cc-mapping 0.1.0__tar.gz → 0.2.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (26) hide show
  1. cc_mapping-0.2.0/LICENSE +28 -0
  2. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/PKG-INFO +7 -3
  3. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/pyproject.toml +18 -3
  4. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/__init__.py +1 -1
  5. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/core.py +22 -35
  6. cc_mapping-0.2.0/src/cc_mapping/feature_selection/__init__.py +92 -0
  7. cc_mapping-0.2.0/src/cc_mapping/feature_selection/_base.py +291 -0
  8. cc_mapping-0.2.0/src/cc_mapping/feature_selection/_persistence.py +231 -0
  9. cc_mapping-0.2.0/src/cc_mapping/feature_selection/_plotting.py +191 -0
  10. cc_mapping-0.2.0/src/cc_mapping/feature_selection/_preprocessing.py +334 -0
  11. cc_mapping-0.2.0/src/cc_mapping/feature_selection/_random_forest.py +540 -0
  12. cc_mapping-0.2.0/src/cc_mapping/feature_selection/_training.py +149 -0
  13. cc_mapping-0.2.0/src/cc_mapping/manifold.py +504 -0
  14. cc_mapping-0.2.0/src/cc_mapping/plot.py +560 -0
  15. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/preprocess.py +29 -8
  16. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/thresholding/__init__.py +1 -1
  17. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/thresholding/base.py +320 -243
  18. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/thresholding/single.py +348 -147
  19. cc_mapping-0.1.0/LICENSE +0 -19
  20. cc_mapping-0.1.0/src/cc_mapping/manifold.py +0 -314
  21. cc_mapping-0.1.0/src/cc_mapping/plot.py +0 -495
  22. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/README.md +0 -0
  23. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/pseudotime.py +0 -0
  24. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/thresholding/sequential.py +0 -0
  25. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/utils.py +0 -0
  26. {cc_mapping-0.1.0 → cc_mapping-0.2.0}/src/cc_mapping/utils_v0.py +0 -0
@@ -0,0 +1,28 @@
1
+ BSD 3-Clause License
2
+
3
+ Copyright (c) 2025, StallaertLab
4
+
5
+ Redistribution and use in source and binary forms, with or without
6
+ modification, are permitted provided that the following conditions are met:
7
+
8
+ 1. Redistributions of source code must retain the above copyright notice, this
9
+ list of conditions and the following disclaimer.
10
+
11
+ 2. Redistributions in binary form must reproduce the above copyright notice,
12
+ this list of conditions and the following disclaimer in the documentation
13
+ and/or other materials provided with the distribution.
14
+
15
+ 3. Neither the name of the copyright holder nor the names of its
16
+ contributors may be used to endorse or promote products derived from
17
+ this software without specific prior written permission.
18
+
19
+ THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
20
+ AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21
+ IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
22
+ DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
23
+ FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24
+ DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
25
+ SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
26
+ CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
27
+ OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28
+ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@@ -1,30 +1,34 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: cc-mapping
3
- Version: 0.1.0
3
+ Version: 0.2.0
4
4
  Summary: Gaussian Mixture Model-based thresholding for single-cell gene expression analysis
5
5
  Home-page: https://github.com/StallaertLab/cc_mapping
6
- License: MIT
6
+ License: BSD-3-Clause
7
7
  Keywords: single-cell,gaussian-mixture-model,thresholding,gene-expression,cell-cycle,anndata,bioinformatics,computational-biology
8
8
  Author: ddpoe
9
9
  Author-email: dap182@pitt.edu
10
10
  Requires-Python: >=3.10,<4.0
11
11
  Classifier: Development Status :: 4 - Beta
12
12
  Classifier: Intended Audience :: Science/Research
13
- Classifier: License :: OSI Approved :: MIT License
13
+ Classifier: License :: OSI Approved :: BSD License
14
14
  Classifier: Programming Language :: Python :: 3
15
15
  Classifier: Programming Language :: Python :: 3.10
16
16
  Classifier: Programming Language :: Python :: 3.11
17
17
  Classifier: Programming Language :: Python :: 3.12
18
18
  Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
19
+ Provides-Extra: manifold
19
20
  Requires-Dist: anndata (>=0.10.0,<0.11.0)
20
21
  Requires-Dist: kneed (>=0.8.5,<0.9.0)
21
22
  Requires-Dist: matplotlib (>=3.7.0,<4.0.0)
22
23
  Requires-Dist: mpl-scatter-density (>=0.8,<0.9)
23
24
  Requires-Dist: numpy (>=1.24.0)
24
25
  Requires-Dist: pandas (>=2.0.0,<3.0.0)
26
+ Requires-Dist: phate (>=1.0.0,<2.0.0) ; extra == "manifold"
25
27
  Requires-Dist: pydantic (>=2.10.0,<3.0.0)
26
28
  Requires-Dist: scikit-learn (>=1.3.0,<2.0.0)
27
29
  Requires-Dist: scipy (>=1.11.0,<2.0.0)
30
+ Requires-Dist: skops (>=0.13.0,<0.14.0)
31
+ Requires-Dist: tqdm (>=4.67.1,<5.0.0)
28
32
  Project-URL: Documentation, https://cc-mapping.readthedocs.io
29
33
  Project-URL: Repository, https://github.com/StallaertLab/cc_mapping
30
34
  Description-Content-Type: text/markdown
@@ -1,11 +1,11 @@
1
1
  [tool.poetry]
2
2
  name = "cc-mapping"
3
- version = "0.1.0"
3
+ version = "0.2.0"
4
4
  description = "Gaussian Mixture Model-based thresholding for single-cell gene expression analysis"
5
5
  authors = ["ddpoe <dap182@pitt.edu>"]
6
6
  readme = "README.md"
7
7
  packages = [{include = "cc_mapping", from = "src"}]
8
- license = "MIT"
8
+ license = "BSD-3-Clause"
9
9
  homepage = "https://github.com/StallaertLab/cc_mapping"
10
10
  repository = "https://github.com/StallaertLab/cc_mapping"
11
11
  documentation = "https://cc-mapping.readthedocs.io"
@@ -23,7 +23,7 @@ classifiers = [
23
23
  "Development Status :: 4 - Beta",
24
24
  "Intended Audience :: Science/Research",
25
25
  "Topic :: Scientific/Engineering :: Bio-Informatics",
26
- "License :: OSI Approved :: MIT License",
26
+ "License :: OSI Approved :: BSD License",
27
27
  "Programming Language :: Python :: 3",
28
28
  "Programming Language :: Python :: 3.10",
29
29
  "Programming Language :: Python :: 3.11",
@@ -41,6 +41,12 @@ anndata = "^0.10.0"
41
41
  pydantic = "^2.10.0"
42
42
  kneed = "^0.8.5"
43
43
  mpl-scatter-density = "^0.8"
44
+ tqdm = "^4.67.1"
45
+ skops = {version = "^0.13.0", optional = true}
46
+ phate = {version = "^1.0.0", optional = true}
47
+
48
+ [tool.poetry.extras]
49
+ manifold = ["phate"]
44
50
 
45
51
  [tool.poetry.group.test.dependencies]
46
52
  pytest = "^8.3.5"
@@ -63,6 +69,15 @@ pydata-sphinx-theme = "^0.16.1"
63
69
  numpydoc = "^1.9.0"
64
70
  myst-nb = "^1.3.0"
65
71
 
72
+
73
+ [tool.poetry.group.dev.dependencies]
74
+ pre-commit = "^4.5.1"
75
+
76
+ [tool.mypy]
77
+ explicit_package_bases = true
78
+ mypy_path = "src"
79
+ ignore_missing_imports = true
80
+
66
81
  [tool.pytest.ini_options]
67
82
  testpaths = ["tests"]
68
83
 
@@ -20,4 +20,4 @@ __all__ = [
20
20
  "create_boolean_label_combination",
21
21
  ]
22
22
 
23
- __version__ = "0.1.0"
23
+ __version__ = "0.2.0"
@@ -1,30 +1,21 @@
1
1
  from typing import Optional
2
- from collections import OrderedDict
3
2
  import warnings
3
+
4
4
  warnings.simplefilter(action="ignore", category=FutureWarning)
5
5
 
6
- import numpy as np
7
- np.seterr(all="ignore")
6
+ import numpy as np # noqa: E402
8
7
 
9
- import re
10
- import anndata as ad
11
- from scipy import stats as st
12
- from tqdm import tqdm
8
+ np.seterr(all="ignore")
13
9
 
14
- import matplotlib
15
- import matplotlib.pyplot as plt
16
- import matplotlib.patches as mpatches
17
- from matplotlib import cm
10
+ import re # noqa: E402
11
+ import anndata as ad # noqa: E402
12
+ from tqdm import tqdm # noqa: E402
18
13
 
19
- from sklearn.svm import SVC
20
- from sklearn.mixture import GaussianMixture
21
- from sklearn import metrics
22
- from sklearn.preprocessing import LabelEncoder
23
- from sklearn.model_selection import train_test_split
24
- from sklearn.ensemble import RandomForestClassifier
14
+ import matplotlib.pyplot as plt # noqa: E402
25
15
 
26
- from .utils import get_str_idx
27
- from .preprocess import row_data_partitioning
16
+ from sklearn import metrics # noqa: E402
17
+ from sklearn.model_selection import train_test_split # noqa: E402
18
+ from sklearn.ensemble import RandomForestClassifier # noqa: E402
28
19
 
29
20
 
30
21
  def train_random_forest_model(
@@ -63,7 +54,9 @@ def train_random_forest_model(
63
54
  accuracy = metrics.accuracy_score(test_labels, rf_pred_labels)
64
55
 
65
56
  if verbose:
66
- print(f"Classification Report for RF model trained with {feature_set_description} feature set")
57
+ print(
58
+ f"Classification Report for RF model trained with {feature_set_description} feature set"
59
+ )
67
60
  print("##################################################################")
68
61
  print()
69
62
  print(metrics.classification_report(test_labels, rf_pred_labels))
@@ -119,7 +112,7 @@ def random_forest_feature_selection(
119
112
  verbose: bool = True,
120
113
  save_path: str = None,
121
114
  cutoff_method: str = "increment",
122
- train_test_split_params: Optional[dict]= None,
115
+ train_test_split_params: Optional[dict] = None,
123
116
  rf_params: Optional[dict] = None,
124
117
  ) -> ad.AnnData:
125
118
  """
@@ -148,7 +141,8 @@ def random_forest_feature_selection(
148
141
  """
149
142
 
150
143
  if rf_params is None:
151
- rf_params = { "min_samples_leaf": 50,
144
+ rf_params = {
145
+ "min_samples_leaf": 50,
152
146
  "n_estimators": 150,
153
147
  "bootstrap": True,
154
148
  "oob_score": True,
@@ -161,14 +155,14 @@ def random_forest_feature_selection(
161
155
  feature_set_name = f"{method}_feature_set"
162
156
 
163
157
  # Get the indices of the features in the training feature set
164
- feature_set_idxs, _ = get_str_idx(training_feature_set, adata.var_names.values)
158
+ feature_set_idxs = np.where(np.isin(adata.var_names.values, training_feature_set))[
159
+ 0
160
+ ]
165
161
 
166
162
  # remove the nan values from the feature set
167
163
  # TODO: I need to make this more generalizable because there are other forms of nan in the data
168
- try:
169
- phase_nan_idx, _ = get_str_idx("nan", adata.obs[training_labels])
170
- except KeyError:
171
- phase_nan_idx = []
164
+ phase_nan_mask = adata.obs[training_labels].astype(str) == "nan"
165
+ phase_nan_idx = np.where(phase_nan_mask)[0]
172
166
 
173
167
  # isolates the feature set from the adata object
174
168
  feature_set = adata.X[:, feature_set_idxs].copy()
@@ -208,7 +202,6 @@ def random_forest_feature_selection(
208
202
  optimum_random_forest_feature_set = sorted_feature_set[:optim_feat_num]
209
203
 
210
204
  elif method == "RF_min_max":
211
-
212
205
  counter = 0
213
206
  max_acc_arg = 0
214
207
  acc_list = [0]
@@ -218,7 +211,6 @@ def random_forest_feature_selection(
218
211
  desc=f"Training RF model iteratively using most important RF features until {stable_counter} stable iterations",
219
212
  disable=not verbose,
220
213
  ):
221
-
222
214
  if counter > stable_counter:
223
215
  break
224
216
 
@@ -247,7 +239,6 @@ def random_forest_feature_selection(
247
239
  # and the number of features is greater than 1 (to avoid the 0th index in the accuracy list)
248
240
  # elif acc_difference > threshold and num_feats > 1:
249
241
  elif acc_difference > threshold:
250
-
251
242
  # if the cuttoff method is jump, then if the difference is greater than the threshold,
252
243
  # then set the maximum accuracy argument to the current number of features and reset counter
253
244
  if cutoff_method == "jump":
@@ -258,7 +249,6 @@ def random_forest_feature_selection(
258
249
  # then the optimal number of features is increased by 1 and the check occurs again until the condition is not met
259
250
  # when the acc_diccerece is less than the threshold, the counter also decreased by 1
260
251
  elif cutoff_method == "increment":
261
-
262
252
  temp_max_acc_arg, temp_counter = max_acc_arg, counter
263
253
  for _ in range(stable_counter):
264
254
  temp_max_acc_arg, temp_counter, continue_bool = (
@@ -310,9 +300,7 @@ def random_forest_feature_selection(
310
300
  print(optimum_random_forest_feature_set)
311
301
 
312
302
  # converts the optimal feature set to a boolean array
313
- feat_idxs, _ = get_str_idx(optimum_random_forest_feature_set, adata.var_names.values)
314
- fs_bool = np.repeat(False, adata.shape[1])
315
- fs_bool[feat_idxs] = True
303
+ fs_bool = np.isin(adata.var_names.values, optimum_random_forest_feature_set)
316
304
 
317
305
  adata.var[feature_set_name] = fs_bool
318
306
 
@@ -357,4 +345,3 @@ def random_forest_feature_selection(
357
345
  plt.close()
358
346
 
359
347
  return adata
360
-
@@ -0,0 +1,92 @@
1
+ """
2
+ Feature selection methods for cell cycle mapping.
3
+
4
+ This module provides modular, scikit-learn-style feature selectors
5
+ for identifying informative features from high-dimensional cell data.
6
+
7
+ Classes
8
+ -------
9
+ FeatureSelector
10
+ Abstract base class for all feature selectors.
11
+ RFTopNSelector
12
+ Select top N features by Random Forest importance.
13
+ RFMinMaxSelector
14
+ Find minimum features that maximize classification accuracy.
15
+
16
+ Functions
17
+ ---------
18
+ prepare_feature_matrix
19
+ Extract and validate feature matrix from AnnData.
20
+ validate_data
21
+ Validate data is ready for feature selection.
22
+
23
+ Data Classes
24
+ ------------
25
+ SelectionResult
26
+ Container for feature selection results.
27
+ PreparedData
28
+ Container for prepared feature matrix and metadata.
29
+
30
+ Examples
31
+ --------
32
+ Basic usage with numpy arrays:
33
+
34
+ >>> from cc_mapping.feature_selection import RFMinMaxSelector, validate_data
35
+ >>>
36
+ >>> validate_data(X, y, feature_names) # Check for NaN/inf
37
+ >>> selector = RFMinMaxSelector(threshold=0.01)
38
+ >>> selector.fit(X, y, feature_names)
39
+ >>>
40
+ >>> print(f"Selected {selector.results.n_features_selected} features")
41
+ >>> mask = selector.get_support()
42
+
43
+ Usage with AnnData:
44
+
45
+ >>> from cc_mapping.feature_selection import prepare_feature_matrix, RFTopNSelector
46
+ >>>
47
+ >>> prepared = prepare_feature_matrix(
48
+ ... adata,
49
+ ... feature_set="intensity_features",
50
+ ... labels="cell_cycle_phase",
51
+ ... )
52
+ >>>
53
+ >>> selector = RFTopNSelector(n_features=30)
54
+ >>> selector.fit(prepared.X, prepared.y, prepared.feature_names)
55
+ >>>
56
+ >>> # Add selection to adata
57
+ >>> adata = selector.transform_adata(adata, var_key="selected_features")
58
+
59
+ Saving and loading:
60
+
61
+ >>> selector.save("my_selector.skops")
62
+ >>> loaded = RFMinMaxSelector.load("my_selector.skops")
63
+ """
64
+
65
+ from ._base import FeatureSelector, SelectionResult
66
+ from ._preprocessing import (
67
+ prepare_feature_matrix,
68
+ validate_data,
69
+ PreparedData,
70
+ )
71
+ from ._random_forest import RFTopNSelector, RFMinMaxSelector
72
+ from ._plotting import plot_accuracy_curve, plot_feature_importances
73
+ from ._training import train_rf_model, TrainingResult
74
+
75
+ __all__ = [
76
+ # Base classes
77
+ "FeatureSelector",
78
+ "SelectionResult",
79
+ # Preprocessing
80
+ "prepare_feature_matrix",
81
+ "validate_data",
82
+ "PreparedData",
83
+ # Selectors
84
+ "RFTopNSelector",
85
+ "RFMinMaxSelector",
86
+ # Plotting
87
+ "plot_accuracy_curve",
88
+ "plot_feature_importances",
89
+ # Training utilities
90
+ "train_rf_model",
91
+ "TrainingResult",
92
+ ]
@@ -0,0 +1,291 @@
1
+ """
2
+ Base classes and data structures for feature selection.
3
+ """
4
+
5
+ from __future__ import annotations
6
+
7
+ from abc import ABC, abstractmethod
8
+ from dataclasses import dataclass, field
9
+ from pathlib import Path
10
+ from typing import Any, TYPE_CHECKING
11
+
12
+ import anndata as ad
13
+ import numpy as np
14
+
15
+ if TYPE_CHECKING:
16
+ from typing_extensions import Self
17
+
18
+
19
+ @dataclass
20
+ class SelectionResult:
21
+ """
22
+ Container for feature selection results.
23
+
24
+ Attributes
25
+ ----------
26
+ selected_features : np.ndarray
27
+ Names of selected features, sorted by importance.
28
+ feature_importances : np.ndarray
29
+ Importance scores for selected features (same order as selected_features).
30
+ n_features_selected : int
31
+ Number of features selected.
32
+ metadata : dict
33
+ Method-specific metadata (e.g., accuracy curve for RF methods).
34
+ """
35
+ selected_features: np.ndarray
36
+ feature_importances: np.ndarray
37
+ n_features_selected: int
38
+ metadata: dict = field(default_factory=dict)
39
+
40
+ def __repr__(self) -> str:
41
+ return (
42
+ f"SelectionResult(n_features={self.n_features_selected}, "
43
+ f"top_features={list(self.selected_features[:3])}...)"
44
+ )
45
+
46
+
47
+ class FeatureSelector(ABC):
48
+ """
49
+ Abstract base class for feature selection methods.
50
+
51
+ All feature selectors should inherit from this class and implement
52
+ the required abstract methods.
53
+
54
+ Attributes
55
+ ----------
56
+ model_ : Any
57
+ The fitted model (e.g., RandomForestClassifier). Available after fit().
58
+ results_ : SelectionResult
59
+ Detailed selection results. Available after fit().
60
+ feature_names_ : np.ndarray
61
+ Feature names used during fitting. Available after fit().
62
+ is_fitted_ : bool
63
+ Whether the selector has been fitted.
64
+ """
65
+
66
+ model_: Any = None
67
+ results_: SelectionResult | None = None
68
+ feature_names_: np.ndarray | None = None
69
+ is_fitted_: bool = False
70
+
71
+ @abstractmethod
72
+ def fit(
73
+ self,
74
+ X: np.ndarray,
75
+ y: np.ndarray,
76
+ feature_names: np.ndarray
77
+ ) -> Self:
78
+ """
79
+ Fit the feature selector to the data.
80
+
81
+ Parameters
82
+ ----------
83
+ X : np.ndarray
84
+ Feature matrix of shape (n_samples, n_features).
85
+ y : np.ndarray
86
+ Target labels of shape (n_samples,).
87
+ feature_names : np.ndarray
88
+ Names of features corresponding to columns in X.
89
+
90
+ Returns
91
+ -------
92
+ Self
93
+ The fitted selector instance (for method chaining).
94
+ """
95
+ ...
96
+
97
+ def get_support(self, indices: bool = False) -> np.ndarray:
98
+ """
99
+ Get a mask or indices of selected features.
100
+
101
+ Parameters
102
+ ----------
103
+ indices : bool, default=False
104
+ If True, return indices instead of boolean mask.
105
+
106
+ Returns
107
+ -------
108
+ np.ndarray
109
+ Boolean mask of shape (n_features,) or integer indices.
110
+
111
+ Raises
112
+ ------
113
+ RuntimeError
114
+ If selector has not been fitted.
115
+ """
116
+ self._check_is_fitted()
117
+
118
+ # Create boolean mask based on selected features
119
+ mask = np.isin(self.feature_names_, self.results_.selected_features)
120
+
121
+ if indices:
122
+ return np.where(mask)[0]
123
+ return mask
124
+
125
+ def get_feature_names_out(self) -> np.ndarray:
126
+ """
127
+ Get names of selected features.
128
+
129
+ Returns
130
+ -------
131
+ np.ndarray
132
+ Array of selected feature names.
133
+
134
+ Raises
135
+ ------
136
+ RuntimeError
137
+ If selector has not been fitted.
138
+ """
139
+ self._check_is_fitted()
140
+ return self.results_.selected_features.copy()
141
+
142
+ @property
143
+ def results(self) -> SelectionResult:
144
+ """
145
+ Get the selection results.
146
+
147
+ Returns
148
+ -------
149
+ SelectionResult
150
+ Detailed results from feature selection.
151
+
152
+ Raises
153
+ ------
154
+ RuntimeError
155
+ If selector has not been fitted.
156
+ """
157
+ self._check_is_fitted()
158
+ return self.results_
159
+
160
+ def fit_adata(
161
+ self,
162
+ adata: ad.AnnData,
163
+ feature_set_key: str | list[str],
164
+ label_key: str,
165
+ drop_na: bool = True,
166
+ drop_inf: bool = True,
167
+ ) -> Self:
168
+ """
169
+ Convenience method to fit directly from AnnData object.
170
+
171
+ Parameters
172
+ ----------
173
+ adata : ad.AnnData
174
+ AnnData object containing the data.
175
+ feature_set_key : str or list[str]
176
+ Either a key in adata.var that marks features (boolean column),
177
+ or a list of feature names.
178
+ label_key : str
179
+ Key in adata.obs containing target labels.
180
+ drop_na : bool, default=True
181
+ Whether to drop rows with NaN values.
182
+ drop_inf : bool, default=True
183
+ Whether to drop rows with infinite values.
184
+
185
+ Returns
186
+ -------
187
+ Self
188
+ The fitted selector instance.
189
+ """
190
+ # Import here to avoid circular imports
191
+ from ._preprocessing import prepare_feature_matrix
192
+
193
+ prepared = prepare_feature_matrix(
194
+ adata=adata,
195
+ feature_set=feature_set_key,
196
+ labels=label_key,
197
+ drop_na=drop_na,
198
+ drop_inf=drop_inf,
199
+ verbose=getattr(self, 'verbose', True),
200
+ )
201
+
202
+ return self.fit(prepared.X, prepared.y, prepared.feature_names)
203
+
204
+ def transform_adata(
205
+ self,
206
+ adata: ad.AnnData,
207
+ var_key: str = "selected_features",
208
+ ) -> ad.AnnData:
209
+ """
210
+ Add selection mask to adata.var.
211
+
212
+ Parameters
213
+ ----------
214
+ adata : ad.AnnData
215
+ AnnData object to modify.
216
+ var_key : str, default="selected_features"
217
+ Key to use in adata.var for the selection mask.
218
+
219
+ Returns
220
+ -------
221
+ ad.AnnData
222
+ Modified AnnData object with selection mask in .var.
223
+
224
+ Raises
225
+ ------
226
+ RuntimeError
227
+ If selector has not been fitted.
228
+ """
229
+ self._check_is_fitted()
230
+
231
+ # Create boolean mask for all features in adata
232
+ mask = np.isin(adata.var_names.values, self.results_.selected_features)
233
+ adata.var[var_key] = mask
234
+
235
+ return adata
236
+
237
+ def save(self, path: str | Path) -> None:
238
+ """
239
+ Save the fitted selector to disk using skops.
240
+
241
+ Parameters
242
+ ----------
243
+ path : str or Path
244
+ File path to save to.
245
+
246
+ Raises
247
+ ------
248
+ RuntimeError
249
+ If selector has not been fitted.
250
+ """
251
+ self._check_is_fitted()
252
+ from ._persistence import save_selector
253
+ save_selector(self, path)
254
+
255
+ @classmethod
256
+ def load(cls, path: str | Path) -> Self:
257
+ """
258
+ Load a fitted selector from disk.
259
+
260
+ Parameters
261
+ ----------
262
+ path : str or Path
263
+ File path to load from.
264
+
265
+ Returns
266
+ -------
267
+ Self
268
+ The loaded selector instance.
269
+ """
270
+ from ._persistence import load_selector
271
+ return load_selector(path)
272
+
273
+ @abstractmethod
274
+ def get_params(self) -> dict:
275
+ """
276
+ Get hyperparameters of this selector.
277
+
278
+ Returns
279
+ -------
280
+ dict
281
+ Dictionary of hyperparameter names and values.
282
+ """
283
+ ...
284
+
285
+ def _check_is_fitted(self) -> None:
286
+ """Raise error if selector is not fitted."""
287
+ if not self.is_fitted_:
288
+ raise RuntimeError(
289
+ f"{self.__class__.__name__} has not been fitted. "
290
+ "Call fit() or fit_adata() first."
291
+ )