diff --git a/CHANGELOG.md b/CHANGELOG.md
index a08bf12..b6dd9e8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,11 @@
# CHANGELOG
+## 1.6.0
+- major package refactor and simplification
+- streamlined TopologicalEmbedding pipeline (numpy computations, removed parallel)
+- fix bug (thanks to F. Hudrisier) due to wrong hash usage
+
## 1.5.0
- major computation gains (joblib.Parallel)
- cleared, streamlined readme with acknowledgements
diff --git a/README.md b/README.md
index a6f56ea..72e8e3b 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,6 @@
-
---
# TDAAD – Topological Data Analysis for Anomaly Detection
@@ -113,7 +112,6 @@ For more advanced usage (e.g. custom embeddings, parameter tuning), see the [exa
- `window_size` controls the time resolution — larger windows capture slower anomalies, smaller ones detect more localized changes.
- `n_centers_by_dim` controls the number of reference shapes used per homology dimension (e.g. connected components in H0, loops in H1, ...). Increasing this improves sensitivity but adds computation time.
- `tda_max_dim` sets the **maximum topological feature dimension** computed (0 = connected components, 1 = loops, 2 = voids, ...). Higher values increase runtime and memory usage.
-- Internally, computations are **parallelized** using `joblib` to scale to larger datasets. Use `n_jobs` to control parallelism.
- Inputs can be `numpy.ndarray` or `pandas.DataFrame`. Column names are preserved in the output when using DataFrames.
⚙️ You can typically handle ~100 sensors and a few hundred time steps per window on a modern machine.
diff --git a/examples/oua_tutorial.ipynb b/examples/oua_tutorial.ipynb
index ae67f59..692e56c 100644
--- a/examples/oua_tutorial.ipynb
+++ b/examples/oua_tutorial.ipynb
@@ -24,15 +24,17 @@
"metadata": {},
"outputs": [],
"source": [
+ "import numpy as np\n",
+ "\n",
"def ornstein_uhlenbeck_anomaly(\n",
- " t,\n",
- " size=1,\n",
- " noise_scale=1,\n",
- " mean_reverting=1,\n",
- " anomaly_freq=1,\n",
- " anomaly_duration=.1,\n",
- " anomaly_scale=1,\n",
- " seed=314,\n",
+ " t,\n",
+ " size=1,\n",
+ " noise_scale=1,\n",
+ " mean_reverting=1,\n",
+ " anomaly_freq=1,\n",
+ " anomaly_duration=.1,\n",
+ " anomaly_scale=1,\n",
+ " seed=314,\n",
"):\n",
" rng = np.random.RandomState(seed)\n",
" length, = t.shape\n",
@@ -159,10 +161,12 @@
}
],
"source": [
- "from tdaad.utils.tda_functions import transform_to_persistence_diagram\n",
+ "from tdaad.topological_embedding import numpy_data_to_similarity, RipsPersistence\n",
"from gudhi import plot_persistence_diagram\n",
"\n",
- "global_pdiagram = transform_to_persistence_diagram(X, tda_max_dim=2)\n",
+ "sim_matrix = numpy_data_to_similarity(X)\n",
+ "rips = RipsPersistence(homology_dimensions=range(3), input_type=\"lower distance matrix\")\n",
+ "global_pdiagram = rips.transform([sim_matrix])[0]\n",
"plot_persistence_diagram(global_pdiagram)"
]
},
@@ -253,7 +257,8 @@
"swv = np.lib.stride_tricks.sliding_window_view(X.index, X.shape[0]//2)[::200, :]\n",
"\n",
"for window in swv:\n",
- " pdiagram = transform_to_persistence_diagram(X.loc[window], tda_max_dim=2)\n",
+ " sim_matrix = numpy_data_to_similarity(X.loc[window])\n",
+ " pdiagram = rips.transform([sim_matrix])[0]\n",
" X.loc[window].plot()\n",
" ax = plot_persistence_diagram(pdiagram)\n",
" ax.set_title(str(window[-1]))"
@@ -287,248 +292,24 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 10,
"id": "bf1787bd",
"metadata": {},
"outputs": [
{
"data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " Atol0__Atol Center 1 | \n",
- " Atol0__Atol Center 2 | \n",
- " Atol1__Atol Center 1 | \n",
- " Atol1__Atol Center 2 | \n",
- " Atol2__Atol Center 1 | \n",
- " Atol2__Atol Center 2 | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 5876e224e0e2cc76cf88d99658e19a5d05f17053 | \n",
- " 8.014427 | \n",
- " 8.337348 | \n",
- " 0.139429 | \n",
- " 2.369379 | \n",
- " 1.041305 | \n",
- " 0.869459 | \n",
- "
\n",
- " \n",
- " | efa37009e7d2560f20e9baed56c1dd228fb57324 | \n",
- " 7.646981 | \n",
- " 8.840381 | \n",
- " 0.905686 | \n",
- " 0.737120 | \n",
- " 0.000000 | \n",
- " 0.000000 | \n",
- "
\n",
- " \n",
- " | 59b90ed4fa88ee1a1db0b4de013b52ebc509cb7c | \n",
- " 8.490968 | \n",
- " 7.406048 | \n",
- " 1.041629 | \n",
- " 1.851082 | \n",
- " 0.934886 | \n",
- " 0.006830 | \n",
- "
\n",
- " \n",
- " | c389c33d12111c0f7710f8d0c02fe459cf6d03d0 | \n",
- " 8.781508 | \n",
- " 7.212324 | \n",
- " 1.795035 | \n",
- " 1.523272 | \n",
- " 0.009076 | \n",
- " 0.957346 | \n",
- "
\n",
- " \n",
- " | 78405d0ae4b74c3bb0232b5ca3963e421d920151 | \n",
- " 10.458802 | \n",
- " 5.208043 | \n",
- " 1.027982 | \n",
- " 1.873740 | \n",
- " 0.000000 | \n",
- " 0.000000 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 02b39cfe47c2e5b6c8efcc391f71294fa3d308e9 | \n",
- " 9.582538 | \n",
- " 4.739616 | \n",
- " 0.158071 | \n",
- " 1.707738 | \n",
- " 0.000000 | \n",
- " 0.000000 | \n",
- "
\n",
- " \n",
- " | ed2c3fa613fbe7d8c3f1ac35e1a7cae4257b1f5e | \n",
- " 9.188312 | \n",
- " 5.705798 | \n",
- " 0.003870 | \n",
- " 1.839969 | \n",
- " 0.000000 | \n",
- " 0.000000 | \n",
- "
\n",
- " \n",
- " | a6cf12b25e6e042083b9bb6de3b5a6032e8ba9de | \n",
- " 9.862403 | \n",
- " 6.028840 | \n",
- " 0.504404 | \n",
- " 1.867278 | \n",
- " 0.128751 | \n",
- " 0.723518 | \n",
- "
\n",
- " \n",
- " | 0d55a03c9d97f415f1451826bd98971b0dee2235 | \n",
- " 8.202467 | \n",
- " 7.330862 | \n",
- " 0.080560 | \n",
- " 2.732715 | \n",
- " 0.000000 | \n",
- " 0.000000 | \n",
- "
\n",
- " \n",
- " | 3139931912f8b6d1541e63495662bbc421644b45 | \n",
- " 8.475916 | \n",
- " 6.191814 | \n",
- " 1.013029 | \n",
- " 2.501380 | \n",
- " 0.205330 | \n",
- " 1.519385 | \n",
- "
\n",
- " \n",
- "
\n",
- "
191 rows × 6 columns
\n",
- "