renard-pipeline 0.6.3__tar.gz → 0.6.5__tar.gz

{renard_pipeline-0.6.3 → renard_pipeline-0.6.5}/PKG-INFO

@@ -1,35 +1,30 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: renard-pipeline
-Version: 0.6.3
+Version: 0.6.5
 Summary: Relationships Extraction from NARrative Documents
-Home-page: https://github.com/CompNet/Renard
+Author-email: Arthur Amalvy <arthur.amalvy@univ-avignon.fr>
 License: GPL-3.0-only
-Author: Arthur Amalvy
-Author-email: arthur.amalvy@univ-avignon.fr
-Requires-Python: >=3.8,<3.12
-Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Requires-Dist: datasets (>=3.0,<4.0)
-Requires-Dist: grimbert (>=0.1,<0.2)
-Requires-Dist: matplotlib (>=3.5,<4.0)
-Requires-Dist: more-itertools (>=10.5,<11.0)
-Requires-Dist: nameparser (>=1.1,<2.0)
-Requires-Dist: networkx (>=3.0,<4.0)
-Requires-Dist: nltk (>=3.9,<4.0)
-Requires-Dist: pandas (>=2.0,<3.0)
-Requires-Dist: pytest (>=8.3.0,<9.0.0)
-Requires-Dist: rank-bm25 (>=0.2.2,<0.3.0)
-Requires-Dist: tibert (>=0.5,<0.6)
-Requires-Dist: torch (>=2.0.0,!=2.0.1)
-Requires-Dist: tqdm (>=4.62.3,<5.0.0)
-Requires-Dist: transformers (>=4.37,<5.0)
+Project-URL: Homepage, https://github.com/CompNet/Renard
 Project-URL: Documentation, https://compnet.github.io/Renard/
 Project-URL: Repository, https://github.com/CompNet/Renard
+Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch!=2.0.1,>=2.0.0
+Requires-Dist: transformers>=4.37
+Requires-Dist: nltk>=3.9
+Requires-Dist: tqdm>=4.62
+Requires-Dist: networkx>=3.0
+Requires-Dist: more-itertools>=10.5
+Requires-Dist: nameparser>=1.1
+Requires-Dist: matplotlib>=3.5
+Requires-Dist: pandas>=2.0
+Requires-Dist: pytest>=8.3.0
+Requires-Dist: tibert>=0.5
+Requires-Dist: grimbert>=0.1
+Requires-Dist: datasets>=3.0
+Requires-Dist: rank-bm25>=0.2.2
+Dynamic: license-file
 
 # Renard
 
@@ -46,7 +41,7 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
-Currently, Renard supports Python>=3.8,<=3.11
+Currently, Renard supports Python>=3.9,<=3.12
 
 
 # Documentation
@@ -90,7 +85,7 @@ For more information, see `renard_tutorial.py`, which is a tutorial in the `jupy
 
 `Renard` uses `pytest` for testing. To launch tests, use the following command : 
 
-> poetry run python -m pytest tests
+> uv run python -m pytest tests
 
 Expensive tests are disabled by default. These can be run by setting the environment variable `RENARD_TEST_ALL` to `1`.
 
@@ -120,4 +115,3 @@ If you use Renard in your research project, please cite it as follows:
 ```
 
 We would be happy to hear about your usage of Renard, so don't hesitate to reach out!
-

{renard_pipeline-0.6.3 → renard_pipeline-0.6.5}/README.md

@@ -13,7 +13,7 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
-Currently, Renard supports Python>=3.8,<=3.11
+Currently, Renard supports Python>=3.9,<=3.12
 
 
 # Documentation
@@ -57,7 +57,7 @@ For more information, see `renard_tutorial.py`, which is a tutorial in the `jupy
 
 `Renard` uses `pytest` for testing. To launch tests, use the following command : 
 
-> poetry run python -m pytest tests
+> uv run python -m pytest tests
 
 Expensive tests are disabled by default. These can be run by setting the environment variable `RENARD_TEST_ALL` to `1`.
 

renard_pipeline-0.6.5/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "renard-pipeline"
+version = "0.6.5"
+description = "Relationships Extraction from NARrative Documents"
+authors = [
+    {name = "Arthur Amalvy", email = "arthur.amalvy@univ-avignon.fr"},
+]
+license = { text = "GPL-3.0-only" }
+readme = "README.md"
+requires-python = ">=3.9,<3.13"
+dependencies = [
+    "torch>=2.0.0,!=2.0.1",
+    "transformers>=4.37",
+    "nltk>=3.9",
+    "tqdm>=4.62",
+    "networkx>=3.0",
+    "more-itertools>=10.5",
+    "nameparser>=1.1",
+    "matplotlib>=3.5",
+    "pandas>=2.0",
+    "pytest>=8.3.0",
+    "tibert>=0.5",
+    "grimbert>=0.1",
+    "datasets>=3.0",
+    "rank-bm25>=0.2.2",
+]
+
+[project.urls]
+Homepage = "https://github.com/CompNet/Renard"
+Documentation = "https://compnet.github.io/Renard/"
+Repository = "https://github.com/CompNet/Renard"
+
+[dependency-groups]
+dev = [
+    "hypothesis>=6.82",
+    "Sphinx>=4.3",
+    "sphinx-rtd-theme>=1.0.0",
+    "sphinx-autodoc-typehints>=1.12.0",
+]

renard_pipeline-0.6.5/renard_pipeline.egg-info/PKG-INFO

@@ -0,0 +1,117 @@
+Metadata-Version: 2.4
+Name: renard-pipeline
+Version: 0.6.5
+Summary: Relationships Extraction from NARrative Documents
+Author-email: Arthur Amalvy <arthur.amalvy@univ-avignon.fr>
+License: GPL-3.0-only
+Project-URL: Homepage, https://github.com/CompNet/Renard
+Project-URL: Documentation, https://compnet.github.io/Renard/
+Project-URL: Repository, https://github.com/CompNet/Renard
+Requires-Python: <3.13,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch!=2.0.1,>=2.0.0
+Requires-Dist: transformers>=4.37
+Requires-Dist: nltk>=3.9
+Requires-Dist: tqdm>=4.62
+Requires-Dist: networkx>=3.0
+Requires-Dist: more-itertools>=10.5
+Requires-Dist: nameparser>=1.1
+Requires-Dist: matplotlib>=3.5
+Requires-Dist: pandas>=2.0
+Requires-Dist: pytest>=8.3.0
+Requires-Dist: tibert>=0.5
+Requires-Dist: grimbert>=0.1
+Requires-Dist: datasets>=3.0
+Requires-Dist: rank-bm25>=0.2.2
+Dynamic: license-file
+
+# Renard
+
+[![DOI](https://joss.theoj.org/papers/10.21105/joss.06574/status.svg)](https://doi.org/10.21105/joss.06574)
+
+Renard (Relationship Extraction from NARrative Documents) is a library for creating and using custom character networks extraction pipelines. Renard can extract dynamic as well as static character networks.
+
+![The Renard logo](./docs/renard.svg)
+
+
+# Installation
+
+You can install the latest version using pip:
+
+> pip install renard-pipeline
+
+Currently, Renard supports Python>=3.9,<=3.12
+
+
+# Documentation
+
+Documentation, including installation instructions, can be found at https://compnet.github.io/Renard/
+
+If you need local documentation, it can be generated using `Sphinx`. From the `docs` directory, `make html` should create documentation under `docs/_build/html`. 
+
+
+# Tutorial
+
+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` uses `pytest` for testing. To launch tests, use the following command : 
+
+> uv run python -m pytest tests
+
+Expensive tests are disabled by default. These can be run by setting the environment variable `RENARD_TEST_ALL` to `1`.
+
+
+# Contributing
+
+see [the "Contributing" section of the documentation](https://compnet.github.io/Renard/contributing.html).
+
+
+# How to cite
+
+If you use Renard in your research project, please cite it as follows:
+
+```bibtex
+@Article{Amalvy2024,
+  doi	       = {10.21105/joss.06574},
+  year	       = {2024},
+  publisher    = {The Open Journal},
+  volume       = {9},
+  number       = {98},
+  pages	       = {6574},
+  author       = {Amalvy, A. and Labatut, V. and Dufour, R.},
+  title	       = {Renard: A Modular Pipeline for Extracting Character
+                  Networks from Narrative Texts},
+  journal      = {Journal of Open Source Software},
+} 
+```
+
+We would be happy to hear about your usage of Renard, so don't hesitate to reach out!

renard_pipeline-0.6.5/renard_pipeline.egg-info/SOURCES.txt

@@ -0,0 +1,52 @@
+LICENSE
+README.md
+pyproject.toml
+renard/gender.py
+renard/graph_utils.py
+renard/ner_utils.py
+renard/nltk_utils.py
+renard/plot_utils.py
+renard/py.typed
+renard/utils.py
+renard/pipeline/__init__.py
+renard/pipeline/character_unification.py
+renard/pipeline/characters_extraction.py
+renard/pipeline/core.py
+renard/pipeline/graph_extraction.py
+renard/pipeline/preconfigured.py
+renard/pipeline/preprocessing.py
+renard/pipeline/progress.py
+renard/pipeline/quote_detection.py
+renard/pipeline/sentiment_analysis.py
+renard/pipeline/speaker_attribution.py
+renard/pipeline/stanford_corenlp.py
+renard/pipeline/tokenization.py
+renard/pipeline/corefs/__init__.py
+renard/pipeline/corefs/corefs.py
+renard/pipeline/ner/__init__.py
+renard/pipeline/ner/ner.py
+renard/pipeline/ner/retrieval.py
+renard/resources/determiners/__init__.py
+renard/resources/determiners/determiners.py
+renard/resources/hypocorisms/__init__.py
+renard/resources/hypocorisms/hypocorisms.py
+renard/resources/pronouns/__init__.py
+renard/resources/pronouns/pronouns.py
+renard/resources/titles/__init__.py
+renard/resources/titles/titles.py
+renard_pipeline.egg-info/PKG-INFO
+renard_pipeline.egg-info/SOURCES.txt
+renard_pipeline.egg-info/dependency_links.txt
+renard_pipeline.egg-info/requires.txt
+renard_pipeline.egg-info/top_level.txt
+tests/test_character_unification.py
+tests/test_corefs.py
+tests/test_graph_extraction.py
+tests/test_graph_utils.py
+tests/test_ner.py
+tests/test_pipeline.py
+tests/test_quote_detection.py
+tests/test_sentiment_analysis.py
+tests/test_stanza.py
+tests/test_tokenization.py
+tests/test_utils.py

renard_pipeline-0.6.5/renard_pipeline.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

renard_pipeline-0.6.5/renard_pipeline.egg-info/requires.txt

@@ -0,0 +1,14 @@
+torch!=2.0.1,>=2.0.0
+transformers>=4.37
+nltk>=3.9
+tqdm>=4.62
+networkx>=3.0
+more-itertools>=10.5
+nameparser>=1.1
+matplotlib>=3.5
+pandas>=2.0
+pytest>=8.3.0
+tibert>=0.5
+grimbert>=0.1
+datasets>=3.0
+rank-bm25>=0.2.2

renard_pipeline-0.6.5/renard_pipeline.egg-info/top_level.txt

@@ -0,0 +1 @@
+renard

renard_pipeline-0.6.5/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

renard_pipeline-0.6.5/tests/test_character_unification.py

@@ -0,0 +1,16 @@
+from renard.pipeline import Mention
+from renard.pipeline.character_unification import (
+    Character,
+    _assign_coreference_mentions,
+)
+
+
+def test_assign_coreference_mentions():
+    characters = _assign_coreference_mentions(
+        [Character(frozenset(["John Traitor"]), [Mention(["John", "Traitor"], 0, 1)])],
+        [[Mention(["John", "Traitor"], 0, 1), Mention(["He"], 10, 10)]],
+    )
+    assert characters[0] == Character(
+        frozenset(["John Traitor"]),
+        [Mention(["John", "Traitor"], 0, 1), Mention(["He"], 10, 10)],
+    )

renard_pipeline-0.6.5/tests/test_corefs.py

@@ -0,0 +1,15 @@
+import os
+import pytest
+from renard.pipeline import Pipeline
+from renard.pipeline.corefs import BertCoreferenceResolver
+
+
+@pytest.mark.skipif(os.getenv("RENARD_TEST_ALL") != "1", reason="performance")
+def test_bert_coreference_resolver_runs():
+    pipeline = Pipeline([BertCoreferenceResolver()], progress_report=None)
+    tokens = "Princess Liana felt sad , because Zarth Arn was gone . The princess went to sleep .".split(
+        " "
+    )
+    corefs = pipeline(tokens=tokens).corefs
+    assert not corefs is None
+    assert len(corefs) >= 1

renard_pipeline-0.6.5/tests/test_graph_extraction.py

@@ -0,0 +1,121 @@
+from collections import defaultdict
+from typing import List
+import itertools, string
+from hypothesis import given
+from hypothesis.strategies import lists, sampled_from
+from hypothesis.strategies._internal.numbers import integers
+import networkx as nx
+from networkx.algorithms import isomorphism
+from renard.pipeline.graph_extraction import CoOccurrencesGraphExtractor
+from renard.pipeline.character_unification import Character
+from renard.pipeline.ner import ner_entities, NEREntity
+
+
+def _characters_from_mentions(mentions: List[NEREntity]) -> List[Character]:
+    """Generate characters from a list of mentions"""
+    name_to_mentions = defaultdict(list)
+    for mention in mentions:
+        name_to_mentions[" ".join(mention.tokens)].append(mention)
+    return [
+        Character(frozenset((name,)), mentions)
+        for name, mentions in name_to_mentions.items()
+    ]
+
+
+# max size used for performance reasons
+@given(lists(sampled_from(string.ascii_uppercase), max_size=7))
+def test_basic_graph_extraction(tokens: List[str]):
+    bio_tags = ["B-PER" for _ in tokens]
+
+    mentions = ner_entities(tokens, bio_tags)
+    characters = _characters_from_mentions(mentions)
+
+    graph_extractor = CoOccurrencesGraphExtractor(len(tokens))
+    out = graph_extractor(set(characters), [tokens])
+
+    characters = {
+        token: Character(
+            frozenset([token]), [m for m in mentions if m.tokens[0] == token]
+        )
+        for token in set(tokens)
+    }
+
+    G = nx.Graph()
+    for character in characters.values():
+        G.add_node(character)
+
+    for i, j in itertools.combinations(range(len(tokens)), 2):
+        A = characters[tokens[i]]
+        B = characters[tokens[j]]
+        if A == B:
+            continue
+        if not G.has_edge(A, B):
+            G.add_edge(A, B, weight=0)
+        G.edges[A, B]["weight"] += 1
+
+    assert nx.is_isomorphic(
+        out["character_network"],
+        G,
+        edge_match=isomorphism.numerical_edge_match("weight", 0),
+    )
+
+
+@given(
+    lists(sampled_from(string.ascii_uppercase), min_size=1),
+    integers(min_value=1, max_value=5),
+)
+def test_dynamic_graph_extraction(tokens: List[str], dynamic_window: int):
+    """
+    .. note::
+
+        only tests execution.
+    """
+    bio_tags = ["B-PER" for _ in tokens]
+
+    mentions = ner_entities(tokens, bio_tags)
+    characters = _characters_from_mentions(mentions)
+
+    graph_extractor = CoOccurrencesGraphExtractor(
+        len(tokens), dynamic=True, dynamic_window=dynamic_window
+    )
+    out = graph_extractor(set(characters), [tokens])
+
+    assert len(out["character_network"]) > 0
+
+
+@given(lists(sampled_from(string.ascii_uppercase)))
+def test_polarity_extraction(tokens: List[str]):
+    graph_extractor = CoOccurrencesGraphExtractor(10)
+
+    bio_tags = ["B-PER"] * len(tokens)
+
+    mentions = ner_entities(tokens, bio_tags)
+    characters = _characters_from_mentions(mentions)
+
+    out = graph_extractor(
+        set(characters),
+        sentences=[tokens],
+        sentences_polarities=[1.0],
+    )
+
+    for character1, character2 in itertools.combinations(characters, 2):
+        if out["character_network"].has_edge(character1, character2):
+            assert "polarity" in out["character_network"].edges[character1, character2]
+
+
+@given(lists(sampled_from(string.ascii_uppercase), min_size=1))
+def test_sent_co_occurence_dist(sent1: List[str]):
+    # sent2 is guaranteed to be different from sent1, so that we
+    # have 2 different characters
+    sent2 = [chr(ord(token) + 1) for token in sent1]
+
+    graph_extractor = CoOccurrencesGraphExtractor((1, "sentences"))
+
+    sentences = [sent1, sent2]
+    tokens = sent1 + sent2
+    tags = ["B-PER"] * len(tokens)
+    characters = _characters_from_mentions(ner_entities(tokens, tags))
+
+    out = graph_extractor(set(characters), sentences)
+
+    assert len(out["character_network"]) > 0

renard_pipeline-0.6.5/tests/test_graph_utils.py

@@ -0,0 +1,14 @@
+import networkx as nx
+from renard.graph_utils import cumulative_graph
+
+
+def test_cumulative_graph():
+    gs = [
+        nx.Graph([(0, 1, {"weight": 1})]),
+        nx.Graph([(0, 1, {"weight": 1}), (0, 2, {"weight": 1})]),
+    ]
+
+    assert nx.is_isomorphic(
+        cumulative_graph(gs)[-1],
+        nx.Graph([(0, 1, {"weight": 2}), (0, 2, {"weight": 1})]),
+    )

renard_pipeline-0.6.5/tests/test_ner.py

@@ -0,0 +1,79 @@
+from typing import List, Type
+import string, os
+import pytest
+from hypothesis import given
+from hypothesis.control import assume
+from hypothesis.strategies import lists, sampled_from
+from transformers import BertTokenizerFast
+from renard.ner_utils import NERDataset
+from renard.pipeline.ner import ner_entities, score_ner
+from renard.pipeline.ner.retrieval import (
+    NERBM25ContextRetriever,
+    NERContextRetriever,
+    NEREnsembleContextRetriever,
+    NERNeighborsContextRetriever,
+    NERSamenounContextRetriever,
+    NERNeuralContextRetriever,
+)
+
+
+@pytest.mark.skipif(
+    os.getenv("RENARD_TEST_SEQEVAL_OPTDEP") != "1",
+    reason="not testing seqeval based functions",
+)
+@given(lists(sampled_from(("B-PER", "I-PER", "O")), min_size=1))
+def test_score_same_tags(tags: List[str]):
+    assume("B-PER" in tags)
+    assert (1.0, 1.0, 1.0) == score_ner(tags, tags)
+
+
+@given(lists(sampled_from(string.ascii_uppercase)))
+def test_has_correct_number_of_entities(tokens: List[str]):
+    bio_tags = ["B-PER" for _ in tokens]
+    entities = ner_entities(tokens, bio_tags)
+    assert len(entities) == len(tokens)
+
+
+@pytest.mark.skipif(os.getenv("RENARD_TEST_ALL") != "1", reason="performance")
+@pytest.mark.parametrize(
+    "retriever_class", [NERSamenounContextRetriever, NERBM25ContextRetriever]
+)
+def test_retrieves_context(retriever_class: Type[NERContextRetriever]):
+    context_retriever = retriever_class(1)
+    tokenizer = BertTokenizerFast.from_pretrained("bert-base-cased")
+    sentences = [
+        "this is some test sentence .".split(" "),
+        "this is another test sentence .".split(" "),
+    ]
+    dataset = NERDataset(sentences, tokenizer)
+    ctx_dataset = context_retriever(dataset)
+    assert ctx_dataset.elements[0] == sentences[0] + sentences[1]
+    assert ctx_dataset.elements[1] == sentences[0] + sentences[1]
+    assert len(ctx_dataset.elements) == len(sentences)
+    assert len(ctx_dataset._context_mask) == len(sentences)
+
+
+@pytest.mark.skipif(os.getenv("RENARD_TEST_ALL") != "1", reason="performance")
+def test_neural_retrieves_context():
+    context_retriever = NERNeuralContextRetriever(
+        NEREnsembleContextRetriever(
+            [
+                NERSamenounContextRetriever(1),
+                NERBM25ContextRetriever(1),
+                NERNeighborsContextRetriever(2),
+            ],
+            k=4,
+        ),
+        k=1,
+    )
+    tokenizer = BertTokenizerFast.from_pretrained("bert-base-cased")
+    sentences = [
+        "this is some test sentence .".split(" "),
+        "this is another test sentence .".split(" "),
+    ]
+    dataset = NERDataset(sentences, tokenizer)
+    ctx_dataset = context_retriever(dataset)
+    assert ctx_dataset.elements[0] == sentences[0] + sentences[1]
+    assert ctx_dataset.elements[1] == sentences[0] + sentences[1]
+    assert len(ctx_dataset.elements) == len(sentences)
+    assert len(ctx_dataset._context_mask) == len(sentences)

renard_pipeline-0.6.5/tests/test_pipeline.py

@@ -0,0 +1,92 @@
+from typing import Set
+import os
+import pytest
+from renard.pipeline.core import Pipeline, PipelineStep
+from renard.pipeline.preconfigured import bert_pipeline, nltk_pipeline
+
+
+script_dir = os.path.abspath(os.path.dirname(__file__))
+
+
+def test_pipeline_is_valid():
+    class TestPipelineStep1(PipelineStep):
+        def needs(self) -> Set[str]:
+            return set()
+
+        def production(self) -> Set[str]:
+            return {"info_1"}
+
+    class TestPipelineStep2(PipelineStep):
+        def needs(self) -> Set[str]:
+            return {"info_1"}
+
+        def production(self) -> Set[str]:
+            return set()
+
+    pipeline = Pipeline([TestPipelineStep1(), TestPipelineStep2()])
+
+    assert pipeline.check_valid()[0]
+
+
+def test_pipeline_is_invalid():
+    class TestPipelineStep1(PipelineStep):
+        def needs(self) -> Set[str]:
+            return set()
+
+        def production(self) -> Set[str]:
+            return set()
+
+    class TestPipelineStep2(PipelineStep):
+        def needs(self) -> Set[str]:
+            return {"info_1"}
+
+        def production(self) -> Set[str]:
+            return set()
+
+    pipeline = Pipeline([TestPipelineStep1(), TestPipelineStep2()])
+
+    assert not pipeline.check_valid()[0]
+
+
+@pytest.mark.skipif(os.getenv("RENARD_TEST_ALL") != "1", reason="performance")
+def test_nltk_pipeline_runs():
+    with open(f"{script_dir}/pp_chapter1.txt") as f:
+        text = f.read()
+    pipeline = nltk_pipeline(
+        warn=False,
+        progress_report=None,
+        graph_extractor_kwargs={"co_occurrences_dist": (1, "sentences")},
+    )
+    pipeline(text)
+
+
+@pytest.mark.skipif(os.getenv("RENARD_TEST_ALL") != "1", reason="performance")
+def test_bert_pipeline_runs():
+    with open(f"{script_dir}/pp_chapter1.txt") as f:
+        text = f.read()
+    pipeline = bert_pipeline(
+        warn=False,
+        progress_report=None,
+        graph_extractor_kwargs={"co_occurrences_dist": (1, "sentences")},
+    )
+    pipeline(text)
+
+
+@pytest.mark.skipif(os.getenv("RENARD_TEST_ALL") != "1", reason="performance")
+def test_conversational_pipeline_runs():
+
+    with open(f"{script_dir}/pp_chapter1.txt") as f:
+        text = f.read()
+    # if the text is too long, speaker attribution takes a long time
+    text = text[:500]
+
+    pipeline = nltk_pipeline(
+        warn=False,
+        progress_report=None,
+        conversational=True,
+        graph_extractor_kwargs={
+            "graph_type": "conversation",
+            "conversation_dist": (3, "sentences"),
+        },
+    )
+    pipeline(text)