coneforest 0.1.0__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 (18) hide show
  1. coneforest-0.1.0/.gitignore +29 -0
  2. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/coneforest/__init__.py +9 -0
  3. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/coneforest/_forest.py +110 -0
  4. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/coneforest-0.1.0.dist-info/licenses/LICENSE +674 -0
  5. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/jax-0.12.1.dist-info/licenses/LICENSE +202 -0
  6. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/ml_dtypes-0.7.0.dist-info/licenses/LICENSE +238 -0
  7. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/numpy/ma/LICENSE +24 -0
  8. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/numpy-2.5.5.dist-info/licenses/numpy/_core/src/highway/LICENSE +371 -0
  9. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/numpy-2.5.5.dist-info/licenses/numpy/_core/src/umath/svml/LICENSE +30 -0
  10. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/numpy-2.5.5.dist-info/licenses/numpy/ma/LICENSE +24 -0
  11. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/opt_einsum-3.4.0.dist-info/licenses/LICENSE +22 -0
  12. coneforest-0.1.0/.package-test-venv/lib/python3.12/site-packages/scipy/_lib/_uarray/LICENSE +29 -0
  13. coneforest-0.1.0/LICENSE +674 -0
  14. coneforest-0.1.0/PKG-INFO +94 -0
  15. coneforest-0.1.0/README.md +75 -0
  16. coneforest-0.1.0/coneforest/__init__.py +9 -0
  17. coneforest-0.1.0/coneforest/_forest.py +110 -0
  18. coneforest-0.1.0/pyproject.toml +38 -0
@@ -0,0 +1,29 @@
1
+ # Python bytecode and caches
2
+ __pycache__/
3
+ *.py[cod]
4
+ .pytest_cache/
5
+ .mypy_cache/
6
+ .ruff_cache/
7
+ .ipynb_checkpoints/
8
+
9
+ # Packaging artifacts
10
+ build/
11
+ dist/
12
+ *.egg-info/
13
+
14
+ # Virtual environments
15
+ .venv/
16
+ venv/
17
+
18
+ # Test and coverage output
19
+ .coverage
20
+ htmlcov/
21
+
22
+ # Local configuration and secrets
23
+ .env
24
+ .env.*
25
+
26
+ # Editor and OS files
27
+ .idea/
28
+ .vscode/
29
+ .DS_Store
@@ -0,0 +1,9 @@
1
+ """ConeForest, an isolation-style anomaly detector built on the JAX library.
2
+
3
+ from coneforest import ConeForest
4
+ scores = ConeForest(seed=0).fit(X_train).decision_function(X_test)
5
+ """
6
+ from ._forest import ConeForest, cone_forest_fit, cone_forest_predict
7
+
8
+ __all__ = ["ConeForest", "cone_forest_fit", "cone_forest_predict"]
9
+ __version__ = "0.1.0"
@@ -0,0 +1,110 @@
1
+ """ConeForest: random oblivious trees, scored by cell mass at every depth.
2
+
3
+ Each of K levels cuts one feature (drawn with replacement) at a threshold
4
+ uniform in the sample's range. A cell code holds the K cut bits. Its low
5
+ j bits are the cell at depth j. Depth j counts start at offset 2**j - 2.
6
+ """
7
+ import math
8
+
9
+ import jax
10
+ import jax.numpy as jnp
11
+ import numpy as np
12
+ from jax import jit, random
13
+
14
+
15
+ def _cone_subsample(key, N, b, psi):
16
+ """Row indices (b, psi) of each tree's sample. Needs psi < N."""
17
+ keys = random.split(key, b)
18
+ if N > 50 * psi:
19
+ # Few repeats at this ratio, and it avoids a full sort of N per tree.
20
+ return jax.vmap(lambda k: random.randint(k, (psi,), 0, N))(keys)
21
+ return jax.vmap(lambda k: random.choice(k, N, (psi,), replace=False))(keys)
22
+
23
+
24
+ def _build_cone_forest(key, X, b, psi, K):
25
+ N, d = X.shape
26
+ k_sub, k_feat, k_thr = random.split(key, 3)
27
+ if psi >= N:
28
+ sub = jnp.broadcast_to(jnp.arange(N), (b, N))
29
+ else:
30
+ sub = _cone_subsample(k_sub, N, b, psi)
31
+ m = sub.shape[1]
32
+
33
+ feats = random.randint(k_feat, (b, K), 0, d)
34
+ S = X[sub[:, :, None], feats[:, None, :]] # (b, m, K)
35
+ lo, hi = S.min(axis=1), S.max(axis=1)
36
+ thr = lo + random.uniform(k_thr, (b, K)) * (hi - lo)
37
+
38
+ weights = (1 << jnp.arange(K)).astype(jnp.int32)
39
+ codes = jnp.sum((S > thr[:, None, :]) * weights, axis=2) # (b, m)
40
+ table = jnp.zeros((b, 1 << K), jnp.int32).at[jnp.arange(b)[:, None], codes].add(1)
41
+ flat = jnp.concatenate(
42
+ [table.reshape(b, 1 << (K - j), 1 << j).sum(axis=1) for j in range(1, K + 1)], axis=1
43
+ ) # (b, 2**(K+1) - 2)
44
+ log_mass = jnp.log((flat + 1.0) / (m + 2.0))
45
+
46
+ # Fold the mean over depths into one score per full code.
47
+ all_codes = jnp.arange(1 << K, dtype=jnp.int32)
48
+ depth = jnp.arange(1, K + 1, dtype=jnp.int32)
49
+ idx = (1 << depth) - 2 + (all_codes[:, None] & ((1 << depth) - 1)) # (2**K, K)
50
+ cell_score = -jnp.mean(log_mass[:, idx], axis=2) # (b, 2**K)
51
+ return feats, thr, cell_score
52
+
53
+
54
+ def _score_cone_splits(X, feats, thr, cell_score):
55
+ b, K = feats.shape
56
+ weights = (1 << jnp.arange(K)).astype(jnp.int32)
57
+ codes = jnp.sum((X[:, feats] > thr[None]) * weights, axis=2) # (n, b)
58
+ return jnp.mean(cell_score[jnp.arange(b)[None, :], codes], axis=1)
59
+
60
+
61
+ build_cone_forest = jit(_build_cone_forest, static_argnums=(2, 3, 4))
62
+ score_cone_splits = jit(_score_cone_splits)
63
+
64
+
65
+ def cone_forest_fit(X_train, *, b=256, psi=256, seed=0):
66
+ X_train = jnp.asarray(X_train, dtype=jnp.float32)
67
+ m = min(psi, X_train.shape[0])
68
+ K = max(1, math.ceil(math.log2(m)))
69
+ feats, thr, cell_score = build_cone_forest(random.key(seed), X_train, b, psi, K)
70
+ return {"feats": feats, "thr": thr, "cell_score": cell_score}
71
+
72
+
73
+ def cone_forest_predict(X, model, chunk=32768):
74
+ """Score in chunks of equal size, so memory stays at about chunk * b * K."""
75
+ X = np.asarray(X, dtype=np.float32)
76
+ n = X.shape[0]
77
+ size = min(chunk, n)
78
+ out = []
79
+ for start in range(0, n, size):
80
+ part = X[start:start + size]
81
+ pad = size - part.shape[0]
82
+ if pad:
83
+ part = np.pad(part, ((0, pad), (0, 0)))
84
+ s = score_cone_splits(jnp.asarray(part), model["feats"], model["thr"], model["cell_score"])
85
+ out.append(np.asarray(s)[:size - pad])
86
+ return np.concatenate(out)
87
+
88
+
89
+ class ConeForest:
90
+ """Anomaly detector. Higher scores mean more anomalous rows.
91
+
92
+ b: number of trees. psi: rows sampled per tree. seed: fixes all draws.
93
+ """
94
+
95
+ def __init__(self, b=256, psi=256, seed=0):
96
+ self.b = b
97
+ self.psi = psi
98
+ self.seed = seed
99
+
100
+ def fit(self, X, y=None):
101
+ self.model_ = cone_forest_fit(X, b=self.b, psi=self.psi, seed=self.seed)
102
+ return self
103
+
104
+ def decision_function(self, X):
105
+ """Anomaly score of each row of X, as a NumPy array."""
106
+ return cone_forest_predict(X, self.model_)
107
+
108
+ def fit_predict(self, X, y=None):
109
+ """Fit on X and return the anomaly scores of the same rows."""
110
+ return self.fit(X).decision_function(X)