renard-pipeline 0.4.0__tar.gz → 0.4.1__tar.gz

{renard_pipeline-0.4.0 → renard_pipeline-0.4.1}/PKG-INFO

@@ -1,7 +1,8 @@
 Metadata-Version: 2.1
 Name: renard-pipeline
-Version: 0.4.0
+Version: 0.4.1
 Summary: Relationships Extraction from NARrative Documents
+Home-page: https://github.com/CompNet/Renard
 License: GPL-3.0-only
 Author: Arthur Amalvy
 Author-email: arthur.amalvy@univ-avignon.fr
@@ -31,6 +32,8 @@ Requires-Dist: tibert (>=0.3.0,<0.4.0)
 Requires-Dist: torch (>=2.0.0,!=2.0.1)
 Requires-Dist: tqdm (>=4.62.3,<5.0.0)
 Requires-Dist: transformers (>=4.36.0,<5.0.0)
+Project-URL: Documentation, https://compnet.github.io/Renard/
+Project-URL: Repository, https://github.com/CompNet/Renard
 Description-Content-Type: text/markdown
 
 # Renard
@@ -46,6 +49,8 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
+Currently, Renard supports Python 3.8, 3.9 and 3.10.
+
 
 # Documentation
 
@@ -56,7 +61,32 @@ If you need local documentation, it can be generated using `Sphinx`. From the `d
 
 # Tutorial
 
-`renard_tutorial.py` is a tutorial in the `jupytext` format. You can open it as a notebook in Jupyter Notebook (or export it as a notebook with `jupytext --to ipynb renard-tutorial.py`).
+Renard's central concept is the `Pipeline`.A `Pipeline` is a list of `PipelineStep` that are run sequentially in order to extract a character graph from a document. Here is a simple example:
+
+```python
+from renard.pipeline import Pipeline
+from renard.pipeline.tokenization import NLTKTokenizer
+from renard.pipeline.ner import NLTKNamedEntityRecognizer
+from renard.pipeline.character_unification import GraphRulesCharacterUnifier
+from renard.pipeline.graph_extraction import CoOccurrencesGraphExtractor
+
+with open("./my_doc.txt") as f:
+	text = f.read()
+
+pipeline = Pipeline(
+	[
+		NLTKTokenizer(),
+		NLTKNamedEntityRecognizer(),
+		GraphRulesCharacterUnifier(min_appearance=10),
+		CoOccurrencesGraphExtractor(co_occurrences_dist=25)
+	]
+)
+
+out = pipeline(text)
+```
+
+For more information, see `renard_tutorial.py`, which is a tutorial in the `jupytext` format. You can open it as a notebook in Jupyter Notebook (or export it as a notebook with `jupytext --to ipynb renard-tutorial.py`).
+
 
 
 # Running tests 

{renard_pipeline-0.4.0 → renard_pipeline-0.4.1}/README.md

@@ -11,6 +11,8 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
+Currently, Renard supports Python 3.8, 3.9 and 3.10.
+
 
 # Documentation
 
@@ -21,7 +23,32 @@ If you need local documentation, it can be generated using `Sphinx`. From the `d
 
 # Tutorial
 
-`renard_tutorial.py` is a tutorial in the `jupytext` format. You can open it as a notebook in Jupyter Notebook (or export it as a notebook with `jupytext --to ipynb renard-tutorial.py`).
+Renard's central concept is the `Pipeline`.A `Pipeline` is a list of `PipelineStep` that are run sequentially in order to extract a character graph from a document. Here is a simple example:
+
+```python
+from renard.pipeline import Pipeline
+from renard.pipeline.tokenization import NLTKTokenizer
+from renard.pipeline.ner import NLTKNamedEntityRecognizer
+from renard.pipeline.character_unification import GraphRulesCharacterUnifier
+from renard.pipeline.graph_extraction import CoOccurrencesGraphExtractor
+
+with open("./my_doc.txt") as f:
+	text = f.read()
+
+pipeline = Pipeline(
+	[
+		NLTKTokenizer(),
+		NLTKNamedEntityRecognizer(),
+		GraphRulesCharacterUnifier(min_appearance=10),
+		CoOccurrencesGraphExtractor(co_occurrences_dist=25)
+	]
+)
+
+out = pipeline(text)
+```
+
+For more information, see `renard_tutorial.py`, which is a tutorial in the `jupytext` format. You can open it as a notebook in Jupyter Notebook (or export it as a notebook with `jupytext --to ipynb renard-tutorial.py`).
+
 
 
 # Running tests 

{renard_pipeline-0.4.0 → renard_pipeline-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "renard-pipeline"
-version = "0.4.0"
+version = "0.4.1"
 description = "Relationships Extraction from NARrative Documents"
 authors = ["Arthur Amalvy <arthur.amalvy@univ-avignon.fr>"]
 license = "GPL-3.0-only"
@@ -8,6 +8,9 @@ readme = "README.md"
 packages = [
     { include = "renard" }
 ]
+homepage = "https://github.com/CompNet/Renard"
+repository = "https://github.com/CompNet/Renard"
+documentation = "https://compnet.github.io/Renard/"
 
 [tool.poetry.dependencies]
 # optional dependencies

{renard_pipeline-0.4.0 → renard_pipeline-0.4.1}/renard/pipeline/core.py

@@ -50,6 +50,13 @@ class Mention:
         self_dict["end_idx"] = self.end_idx + shift
         return self.__class__(**self_dict)
 
+    def __eq__(self, other: Mention) -> bool:
+        return (
+            self.tokens == other.tokens
+            and self.start_idx == other.start_idx
+            and self.end_idx == other.end_idx
+        )
+
     def __hash__(self) -> int:
         return hash(tuple(self.tokens) + (self.start_idx, self.end_idx))