refactor ~bacdive~ => microbe

.cruft.json

@@ -4,8 +4,8 @@
   "checkout": null,
   "context": {
     "cookiecutter": {
-      "project_name": "kg-bacdive",
-      "__project_slug": "kg_bacdive",
+      "project_name": "kg-microbe",
+      "__project_slug": "kg_microbe",
       "project_description": "Knowledge graph construction for BacDive data",
       "min_python_version": "3.9",
       "full_name": "Harshad Hegde",

.github/workflows/deploy-docs.yml

@@ -28,11 +28,11 @@ jobs:
 
     - name: Build documentation.
       run: |
-        echo ${{ secrets.GH_TOKEN }} >> kg_bacdive/token.txt
+        echo ${{ secrets.GH_TOKEN }} >> kg_microbe/token.txt
         mkdir gh-pages
         touch gh-pages/.nojekyll
         cd docs/
-        poetry run sphinx-apidoc -o . ../kg_bacdive/ --ext-autodoc -f
+        poetry run sphinx-apidoc -o . ../kg_microbe/ --ext-autodoc -f
         poetry run sphinx-build -b html . _build
         cp -r _build/* ../gh-pages/
 

.github/workflows/qc.yml

@@ -1,4 +1,4 @@
-name: kg-bacdive QC
+name: kg-microbe QC
 
 on:
   push:

.gitignore

@@ -135,7 +135,7 @@ data/raw/robot
 !data/raw/.keep
 !data/raw/exclusion_branches.tsv
 !data/raw/nlp/*
-kg_bacdive/transform_utils/*/tmp/*/*.yaml
+kg_microbe/transform_utils/*/tmp/*/*.yaml
 data/transformed/ontologies/*.tsv
 *.sqlite
 data/merged/*

README.md

@@ -1,13 +1,13 @@
-# kg-bacdive
+# kg-microbe
 
 Knowledge graph construction for BacDive data
 
 # Setup
  - Create a vrtual environment of your choice.
  - Install poetry using `pip install poetry`
  - `poetry install`
- - `git clone https://github.com/Knowledge-Graph-Hub/kg-bacdive.git`
- - `cd kg-bacdive`
+ - `git clone https://github.com/Knowledge-Graph-Hub/kg-microbe.git`
+ - `cd kg-microbe`
 
 ## Download resources needed
  - `poetry run kg download` : This will download the resources needed for this project.

docs/conf.py

@@ -7,7 +7,7 @@
 import re
 import sys
 from datetime import date
-from kg_bacdive import __version__
+from kg_microbe import __version__
 # -- Project information -----------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 

docs/modules.rst

@@ -4,7 +4,7 @@ kg-microbe
 .. toctree::
    :maxdepth: 4
 
-   kg_bacdive
+   kg_microbe
    query_utils
    run
    setup

kg_bacdive/__init__.py → kg_microbe/__init__.py

@@ -1,4 +1,4 @@
-"""kg-bacdive package."""
+"""kg-microbe package."""
 from importlib import metadata
 
 from .download import download

kg_bacdive/run.py → kg_microbe/run.py

@@ -3,11 +3,11 @@
 
 import click
 
-from kg_bacdive import download as kg_download
-from kg_bacdive.merge_utils.merge_kg import load_and_merge
-from kg_bacdive.query import parse_query_yaml, result_dict_to_tsv, run_query
-from kg_bacdive.transform import DATA_SOURCES
-from kg_bacdive.transform import transform as kg_transform
+from kg_microbe import download as kg_download
+from kg_microbe.merge_utils.merge_kg import load_and_merge
+from kg_microbe.query import parse_query_yaml, result_dict_to_tsv, run_query
+from kg_microbe.transform import DATA_SOURCES
+from kg_microbe.transform import transform as kg_transform
 
 
 @click.group()

kg_bacdive/transform.py → kg_microbe/transform.py

@@ -3,10 +3,10 @@
 from pathlib import Path
 from typing import List, Optional
 
-from kg_bacdive.transform_utils.bacdive.bacdive import BacDiveTransform
-from kg_bacdive.transform_utils.mediadive.mediadive import MediaDiveTransform
-from kg_bacdive.transform_utils.ontology.ontology_transform import ONTOLOGIES, OntologyTransform
-from kg_bacdive.transform_utils.traits.traits import TraitsTransform
+from kg_microbe.transform_utils.bacdive.bacdive import BacDiveTransform
+from kg_microbe.transform_utils.mediadive.mediadive import MediaDiveTransform
+from kg_microbe.transform_utils.ontology.ontology_transform import ONTOLOGIES, OntologyTransform
+from kg_microbe.transform_utils.traits.traits import TraitsTransform
 
 DATA_SOURCES = {
     "OntologyTransform": OntologyTransform,
@@ -30,7 +30,7 @@ def transform(
     """
     Transform based on resource and class declared in DATA_SOURCES.
 
-    Call scripts in kg_bacdive/transform/[source name]/ to
+    Call scripts in kg_microbe/transform/[source name]/ to
     transform each source into a graph format that
     KGX can ingest directly, in either TSV or JSON format:
     https://github.com/biolink/kgx/blob/master/data-preparation.md

kg_bacdive/transform_utils/bacdive/bacdive.py → kg_microbe/transform_utils/bacdive/bacdive.py

@@ -21,7 +21,7 @@
 from oaklib import get_adapter
 from tqdm import tqdm
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     BACDIVE_API_BASE_URL,
     BACDIVE_ID_COLUMN,
     BACDIVE_MEDIUM_DICT,
@@ -60,8 +60,8 @@
     SPECIES,
     STRAIN,
 )
-from kg_bacdive.transform_utils.transform import Transform
-from kg_bacdive.utils.pandas_utils import drop_duplicates
+from kg_microbe.transform_utils.transform import Transform
+from kg_microbe.utils.pandas_utils import drop_duplicates
 
 
 class BacDiveTransform(Transform):

kg_bacdive/transform_utils/example_transform/example_transform.py → kg_microbe/transform_utils/example_transform/example_transform.py

@@ -20,7 +20,7 @@
 
 from transform_utils.transform import Transform
 
-from kg_bacdive.utils.robot_utils import convert_to_json, extract_convert_to_json
+from kg_microbe.utils.robot_utils import convert_to_json, extract_convert_to_json
 
 
 class YourTransform(Transform):

kg_bacdive/transform_utils/mediadive/mediadive.py → kg_microbe/transform_utils/mediadive/mediadive.py

@@ -27,7 +27,7 @@
 from oaklib import get_adapter
 from tqdm import tqdm
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     CAS_RN_KEY,
     CAS_RN_PREFIX,
     CHEBI_KEY,
@@ -71,8 +71,8 @@
     SOLUTIONS_COLUMN,
     SOLUTIONS_KEY,
 )
-from kg_bacdive.transform_utils.transform import Transform
-from kg_bacdive.utils.pandas_utils import drop_duplicates, establish_transitive_relationship
+from kg_microbe.transform_utils.transform import Transform
+from kg_microbe.utils.pandas_utils import drop_duplicates, establish_transitive_relationship
 
 
 class MediaDiveTransform(Transform):

kg_bacdive/transform_utils/ontology/ontology_transform.py → kg_microbe/transform_utils/ontology/ontology_transform.py

@@ -7,12 +7,12 @@
 # from kgx.transformer import Transformer
 from kgx.cli.cli_utils import transform
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     EXCLUSION_TERMS_FILE,
     NCBITAXON_PREFIX,
     ROBOT_REMOVED_SUFFIX,
 )
-from kg_bacdive.utils.robot_utils import convert_to_json, remove_convert_to_json
+from kg_microbe.utils.robot_utils import convert_to_json, remove_convert_to_json
 
 from ..transform import Transform
 

kg_bacdive/transform_utils/traits/traits.py → kg_microbe/transform_utils/traits/traits.py

@@ -9,7 +9,7 @@
 import yaml
 from oaklib.utilities.ner_utilities import get_exclusion_token_list
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     ACTUAL_TERM_KEY,
     BIOLOGICAL_PROCESS,
     CARBON_SUBSTRATE_CATEGORY,
@@ -48,9 +48,9 @@
     TROPHICALLY_INTERACTS_WITH,
     TYPE_COLUMN,
 )
-from kg_bacdive.transform_utils.transform import Transform
-from kg_bacdive.utils.ner_utils import annotate
-from kg_bacdive.utils.pandas_utils import drop_duplicates
+from kg_microbe.transform_utils.transform import Transform
+from kg_microbe.utils.ner_utils import annotate
+from kg_microbe.utils.pandas_utils import drop_duplicates
 
 OUTPUT_FILE_SUFFIX = "_ner.tsv"
 STOPWORDS_FN = "stopwords.txt"

kg_bacdive/transform_utils/transform.py → kg_microbe/transform_utils/transform.py

@@ -5,7 +5,7 @@
 
 import yaml
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     CATEGORY_COLUMN,
     DESCRIPTION_COLUMN,
     ID_COLUMN,

kg_bacdive/utils/ner_utils.py → kg_microbe/utils/ner_utils.py

@@ -7,7 +7,7 @@
 from oaklib import get_adapter
 from oaklib.datamodels.text_annotator import TextAnnotationConfiguration
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     END_COLUMN,
     MATCHES_WHOLE_TEXT_COLUMN,
     OBJECT_ALIASES_COLUMN,

kg_bacdive/utils/pandas_utils.py → kg_microbe/utils/pandas_utils.py

@@ -3,7 +3,7 @@
 
 import pandas as pd
 
-from kg_bacdive.transform_utils.constants import OBJECT_COLUMN, PREDICATE_COLUMN, SUBJECT_COLUMN
+from kg_microbe.transform_utils.constants import OBJECT_COLUMN, PREDICATE_COLUMN, SUBJECT_COLUMN
 
 
 def drop_duplicates(file_path: Path):

kg_bacdive/utils/robot_utils.py → kg_microbe/utils/robot_utils.py

@@ -4,7 +4,7 @@
 from pathlib import Path
 from typing import List, Union
 
-from kg_bacdive.transform_utils.constants import (
+from kg_microbe.transform_utils.constants import (
     ROBOT_REMOVED_SUFFIX,
 )
 

merge.yaml

@@ -12,7 +12,7 @@ configuration:
     # define the type for non-canonical properties for RDF export
 
 merged_graph:
-  name: kg-bacdive graph
+  name: kg-microbe graph
   source:
     ncbitaxon:
       name: "NCBITaxon"
@@ -52,7 +52,7 @@ merged_graph:
   operations:
     - name: kgx.graph_operations.summarize_graph.generate_graph_stats
       args:
-        graph_name: kg-bacdive graph
+        graph_name: kg-microbe graph
         filename: merged_graph_stats.yaml
         node_facet_properties:
           - provided_by
@@ -67,4 +67,4 @@ merged_graph:
     # merged-kg-nt:
     #   format: nt
     #   compression: gz
-    #   filename: kg_bacdive.nt.gz
+    #   filename: kg_microbe.nt.gz

merged_graph_stats.yaml

@@ -465,7 +465,7 @@ edge_stats:
   source:
   - unknown
   total_edges: 1341461
-graph_name: kg-bacdive graph
+graph_name: kg-microbe graph
 node_stats:
   count_by_category:
     biolink:AbstractEntity:

notebook/kg_bacdive.ipynb

@@ -640,7 +640,7 @@
    "source": [
     "from grape import Graph\n",
     "\n",
-    "kg_bacdive = Graph.from_csv(\n",
+    "kg_microbe = Graph.from_csv(\n",
     "    # Edges related parameters\n",
     "\n",
     "    ## The path to the edges list tsv\n",

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
-name = "kg-bacdive"
+name = "kg-microbe"
 version = "0.0.0"
-description = "kg-bacdive"
+description = "kg-microbe"
 authors = ["Harshad Hegde <[email protected]>"]
 license = "MIT"
 readme = "README.md"
@@ -44,7 +44,7 @@ docs = [
     ]
 
 [tool.poetry.scripts]
-kg = 'kg_bacdive.run:main'
+kg = 'kg_microbe.run:main'
 
 [tool.poetry-dynamic-versioning]
 enable = true

templates/README.build

@@ -1,10 +1,10 @@
-The files in this directory represent a build of the kg-bacdive knowledge graph.
+The files in this directory represent a build of the kg-microbe knowledge graph.
 
 These file include:
 	*	Jenkinsfile - the exact command run to produce this build of the KG
-	*	kg-bacdive.jnl.gz - a blazegraph journal that can be loaded to produce a Blazegraph endpoint
-	*	kg-bacdive.nt.gz- an ntriples/RDF version of the KG
-	*	kg-bacdive.tar.gz - a tar.gz file containing the KG in KGX TSV format (with 'merged-kg' within the name of both node and edge files)
+	*	kg-microbe.jnl.gz - a blazegraph journal that can be loaded to produce a Blazegraph endpoint
+	*	kg-microbe.nt.gz- an ntriples/RDF version of the KG
+	*	kg-microbe.tar.gz - a tar.gz file containing the KG in KGX TSV format (with 'merged-kg' within the name of both node and edge files)
 
 The subdirectories in this directory are:
 

templates/README.toplevel

@@ -1,4 +1,4 @@
-The subdirectories here each contain a build of the kg-bacdive knowledge graph.
+The subdirectories here each contain a build of the kg-microbe knowledge graph.
 The directories are named with a date (ISO 8601 format, YYYYMMDD) according to when
 the build was produced. The current/ directory is the most recent build.
 

tests/__init__.py

@@ -1 +1 @@
-"""Tests for kg-bacdive."""
+"""Tests for kg-microbe."""

tests/demo_test.py

@@ -2,7 +2,7 @@
 
 import unittest
 
-from kg_bacdive import __version__
+from kg_microbe import __version__
 
 
 class TestVersion(unittest.TestCase):

tox.ini

@@ -38,8 +38,8 @@ deps =
     ruff
 skip_install = true
 commands =
-    black kg_bacdive/ tests/
-    ruff --fix kg_bacdive/ tests/
+    black kg_microbe/ tests/
+    ruff --fix kg_microbe/ tests/
 description = Run linters.
 
 # This is used for QC checks.
@@ -49,8 +49,8 @@ deps =
     ruff
 skip_install = true
 commands =
-    black --check --diff kg_bacdive/ tests/
-    ruff check kg_bacdive/ tests/
+    black --check --diff kg_microbe/ tests/
+    ruff check kg_microbe/ tests/
 description = Run linters.
 
 [testenv:doclint]
@@ -67,20 +67,20 @@ skip_install = true
 deps = 
     codespell
     tomli  # required for getting config from pyproject.toml
-commands = codespell kg_bacdive/ tests/ -S kg_bacdive/transform_utils/*/tmp/*
+commands = codespell kg_microbe/ tests/ -S kg_microbe/transform_utils/*/tmp/*
 
 [testenv:codespell-write]
 description = Run spell checker and write corrections.
 skip_install = true
 deps = 
     codespell
     tomli
-commands = codespell kg_bacdive/ tests/ --write-changes -S kg_bacdive/transform_utils/*/tmp/*
+commands = codespell kg_microbe/ tests/ --write-changes -S kg_microbe/transform_utils/*/tmp/*
 
 [testenv:docstr-coverage]
 skip_install = true
 deps =
     docstr-coverage
 commands =
-    docstr-coverage kg_bacdive/ tests/ --skip-private --skip-magic
+    docstr-coverage kg_microbe/ tests/ --skip-private --skip-magic
 description = Run the docstr-coverage tool to check documentation coverage