adaptivepy-sampling 0.1.1__tar.gz → 0.2.0__tar.gz

adaptivepy_sampling-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Hassan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

adaptivepy_sampling-0.2.0/PKG-INFO

@@ -0,0 +1,136 @@
+Metadata-Version: 2.4
+Name: adaptivepy-sampling
+Version: 0.2.0
+Summary: Adaptive sampling on MD trajectories via clustering and policy-driven seed selection
+Author: Hassan
+License: MIT License
+        
+        Copyright (c) 2026 Hassan
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.20
+Requires-Dist: scikit-learn>=1.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: click>=8.0
+Requires-Dist: joblib>=1.0
+Requires-Dist: mdtraj>=1.9
+Requires-Dist: scipy>=1.7
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs-material>=9.0; extra == "docs"
+Requires-Dist: mkdocstrings[python]>=0.24; extra == "docs"
+Dynamic: license-file
+
+# AdaptivePy
+
+**Adaptive sampling for molecular dynamics trajectories**
+
+Clustering-based state space partitioning and policy-driven seed selection for MD workflows.
+
+[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue?style=for-the-badge)](https://hnadeem2.github.io/AdaptivePy/)
+[![PyPI](https://img.shields.io/badge/PyPI-adaptivepy--sampling-orange?style=for-the-badge)](https://pypi.org/project/adaptivepy-sampling/)
+[![Python](https://img.shields.io/badge/python-3.9+-green?style=for-the-badge)](https://www.python.org/)
+
+---
+
+## Overview
+
+AdaptivePy helps you identify under-sampled regions of conformational space and select seed frames for new simulations. It loads per-trajectory feature arrays, clusters frames, applies adaptive policies, and writes reproducible metadata and optional PDB structures.
+
+**Full documentation:** [https://hnadeem2.github.io/AdaptivePy/](https://hnadeem2.github.io/AdaptivePy/)
+
+| | |
+|---|---|
+| **Input** | Feature arrays (`.npy` / `.pkl`), optional coordinate trajectories |
+| **Clustering** | KMeans, MiniBatch KMeans, regular-space |
+| **Policies** | Least counts, random, FAST, MA-REAP (extensible) |
+| **Output** | Seeds, cluster assignments, model, logs, optional PDBs |
+
+## Installation
+
+```bash
+pip install adaptivepy-sampling
+```
+
+For development:
+
+```bash
+git clone https://github.com/hnadeem2/AdaptivePy.git
+cd AdaptivePy
+pip install -e ".[dev,docs]"
+```
+
+## Quick start
+
+1. **Prepare features** — one file per trajectory, shape `(n_frames, n_features)`:
+
+   ```text
+   features/
+   ├── traj_0.npy
+   └── traj_1.pkl
+   ```
+
+2. **Configure** — edit `examples/config.yaml` (or create your own).
+
+3. **Run**:
+
+   ```bash
+   adaptivepy run examples/config.yaml
+   ```
+
+See the [Getting Started guide](https://hnadeem2.github.io/AdaptivePy/getting-started/) for a complete walkthrough.
+
+## CLI
+
+```bash
+adaptivepy run config.yaml       # run adaptive sampling
+adaptivepy validate config.yaml  # validate inputs only
+adaptivepy list-policies         # list available policies
+```
+
+## Python API
+
+```python
+from adaptivepy import run_adaptive_sampling
+
+results = run_adaptive_sampling("config.yaml")
+```
+
+## Documentation
+
+| Guide | Description |
+|-------|-------------|
+| [Getting Started](https://hnadeem2.github.io/AdaptivePy/getting-started/) | First run in minutes |
+| [Configuration](https://hnadeem2.github.io/AdaptivePy/configuration/) | YAML options and defaults |
+| [Feature Inputs](https://hnadeem2.github.io/AdaptivePy/features/) | File formats and layout |
+| [Policies](https://hnadeem2.github.io/AdaptivePy/policies/) | Seed selection strategies |
+| [API Reference](https://hnadeem2.github.io/AdaptivePy/reference/api/) | Module documentation |
+
+## Contributors
+
+- Hassan
+
+## License
+
+MIT. See [LICENSE](LICENSE) for details.

adaptivepy_sampling-0.2.0/README.md

@@ -0,0 +1,92 @@
+# AdaptivePy
+
+**Adaptive sampling for molecular dynamics trajectories**
+
+Clustering-based state space partitioning and policy-driven seed selection for MD workflows.
+
+[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue?style=for-the-badge)](https://hnadeem2.github.io/AdaptivePy/)
+[![PyPI](https://img.shields.io/badge/PyPI-adaptivepy--sampling-orange?style=for-the-badge)](https://pypi.org/project/adaptivepy-sampling/)
+[![Python](https://img.shields.io/badge/python-3.9+-green?style=for-the-badge)](https://www.python.org/)
+
+---
+
+## Overview
+
+AdaptivePy helps you identify under-sampled regions of conformational space and select seed frames for new simulations. It loads per-trajectory feature arrays, clusters frames, applies adaptive policies, and writes reproducible metadata and optional PDB structures.
+
+**Full documentation:** [https://hnadeem2.github.io/AdaptivePy/](https://hnadeem2.github.io/AdaptivePy/)
+
+| | |
+|---|---|
+| **Input** | Feature arrays (`.npy` / `.pkl`), optional coordinate trajectories |
+| **Clustering** | KMeans, MiniBatch KMeans, regular-space |
+| **Policies** | Least counts, random, FAST, MA-REAP (extensible) |
+| **Output** | Seeds, cluster assignments, model, logs, optional PDBs |
+
+## Installation
+
+```bash
+pip install adaptivepy-sampling
+```
+
+For development:
+
+```bash
+git clone https://github.com/hnadeem2/AdaptivePy.git
+cd AdaptivePy
+pip install -e ".[dev,docs]"
+```
+
+## Quick start
+
+1. **Prepare features** — one file per trajectory, shape `(n_frames, n_features)`:
+
+   ```text
+   features/
+   ├── traj_0.npy
+   └── traj_1.pkl
+   ```
+
+2. **Configure** — edit `examples/config.yaml` (or create your own).
+
+3. **Run**:
+
+   ```bash
+   adaptivepy run examples/config.yaml
+   ```
+
+See the [Getting Started guide](https://hnadeem2.github.io/AdaptivePy/getting-started/) for a complete walkthrough.
+
+## CLI
+
+```bash
+adaptivepy run config.yaml       # run adaptive sampling
+adaptivepy validate config.yaml  # validate inputs only
+adaptivepy list-policies         # list available policies
+```
+
+## Python API
+
+```python
+from adaptivepy import run_adaptive_sampling
+
+results = run_adaptive_sampling("config.yaml")
+```
+
+## Documentation
+
+| Guide | Description |
+|-------|-------------|
+| [Getting Started](https://hnadeem2.github.io/AdaptivePy/getting-started/) | First run in minutes |
+| [Configuration](https://hnadeem2.github.io/AdaptivePy/configuration/) | YAML options and defaults |
+| [Feature Inputs](https://hnadeem2.github.io/AdaptivePy/features/) | File formats and layout |
+| [Policies](https://hnadeem2.github.io/AdaptivePy/policies/) | Seed selection strategies |
+| [API Reference](https://hnadeem2.github.io/AdaptivePy/reference/api/) | Module documentation |
+
+## Contributors
+
+- Hassan
+
+## License
+
+MIT. See [LICENSE](LICENSE) for details.

{adaptivepy_sampling-0.1.1 → adaptivepy_sampling-0.2.0}/adaptivepy/__init__.py

@@ -1,6 +1,6 @@
 """AdaptivePy: adaptive sampling for molecular dynamics trajectories."""
 
-__version__ = "0.1.1"
+__version__ = "0.2.0"
 
 from adaptivepy.api import run_adaptive_sampling
 

{adaptivepy_sampling-0.1.1 → adaptivepy_sampling-0.2.0}/adaptivepy/api.py

@@ -9,8 +9,9 @@ from typing import Dict, List, Optional
 import numpy as np
 
 from adaptivepy.clustering import create_clusterer, fit_clusterer
-from adaptivepy.config.schema import RunConfig, load_config
+from adaptivepy.config.schema import RunConfig, build_policy_kwargs, load_config
 from adaptivepy.io.loader import (
+    list_feature_files,
     list_trajectory_files,
     load_features,
     validate_dataset,
@@ -27,6 +28,8 @@ from adaptivepy.output.writer import (
     write_cluster_model,
     write_cluster_statistics,
     write_combined_metadata,
+    write_fast_scores,
+    write_ma_reap_outputs,
     write_policy_outputs,
     write_run_config,
 )
@@ -84,7 +87,7 @@ def run_adaptive_sampling(
     np.random.seed(config.random_seed)
 
     # --- Load and validate data ---
-    feature_files = sorted(Path(config.features_dir).glob("*.npy"))
+    feature_files = list_feature_files(config.features_dir)
     trajectory_files: Optional[List[Path]] = None
     trajectory_map: Optional[Dict[int, Path]] = None
 
@@ -120,6 +123,7 @@ def run_adaptive_sampling(
 
     cluster_stats = compute_cluster_stats(dataset)
     centers = clusterer.cluster_centers_
+    n_features = dataset.feature_matrix.shape[1]
 
     logger.info(
         "Clustering complete: %d clusters, %d total frames",
@@ -138,9 +142,15 @@ def run_adaptive_sampling(
 
     for policy_name in config.policies:
         logger.info("Applying policy: %s", policy_name)
-        policy_kwargs = {}
-        if policy_name == "random":
-            policy_kwargs["random_state"] = config.random_seed
+        policy_kwargs = build_policy_kwargs(
+            policy_name,
+            config,
+            n_features=n_features,
+            traj_names=dataset.traj_names,
+            n_clusters=len(cluster_stats),
+        )
+        if policy_name == "ma_reap":
+            policy_kwargs["cluster_centers"] = centers
 
         policy = get_policy(policy_name, **policy_kwargs)
         selected_clusters = policy.select_clusters(
@@ -160,6 +170,20 @@ def run_adaptive_sampling(
             policy_name, seeds, cluster_stats, output_dir
         )
 
+        if policy_name == "fast" and hasattr(policy, "last_scores"):
+            write_fast_scores(policy.last_scores, policy_dir)
+
+        if policy_name == "ma_reap" and hasattr(policy, "last_scores"):
+            write_ma_reap_outputs(
+                scores=policy.last_scores,
+                weights=policy.last_weights,
+                stakes=policy.last_stakes,
+                executors=policy.last_executors,
+                agent_names=policy.agent_names,
+                seeds=seeds,
+                output_dir=policy_dir,
+            )
+
         if (
             config.write_pdbs
             and trajectory_map is not None
@@ -199,9 +223,7 @@ def validate_config(config_path: str | Path) -> RunConfig:
     config_path = Path(config_path)
     config = load_config(config_path)
 
-    feature_files = sorted(Path(config.features_dir).glob("*.npy"))
-    if not feature_files:
-        raise ValueError(f"No feature files in {config.features_dir}")
+    feature_files = list_feature_files(config.features_dir)
 
     trajectory_files = None
     if config.trajectories_dir is not None:
@@ -210,6 +232,7 @@ def validate_config(config_path: str | Path) -> RunConfig:
 
     dataset = load_features(config.features_dir)
     validate_dataset(dataset, trajectory_files)
+    n_features = dataset.feature_matrix.shape[1]
 
     if config.trajectories_dir is not None and config.topology is not None:
         trajectory_map = build_trajectory_map(
@@ -224,6 +247,14 @@ def validate_config(config_path: str | Path) -> RunConfig:
         )
 
     for policy_name in config.policies:
-        get_policy(policy_name)
+        get_policy(
+            policy_name,
+            **build_policy_kwargs(
+                policy_name,
+                config,
+                n_features=n_features,
+                traj_names=dataset.traj_names,
+            ),
+        )
 
     return config