graph-seeder 1.0.0.dev0__tar.gz

graph_seeder-1.0.0.dev0/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+*.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+.vscode
+
+stat
+
+data/
+
+*.json
+!src/graph_seeder/configs/*.json
+
+src/test.py

graph_seeder-1.0.0.dev0/PKG-INFO

@@ -0,0 +1,191 @@
+Metadata-Version: 2.4
+Name: graph-seeder
+Version: 1.0.0.dev0
+Summary: A powerful tool to extract and densify subgraphs from Knowledge Graphs via SPARQL or LMDB, with different extraction strategies.
+Requires-Python: >=3.9
+Requires-Dist: lmdb>=2.2.0
+Requires-Dist: networkx<4.0.0,>=3.2.1
+Requires-Dist: pandas<3.0.0,>=2.3.3
+Requires-Dist: rdflib>=7.6.0
+Requires-Dist: requests>=2.32.5
+Requires-Dist: rich>=15.0.0
+Requires-Dist: sparqlwrapper>=2.0.0
+Requires-Dist: urllib3>=2.6.3
+Description-Content-Type: text/markdown
+
+# Graph densifier
+
+Graph Densifier is a collection of tools that can be used for enriching, analyzing, and extracting subgraphs from
+knowledge graphs represented as triplet datasets.
+
+It offers the following functions:
+
+- **Densify graphs** by enriching an existing knowledge graph with additional Wikidata triplets between known entities.
+- **Compute statistics** to analyze the graph's composition and connectivity.
+- **Extract paths from Wikidata** dynamically by finding connections between pairs of entities.
+- **Extract local subgraphs** from an existing dataset using shortest paths or neighborhood expansion around seed
+  entities.
+
+## Installation
+
+Follow these steps to set up the project locally:
+
+### 1. Clone the repository
+
+```bash
+git clone https://github.com/Wimmics/graph-densifier.git
+cd graph-densifier
+```
+
+### 2. Install dependencies
+
+#### Option A (recommended): using uv
+
+We recommend using uv for fast and reliable dependency management.
+
+- [Install uv](https://docs.astral.sh/uv/#installation) by following the official guide
+- Then run:
+
+```bash
+uv sync
+```
+
+#### Option B: using pip
+
+If you prefer not to use uv, you can install dependencies with pip:
+
+```bash
+pip install -r requirements.txt
+```
+
+### 3. Environment configuration
+
+> [!note]
+> To avoid being rate-limited or blocked when querying Wikidata, you should configure a user identity.
+> - Create a `.env` file at the root of the project
+> - Add the following line to the file with your Wikidata username:
+> ```bash
+> USER_AGENT="graph_densify/1.0 (contact: wikidata_username)"
+> ```
+> While this step is not strictly required to run the project, it is **recommended**. Without it, requests to Wikidata
+> may be throttled or blocked during large runs, which can interrupt the graph densification and path extraction
+> processes.
+
+## Usage
+
+The project provides four main scripts:
+
+1. **graph_densify.py** – enrich a local graph with additional Wikidata triplets.
+2. **statistics.py** – compute statistics for a triplet dataset.
+3. **subgraph_extract.py** – query Wikidata to find paths between entity pairs.
+4. **hashmap_extract_subgraph.py** – extract relevant subgraphs from a local CSV graph.
+
+## 1. Graph Densification (`graph_densify.py`)
+
+This script enriches the input graph by querying Wikidata for additional relationships between entities already present
+in the graph. It identifies all unique entities in the `subject` and `object` columns and adds any newly discovered
+direct relations to the dataset.
+
+### Command
+
+```bash
+python src/graph_densify.py --input path/to/input.csv --output path/to/output.csv
+```
+
+## 2. Graph Statistics (`statistics.py`)
+
+This script computes descriptive statistics for a triplet dataset and generates a summary CSV file in the `stat/`
+directory.
+
+### Command
+
+```bash
+python src/statistics.py --input path/to/graph.csv
+```
+
+### Computed Statistics
+
+| Metric                        | Description                                        |
+|-------------------------------|----------------------------------------------------|
+| `total_triplets`              | Total number of triplets                           |
+| `unique_subjects`             | Number of unique subjects                          |
+| `unique_predicates`           | Number of unique predicates                        |
+| `unique_objects`              | Number of unique objects                           |
+| `unique_entities`             | Unique entities across subjects and objects        |
+| `unique_subject_object_pairs` | Distinct `(subject, object)` pairs                 |
+| `connected_components`        | Number of weakly connected components in the graph |
+
+## 3. Wikidata Path Extraction (`subgraph_extract.py`)
+
+This script takes a list of entity pairs and dynamically queries Wikidata to find a short path (not necessarily the
+shortest) between them. It outputs the discovered path triplets as a CSV and saves the explored network as a `.gpickle`
+graph file.
+
+### Command
+
+```bash
+python src/subgraph_extract.py --input path/to/pairs.csv --output path/to/extracted_paths.csv
+```
+
+---
+
+## 4. Local Subgraph Extraction (`hashmap_extract_subgraph.py`)
+
+This script extracts subgraphs from a **local** graph dataset (CSV) using one of the two modes:
+
+### Mode A — Shortest paths between seed/target pairs
+
+Extracts all shortest paths between specified source-target entity pairs.
+
+```bash
+python src/hashmap_extract_subgraph.py \
+    --sub_graph path/to/main_graph.csv \
+    --seed_target_pairs path/to/pairs.csv
+```
+
+### Mode B — Radius around seed nodes
+
+Extracts all nodes within a specified number of hops (default: 2) from a list of seed entities.
+
+```bash
+python src/hashmap_extract_subgraph.py \
+    --sub_graph path/to/main_graph.csv \
+    --seeds_only path/to/seeds.csv \
+    --max_length 2
+```
+
+**Output:** The extracted subgraph is saved by default to `data/extracted_subgraph.csv`.
+
+---
+
+## Dataset Structure
+
+All datasets are expected to be provided as CSV files.
+
+### Main Graph Dataset
+
+Must contain three columns representing a knowledge graph triplet:
+
+| subject | predicate | object |
+|---------|-----------|--------|
+| Q937    | P36       | Q90    |
+| Q90     | P17       | Q142   |
+
+### Seed-Target Pair Dataset
+
+Used for finding paths between specific entities. Must contain two columns:
+
+| subject | object |
+|---------|--------|
+| Q937    | Q304   |
+| Q90     | Q183   |
+
+### Seed-Only Dataset
+
+Used for neighborhood expansion. Must contain one column representing the seed entity (the column can be named `seed` or
+be the first column):
+
+| seed |
+|------|
+| Q937 |
+| Q90  |

graph_seeder-1.0.0.dev0/README.md

@@ -0,0 +1,176 @@
+# Graph densifier
+
+Graph Densifier is a collection of tools that can be used for enriching, analyzing, and extracting subgraphs from
+knowledge graphs represented as triplet datasets.
+
+It offers the following functions:
+
+- **Densify graphs** by enriching an existing knowledge graph with additional Wikidata triplets between known entities.
+- **Compute statistics** to analyze the graph's composition and connectivity.
+- **Extract paths from Wikidata** dynamically by finding connections between pairs of entities.
+- **Extract local subgraphs** from an existing dataset using shortest paths or neighborhood expansion around seed
+  entities.
+
+## Installation
+
+Follow these steps to set up the project locally:
+
+### 1. Clone the repository
+
+```bash
+git clone https://github.com/Wimmics/graph-densifier.git
+cd graph-densifier
+```
+
+### 2. Install dependencies
+
+#### Option A (recommended): using uv
+
+We recommend using uv for fast and reliable dependency management.
+
+- [Install uv](https://docs.astral.sh/uv/#installation) by following the official guide
+- Then run:
+
+```bash
+uv sync
+```
+
+#### Option B: using pip
+
+If you prefer not to use uv, you can install dependencies with pip:
+
+```bash
+pip install -r requirements.txt
+```
+
+### 3. Environment configuration
+
+> [!note]
+> To avoid being rate-limited or blocked when querying Wikidata, you should configure a user identity.
+> - Create a `.env` file at the root of the project
+> - Add the following line to the file with your Wikidata username:
+> ```bash
+> USER_AGENT="graph_densify/1.0 (contact: wikidata_username)"
+> ```
+> While this step is not strictly required to run the project, it is **recommended**. Without it, requests to Wikidata
+> may be throttled or blocked during large runs, which can interrupt the graph densification and path extraction
+> processes.
+
+## Usage
+
+The project provides four main scripts:
+
+1. **graph_densify.py** – enrich a local graph with additional Wikidata triplets.
+2. **statistics.py** – compute statistics for a triplet dataset.
+3. **subgraph_extract.py** – query Wikidata to find paths between entity pairs.
+4. **hashmap_extract_subgraph.py** – extract relevant subgraphs from a local CSV graph.
+
+## 1. Graph Densification (`graph_densify.py`)
+
+This script enriches the input graph by querying Wikidata for additional relationships between entities already present
+in the graph. It identifies all unique entities in the `subject` and `object` columns and adds any newly discovered
+direct relations to the dataset.
+
+### Command
+
+```bash
+python src/graph_densify.py --input path/to/input.csv --output path/to/output.csv
+```
+
+## 2. Graph Statistics (`statistics.py`)
+
+This script computes descriptive statistics for a triplet dataset and generates a summary CSV file in the `stat/`
+directory.
+
+### Command
+
+```bash
+python src/statistics.py --input path/to/graph.csv
+```
+
+### Computed Statistics
+
+| Metric                        | Description                                        |
+|-------------------------------|----------------------------------------------------|
+| `total_triplets`              | Total number of triplets                           |
+| `unique_subjects`             | Number of unique subjects                          |
+| `unique_predicates`           | Number of unique predicates                        |
+| `unique_objects`              | Number of unique objects                           |
+| `unique_entities`             | Unique entities across subjects and objects        |
+| `unique_subject_object_pairs` | Distinct `(subject, object)` pairs                 |
+| `connected_components`        | Number of weakly connected components in the graph |
+
+## 3. Wikidata Path Extraction (`subgraph_extract.py`)
+
+This script takes a list of entity pairs and dynamically queries Wikidata to find a short path (not necessarily the
+shortest) between them. It outputs the discovered path triplets as a CSV and saves the explored network as a `.gpickle`
+graph file.
+
+### Command
+
+```bash
+python src/subgraph_extract.py --input path/to/pairs.csv --output path/to/extracted_paths.csv
+```
+
+---
+
+## 4. Local Subgraph Extraction (`hashmap_extract_subgraph.py`)
+
+This script extracts subgraphs from a **local** graph dataset (CSV) using one of the two modes:
+
+### Mode A — Shortest paths between seed/target pairs
+
+Extracts all shortest paths between specified source-target entity pairs.
+
+```bash
+python src/hashmap_extract_subgraph.py \
+    --sub_graph path/to/main_graph.csv \
+    --seed_target_pairs path/to/pairs.csv
+```
+
+### Mode B — Radius around seed nodes
+
+Extracts all nodes within a specified number of hops (default: 2) from a list of seed entities.
+
+```bash
+python src/hashmap_extract_subgraph.py \
+    --sub_graph path/to/main_graph.csv \
+    --seeds_only path/to/seeds.csv \
+    --max_length 2
+```
+
+**Output:** The extracted subgraph is saved by default to `data/extracted_subgraph.csv`.
+
+---
+
+## Dataset Structure
+
+All datasets are expected to be provided as CSV files.
+
+### Main Graph Dataset
+
+Must contain three columns representing a knowledge graph triplet:
+
+| subject | predicate | object |
+|---------|-----------|--------|
+| Q937    | P36       | Q90    |
+| Q90     | P17       | Q142   |
+
+### Seed-Target Pair Dataset
+
+Used for finding paths between specific entities. Must contain two columns:
+
+| subject | object |
+|---------|--------|
+| Q937    | Q304   |
+| Q90     | Q183   |
+
+### Seed-Only Dataset
+
+Used for neighborhood expansion. Must contain one column representing the seed entity (the column can be named `seed` or
+be the first column):
+
+| seed |
+|------|
+| Q937 |
+| Q90  |

graph_seeder-1.0.0.dev0/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/graph_seeder"]
+
+[project]
+name = "graph-seeder"
+version = "1.0.0.dev0"
+description = "A powerful tool to extract and densify subgraphs from Knowledge Graphs via SPARQL or LMDB, with different extraction strategies."
+readme = "README.md"
+requires-python = ">=3.9"
+dependencies = [
+    "lmdb>=2.2.0",
+    "networkx>=3.2.1,<4.0.0",
+    "pandas>=2.3.3,<3.0.0",
+    "rdflib>=7.6.0",
+    "requests>=2.32.5",
+    "rich>=15.0.0",
+    "sparqlwrapper>=2.0.0",
+    "urllib3>=2.6.3",
+]
+
+[project.scripts]
+graph-seeder = "graph_seeder.GraphSeeder:main"

graph_seeder-1.0.0.dev0/requirements.txt

@@ -0,0 +1,65 @@
+# This file was autogenerated by uv via the following command:
+#    uv export --no-hashes --format requirements.txt
+-e .
+certifi==2026.4.22
+    # via requests
+charset-normalizer==3.4.7
+    # via requests
+idna==3.15
+    # via requests
+isodate==0.7.2 ; python_full_version < '3.11'
+    # via rdflib
+lmdb==2.2.0
+    # via graph-seeder
+markdown-it-py==3.0.0 ; python_full_version < '3.10'
+    # via rich
+markdown-it-py==4.2.0 ; python_full_version >= '3.10'
+    # via rich
+mdurl==0.1.2
+    # via markdown-it-py
+networkx==3.2.1 ; python_full_version < '3.10'
+    # via graph-seeder
+networkx==3.4.2 ; python_full_version == '3.10.*'
+    # via graph-seeder
+networkx==3.6.1 ; python_full_version >= '3.11'
+    # via graph-seeder
+numpy==2.0.2 ; python_full_version < '3.10'
+    # via pandas
+numpy==2.2.6 ; python_full_version == '3.10.*'
+    # via pandas
+numpy==2.4.4 ; python_full_version >= '3.11'
+    # via pandas
+pandas==2.3.3
+    # via graph-seeder
+pygments==2.20.0
+    # via rich
+pyparsing==3.3.2
+    # via rdflib
+python-dateutil==2.9.0.post0
+    # via pandas
+pytz==2026.2
+    # via pandas
+rdflib==7.6.0
+    # via
+    #   graph-seeder
+    #   sparqlwrapper
+requests==2.32.5 ; python_full_version < '3.10'
+    # via graph-seeder
+requests==2.34.0 ; python_full_version >= '3.10'
+    # via graph-seeder
+rich==15.0.0
+    # via graph-seeder
+six==1.17.0
+    # via python-dateutil
+sparqlwrapper==2.0.0
+    # via graph-seeder
+tzdata==2025.3
+    # via pandas
+urllib3==2.6.3 ; python_full_version < '3.10'
+    # via
+    #   graph-seeder
+    #   requests
+urllib3==2.7.0 ; python_full_version >= '3.10'
+    # via
+    #   graph-seeder
+    #   requests