synthyverse 0.2.3__tar.gz → 0.2.4__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 (79) hide show
  1. {synthyverse-0.2.3 → synthyverse-0.2.4}/PKG-INFO +2 -1
  2. {synthyverse-0.2.3 → synthyverse-0.2.4}/THIRD_PARTY_NOTICES.md +10 -1
  3. {synthyverse-0.2.3 → synthyverse-0.2.4}/pyproject.toml +2 -1
  4. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/__init__.py +3 -0
  5. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/dgm_utils.py +11 -22
  6. synthyverse-0.2.4/synthyverse/generators/tabcascade_generator/__init__.py +1 -0
  7. synthyverse-0.2.4/synthyverse/generators/tabcascade_generator/disttree.py +289 -0
  8. synthyverse-0.2.4/synthyverse/generators/tabcascade_generator/encoder.py +120 -0
  9. synthyverse-0.2.4/synthyverse/generators/tabcascade_generator/highres.py +262 -0
  10. synthyverse-0.2.4/synthyverse/generators/tabcascade_generator/lowres.py +400 -0
  11. synthyverse-0.2.4/synthyverse/generators/tabcascade_generator/tabcascade.py +644 -0
  12. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabsyn_generator/tabsyn.py +2 -6
  13. synthyverse-0.2.4/synthyverse/generators/xgbddpm_generator/__init__.py +1 -0
  14. synthyverse-0.2.4/synthyverse/generators/xgbddpm_generator/xgbddpm.py +580 -0
  15. synthyverse-0.2.4/synthyverse/generators/xgbdiffusion_generator/__init__.py +1 -0
  16. synthyverse-0.2.4/synthyverse/generators/xgbdiffusion_generator/xgbdiffusion.py +340 -0
  17. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse.egg-info/PKG-INFO +2 -1
  18. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse.egg-info/SOURCES.txt +10 -0
  19. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse.egg-info/requires.txt +1 -0
  20. {synthyverse-0.2.3 → synthyverse-0.2.4}/LICENSE +0 -0
  21. {synthyverse-0.2.3 → synthyverse-0.2.4}/LICENSES/Apache-2.0.txt +0 -0
  22. {synthyverse-0.2.3 → synthyverse-0.2.4}/LICENSES/CTGAN-BSL-1.1.txt +0 -0
  23. {synthyverse-0.2.3 → synthyverse-0.2.4}/LICENSES/MIT.txt +0 -0
  24. {synthyverse-0.2.3 → synthyverse-0.2.4}/MANIFEST.in +0 -0
  25. {synthyverse-0.2.3 → synthyverse-0.2.4}/NOTICE +0 -0
  26. {synthyverse-0.2.3 → synthyverse-0.2.4}/README.md +0 -0
  27. {synthyverse-0.2.3 → synthyverse-0.2.4}/logo/logo.png +0 -0
  28. {synthyverse-0.2.3 → synthyverse-0.2.4}/setup.cfg +0 -0
  29. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/__init__.py +0 -0
  30. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/benchmark/__init__.py +0 -0
  31. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/benchmark/synthesis.py +0 -0
  32. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/__init__.py +0 -0
  33. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/eval.py +0 -0
  34. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/fidelity.py +0 -0
  35. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/gower.py +0 -0
  36. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/ml.py +0 -0
  37. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/preprocessing.py +0 -0
  38. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/privacy.py +0 -0
  39. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/evaluation/utility.py +0 -0
  40. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/_optional.py +0 -0
  41. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/arf_generator/__init__.py +0 -0
  42. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/arf_generator/arf.py +0 -0
  43. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/arf_generator/model.py +0 -0
  44. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/arf_generator/utils.py +0 -0
  45. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/base.py +0 -0
  46. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/cdtd_generator/__init__.py +0 -0
  47. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/cdtd_generator/cdtd.py +0 -0
  48. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/cdtd_generator/layers.py +0 -0
  49. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/cdtd_generator/utils.py +0 -0
  50. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/ctgan_generator/__init__.py +0 -0
  51. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/ctgan_generator/ct_gan.py +0 -0
  52. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/persistence.py +0 -0
  53. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/smote_generator/__init__.py +0 -0
  54. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/smote_generator/smote.py +0 -0
  55. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/synthpop_generator/__init__.py +0 -0
  56. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/synthpop_generator/synthpop.py +0 -0
  57. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabddpm_generator/__init__.py +0 -0
  58. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabddpm_generator/ddpm_utils.py +0 -0
  59. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabddpm_generator/gaussian_multinomial_diffsuion.py +0 -0
  60. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabddpm_generator/modules.py +0 -0
  61. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabddpm_generator/tabddpm.py +0 -0
  62. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabdiff_generator/__init__.py +0 -0
  63. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabdiff_generator/diffusion.py +0 -0
  64. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabdiff_generator/modules.py +0 -0
  65. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabdiff_generator/noise_schedule.py +0 -0
  66. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabdiff_generator/tabdiff.py +0 -0
  67. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabdiff_generator/transformer.py +0 -0
  68. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabsyn_generator/__init__.py +0 -0
  69. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabsyn_generator/diffusion.py +0 -0
  70. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tabsyn_generator/vae.py +0 -0
  71. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tvae_generator/__init__.py +0 -0
  72. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/tvae_generator/tvae.py +0 -0
  73. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/univariate_generator/__init__.py +0 -0
  74. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/generators/univariate_generator/univariate.py +0 -0
  75. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/utils/__init__.py +0 -0
  76. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/utils/reproducibility.py +0 -0
  77. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse/utils/utils.py +0 -0
  78. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse.egg-info/dependency_links.txt +0 -0
  79. {synthyverse-0.2.3 → synthyverse-0.2.4}/synthyverse.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: synthyverse
3
- Version: 0.2.3
3
+ Version: 0.2.4
4
4
  Summary: Synthetic data generation and evaluation library
5
5
  Author: Jim Achterberg, Saif Ul Islam, Zia Ur Rehman
6
6
  License: MIT License
@@ -40,6 +40,7 @@ Requires-Dist: torch
40
40
  Requires-Dist: torch-ema
41
41
  Requires-Dist: einops
42
42
  Requires-Dist: imbalanced-learn
43
+ Requires-Dist: xgb-diffusion
43
44
  Provides-Extra: ctgan
44
45
  Requires-Dist: ctgan; extra == "ctgan"
45
46
  Provides-Extra: docs
@@ -45,10 +45,19 @@ The MIT license text for these adapted implementations is kept in
45
45
  - Upstream project: `TabDiff (https://github.com/MinkaiXu/TabDiff/)`
46
46
  - Upstream license: MIT License
47
47
  - Upstream copyright notice: `Copyright 2024 Minkai Xu`
48
- - Imported or last compared against: `5ecdb33`
48
+ - Imported or last compared against: `Commit 5ecdb33`
49
49
  - Modifications: `Refactored API, speed-up masked diffusion by vectorizing loops, fast tensor dataloader.`
50
50
  - Upstream NOTICE text, if any: `None`
51
51
 
52
+ ### TabCascadeGenerator
53
+
54
+ - Synthyverse files: `synthyverse/generators/tabcascade_generator/*`
55
+ - Upstream project: `TabCascade (https://github.com/muellermarkus/tabcascade)`
56
+ - Upstream license: MIT License
57
+ - Upstream copyright notice: `Copyright (c) 2026 Markus Mueller`
58
+ - Imported or last compared against: `Commit c8f44bb`
59
+ - Modifications: `Refactored API, simple ordinal encoding for categories.`
60
+ - Upstream NOTICE text, if any: `None`
52
61
 
53
62
  ## Apache-2.0-licensed adapted implementations
54
63
 
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "synthyverse"
7
- version = "0.2.3"
7
+ version = "0.2.4"
8
8
  description = "Synthetic data generation and evaluation library"
9
9
  readme = "README.md"
10
10
  requires-python = ">=3.8"
@@ -43,6 +43,7 @@ dependencies = [
43
43
  "torch-ema",
44
44
  "einops",
45
45
  "imbalanced-learn",
46
+ "xgb-diffusion",
46
47
  ]
47
48
 
48
49
  [tool.setuptools]
@@ -16,9 +16,12 @@ _BASE_GENERATORS = {
16
16
  "CDTDGenerator": (".cdtd_generator", "cdtd"),
17
17
  "TabDDPMGenerator": (".tabddpm_generator", "tabddpm"),
18
18
  "TabDiffGenerator": (".tabdiff_generator", "tabdiff"),
19
+ "TabCascadeGenerator": (".tabcascade_generator", "tabcascade"),
19
20
  "UnivariateGenerator": (".univariate_generator", "univariate"),
20
21
  "SMOTEGenerator": (".smote_generator", "smote"),
21
22
  "SynthpopGenerator": (".synthpop_generator", "synthpop"),
23
+ "XGBDDPMGenerator": (".xgbddpm_generator", "xgbddpm"),
24
+ "XGBDiffusionGenerator": (".xgbdiffusion_generator", "xgbdiffusion"),
22
25
  }
23
26
 
24
27
  _CTGAN_GENERATORS = {
@@ -55,15 +55,12 @@ class MLPDiffusion(nn.Module):
55
55
 
56
56
 
57
57
  class FastTensorDataLoader:
58
- """Iterate over categorical and continuous tensors in mini-batches."""
58
+ """Iterate over tensors in mini-batches."""
59
59
 
60
- def __init__(self, X_cat, X_cont, batch_size=32, shuffle=False, drop_last=False):
61
- self.dataset_len = X_cat.shape[0] if X_cat is not None else X_cont.shape[0]
62
- assert all(
63
- t.shape[0] == self.dataset_len for t in (X_cat, X_cont) if t is not None
64
- )
65
- self.X_cat = X_cat
66
- self.X_cont = X_cont
60
+ def __init__(self, *data, batch_size=32, shuffle=False, drop_last=False):
61
+ self.dataset_len = next(t.shape[0] for t in data if t is not None)
62
+ assert all(t.shape[0] == self.dataset_len for t in data if t is not None)
63
+ self.data = data
67
64
  self.batch_size = batch_size
68
65
  self.shuffle = shuffle
69
66
 
@@ -84,22 +81,14 @@ class FastTensorDataLoader:
84
81
 
85
82
  if self.indices is not None:
86
83
  indices = self.indices[self.i : self.i + self.batch_size]
87
- batch = (
88
- torch.index_select(self.X_cat, 0, indices)
89
- if self.X_cat is not None
90
- else None,
91
- torch.index_select(self.X_cont, 0, indices)
92
- if self.X_cont is not None
93
- else None,
84
+ batch = tuple(
85
+ torch.index_select(t, 0, indices) if t is not None else None
86
+ for t in self.data
94
87
  )
95
88
  else:
96
- batch = (
97
- self.X_cat[self.i : self.i + self.batch_size]
98
- if self.X_cat is not None
99
- else None,
100
- self.X_cont[self.i : self.i + self.batch_size]
101
- if self.X_cont is not None
102
- else None,
89
+ batch = tuple(
90
+ t[self.i : self.i + self.batch_size] if t is not None else None
91
+ for t in self.data
103
92
  )
104
93
 
105
94
  self.i += self.batch_size
@@ -0,0 +1 @@
1
+ from .tabcascade import TabCascadeGenerator
@@ -0,0 +1,289 @@
1
+ from dataclasses import dataclass
2
+ import math
3
+
4
+ import numpy as np
5
+ import pandas as pd
6
+ from scipy import stats
7
+ from scipy.optimize import minimize
8
+ from scipy.stats import chi2
9
+ from sklearn.preprocessing import OrdinalEncoder
10
+
11
+
12
+ class GaussianFamily:
13
+ npar = 2
14
+
15
+ def start_params(self, y, weights=None):
16
+ if weights is None:
17
+ mu = float(np.mean(y))
18
+ sigma = float(np.std(y, ddof=1)) or 1.0
19
+ else:
20
+ w = weights / weights.sum()
21
+ mu = float(np.dot(w, y))
22
+ sigma = float(np.sqrt(np.dot(w, (y - mu) ** 2))) or 1.0
23
+ return np.array([mu, np.log(sigma)])
24
+
25
+ def inverse_link(self, eta):
26
+ return np.asarray(eta, dtype=float).copy()
27
+
28
+ def link_bounds(self):
29
+ return [(None, None), (-100.0, None)]
30
+
31
+ def log_likelihood(self, y, params, weights=None):
32
+ mu, log_sigma = float(params[0]), float(params[1])
33
+ weights = np.ones(len(y)) if weights is None else np.asarray(weights, dtype=float)
34
+ ll = (
35
+ -0.5 * np.log(2.0 * np.pi)
36
+ - log_sigma
37
+ - 0.5 * (y - mu) ** 2 * np.exp(-2.0 * log_sigma)
38
+ )
39
+ return float(np.dot(weights, ll))
40
+
41
+ def score(self, y, params, weights=None):
42
+ mu, log_sigma = float(params[0]), float(params[1])
43
+ weights = np.ones(len(y)) if weights is None else np.asarray(weights, dtype=float)
44
+ residual = y - mu
45
+ exp_neg2 = np.exp(-2.0 * log_sigma)
46
+ score = np.column_stack(
47
+ [residual * exp_neg2, residual**2 * exp_neg2 - 1.0]
48
+ )
49
+ return score * weights[:, np.newaxis]
50
+
51
+ def hessian(self, y, params, weights=None):
52
+ mu, log_sigma = float(params[0]), float(params[1])
53
+ weights = np.ones(len(y)) if weights is None else np.asarray(weights, dtype=float)
54
+ residual = y - mu
55
+ exp_neg2 = np.exp(-2.0 * log_sigma)
56
+ return np.array(
57
+ [
58
+ [-weights.sum() * exp_neg2, -2.0 * np.dot(weights, residual) * exp_neg2],
59
+ [
60
+ -2.0 * np.dot(weights, residual) * exp_neg2,
61
+ -2.0 * np.dot(weights, residual**2) * exp_neg2,
62
+ ],
63
+ ]
64
+ )
65
+
66
+ def to_user_params(self, params):
67
+ return np.array([float(params[0]), np.exp(float(params[1]))]), ["mu", "sigma"]
68
+
69
+ def mean(self, params):
70
+ return float(params[0])
71
+
72
+
73
+ class DistFit:
74
+ def __init__(self, family=None):
75
+ self.family = family or GaussianFamily()
76
+
77
+ def fit(self, y, sample_weight=None):
78
+ y = np.asarray(y, dtype=float)
79
+ weights = np.ones(len(y)) if sample_weight is None else np.asarray(sample_weight, dtype=float)
80
+ eta0 = self.family.start_params(y, weights)
81
+
82
+ def neg_loglik(eta):
83
+ return -self.family.log_likelihood(y, self.family.inverse_link(eta), weights)
84
+
85
+ def neg_score_eta(eta):
86
+ params = self.family.inverse_link(eta)
87
+ return -self.family.score(y, params, weights).sum(axis=0)
88
+
89
+ result = minimize(
90
+ neg_loglik,
91
+ eta0,
92
+ jac=neg_score_eta,
93
+ method="L-BFGS-B",
94
+ bounds=self.family.link_bounds(),
95
+ options={"maxiter": 500, "ftol": 1e-12, "gtol": 1e-8},
96
+ )
97
+ params = self.family.inverse_link(result.x)
98
+ display, names = self.family.to_user_params(params)
99
+ self.coef_ = {name: float(value) for name, value in zip(names, display)}
100
+ self.coef_array_ = display.copy()
101
+ self.loglik_ = float(-result.fun)
102
+ self.score_matrix_ = self.family.score(y, params, weights)
103
+ self.hessian_ = self.family.hessian(y, params, weights)
104
+ self.estfun_ = self.score_matrix_
105
+ return self
106
+
107
+
108
+ def _quadratic_stat(t, mu, sigma):
109
+ diff = t - mu
110
+ eigvals, eigvecs = np.linalg.eigh(sigma)
111
+ tol = max(1e-14, 1e-10 * float(np.abs(eigvals).max() or 1.0))
112
+ pos = eigvals > tol
113
+ if not pos.any():
114
+ return 0.0, 0
115
+ sigma_pinv = eigvecs[:, pos] @ np.diag(1.0 / eigvals[pos]) @ eigvecs[:, pos].T
116
+ return float(diff @ sigma_pinv @ diff), int(pos.sum())
117
+
118
+
119
+ def select_variable(X, distfit, alpha=0.05):
120
+ h = distfit.estfun_
121
+ n, p_vars = X.shape
122
+ p_values = np.ones(p_vars)
123
+ for j in range(p_vars):
124
+ g = X[:, j]
125
+ h_bar = h.mean(axis=0)
126
+ h_c = h - h_bar
127
+ v_h = (h_c.T @ h_c) / n
128
+ sigma_g = (n / (n - 1)) * float(g @ g) - (1 / (n - 1)) * float(g.sum()) ** 2
129
+ stat, df = _quadratic_stat(g @ h, g.sum() * h_bar, sigma_g * v_h)
130
+ p_values[j] = float(chi2.sf(stat, df=df)) if df > 0 else 1.0
131
+ j_star = int(np.argmin(p_values))
132
+ return j_star if min(p_vars * float(p_values[j_star]), 1.0) < alpha else None
133
+
134
+
135
+ def find_split(x, distfit, minbucket):
136
+ h = distfit.estfun_
137
+ n = h.shape[0]
138
+ order = np.argsort(x, kind="stable")
139
+ x_sorted = x[order]
140
+ h_sorted = h[order]
141
+ h_bar = h.mean(axis=0)
142
+ h_c = h - h_bar
143
+ v_h = (h_c.T @ h_c) / n
144
+ eigvals, eigvecs = np.linalg.eigh(v_h)
145
+ tol = max(1e-14, 1e-10 * float(np.abs(eigvals).max() or 1.0))
146
+ pos = eigvals > tol
147
+ if not pos.any():
148
+ return None
149
+ v_h_pinv = eigvecs[:, pos] @ np.diag(1.0 / eigvals[pos]) @ eigvecs[:, pos].T
150
+ h_cumsum = np.cumsum(h_sorted, axis=0)
151
+ best_stat = -np.inf
152
+ best_k = None
153
+ for k in range(minbucket, n - minbucket + 1):
154
+ if x_sorted[k - 1] == x_sorted[k]:
155
+ continue
156
+ diff = h_cumsum[k - 1] - k * h_bar
157
+ sigma_g = k * (n - k) / (n - 1)
158
+ stat = float(diff @ v_h_pinv @ diff) / sigma_g
159
+ if stat > best_stat:
160
+ best_stat = stat
161
+ best_k = k
162
+ return None if best_k is None else float(x_sorted[best_k - 1])
163
+
164
+
165
+ @dataclass
166
+ class Node:
167
+ node_id: int
168
+ depth: int
169
+ n_samples: int
170
+ distfit: DistFit
171
+ is_leaf: bool = True
172
+ split_var: int = None
173
+ split_val: float = None
174
+ left: "Node" = None
175
+ right: "Node" = None
176
+
177
+
178
+ class DistTreeRegressor:
179
+ def __init__(self, max_depth=None, alpha=0.05, minprob=0.01):
180
+ self.family = GaussianFamily()
181
+ self.max_depth = max_depth
182
+ self.alpha = alpha
183
+ self.minprob = minprob
184
+
185
+ def fit(self, X, y):
186
+ X = np.asarray(X, dtype=float)
187
+ y = np.asarray(y, dtype=float).ravel()
188
+ self._node_counter = 0
189
+ self.tree_ = self._grow(np.arange(len(y)), X, y, 0, math.ceil(10 * self.family.npar))
190
+ return self
191
+
192
+ def _next_id(self):
193
+ node_id = self._node_counter
194
+ self._node_counter += 1
195
+ return node_id
196
+
197
+ def _grow(self, indices, X, y, depth, min_leaf):
198
+ y_node = y[indices]
199
+ if float(np.var(y_node)) < 1e-14:
200
+ return Node(self._next_id(), depth, len(indices), DistFit(self.family).fit(y_node))
201
+
202
+ distfit = DistFit(self.family).fit(y_node)
203
+ node = Node(self._next_id(), depth, len(indices), distfit)
204
+ if (
205
+ not np.all(np.isfinite(distfit.estfun_))
206
+ or (self.max_depth is not None and depth >= self.max_depth)
207
+ or len(indices) < min_leaf
208
+ ):
209
+ return node
210
+
211
+ X_node = X[indices]
212
+ split_var = select_variable(X_node, distfit, self.alpha)
213
+ if split_var is None:
214
+ return node
215
+ threshold = find_split(
216
+ X_node[:, split_var],
217
+ distfit,
218
+ max(min_leaf, math.ceil(self.minprob * len(indices))),
219
+ )
220
+ if threshold is None:
221
+ return node
222
+
223
+ left_mask = X_node[:, split_var] <= threshold
224
+ node.is_leaf = False
225
+ node.split_var = split_var
226
+ node.split_val = threshold
227
+ node.left = self._grow(indices[left_mask], X, y, depth + 1, min_leaf)
228
+ node.right = self._grow(indices[~left_mask], X, y, depth + 1, min_leaf)
229
+ return node
230
+
231
+ def _apply_one(self, x):
232
+ node = self.tree_
233
+ while not node.is_leaf:
234
+ node = node.left if x[node.split_var] <= node.split_val else node.right
235
+ return node
236
+
237
+ def predict_params(self, X):
238
+ leaves = [self._apply_one(row) for row in np.asarray(X, dtype=float)]
239
+ return {
240
+ "mu": np.array([leaf.distfit.coef_["mu"] for leaf in leaves]),
241
+ "sigma": np.array([leaf.distfit.coef_["sigma"] for leaf in leaves]),
242
+ }
243
+
244
+
245
+ class DistTree:
246
+ def __init__(self, max_depth=3):
247
+ self.max_depth = max_depth
248
+ self.models = []
249
+
250
+ def fit(self, x):
251
+ self.ord_enc = []
252
+ self.ord_enc_joint = []
253
+ self.means = []
254
+ self.stds = []
255
+ for i in range(x.shape[1]):
256
+ d = x[:, i].clone()
257
+ df = pd.DataFrame(d, columns=["x"]).dropna()
258
+ model = DistTreeRegressor(max_depth=self.max_depth)
259
+ model.fit(df["x"].to_frame(), df["x"])
260
+ self.models.append(model)
261
+ preds = pd.DataFrame(model.predict_params(df["x"].to_frame()), columns=["mu", "sigma"])
262
+ ord_enc = OrdinalEncoder(dtype=int)
263
+ df_enc = ord_enc.fit_transform(preds)
264
+ self.ord_enc.append(ord_enc)
265
+ joint_group = np.char.add(np.char.add(df_enc[:, 0].astype(str), "_"), df_enc[:, 1].astype(str))
266
+ ord_enc_joint = OrdinalEncoder(dtype=int)
267
+ joint_group = ord_enc_joint.fit_transform(joint_group.reshape(-1, 1))
268
+ self.ord_enc_joint.append(ord_enc_joint)
269
+ df_aux = pd.DataFrame(
270
+ np.column_stack((preds.to_numpy(), joint_group)),
271
+ columns=["mu", "sigma", "group"],
272
+ )
273
+ self.means.append(df_aux.drop_duplicates(["group"]).sort_values("group")["mu"].to_list())
274
+ self.stds.append(df_aux.drop_duplicates(["group"]).sort_values("group")["sigma"].to_list())
275
+
276
+ def get_groups(self, x):
277
+ groups = []
278
+ for i in range(x.shape[1]):
279
+ d = x[:, i].clone()
280
+ miss_mask = d.isnan()
281
+ d[miss_mask] = d.nanmean()
282
+ preds = pd.DataFrame(self.models[i].predict_params(d.reshape(-1, 1)), columns=["mu", "sigma"])
283
+ df_enc = self.ord_enc[i].transform(preds)
284
+ joint_group = np.char.add(np.char.add(df_enc[:, 0].astype(str), "_"), df_enc[:, 1].astype(str))
285
+ joint_group = self.ord_enc_joint[i].transform(joint_group.reshape(-1, 1))
286
+ joint_group = joint_group.astype(float).flatten()
287
+ joint_group[miss_mask] = np.nan
288
+ groups.append(joint_group)
289
+ return np.column_stack(groups)
@@ -0,0 +1,120 @@
1
+ import numpy as np
2
+ import pandas as pd
3
+ import torch
4
+ from sklearn.mixture import BayesianGaussianMixture
5
+ from sklearn.preprocessing import OrdinalEncoder
6
+
7
+ from .disttree import DistTree
8
+
9
+
10
+ class Discretizer:
11
+ def __init__(
12
+ self,
13
+ X_num_trn,
14
+ variant="dt",
15
+ k_max=20,
16
+ perc_obs=0.03,
17
+ seed=42,
18
+ adjust_means=False,
19
+ max_depth=3,
20
+ ):
21
+ self.seed = seed
22
+ self.variant = variant
23
+ self.adjust_means = adjust_means
24
+ self.max_depth = max_depth
25
+ self.k_max = k_max
26
+ self.perc_obs = perc_obs
27
+ self.fit_gmm_ord_enc = True
28
+ self.has_missing = torch.isnan(X_num_trn).any(0).numpy()
29
+ miss_mean = torch.nanmean(X_num_trn, dim=0)
30
+
31
+ if self.variant == "gmm":
32
+ self.gmms = self._train_bgmms(X_num_trn, k_max=k_max)
33
+ groups = self._get_gmm_groups(X_num_trn)
34
+ elif self.variant == "dt":
35
+ self.disttree = DistTree(max_depth)
36
+ self.disttree.fit(X_num_trn)
37
+ groups = self.disttree.get_groups(X_num_trn)
38
+
39
+ if self.adjust_means:
40
+ means, stds = [], []
41
+ for i in range(X_num_trn.shape[1]):
42
+ df = pd.DataFrame({"x": X_num_trn[:, i].clone(), "group": groups[:, i]})
43
+ df_stats = df.groupby("group").agg(["mean", "std"]).droplevel(0, axis=1)
44
+ means.append(torch.tensor(df_stats["mean"].to_numpy(), dtype=torch.float32))
45
+ stds.append(torch.tensor(df_stats["std"].to_numpy(), dtype=torch.float32))
46
+ elif self.variant == "gmm":
47
+ means = [torch.tensor(gmm.means_.squeeze(), dtype=torch.float32) for gmm in self.gmms]
48
+ stds = [torch.tensor(np.sqrt(gmm.covariances_.squeeze()), dtype=torch.float32) for gmm in self.gmms]
49
+ elif self.variant == "dt":
50
+ means = [torch.tensor(m, dtype=torch.float32) for m in self.disttree.means]
51
+ stds = [torch.tensor(s, dtype=torch.float32) for s in self.disttree.stds]
52
+
53
+ self.has_inflated = []
54
+ self.infl_groups = []
55
+ for i in range(X_num_trn.shape[1]):
56
+ df = pd.DataFrame({"x": X_num_trn[:, i].clone(), "group": groups[:, i]})
57
+ df_stats = df.groupby("group").agg(["mean", "std"]).droplevel(0, axis=1)
58
+ infl_idx = df_stats.loc[df_stats["std"] == 0].index.to_list()
59
+ self.has_inflated.append(len(infl_idx) > 0)
60
+ self.infl_groups.append(infl_idx)
61
+ stds[i][infl_idx] = 0
62
+
63
+ if self.has_missing.any():
64
+ for i in range(X_num_trn.shape[1]):
65
+ if self.has_missing[i]:
66
+ means[i] = torch.cat((miss_mean[i].unsqueeze(0), means[i]))
67
+ stds[i] = torch.cat((torch.zeros(1), stds[i]))
68
+ self.means = means
69
+ self.stds = stds
70
+
71
+ def encode(self, X):
72
+ groups = self._get_gmm_groups(X) if self.variant == "gmm" else self.disttree.get_groups(X)
73
+ return (*self.postprocess_groups(groups), self.infl_groups, self.has_missing)
74
+
75
+ def postprocess_groups(self, groups):
76
+ infl_mask = []
77
+ for i in range(groups.shape[1]):
78
+ infl_mask.append(torch.tensor(np.isin(groups[:, i], self.infl_groups[i]), dtype=torch.bool))
79
+ infl_mask = torch.column_stack(infl_mask)
80
+
81
+ miss_mask = []
82
+ for i in range(groups.shape[1]):
83
+ g_i = groups[:, i]
84
+ miss_mask.append(np.isnan(g_i))
85
+ if self.has_missing[i]:
86
+ groups[:, i] = np.nan_to_num(g_i.copy() + 1, nan=0, copy=True)
87
+ miss_mask = np.column_stack(miss_mask) if len(miss_mask) > 0 else None
88
+ miss_mask = torch.tensor(miss_mask, dtype=torch.bool) if self.has_missing.any() else None
89
+ return torch.tensor(groups, dtype=torch.long), miss_mask | infl_mask if miss_mask is not None else infl_mask
90
+
91
+ def _get_gmm_groups(self, X):
92
+ groups = []
93
+ for i in range(X.shape[1]):
94
+ d = X[:, i].clone()
95
+ miss_mask = d.isnan()
96
+ d[miss_mask] = d.nanmean()
97
+ group = self.gmms[i].predict(d.reshape(-1, 1)).astype(float)
98
+ group[miss_mask] = np.nan
99
+ groups.append(group)
100
+ groups = np.column_stack(groups)
101
+ if self.fit_gmm_ord_enc:
102
+ self.fit_gmm_ord_enc = False
103
+ self.gmm_ord_enc = OrdinalEncoder()
104
+ self.gmm_ord_enc.fit(groups)
105
+ return self.gmm_ord_enc.transform(groups)
106
+
107
+ def _train_bgmms(self, X, k_max=20):
108
+ bgmms = []
109
+ for i in range(X.shape[1]):
110
+ d = X[:, i].clone()
111
+ d = d[~d.isnan()]
112
+ bgmm = BayesianGaussianMixture(
113
+ n_components=k_max,
114
+ random_state=self.seed,
115
+ weight_concentration_prior_type="dirichlet_process",
116
+ weight_concentration_prior=0.001,
117
+ n_init=1,
118
+ )
119
+ bgmms.append(bgmm.fit(d.reshape(-1, 1)))
120
+ return bgmms