Make all imputation methods consistent in regard to encoding requirem…

…ents (#827)

* Before test

* After tests

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Apply suggestions from code review part 1

Co-authored-by: Lukas Heumos <lukas.heumos@posteo.net>

* @nicolassidoux
@Zethson
Apply suggestions from code review part 2

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Updated _base_check_imputation to throw exception

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Added spinner support

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* After @eroell review

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Changed spinner to Rich

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fixed missing import

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* After @eroell review

* Updated returns in imputation, rewrote miss_forest_impute

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fixed imputation returns

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Lukas Heumos <lukas.heumos@posteo.net>
Co-authored-by: PRECIPOINT\nicolas.sidoux <nicolas.sidoux@precipoint.de>

ehrapy/_settings.py

@@ -53,7 +53,7 @@ def __init__(
         figdir: str | Path = "./figures/",
         cache_compression: str | None = "lzf",
         max_memory=15,
-        n_jobs: int = 1,
+        n_jobs: int = -1,
         logfile: str | Path | None = None,
         categories_to_ignore: Iterable[str] = ("N/A", "dontknow", "no_gate", "?"),
         _frameon: bool = True,

ehrapy/core/_tool_available.py → ehrapy/_utils_available.py

@@ -4,7 +4,7 @@
 from subprocess import PIPE, Popen
 
 
-def _check_module_importable(package: str) -> bool:  # pragma: no cover
+def _check_module_importable(package: str) -> bool:
     """Checks whether a module is installed and can be loaded.
 
     Args:
@@ -19,7 +19,7 @@ def _check_module_importable(package: str) -> bool:  # pragma: no cover
     return module_available
 
 
-def _shell_command_accessible(command: list[str]) -> bool:  # pragma: no cover
+def _shell_command_accessible(command: list[str]) -> bool:
     """Checks whether the provided command is accessible in the current shell.
 
     Args:
@@ -29,7 +29,7 @@ def _shell_command_accessible(command: list[str]) -> bool:  # pragma: no cover
         True if the command is accessible, False otherwise.
     """
     command_accessible = Popen(command, stdout=PIPE, stderr=PIPE, universal_newlines=True, shell=True)
-    (commmand_stdout, command_stderr) = command_accessible.communicate()
+    command_accessible.communicate()
     if command_accessible.returncode != 0:
         return False
 

ehrapy/_utils_rendering.py

@@ -0,0 +1,21 @@
+import functools
+
+from rich.progress import Progress, SpinnerColumn
+
+
+def spinner(message: str = "Running task"):
+    def wrap(func):
+        @functools.wraps(func)
+        def wrapped_f(*args, **kwargs):
+            with Progress(
+                "[progress.description]{task.description}",
+                SpinnerColumn(),
+                refresh_per_second=1500,
+            ) as progress:
+                progress.add_task(f"[blue]{message}", total=1)
+                result = func(*args, **kwargs)
+            return result
+
+        return wrapped_f
+
+    return wrap

ehrapy/anndata/anndata_ext.py

@@ -3,7 +3,7 @@
 import random
 from collections import OrderedDict
 from string import ascii_letters
-from typing import TYPE_CHECKING, NamedTuple
+from typing import TYPE_CHECKING, Any, NamedTuple
 
 import numpy as np
 import pandas as pd
@@ -303,7 +303,7 @@ def move_to_x(adata: AnnData, to_x: list[str] | str) -> AnnData:
     return new_adata
 
 
-def _get_column_indices(adata: AnnData, col_names: str | Iterable[str]) -> list[int]:
+def get_column_indices(adata: AnnData, col_names: str | Iterable[str]) -> list[int]:
     """Fetches the column indices in X for a given list of column names
 
     Args:
@@ -383,7 +383,7 @@ def set_numeric_vars(
     if copy:
         adata = adata.copy()
 
-    vars_idx = _get_column_indices(adata, vars)
+    vars_idx = get_column_indices(adata, vars)
 
     adata.X[:, vars_idx] = values
 
@@ -663,3 +663,49 @@ def get_rank_features_df(
 
 class NotEncodedError(AssertionError):
     pass
+
+
+def _are_ndarrays_equal(arr1: np.ndarray, arr2: np.ndarray) -> np.bool_:
+    """Check if two arrays are equal member-wise.
+
+    Note: Two NaN are considered equal.
+
+    Args:
+        arr1: First array to compare
+        arr2: Second array to compare
+
+    Returns:
+        True if the two arrays are equal member-wise
+    """
+    return np.all(np.equal(arr1, arr2, dtype=object) | ((arr1 != arr1) & (arr2 != arr2)))
+
+
+def _is_val_missing(data: np.ndarray) -> np.ndarray[Any, np.dtype[np.bool_]]:
+    """Check if values in a AnnData matrix are missing.
+
+    Args:
+        data: The AnnData matrix to check
+
+    Returns:
+        An array of bool representing the missingness of the original data, with the same shape
+    """
+    return np.isin(data, [None, ""]) | (data != data)
+
+
+def _to_dense_matrix(adata: AnnData, layer: str | None = None) -> np.ndarray:  # pragma: no cover
+    """Extract a layer from an AnnData object and convert it to a dense matrix if required.
+
+    Args:
+        adata: The AnnData where to extract the layer from.
+        layer: Name of the layer to extract. If omitted, X is considered.
+
+    Returns:
+        The layer as a dense matrix. If a conversion was required, this function returns a copy of the original layer,
+        othersize this function returns a reference.
+    """
+    from scipy.sparse import issparse
+
+    if layer is None:
+        return adata.X.toarray() if issparse(adata.X) else adata.X
+    else:
+        return adata.layers[layer].toarray() if issparse(adata.layers[layer]) else adata.layers[layer]

ehrapy/plot/_scanpy_pl_api.py

@@ -9,7 +9,7 @@
 import scanpy as sc
 from scanpy.plotting import DotPlot, MatrixPlot, StackedViolin
 
-from ehrapy._doc_util import (
+from ehrapy._utils_doc import (
     _doc_params,
     doc_adata_color_etc,
     doc_common_groupby_plot_args,