deep-river 0.2.6__tar.gz → 0.2.8__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 (40) hide show
  1. {deep_river-0.2.6 → deep_river-0.2.8}/PKG-INFO +29 -109
  2. {deep_river-0.2.6 → deep_river-0.2.8}/README.md +9 -5
  3. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/__version__.py +1 -1
  4. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/anomaly/__init__.py +1 -5
  5. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/anomaly/ae.py +55 -29
  6. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/anomaly/probability_weighted_ae.py +18 -19
  7. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/anomaly/rolling_ae.py +18 -29
  8. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/anomaly/scaler.py +2 -6
  9. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/base.py +102 -15
  10. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/classification/__init__.py +1 -4
  11. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/classification/classifier.py +95 -149
  12. deep_river-0.2.8/deep_river/classification/rolling_classifier.py +282 -0
  13. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/classification/zoo.py +38 -28
  14. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/regression/multioutput.py +10 -13
  15. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/regression/regressor.py +32 -31
  16. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/regression/rolling_regressor.py +39 -39
  17. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/regression/zoo.py +25 -20
  18. deep_river-0.2.8/deep_river/utils/layer_adaptation.py +239 -0
  19. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/utils/params.py +11 -16
  20. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/utils/tensor_conversion.py +59 -24
  21. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/utils/test_estimators.py +2 -6
  22. deep_river-0.2.8/deep_river/utils/test_layer_adaptation.py +179 -0
  23. deep_river-0.2.8/deep_river/utils/test_tensor_conversion.py +150 -0
  24. deep_river-0.2.8/pyproject.toml +83 -0
  25. deep_river-0.2.6/deep_river/classification/rolling_classifier.py +0 -605
  26. deep_river-0.2.6/deep_river/utils/test_tensor_conversion.py +0 -117
  27. deep_river-0.2.6/deep_river.egg-info/PKG-INFO +0 -289
  28. deep_river-0.2.6/deep_river.egg-info/SOURCES.txt +0 -34
  29. deep_river-0.2.6/deep_river.egg-info/dependency_links.txt +0 -1
  30. deep_river-0.2.6/deep_river.egg-info/requires.txt +0 -101
  31. deep_river-0.2.6/deep_river.egg-info/top_level.txt +0 -1
  32. deep_river-0.2.6/pyproject.toml +0 -63
  33. deep_river-0.2.6/setup.cfg +0 -9
  34. deep_river-0.2.6/setup.py +0 -111
  35. {deep_river-0.2.6 → deep_river-0.2.8}/LICENSE +0 -0
  36. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/__init__.py +0 -0
  37. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/regression/__init__.py +0 -0
  38. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/utils/__init__.py +0 -0
  39. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/utils/estimator_checks.py +0 -0
  40. {deep_river-0.2.6 → deep_river-0.2.8}/deep_river/utils/hooks.py +0 -0
@@ -1,119 +1,34 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: deep_river
3
- Version: 0.2.6
3
+ Version: 0.2.8
4
4
  Summary: Online Deep Learning for river
5
- Home-page: https://online-ml.github.io/deep-river/
5
+ Home-page: https://github.com/online-ml/deep-river
6
+ License: BSD-3-Clause
7
+ Keywords: online-learning,deep-learning,data-streams
6
8
  Author: Cedric Kulbach
7
9
  Author-email: cedric.kulbach@googlemail.com
8
- License: BSD-3
10
+ Requires-Python: >=3.10,<3.13
9
11
  Classifier: License :: OSI Approved :: BSD License
10
12
  Classifier: Programming Language :: Python
11
13
  Classifier: Programming Language :: Python :: 3
12
- Classifier: Programming Language :: Python :: 3.8
13
- Classifier: Programming Language :: Python :: 3.9
14
14
  Classifier: Programming Language :: Python :: 3.10
15
+ Classifier: Programming Language :: Python :: 3.11
16
+ Classifier: Programming Language :: Python :: 3.12
15
17
  Classifier: Programming Language :: Python :: Implementation :: CPython
16
18
  Classifier: Programming Language :: Python :: Implementation :: PyPy
17
- Requires-Python: >=3.6.0
19
+ Requires-Dist: mkdocstrings[python] (>=0.19.0)
20
+ Requires-Dist: numpy (>=1.26.4,<1.27.0)
21
+ Requires-Dist: ordered-set (>=4.1.0,<4.2.0)
22
+ Requires-Dist: pandas (>=2.2.2,<2.3.0)
23
+ Requires-Dist: pytkdocs[numpy-style] (>=0.5.0)
24
+ Requires-Dist: river
25
+ Requires-Dist: scikit-learn (>=1.5.0,<1.6.0)
26
+ Requires-Dist: torch (>=2.2.2,<2.3.0)
27
+ Requires-Dist: torchviz (>=0.0.2,<0.1.0)
28
+ Requires-Dist: tqdm (>=4.66.5,<4.67.0)
29
+ Project-URL: Documentation, https://github.com/online-ml/deep-river
30
+ Project-URL: Repository, https://github.com/online-ml/deep-river
18
31
  Description-Content-Type: text/markdown
19
- License-File: LICENSE
20
- Requires-Dist: scikit-learn~=1.4.2
21
- Requires-Dist: torch~=2.2.2
22
- Requires-Dist: pandas~=2.2.2
23
- Requires-Dist: numpy~=1.26.4
24
- Requires-Dist: river~=0.21.1
25
- Requires-Dist: tqdm~=4.66.4
26
- Requires-Dist: ordered-set~=4.1.0
27
- Requires-Dist: torchviz~=0.0.2
28
- Provides-Extra: dev
29
- Requires-Dist: scikit-learn~=1.4.2; extra == "dev"
30
- Requires-Dist: torch~=2.2.2; extra == "dev"
31
- Requires-Dist: pandas~=2.2.2; extra == "dev"
32
- Requires-Dist: numpy~=1.26.4; extra == "dev"
33
- Requires-Dist: river~=0.21.1; extra == "dev"
34
- Requires-Dist: tqdm~=4.66.4; extra == "dev"
35
- Requires-Dist: ordered-set~=4.1.0; extra == "dev"
36
- Requires-Dist: torchviz~=0.0.2; extra == "dev"
37
- Requires-Dist: graphviz>=0.10.1; extra == "dev"
38
- Requires-Dist: matplotlib>=3.0.2; extra == "dev"
39
- Requires-Dist: mypy>=0.990; extra == "dev"
40
- Requires-Dist: pre-commit>=2.20.0; extra == "dev"
41
- Requires-Dist: pytest>=7.2.0; extra == "dev"
42
- Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
43
- Requires-Dist: scikit-learn>=0.22.1; extra == "dev"
44
- Requires-Dist: black>=22.10.0; extra == "dev"
45
- Requires-Dist: flake8>=5.0.4; extra == "dev"
46
- Requires-Dist: isort>=5.10.1; extra == "dev"
47
- Requires-Dist: jupyter>=1.0.0; extra == "dev"
48
- Requires-Dist: pyupgrade==3.2.0; extra == "dev"
49
- Provides-Extra: docs
50
- Requires-Dist: scikit-learn~=1.4.2; extra == "docs"
51
- Requires-Dist: torch~=2.2.2; extra == "docs"
52
- Requires-Dist: pandas~=2.2.2; extra == "docs"
53
- Requires-Dist: numpy~=1.26.4; extra == "docs"
54
- Requires-Dist: river~=0.21.1; extra == "docs"
55
- Requires-Dist: tqdm~=4.66.4; extra == "docs"
56
- Requires-Dist: ordered-set~=4.1.0; extra == "docs"
57
- Requires-Dist: torchviz~=0.0.2; extra == "docs"
58
- Requires-Dist: flask>=2.0.2; extra == "docs"
59
- Requires-Dist: ipykernel>=6.9.0; extra == "docs"
60
- Requires-Dist: mike>=0.5.3; extra == "docs"
61
- Requires-Dist: mkdocs>=1.2.3; extra == "docs"
62
- Requires-Dist: mkdocs-awesome-pages-plugin>=2.7.0; extra == "docs"
63
- Requires-Dist: mkdocs-gen-files>=0.3.5; extra == "docs"
64
- Requires-Dist: mkdocs-charts-plugin>=0.0.8; extra == "docs"
65
- Requires-Dist: mkdocs-literate-nav>=0.4.1; extra == "docs"
66
- Requires-Dist: mkdocs-material>=8.1.11; extra == "docs"
67
- Requires-Dist: mkdocstrings[python]>=0.19.0; extra == "docs"
68
- Requires-Dist: pytkdocs[numpy-style]>=0.5.0; extra == "docs"
69
- Requires-Dist: ipython_genutils>=0.1.0; extra == "docs"
70
- Requires-Dist: mkdocs-jupyter>=0.20.0; extra == "docs"
71
- Requires-Dist: nbconvert>=6.4.2; extra == "docs"
72
- Requires-Dist: numpydoc>=1.2; extra == "docs"
73
- Requires-Dist: spacy>=3.2.2; extra == "docs"
74
- Requires-Dist: jinja2>=3.0.3; extra == "docs"
75
- Requires-Dist: dominate; extra == "docs"
76
- Requires-Dist: jupyter-client; extra == "docs"
77
- Requires-Dist: mkdocs-charts-plugin; extra == "docs"
78
- Requires-Dist: python-slugify; extra == "docs"
79
- Requires-Dist: watermark==2.3.1; extra == "docs"
80
- Provides-Extra: all
81
- Requires-Dist: graphviz>=0.10.1; extra == "all"
82
- Requires-Dist: matplotlib>=3.0.2; extra == "all"
83
- Requires-Dist: mypy>=0.990; extra == "all"
84
- Requires-Dist: pre-commit>=2.20.0; extra == "all"
85
- Requires-Dist: pytest>=7.2.0; extra == "all"
86
- Requires-Dist: pytest-cov>=4.0.0; extra == "all"
87
- Requires-Dist: scikit-learn>=0.22.1; extra == "all"
88
- Requires-Dist: black>=22.10.0; extra == "all"
89
- Requires-Dist: flake8>=5.0.4; extra == "all"
90
- Requires-Dist: isort>=5.10.1; extra == "all"
91
- Requires-Dist: jupyter>=1.0.0; extra == "all"
92
- Requires-Dist: pyupgrade==3.2.0; extra == "all"
93
- Requires-Dist: flask>=2.0.2; extra == "all"
94
- Requires-Dist: ipykernel>=6.9.0; extra == "all"
95
- Requires-Dist: mike>=0.5.3; extra == "all"
96
- Requires-Dist: mkdocs>=1.2.3; extra == "all"
97
- Requires-Dist: mkdocs-awesome-pages-plugin>=2.7.0; extra == "all"
98
- Requires-Dist: mkdocs-gen-files>=0.3.5; extra == "all"
99
- Requires-Dist: mkdocs-charts-plugin>=0.0.8; extra == "all"
100
- Requires-Dist: mkdocs-literate-nav>=0.4.1; extra == "all"
101
- Requires-Dist: mkdocs-material>=8.1.11; extra == "all"
102
- Requires-Dist: mkdocstrings[python]>=0.19.0; extra == "all"
103
- Requires-Dist: pytkdocs[numpy-style]>=0.5.0; extra == "all"
104
- Requires-Dist: ipython_genutils>=0.1.0; extra == "all"
105
- Requires-Dist: mkdocs-jupyter>=0.20.0; extra == "all"
106
- Requires-Dist: nbconvert>=6.4.2; extra == "all"
107
- Requires-Dist: numpydoc>=1.2; extra == "all"
108
- Requires-Dist: spacy>=3.2.2; extra == "all"
109
- Requires-Dist: jinja2>=3.0.3; extra == "all"
110
- Requires-Dist: dominate; extra == "all"
111
- Requires-Dist: jupyter-client; extra == "all"
112
- Requires-Dist: mkdocs-charts-plugin; extra == "all"
113
- Requires-Dist: python-slugify; extra == "all"
114
- Requires-Dist: watermark==2.3.1; extra == "all"
115
- Requires-Dist: dataclasses; python_version == "3.6"
116
-
117
32
 
118
33
  <p align="center">
119
34
  <img height="150px" src="https://raw.githubusercontent.com/online-ml/deep-river/master/docs/img/logo.png" alt="incremental dl logo">
@@ -123,8 +38,10 @@ Requires-Dist: dataclasses; python_version == "3.6"
123
38
  <a href="https://codecov.io/gh/online-ml/deep-river" >
124
39
  <img src="https://codecov.io/gh/online-ml/deep-river/branch/master/graph/badge.svg?token=ZKUIISZAYA"/>
125
40
  </a>
41
+ <img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/deep-river">
126
42
  <img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/deep-river">
127
43
  <img alt="GitHub" src="https://img.shields.io/github/license/online-ml/deep-river">
44
+ <a href="https://joss.theoj.org/papers/6a76784f55e8b041d71a7fa776eb386a"><img src="https://joss.theoj.org/papers/6a76784f55e8b041d71a7fa776eb386a/status.svg"></a>
128
45
  </p>
129
46
  <p align="center">
130
47
  deep-river is a Python library for online deep learning.
@@ -133,7 +50,9 @@ Requires-Dist: dataclasses; python_version == "3.6"
133
50
  </p>
134
51
 
135
52
  ## 📚 [Documentation](https://online-ml.github.io/deep-river/)
136
- The [documentation](https://online-ml.github.io/deep-river/) contains an overview of all features of this repository as well as the repository's full features list. In each of these, the git repo reference is listed in a section that shows examples of the features and functionality.
53
+ The [documentation](https://online-ml.github.io/deep-river/) contains an overview of all features of this repository as well as the repository's full features list.
54
+ In each of these, the git repo reference is listed in a section that shows [examples](https://github.com/online-ml/deep-river/blob/master/docs/examples) of the features and functionality.
55
+ As we are always looking for further use cases and examples, feel free to contribute to the documentation or the repository itself via a pull request
137
56
 
138
57
  ## 💈 Installation
139
58
 
@@ -194,7 +113,7 @@ For further examples check out the <a href="https://online-ml.github.io/deep-riv
194
113
  ... metric.update(y, y_pred) # update the metric
195
114
  ... model_pipeline.learn_one(x, y) # make the model learn
196
115
  >>> print(f"Accuracy: {metric.get():.4f}")
197
- Accuracy: 0.6736
116
+ Accuracy: 0.7264
198
117
 
199
118
  ```
200
119
  ### Multi Target Regression
@@ -248,7 +167,7 @@ MicroAverage(MAE): 34.31
248
167
  >>> from river.preprocessing import MinMaxScaler
249
168
 
250
169
  >>> dataset = CreditCard().take(5000)
251
- >>> metric = metrics.ROCAUC(n_thresholds=50)
170
+ >>> metric = metrics.RollingROCAUC(window_size=5000)
252
171
 
253
172
  >>> class MyAutoEncoder(nn.Module):
254
173
  ... def __init__(self, n_features, latent_dim=3):
@@ -273,8 +192,8 @@ MicroAverage(MAE): 34.31
273
192
  ... model.learn_one(x=x)
274
193
  ... metric.update(y, score)
275
194
  ...
276
- >>> print(f"ROCAUC: {metric.get():.4f}")
277
- ROCAUC: 0.9017
195
+ >>> print(f"Rolling ROCAUC: {metric.get():.4f}")
196
+ Rolling ROCAUC: 0.8901
278
197
 
279
198
  ```
280
199
 
@@ -287,3 +206,4 @@ ROCAUC: 0.9017
287
206
  <p align="center">
288
207
  <img src="https://lieferbotnet.de/wp-content/uploads/2022/09/LieferBotNet-Logo.png?raw=true" alt="Lieferbot net" height="200"/>
289
208
  </p>
209
+
@@ -6,8 +6,10 @@
6
6
  <a href="https://codecov.io/gh/online-ml/deep-river" >
7
7
  <img src="https://codecov.io/gh/online-ml/deep-river/branch/master/graph/badge.svg?token=ZKUIISZAYA"/>
8
8
  </a>
9
+ <img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/deep-river">
9
10
  <img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/deep-river">
10
11
  <img alt="GitHub" src="https://img.shields.io/github/license/online-ml/deep-river">
12
+ <a href="https://joss.theoj.org/papers/6a76784f55e8b041d71a7fa776eb386a"><img src="https://joss.theoj.org/papers/6a76784f55e8b041d71a7fa776eb386a/status.svg"></a>
11
13
  </p>
12
14
  <p align="center">
13
15
  deep-river is a Python library for online deep learning.
@@ -16,7 +18,9 @@
16
18
  </p>
17
19
 
18
20
  ## 📚 [Documentation](https://online-ml.github.io/deep-river/)
19
- The [documentation](https://online-ml.github.io/deep-river/) contains an overview of all features of this repository as well as the repository's full features list. In each of these, the git repo reference is listed in a section that shows examples of the features and functionality.
21
+ The [documentation](https://online-ml.github.io/deep-river/) contains an overview of all features of this repository as well as the repository's full features list.
22
+ In each of these, the git repo reference is listed in a section that shows [examples](https://github.com/online-ml/deep-river/blob/master/docs/examples) of the features and functionality.
23
+ As we are always looking for further use cases and examples, feel free to contribute to the documentation or the repository itself via a pull request
20
24
 
21
25
  ## 💈 Installation
22
26
 
@@ -77,7 +81,7 @@ For further examples check out the <a href="https://online-ml.github.io/deep-riv
77
81
  ... metric.update(y, y_pred) # update the metric
78
82
  ... model_pipeline.learn_one(x, y) # make the model learn
79
83
  >>> print(f"Accuracy: {metric.get():.4f}")
80
- Accuracy: 0.6736
84
+ Accuracy: 0.7264
81
85
 
82
86
  ```
83
87
  ### Multi Target Regression
@@ -131,7 +135,7 @@ MicroAverage(MAE): 34.31
131
135
  >>> from river.preprocessing import MinMaxScaler
132
136
 
133
137
  >>> dataset = CreditCard().take(5000)
134
- >>> metric = metrics.ROCAUC(n_thresholds=50)
138
+ >>> metric = metrics.RollingROCAUC(window_size=5000)
135
139
 
136
140
  >>> class MyAutoEncoder(nn.Module):
137
141
  ... def __init__(self, n_features, latent_dim=3):
@@ -156,8 +160,8 @@ MicroAverage(MAE): 34.31
156
160
  ... model.learn_one(x=x)
157
161
  ... metric.update(y, score)
158
162
  ...
159
- >>> print(f"ROCAUC: {metric.get():.4f}")
160
- ROCAUC: 0.9017
163
+ >>> print(f"Rolling ROCAUC: {metric.get():.4f}")
164
+ Rolling ROCAUC: 0.8901
161
165
 
162
166
  ```
163
167
 
@@ -1,3 +1,3 @@
1
- VERSION = (0, 2, 6)
1
+ VERSION = (0, 2, 8)
2
2
 
3
3
  __version__ = ".".join(map(str, VERSION)) # noqa: F401
@@ -1,11 +1,7 @@
1
1
  from .ae import Autoencoder
2
2
  from .probability_weighted_ae import ProbabilityWeightedAutoencoder
3
3
  from .rolling_ae import RollingAutoencoder
4
- from .scaler import (
5
- AnomalyMeanScaler,
6
- AnomalyMinMaxScaler,
7
- AnomalyStandardScaler,
8
- )
4
+ from .scaler import AnomalyMeanScaler, AnomalyMinMaxScaler, AnomalyStandardScaler
9
5
 
10
6
  """
11
7
  This module contains the anomaly detection algorithms for the
@@ -1,4 +1,4 @@
1
- from typing import Any, Callable, Type, Union
1
+ from typing import Any, Callable, Dict, Type, Union
2
2
 
3
3
  import numpy as np
4
4
  import pandas as pd
@@ -8,6 +8,7 @@ from torch import nn
8
8
 
9
9
  from deep_river.base import DeepEstimator
10
10
  from deep_river.utils import dict2tensor
11
+ from deep_river.utils.layer_adaptation import expand_layer
11
12
  from deep_river.utils.tensor_conversion import df2tensor
12
13
 
13
14
 
@@ -67,7 +68,7 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
67
68
  >>> from river.preprocessing import MinMaxScaler
68
69
 
69
70
  >>> dataset = CreditCard().take(5000)
70
- >>> metric = metrics.ROCAUC(n_thresholds=50)
71
+ >>> metric = metrics.RollingROCAUC(window_size=5000)
71
72
 
72
73
  >>> class MyAutoEncoder(torch.nn.Module):
73
74
  ... def __init__(self, n_features, latent_dim=3):
@@ -92,8 +93,8 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
92
93
  ... model.learn_one(x=x)
93
94
  ... metric.update(y, score)
94
95
  ...
95
- >>> print(f"ROCAUC: {metric.get():.4f}")
96
- ROCAUC: 0.9017
96
+ >>> print(f"Rolling ROCAUC: {metric.get():.4f}")
97
+ Rolling ROCAUC: 0.8901
97
98
  """
98
99
 
99
100
  def __init__(
@@ -102,6 +103,7 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
102
103
  loss_fn: Union[str, Callable] = "mse",
103
104
  optimizer_fn: Union[str, Callable] = "sgd",
104
105
  lr: float = 1e-3,
106
+ is_feature_incremental: bool = False,
105
107
  device: str = "cpu",
106
108
  seed: int = 42,
107
109
  **kwargs,
@@ -111,10 +113,12 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
111
113
  loss_fn=loss_fn,
112
114
  optimizer_fn=optimizer_fn,
113
115
  lr=lr,
116
+ is_feature_incremental=is_feature_incremental,
114
117
  device=device,
115
118
  seed=seed,
116
119
  **kwargs,
117
120
  )
121
+ self.is_class_incremental = is_feature_incremental
118
122
 
119
123
  @classmethod
120
124
  def _unit_test_params(cls):
@@ -133,6 +137,7 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
133
137
  "module": _TestAutoencoder,
134
138
  "loss_fn": "mse",
135
139
  "optimizer_fn": "sgd",
140
+ "is_feature_incremental": True,
136
141
  }
137
142
 
138
143
  @classmethod
@@ -148,13 +153,7 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
148
153
  set
149
154
  Set of checks to skip during unit testing.
150
155
  """
151
- return {
152
- "check_shuffle_features_no_impact",
153
- "check_emerging_features",
154
- "check_disappearing_features",
155
- "check_predict_proba_one",
156
- "check_predict_proba_one_binary",
157
- }
156
+ return set()
158
157
 
159
158
  def learn_one(self, x: dict, y: Any = None, **kwargs) -> "Autoencoder":
160
159
  """
@@ -173,14 +172,17 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
173
172
  The model itself.
174
173
  """
175
174
  if not self.module_initialized:
176
- self.kwargs["n_features"] = len(x)
177
- self.initialize_module(**self.kwargs)
178
- return self._learn(dict2tensor(x, device=self.device))
175
+ self._update_observed_features(x)
176
+ self.initialize_module(x=x, **self.kwargs)
177
+ self._adapt_input_dim(x)
178
+ return self._learn(
179
+ dict2tensor(x, features=self.observed_features, device=self.device)
180
+ )
179
181
 
180
182
  def _learn(self, x: torch.Tensor) -> "Autoencoder":
181
183
  self.module.train()
182
184
  x_pred = self.module(x)
183
- loss = self.loss_fn(x_pred, x)
185
+ loss = self.loss_func(x_pred, x)
184
186
  loss.backward()
185
187
  self.optimizer.step()
186
188
  self.optimizer.zero_grad()
@@ -205,14 +207,16 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
205
207
  """
206
208
 
207
209
  if not self.module_initialized:
208
- self.kwargs["n_features"] = len(x)
209
- self.initialize_module(**self.kwargs)
210
+ self._update_observed_features(x)
211
+ self.initialize_module(x=x, **self.kwargs)
210
212
 
211
- x_t = dict2tensor(x, device=self.device)
213
+ self._adapt_input_dim(x)
214
+
215
+ x_t = dict2tensor(x, features=self.observed_features, device=self.device)
212
216
  self.module.eval()
213
217
  with torch.inference_mode():
214
218
  x_pred = self.module(x_t)
215
- loss = self.loss_fn(x_pred, x_t).item()
219
+ loss = self.loss_func(x_pred, x_t).item()
216
220
  return loss
217
221
 
218
222
  def learn_many(self, X: pd.DataFrame) -> "Autoencoder":
@@ -231,10 +235,13 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
231
235
 
232
236
  """
233
237
  if not self.module_initialized:
234
- self.kwargs["n_features"] = len(X.columns)
235
- self.initialize_module(**self.kwargs)
236
- X = df2tensor(X, device=self.device)
237
- return self._learn(X)
238
+
239
+ self._update_observed_features(X)
240
+ self.initialize_module(x=X, **self.kwargs)
241
+
242
+ self._adapt_input_dim(X)
243
+ X_t = df2tensor(X, features=self.observed_features, device=self.device)
244
+ return self._learn(X_t)
238
245
 
239
246
  def score_many(self, X: pd.DataFrame) -> np.ndarray:
240
247
  """
@@ -253,16 +260,35 @@ class Autoencoder(DeepEstimator, AnomalyDetector):
253
260
  indicate more anomalous examples.
254
261
  """
255
262
  if not self.module_initialized:
256
- self.kwargs["n_features"] = len(X.columns)
257
- self.initialize_module(**self.kwargs)
258
- X = df2tensor(X, device=self.device)
263
+ self._update_observed_features(X)
264
+ self.initialize_module(x=X, **self.kwargs)
265
+
266
+ self._adapt_input_dim(X)
267
+ X_t = df2tensor(X, features=self.observed_features, device=self.device)
259
268
 
260
269
  self.module.eval()
261
270
  with torch.inference_mode():
262
- X_pred = self.module(X)
271
+ X_pred = self.module(X_t)
263
272
  loss = torch.mean(
264
- self.loss_fn(X_pred, X, reduction="none"),
265
- dim=list(range(1, X.dim())),
273
+ self.loss_func(X_pred, X_t, reduction="none"),
274
+ dim=list(range(1, X_t.dim())),
266
275
  )
267
276
  score = loss.cpu().detach().numpy()
268
277
  return score
278
+
279
+ def _adapt_input_dim(self, x: Dict | pd.DataFrame):
280
+ has_new_feature = self._update_observed_features(x)
281
+
282
+ if has_new_feature and self.is_feature_incremental:
283
+ expand_layer(
284
+ self.input_layer,
285
+ self.input_expansion_instructions,
286
+ len(self.observed_features),
287
+ output=False,
288
+ )
289
+ expand_layer(
290
+ self.output_layer,
291
+ self.output_expansion_instructions,
292
+ len(self.observed_features),
293
+ output=True,
294
+ )
@@ -8,6 +8,7 @@ from scipy.special import ndtr
8
8
 
9
9
  from deep_river.anomaly import ae
10
10
  from deep_river.utils import dict2tensor
11
+ from deep_river.utils.tensor_conversion import df2tensor
11
12
 
12
13
 
13
14
  class ProbabilityWeightedAutoencoder(ae.Autoencoder):
@@ -61,7 +62,7 @@ class ProbabilityWeightedAutoencoder(ae.Autoencoder):
61
62
 
62
63
  >>> _ = manual_seed(42)
63
64
  >>> dataset = CreditCard().take(5000)
64
- >>> metric = metrics.ROCAUC(n_thresholds=50)
65
+ >>> metric = metrics.RollingROCAUC(window_size=5000)
65
66
 
66
67
  >>> class MyAutoEncoder(torch.nn.Module):
67
68
  ... def __init__(self, n_features, latent_dim=3):
@@ -86,8 +87,8 @@ class ProbabilityWeightedAutoencoder(ae.Autoencoder):
86
87
  ... model.learn_one(x=x)
87
88
  ... metric.update(y, score)
88
89
  ...
89
- >>> print(f"ROCAUC: {metric.get():.4f}")
90
- ROCAUC: 0.8599
90
+ >>> print(f"Rolling ROCAUC: {metric.get():.4f}")
91
+ Rolling ROCAUC: 0.8530
91
92
  """
92
93
 
93
94
  def __init__(
@@ -113,9 +114,7 @@ class ProbabilityWeightedAutoencoder(ae.Autoencoder):
113
114
  )
114
115
  self.window_size = window_size
115
116
  self.skip_threshold = skip_threshold
116
- self.rolling_mean = utils.Rolling(
117
- stats.Mean(), window_size=window_size
118
- )
117
+ self.rolling_mean = utils.Rolling(stats.Mean(), window_size=window_size)
119
118
  self.rolling_var = utils.Rolling(stats.Var(), window_size=window_size)
120
119
 
121
120
  def learn_one(
@@ -138,13 +137,15 @@ class ProbabilityWeightedAutoencoder(ae.Autoencoder):
138
137
  The autoencoder itself.
139
138
  """
140
139
  if not self.module_initialized:
141
- self.kwargs["n_features"] = len(x)
142
- self.initialize_module(**self.kwargs)
143
- x_t = dict2tensor(x, device=self.device)
140
+ self._update_observed_features(x)
141
+ self.initialize_module(x=x, **self.kwargs)
142
+
143
+ self._adapt_input_dim(x)
144
+ x_t = dict2tensor(x, self.observed_features, device=self.device)
144
145
 
145
146
  self.module.train()
146
147
  x_pred = self.module(x_t)
147
- loss = self.loss_fn(x_pred, x_t)
148
+ loss = self.loss_func(x_pred, x_t)
148
149
  self._apply_loss(loss)
149
150
  return self
150
151
 
@@ -162,10 +163,7 @@ class ProbabilityWeightedAutoencoder(ae.Autoencoder):
162
163
 
163
164
  loss_scaled = (losses_numpy - mean) / math.sqrt(var)
164
165
  prob = ndtr(loss_scaled)
165
- loss = (
166
- torch.tensor((self.skip_threshold - prob) / self.skip_threshold)
167
- * loss
168
- )
166
+ loss = torch.tensor((self.skip_threshold - prob) / self.skip_threshold) * loss
169
167
 
170
168
  self.optimizer.zero_grad()
171
169
  loss.backward()
@@ -173,15 +171,16 @@ class ProbabilityWeightedAutoencoder(ae.Autoencoder):
173
171
 
174
172
  def learn_many(self, X: pd.DataFrame) -> "ProbabilityWeightedAutoencoder":
175
173
  if not self.module_initialized:
176
- self.kwargs["n_features"] = len(X.columns)
177
- self.initialize_module(**self.kwargs)
178
- X = dict2tensor(X.to_dict(), device=self.device)
174
+ self._update_observed_features(X)
175
+ self.initialize_module(x=X, **self.kwargs)
176
+ self._adapt_input_dim(X)
177
+ X_t = df2tensor(X, features=self.observed_features, device=self.device)
179
178
 
180
179
  self.module.train()
181
180
  x_pred = self.module(X)
182
181
  loss = torch.mean(
183
- self.loss_fn(x_pred, X, reduction="none"),
184
- dim=list(range(1, X.dim())),
182
+ self.loss_func(x_pred, X_t, reduction="none"),
183
+ dim=list(range(1, X_t.dim())),
185
184
  )
186
185
  self._apply_loss(loss)
187
186
  return self
@@ -11,9 +11,7 @@ from deep_river.utils.tensor_conversion import deque2rolling_tensor
11
11
 
12
12
 
13
13
  class _TestLSTMAutoencoder(nn.Module):
14
- def __init__(
15
- self, n_features, hidden_size=30, n_layers=1, batch_first=False
16
- ):
14
+ def __init__(self, n_features, hidden_size=30, n_layers=1, batch_first=False):
17
15
  super().__init__()
18
16
  self.n_features = n_features
19
17
  self.hidden_size = hidden_size
@@ -26,20 +24,10 @@ class _TestLSTMAutoencoder(nn.Module):
26
24
  num_layers=n_layers,
27
25
  batch_first=batch_first,
28
26
  )
29
- self.decoder = nn.LSTM(
30
- input_size=hidden_size,
31
- hidden_size=n_features,
32
- num_layers=n_layers,
33
- batch_first=batch_first,
34
- )
35
27
 
36
28
  def forward(self, x):
37
- _, (h, _) = self.encoder(x)
38
- h = h[-1].view(1, 1, -1)
39
- x_flipped = torch.flip(x[1:], dims=[self.time_axis])
40
- input = torch.cat((h, x_flipped), dim=self.time_axis)
41
- x_hat, _ = self.decoder(input)
42
- return torch.flip(x_hat, dims=[self.time_axis])
29
+ output, (h, c) = self.encoder(x)
30
+ return output
43
31
 
44
32
 
45
33
  class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
@@ -146,15 +134,13 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
146
134
  def _learn(self, x: torch.Tensor):
147
135
  self.module.train()
148
136
  x_pred = self.module(x)
149
- loss = self.loss_fn(x_pred, x)
137
+ loss = self.loss_func(x_pred, x)
150
138
 
151
139
  self.optimizer.zero_grad()
152
140
  loss.backward()
153
141
  self.optimizer.step()
154
142
 
155
- def learn_one(
156
- self, x: dict, y: Any = None, **kwargs
157
- ) -> "RollingAutoencoder":
143
+ def learn_one(self, x: dict, y: Any = None, **kwargs) -> "RollingAutoencoder":
158
144
  """
159
145
  Performs one step of training with a single example.
160
146
 
@@ -169,8 +155,8 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
169
155
  The estimator itself.
170
156
  """
171
157
  if not self.module_initialized:
172
- self.kwargs["n_features"] = len(x)
173
- self.initialize_module(**self.kwargs)
158
+ self._update_observed_features(x)
159
+ self.initialize_module(x=x, **self.kwargs)
174
160
 
175
161
  self._x_window.append(list(x.values()))
176
162
 
@@ -197,8 +183,8 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
197
183
  The estimator itself.
198
184
  """
199
185
  if not self.module_initialized:
200
- self.kwargs["n_features"] = len(X.columns)
201
- self.initialize_module(**self.kwargs)
186
+ self._update_observed_features(X)
187
+ self.initialize_module(x=X, **self.kwargs)
202
188
 
203
189
  self._x_window.append(X.values.tolist())
204
190
  if len(self._x_window) == self.window_size:
@@ -209,8 +195,10 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
209
195
  def score_one(self, x: dict) -> float:
210
196
  res = 0.0
211
197
  if not self.module_initialized:
212
- self.kwargs["n_features"] = len(x)
213
- self.initialize_module(**self.kwargs)
198
+
199
+ self._update_observed_features(x)
200
+
201
+ self.initialize_module(x=x, **self.kwargs)
214
202
 
215
203
  if len(self._x_window) == self.window_size:
216
204
  x_win = self._x_window.copy()
@@ -219,7 +207,7 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
219
207
  self.module.eval()
220
208
  with torch.inference_mode():
221
209
  x_pred = self.module(x_t)
222
- loss = self.loss_fn(x_pred, x_t)
210
+ loss = self.loss_func(x_pred, x_t)
223
211
  res = loss.item()
224
212
 
225
213
  if self.append_predict:
@@ -228,8 +216,9 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
228
216
 
229
217
  def score_many(self, X: pd.DataFrame) -> List[Any]:
230
218
  if not self.module_initialized:
231
- self.kwargs["n_features"] = len(X.columns)
232
- self.initialize_module(**self.kwargs)
219
+
220
+ self._update_observed_features(X)
221
+ self.initialize_module(x=X, **self.kwargs)
233
222
 
234
223
  x_win = self._x_window.copy()
235
224
  x_win.append(X.values.tolist())
@@ -242,7 +231,7 @@ class RollingAutoencoder(RollingDeepEstimator, anomaly.base.AnomalyDetector):
242
231
  with torch.inference_mode():
243
232
  x_pred = self.module(X_t)
244
233
  loss = torch.mean(
245
- self.loss_fn(x_pred, x_pred, reduction="none"),
234
+ self.loss_func(x_pred, x_pred, reduction="none"),
246
235
  dim=list(range(1, x_pred.dim())),
247
236
  )
248
237
  losses = loss.detach().numpy()
@@ -145,9 +145,7 @@ class AnomalyStandardScaler(AnomalyScaler):
145
145
  super().__init__(anomaly_detector)
146
146
  self.rolling = rolling
147
147
  self.window_size = window_size
148
- self.mean = (
149
- utils.Rolling(Mean(), self.window_size) if self.rolling else Mean()
150
- )
148
+ self.mean = utils.Rolling(Mean(), self.window_size) if self.rolling else Mean()
151
149
  self.sq_mean = (
152
150
  utils.Rolling(Mean(), self.window_size) if self.rolling else Mean()
153
151
  )
@@ -208,9 +206,7 @@ class AnomalyMeanScaler(AnomalyScaler):
208
206
  super().__init__(anomaly_detector=anomaly_detector)
209
207
  self.rolling = rolling
210
208
  self.window_size = window_size
211
- self.mean = (
212
- utils.Rolling(Mean(), self.window_size) if self.rolling else Mean()
213
- )
209
+ self.mean = utils.Rolling(Mean(), self.window_size) if self.rolling else Mean()
214
210
 
215
211
  def score_one(self, *args):
216
212
  """