: | ||
| A new dataframe containing the ALR transformed data. | ||
| Raises: | ||
| InvalidColumnException: The input column isn't found in the dataframe. | ||
| InvalidCompositionException: Data is not normalized to the expected value. | ||
| NumericValueSignException: Data contains zeros or negative values. | ||
| """ | ||
| check_in_simplex_sample_space(df) | ||
|
|
||
| if column is not None and column not in df.columns: | ||
| raise InvalidColumnException(f"The column {column} was not found in the dataframe.") | ||
|
|
||
| column = column if column is not None else df.columns[-1] | ||
|
|
||
| columns = [col for col in df.columns] | ||
|
|
||
| if not keep_denominator_column and column in columns: | ||
| columns.remove(column) | ||
|
|
||
| return rename_columns_by_pattern(_alr_transform(df, columns, column)) | ||
|
|
||
|
|
||
| @beartype | ||
| def _inverse_alr(df: pd.DataFrame, denominator_column: str, scale: Number = 1.0) -> pd.DataFrame: | ||
| dfc = df.copy() | ||
|
|
||
| if denominator_column not in dfc.columns.values: | ||
| # Add the denominator column | ||
| dfc[denominator_column] = 0.0 | ||
|
|
||
| return _closure(np.exp(dfc), scale) | ||
|
|
||
|
|
||
| @beartype | ||
| def inverse_alr(df: pd.DataFrame, denominator_column: str, scale: Number = 1.0) -> pd.DataFrame: | ||
| """ | ||
| Perform the inverse transformation for a set of ALR transformed data. | ||
| Args: | ||
| df: A dataframe of ALR transformed compositional data. | ||
| denominator_column: The name of the denominator column. | ||
| scale: The value to which each composition should be normalized. Eg., if the composition is expressed | ||
| as percentages, scale=100. | ||
| Returns: | ||
| A dataframe containing the inverse transformed data. | ||
| Raises: | ||
| NumericValueSignException: The input scale value is zero or less. | ||
| """ | ||
| if scale <= 0: | ||
| raise NumericValueSignException("The scale value should be positive.") | ||
|
|
||
| return _inverse_alr(df, denominator_column, scale) | ||
| from numbers import Number | ||
|
|
||
| import numpy as np | ||
| import pandas as pd | ||
| from beartype import beartype | ||
| from beartype.typing import Optional, Sequence | ||
|
|
||
| from eis_toolkit.exceptions import InvalidColumnException, NumericValueSignException | ||
| from eis_toolkit.utilities.aitchison_geometry import _closure | ||
| from eis_toolkit.utilities.checks.compositional import check_compositional_data | ||
| from eis_toolkit.utilities.miscellaneous import rename_columns_by_pattern | ||
|
|
||
|
|
||
| @beartype | ||
| def _alr_transform(df: pd.DataFrame, columns: Sequence[str], denominator_column: str) -> pd.DataFrame: | ||
|
|
||
| ratios = df[columns].div(df[denominator_column], axis=0) | ||
| return np.log(ratios) | ||
|
|
||
|
|
||
| @beartype | ||
| def alr_transform( | ||
| df: pd.DataFrame, column: Optional[str] = None, keep_denominator_column: bool = False | ||
| ) -> pd.DataFrame: | ||
| """ | ||
| Perform an additive logratio transformation on the data. | ||
| Args: | ||
| df: A dataframe of compositional data. | ||
| column: The name of the column to be used as the denominator column. | ||
| keep_denominator_column: Whether to include the denominator column in the result. If True, the returned | ||
| dataframe retains its original shape. | ||
| Returns: | ||
| A new dataframe containing the ALR transformed data. | ||
| Raises: | ||
| InvalidColumnException: The input column isn't found in the dataframe. | ||
| InvalidCompositionException: Data is not normalized to the expected value. | ||
| NumericValueSignException: Data contains zeros or negative values. | ||
| """ | ||
| check_compositional_data(df) | ||
|
|
||
| if column is not None and column not in df.columns: | ||
| raise InvalidColumnException(f"The column {column} was not found in the dataframe.") | ||
|
|
||
| column = column if column is not None else df.columns[-1] | ||
|
|
||
| columns = [col for col in df.columns] | ||
|
|
||
| if not keep_denominator_column and column in columns: | ||
| columns.remove(column) | ||
|
|
||
| return rename_columns_by_pattern(_alr_transform(df, columns, column)) | ||
|
|
||
|
|
||
| @beartype | ||
| def _inverse_alr(df: pd.DataFrame, denominator_column: str, scale: Number = 1.0) -> pd.DataFrame: | ||
| dfc = df.copy() | ||
|
|
||
| if denominator_column not in dfc.columns.values: | ||
| # Add the denominator column | ||
| dfc[denominator_column] = 0.0 | ||
|
|
||
| return _closure(np.exp(dfc), scale) | ||
|
|
||
|
|
||
| @beartype | ||
| def inverse_alr(df: pd.DataFrame, denominator_column: str, scale: Number = 1.0) -> pd.DataFrame: | ||
| """ | ||
| Perform the inverse transformation for a set of ALR transformed data. | ||
| Args: | ||
| df: A dataframe of ALR transformed compositional data. | ||
| denominator_column: The name of the denominator column. | ||
| scale: The value to which each composition should be normalized. Eg., if the composition is expressed | ||
| as percentages, scale=100. | ||
| Returns: | ||
| A dataframe containing the inverse transformed data. | ||
| Raises: | ||
| NumericValueSignException: The input scale value is zero or less. | ||
| """ | ||
| if scale <= 0: | ||
| raise NumericValueSignException("The scale value should be positive.") | ||
|
|
||
| return _inverse_alr(df, denominator_column, scale) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,79 +1,79 @@ | ||
| from numbers import Number | ||
|
|
||
| import numpy as np | ||
| import pandas as pd | ||
| from beartype import beartype | ||
| from beartype.typing import Optional, Sequence | ||
| from scipy.stats import gmean | ||
|
|
||
| from eis_toolkit.exceptions import NumericValueSignException | ||
| from eis_toolkit.utilities.aitchison_geometry import _closure | ||
| from eis_toolkit.utilities.checks.compositional import check_in_simplex_sample_space | ||
| from eis_toolkit.utilities.miscellaneous import rename_columns, rename_columns_by_pattern | ||
|
|
||
|
|
||
| @beartype | ||
| def _centered_ratio(row: pd.Series) -> pd.Series: | ||
|
|
||
| return row / gmean(row) | ||
|
|
||
|
|
||
| @beartype | ||
| def _clr_transform(df: pd.DataFrame) -> pd.DataFrame: | ||
|
|
||
| dfc = df.copy() | ||
| dfc = dfc.apply(_centered_ratio, axis=1) | ||
|
|
||
| return np.log(dfc) | ||
|
|
||
|
|
||
| @beartype | ||
| def clr_transform(df: pd.DataFrame) -> pd.DataFrame: | ||
| """ | ||
| Perform a centered logratio transformation on the data. | ||
| Args: | ||
| df: A dataframe of compositional data. | ||
| Returns: | ||
| A new dataframe containing the CLR transformed data. | ||
| Raises: | ||
| InvalidCompositionException: Data is not normalized to the expected value. | ||
| NumericValueSignException: Data contains zeros or negative values. | ||
| """ | ||
| check_in_simplex_sample_space(df) | ||
| return rename_columns_by_pattern(_clr_transform(df)) | ||
|
|
||
|
|
||
| @beartype | ||
| def _inverse_clr(df: pd.DataFrame, colnames: Optional[Sequence[str]] = None, scale: Number = 1.0) -> pd.DataFrame: | ||
| inverse = _closure(np.exp(df), scale) | ||
|
|
||
| if colnames is not None: | ||
| return rename_columns(inverse, colnames) | ||
|
|
||
| return inverse | ||
|
|
||
|
|
||
| @beartype | ||
| def inverse_clr(df: pd.DataFrame, colnames: Optional[Sequence[str]] = None, scale: Number = 1.0) -> pd.DataFrame: | ||
| """ | ||
| Perform the inverse transformation for a set of CLR transformed data. | ||
| Args: | ||
| df: A dataframe of CLR transformed compositional data. | ||
| colnames: List of column names to rename the columns to. | ||
| scale: The value to which each composition should be normalized. Eg., if the composition is expressed | ||
| as percentages, scale=100. | ||
| Returns: | ||
| A dataframe containing the inverse transformed data. | ||
| Raises: | ||
| NumericValueSignException: The input scale value is zero or less. | ||
| """ | ||
| if scale <= 0: | ||
| raise NumericValueSignException("The scale value should be positive.") | ||
|
|
||
| return _inverse_clr(df, colnames, scale) | ||
| from numbers import Number | ||
|
|
||
| import numpy as np | ||
| import pandas as pd | ||
| from beartype import beartype | ||
| from beartype.typing import Optional, Sequence | ||
| from scipy.stats import gmean | ||
|
|
||
| from eis_toolkit.exceptions import NumericValueSignException | ||
| from eis_toolkit.utilities.aitchison_geometry import _closure | ||
| from eis_toolkit.utilities.checks.compositional import check_compositional_data | ||
| from eis_toolkit.utilities.miscellaneous import rename_columns, rename_columns_by_pattern | ||
|
|
||
|
|
||
| @beartype | ||
| def _centered_ratio(row: pd.Series) -> pd.Series: | ||
|
|
||
| return row / gmean(row) | ||
|
|
||
|
|
||
| @beartype | ||
| def _clr_transform(df: pd.DataFrame) -> pd.DataFrame: | ||
|
|
||
| dfc = df.copy() | ||
| dfc = dfc.apply(_centered_ratio, axis=1) | ||
|
|
||
| return np.log(dfc) | ||
|
|
||
|
|
||
| @beartype | ||
| def clr_transform(df: pd.DataFrame) -> pd.DataFrame: | ||
| """ | ||
| Perform a centered logratio transformation on the data. | ||
| Args: | ||
| df: A dataframe of compositional data. | ||
| Returns: | ||
| A new dataframe containing the CLR transformed data. | ||
| Raises: | ||
| InvalidCompositionException: Data is not normalized to the expected value. | ||
| NumericValueSignException: Data contains zeros or negative values. | ||
| """ | ||
| check_compositional_data(df) | ||
| return rename_columns_by_pattern(_clr_transform(df)) | ||
|
|
||
|
|
||
| @beartype | ||
| def _inverse_clr(df: pd.DataFrame, colnames: Optional[Sequence[str]] = None, scale: Number = 1.0) -> pd.DataFrame: | ||
| inverse = _closure(np.exp(df), scale) | ||
|
|
||
| if colnames is not None: | ||
| return rename_columns(inverse, colnames) | ||
|
|
||
| return inverse | ||
|
|
||
|
|
||
| @beartype | ||
| def inverse_clr(df: pd.DataFrame, colnames: Optional[Sequence[str]] = None, scale: Number = 1.0) -> pd.DataFrame: | ||
| """ | ||
| Perform the inverse transformation for a set of CLR transformed data. | ||
| Args: | ||
| df: A dataframe of CLR transformed compositional data. | ||
| colnames: List of column names to rename the columns to. | ||
| scale: The value to which each composition should be normalized. Eg., if the composition is expressed | ||
| as percentages, scale=100. | ||
| Returns: | ||
| A dataframe containing the inverse transformed data. | ||
| Raises: | ||
| NumericValueSignException: The input scale value is zero or less. | ||
| """ | ||
| if scale <= 0: | ||
| raise NumericValueSignException("The scale value should be positive.") | ||
|
|
||
| return _inverse_clr(df, colnames, scale) |
Oops, something went wrong.