gridfm-datakit 0.0.1__tar.gz

gridfm_datakit-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

gridfm_datakit-0.0.1/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: gridfm-datakit
+Version: 0.0.1
+Summary: Data Generation Kit
+Author-email: Alban Puech <apuech@seas.harvard.edu>, Matteo Mazzonelli <matteo.mazzonelli1@ibm.com>, Tamara Govindasamy <tamara.govindasamy@ibm.com>, Mangaliso Mngomezulu <mngomezulum@ibm.com>, Etienne Vos <etienne.vos@ibm.com>, Jonas Weiss <jwe@zurich.ibm.com>
+Maintainer-email: Alban Puech <apuech@seas.harvard.edu>
+License-Expression: Apache-2.0
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: <3.13,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: ipykernel
+Requires-Dist: matplotlib
+Requires-Dist: matpowercaseframes
+Requires-Dist: nbformat
+Requires-Dist: numba
+Requires-Dist: numpy
+Requires-Dist: pandapower==2.14.11
+Requires-Dist: pandas
+Requires-Dist: pathlib
+Requires-Dist: plotly
+Requires-Dist: pyaml
+Requires-Dist: requests
+Requires-Dist: urllib3<2.0.0
+Requires-Dist: ipywidgets
+Provides-Extra: dev
+Requires-Dist: mkdocs; extra == "dev"
+Requires-Dist: mkdocs-material; extra == "dev"
+Requires-Dist: mkdocstrings[python]; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: bandit; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest-cov; extra == "test"
+Dynamic: license-file
+
+[![Docs](https://img.shields.io/badge/docs-available-brightgreen)](https://gridfm.github.io/gridfm-datakit/)
+![Coverage](https://img.shields.io/badge/coverage-76%25-yellow)
+
+
+# Overview
+
+
+This library is brought to you by the GridFM team to generate power flow data to train machine learning and foundation models.
+
+
+
+<p align="center">
+  <img src="figs/pipeline.png" alt=""/>
+  <br/>
+</p>
+
+
+---
+
+
+
+## Comparison with other PF datasets/ libraries
+
+| Feature                                                    | GraphNeuralSolver [\[1\]](https://doi.org/10.1016/j.epsr.2020.106547)| OPFData [\[2\]](https://arxiv.org/abs/2406.07234) | OPFLearn [\[3\]](https://arxiv.org/abs/2111.01228)| PowerFlowNet [\[4\]](https://arxiv.org/abs/2311.03415) | TypedGNN [\[5\]](https://doi.org/10.1016/j.engappai.2022.105567)| PF△ [\[6\]](https://www.climatechange.ai/papers/iclr2025/67)| **gridfm-datakit** [\[7\]](https://www.cell.com/joule/fulltext/S2542-4351(24)00470-7) |
+| ---------------------------------------------------------- | ----------------- | ------- | -------- | ------------ | -------- | --- | ---------- |
+| Generator Profile                                          | ✅                | ❌      | ❌       | ✅           | ✅       | ✅  | ❌         |
+| N-1                                                        | ❌                | ✅      | ✅       | ✅           | ✅       | ✅  | ✅         |
+| > 1000 Buses                                               | ❌                | ✅      | ✅       | ❌           | ❌       | ✅  | ✅         |
+| N-k, k > 1                                                 | ❌                | ❌      | ❌       | ❌           | ❌       | ❌  | ✅         |
+| Load Scenarios from Real World Data                        | ❌                | ❌      | ❌       | ❌           | ❌       | ❌  | ✅         |
+| Multi-processing and scalable to very large (1M+) datasets | ❌                | ❌      | ❌       | ❌           | ❌       | ❌  | ✅         |
+
+
+# Installation
+
+1. ⭐ Star the [repository](https://github.com/gridfm/gridfm-datakit) on GitHub to support the project!
+
+2. Clone the repository and set up a Python virtual environment:
+
+```bash
+git clone https://github.com/gridfm/gridfm-datakit.git
+cd "gridfm-datakit"
+python3 -m venv venv
+source venv/bin/activate
+python -m pip install --upgrade pip  # Upgrade pip to ensure compatibility with pyproject.toml
+pip3 install .
+```
+
+# Getting Started
+
+## Option 1: Run data gen using interactive interface
+
+To use the interactive interface, either open `scripts/interactive_interface.ipynb` or copy the following into a Jupyter notebook and follow the instructions:
+
+```python
+from gridfm_datakit.interactive_utils import interactive_interface
+interactive_interface()
+```
+
+
+## Option 2: Using the command line interface
+
+Run the data generation routine from the command line:
+
+```bash
+gridfm_datakit path/to/config.yaml
+```
+
+
+## Configuration Overview
+
+Refer to the sections [Network](network.md), [Load Scenarios](load_scenarios.md), and [Topology perturbations](topology_perturbations.md) for a description of the configuration parameters.
+
+Sample configuration files are provided in `scripts/config`, e.g. `default.yaml`:
+
+```yaml
+network:
+  name: "case24_ieee_rts" # Name of the power grid network (without extension)
+  source: "pglib" # Data source for the grid; options: pglib, pandapower, file
+  network_dir: "scripts/grids" # if using source "file", this is the directory containing the network file (relative to the project root)
+
+
+load:
+  generator: "agg_load_profile" # Name of the load generator; options: agg_load_profile, powergraph
+  agg_profile: "default" # Name of the aggregated load profile
+  scenarios: 200 # Number of different load scenarios to generate
+  # WARNING: the following parameters are only used if generator is "agg_load_profile"
+  # if using generator "powergraph", these parameters are ignored
+  sigma: 0.05 # max local noise
+  change_reactive_power: true # If true, changes reactive power of loads. If False, keeps the ones from the case file
+  global_range: 0.4 # Range of the global scaling factor. used to set the lower bound of the scaling factor
+  max_scaling_factor: 4.0 # Max upper bound of the global scaling factor
+  step_size: 0.025 # Step size when finding the upper bound of the global scaling factor
+  start_scaling_factor: 0.8 # Initial value of the global scaling factor
+
+topology_perturbation:
+  type: "random" # Type of topology generator; options: n_minus_k, random, none
+  # WARNING: the following parameters are only used if type is not "none"
+  k: 1 # Maximum number of components to drop in each perturbation
+  n_topology_variants: 5 # Number of unique perturbed topologies per scenario
+  elements: ["line", "trafo", "gen", "sgen"] # elements to perturb options: line, trafo, gen, sgen
+
+settings:
+  num_processes: 10 # Number of parallel processes to use
+  data_dir: "./data_out" # Directory to save generated data relative to the project root
+  large_chunk_size: 50 # Number of load scenarios processed before saving
+  no_stats: false # If true, disables statistical calculations
+  overwrite: true # If true, overwrites existing files, if false, appends to files (note that bus_params.csv, edge_params.csv, scenarios_{load.generator}.csv and scenarios_{load.generator}.html will still be overwritten)
+  mode: "pf" # Mode of the script; options: contingency, pf
+```
+
+<br>
+
+## Output Files
+
+The data generation process produces several output files in the specified data directory:
+
+- **tqdm.log**: Progress bar log.
+- **error.log**: Log of the errors raised during data generation.
+- **args.log**: Copy of the config file used.
+- **pf_node.csv**: Data related to the nodes (buses) in the network, such as voltage levels and power injections.
+- **pf_edge.csv**: Branch admittance matrix for each pf case.
+- **branch_idx_removed.csv**: List of the indices of the branches (lines and transformers) that got removed when perturbing the topologies.
+- **edge_params.csv**: Branch admittance matrix and branch rate limits for the unperturbed topology.
+- **bus_params.csv**: Parameters for the buses (voltage limits and the base voltage).
+- **scenario_{args.load.generator}.csv**: Load element-level load profile obtained after using the load scenario generator.
+- **scenario_{args.load.generator}.html**: Plots of the element-level load profile.
+- **scenario_{args.load.generator}.log**: If generator is "agg_load_profile", stores the upper and lower bounds for the global scaling factor.
+- **stats.csv**: Stats about the generated data.
+- **stats_plot.html**: Plots of the stats about the generated data.

gridfm_datakit-0.0.1/README.md

@@ -0,0 +1,130 @@
+[![Docs](https://img.shields.io/badge/docs-available-brightgreen)](https://gridfm.github.io/gridfm-datakit/)
+![Coverage](https://img.shields.io/badge/coverage-76%25-yellow)
+
+
+# Overview
+
+
+This library is brought to you by the GridFM team to generate power flow data to train machine learning and foundation models.
+
+
+
+<p align="center">
+  <img src="figs/pipeline.png" alt=""/>
+  <br/>
+</p>
+
+
+---
+
+
+
+## Comparison with other PF datasets/ libraries
+
+| Feature                                                    | GraphNeuralSolver [\[1\]](https://doi.org/10.1016/j.epsr.2020.106547)| OPFData [\[2\]](https://arxiv.org/abs/2406.07234) | OPFLearn [\[3\]](https://arxiv.org/abs/2111.01228)| PowerFlowNet [\[4\]](https://arxiv.org/abs/2311.03415) | TypedGNN [\[5\]](https://doi.org/10.1016/j.engappai.2022.105567)| PF△ [\[6\]](https://www.climatechange.ai/papers/iclr2025/67)| **gridfm-datakit** [\[7\]](https://www.cell.com/joule/fulltext/S2542-4351(24)00470-7) |
+| ---------------------------------------------------------- | ----------------- | ------- | -------- | ------------ | -------- | --- | ---------- |
+| Generator Profile                                          | ✅                | ❌      | ❌       | ✅           | ✅       | ✅  | ❌         |
+| N-1                                                        | ❌                | ✅      | ✅       | ✅           | ✅       | ✅  | ✅         |
+| > 1000 Buses                                               | ❌                | ✅      | ✅       | ❌           | ❌       | ✅  | ✅         |
+| N-k, k > 1                                                 | ❌                | ❌      | ❌       | ❌           | ❌       | ❌  | ✅         |
+| Load Scenarios from Real World Data                        | ❌                | ❌      | ❌       | ❌           | ❌       | ❌  | ✅         |
+| Multi-processing and scalable to very large (1M+) datasets | ❌                | ❌      | ❌       | ❌           | ❌       | ❌  | ✅         |
+
+
+# Installation
+
+1. ⭐ Star the [repository](https://github.com/gridfm/gridfm-datakit) on GitHub to support the project!
+
+2. Clone the repository and set up a Python virtual environment:
+
+```bash
+git clone https://github.com/gridfm/gridfm-datakit.git
+cd "gridfm-datakit"
+python3 -m venv venv
+source venv/bin/activate
+python -m pip install --upgrade pip  # Upgrade pip to ensure compatibility with pyproject.toml
+pip3 install .
+```
+
+# Getting Started
+
+## Option 1: Run data gen using interactive interface
+
+To use the interactive interface, either open `scripts/interactive_interface.ipynb` or copy the following into a Jupyter notebook and follow the instructions:
+
+```python
+from gridfm_datakit.interactive_utils import interactive_interface
+interactive_interface()
+```
+
+
+## Option 2: Using the command line interface
+
+Run the data generation routine from the command line:
+
+```bash
+gridfm_datakit path/to/config.yaml
+```
+
+
+## Configuration Overview
+
+Refer to the sections [Network](network.md), [Load Scenarios](load_scenarios.md), and [Topology perturbations](topology_perturbations.md) for a description of the configuration parameters.
+
+Sample configuration files are provided in `scripts/config`, e.g. `default.yaml`:
+
+```yaml
+network:
+  name: "case24_ieee_rts" # Name of the power grid network (without extension)
+  source: "pglib" # Data source for the grid; options: pglib, pandapower, file
+  network_dir: "scripts/grids" # if using source "file", this is the directory containing the network file (relative to the project root)
+
+
+load:
+  generator: "agg_load_profile" # Name of the load generator; options: agg_load_profile, powergraph
+  agg_profile: "default" # Name of the aggregated load profile
+  scenarios: 200 # Number of different load scenarios to generate
+  # WARNING: the following parameters are only used if generator is "agg_load_profile"
+  # if using generator "powergraph", these parameters are ignored
+  sigma: 0.05 # max local noise
+  change_reactive_power: true # If true, changes reactive power of loads. If False, keeps the ones from the case file
+  global_range: 0.4 # Range of the global scaling factor. used to set the lower bound of the scaling factor
+  max_scaling_factor: 4.0 # Max upper bound of the global scaling factor
+  step_size: 0.025 # Step size when finding the upper bound of the global scaling factor
+  start_scaling_factor: 0.8 # Initial value of the global scaling factor
+
+topology_perturbation:
+  type: "random" # Type of topology generator; options: n_minus_k, random, none
+  # WARNING: the following parameters are only used if type is not "none"
+  k: 1 # Maximum number of components to drop in each perturbation
+  n_topology_variants: 5 # Number of unique perturbed topologies per scenario
+  elements: ["line", "trafo", "gen", "sgen"] # elements to perturb options: line, trafo, gen, sgen
+
+settings:
+  num_processes: 10 # Number of parallel processes to use
+  data_dir: "./data_out" # Directory to save generated data relative to the project root
+  large_chunk_size: 50 # Number of load scenarios processed before saving
+  no_stats: false # If true, disables statistical calculations
+  overwrite: true # If true, overwrites existing files, if false, appends to files (note that bus_params.csv, edge_params.csv, scenarios_{load.generator}.csv and scenarios_{load.generator}.html will still be overwritten)
+  mode: "pf" # Mode of the script; options: contingency, pf
+```
+
+<br>
+
+## Output Files
+
+The data generation process produces several output files in the specified data directory:
+
+- **tqdm.log**: Progress bar log.
+- **error.log**: Log of the errors raised during data generation.
+- **args.log**: Copy of the config file used.
+- **pf_node.csv**: Data related to the nodes (buses) in the network, such as voltage levels and power injections.
+- **pf_edge.csv**: Branch admittance matrix for each pf case.
+- **branch_idx_removed.csv**: List of the indices of the branches (lines and transformers) that got removed when perturbing the topologies.
+- **edge_params.csv**: Branch admittance matrix and branch rate limits for the unperturbed topology.
+- **bus_params.csv**: Parameters for the buses (voltage limits and the base voltage).
+- **scenario_{args.load.generator}.csv**: Load element-level load profile obtained after using the load scenario generator.
+- **scenario_{args.load.generator}.html**: Plots of the element-level load profile.
+- **scenario_{args.load.generator}.log**: If generator is "agg_load_profile", stores the upper and lower bounds for the global scaling factor.
+- **stats.csv**: Stats about the generated data.
+- **stats_plot.html**: Plots of the stats about the generated data.

gridfm_datakit-0.0.1/gridfm_datakit/__init__.py

@@ -0,0 +1,10 @@
+"""gridfm-datakit - A library for generating synthetic power grid data."""
+
+from gridfm_datakit.generate import (
+    generate_power_flow_data,
+    generate_power_flow_data_distributed,
+)
+
+__version__ = "0.1.0"
+
+__all__ = ["generate_power_flow_data", "generate_power_flow_data_distributed"]

gridfm_datakit-0.0.1/gridfm_datakit/cli.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+"""Command-line interface for generating power flow data."""
+
+import argparse
+from gridfm_datakit.generate import (
+    generate_power_flow_data_distributed,
+)
+
+
+def main():
+    """Command-line interface for the data generation script."""
+    parser = argparse.ArgumentParser(
+        description="Generate power flow data for grid analysis",
+    )
+
+    parser.add_argument(
+        "config",
+        type=str,
+        help="Path to config file",
+    )
+
+    args = parser.parse_args()
+    file_paths = generate_power_flow_data_distributed(args.config)
+
+    print("\nData generation complete.")
+    print("Generated files:")
+    for key, path in file_paths.items():
+        print(f"- {key}: {path}")
+
+
+if __name__ == "__main__":
+    main()