wip

.gitignore

@@ -1,3 +1,147 @@
-*.csv
-csv/
-zip/
+dataset/
+
+*.env
+!*/env/DEFAULT.env
+
+
+#Python stuff
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/

.vscode/settings.json

@@ -0,0 +1,8 @@
+{
+    "python.formatting.provider": "black",
+    "python.pythonPath": "/usr/bin/python3.7",
+    "files.watcherExclude": {
+        "**/dataset/**": true,
+    }
+
+}

dataloader/config.py

@@ -0,0 +1,105 @@
+import os
+from Configs import ConfigBase
+
+
+class DEFAULT(ConfigBase):
+    SCRIPT_DIR = os.path.dirname(
+        os.path.realpath(os.path.join(os.getcwd(), os.path.expanduser(__file__)))
+    )
+    # Load to db every n patent file
+    # Increase or decrease this according to the amount of memory you have
+    BATCH_SIZE = 300
+
+    # Commit to db every n nodes
+    COMMIT_INTERVAL = 10000
+
+    LOG_LEVEL = "INFO"
+    GC_NEO4J_URL = "localhost"
+    GC_NEO4J_USER = None
+    GC_NEO4J_PASSWORD = None
+
+    # if set to True, the dataset will always be downloaded, regardless of its allready existing
+    REDOWNLOAD_DATASET_IF_EXISTENT = False
+
+    DATASET_SOURCE_URLS = [
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-broad-keyword-based-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-patents-SARS-and-MERS.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-patents-SARS-and-MERS-TAC.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-limited-keywords-based-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-CPC-based-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-declared-patseq-organism.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-SARS-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-MERS-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-SARS-diagnosis-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-MERS-diagnosis-patents.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-SARS-treatment.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Coronavirus-MERS-treatment.zip",
+        "https://lens-public.s3.us-west-2.amazonaws.com/coronavirus/patent/fulltext/Ventilators.zip",
+    ]
+    # Where to store the downloaded dataset
+    DATASET_BASE_DIR = os.path.join(SCRIPT_DIR, "../dataset/")
+
+    JSON2GRAPH_DEFAULT_IDS = [
+        "lens_id",
+        "family_id",
+        "_id",
+    ]
+
+    JSON2GRAPH_LABEL_OVERRIDE = {
+        "bibliographic_data": "Patent",
+        "nlp_cit": "NonPatentLiteratureCitation",
+        "pat_cit": "PatentLiteratureCitation",
+        "claims": "PatentClaim",
+        "description": "PatentDescription",
+        "abstract": "PatentAbstract",
+        "title": "PatentTitle",
+        "Collection_NonPatentLiteratureCitation": "PatentCitations",
+        "Collection_PatentLiteratureCitation": "PatentCitations",
+        "family_extended": {"Family": {"type": "extended"}},
+        "family_simple": {"Family": {"type": "simple"}},
+    }
+    JSON2GRAPH_COLLECTION_ANCHOR_EXTRA_LABELS = []
+
+    JSON2GRAPH_PRIMARYKEY_ATTR_BY_LABEL = {}
+    JSON2GRAPH_PRIMARYKEY_GENERATED_HASHED_ATTRS_BY_LABEL = {
+        "PatentDescription": ["text"],
+        "PatentClaim": ["text"],
+        "PatentAbstract": ["text"],
+        "PatentLiteratureCitation": "AllAttributes",
+        "NonPatentLiteratureCitation": "AllAttributes",
+    }
+
+    JSON2GRAPH_SKIP_COLLECTION_HUBS = [
+        "Collection_PatentTitle",
+        "Collection_PatentClaim",
+        "Collection_PatentAbstract",
+        "Collection_Entity",
+        "Collection_PatentDescription",
+        "Collection_lens_id",
+    ]
+
+    JSON2GRAPH_ATTR_TO_RELTYPE_INSTEAD_OF_LABEL = {
+        "inventor": "Entity",
+        "owner": "Entity",
+        "applicant": "Entity",
+    }
+
+    JSON2GRAPH_PROPERTY_NAME_OVERRIDE = {
+        "Entity": {"inventor": "name", "owner": "name", "applicant": "name"}
+    }
+
+    JSON2GRAPH_RELTYPE_OVERRIDE = {}
+
+    JSON2GRAPH_INTERFOLD_JSON_ATTR = {"bibliographic_data": ["family"]}
+
+
+class DEV(ConfigBase):
+    pass
+
+
+class PROD(ConfigBase):
+    pass
+
+
+class LOCAL(ConfigBase):
+    pass

dataloader/download.py

@@ -0,0 +1,52 @@
+import os
+import logging
+import requests
+import zipfile
+from Configs import getConfig
+
+
+config = getConfig()
+log = logging.getLogger(__name__)
+log.addHandler(logging.StreamHandler())
+log.setLevel(getattr(logging, config.LOG_LEVEL))
+
+
+def download():
+
+    if not os.path.isdir(config.DATASET_BASE_DIR):
+        os.makedirs(config.DATASET_BASE_DIR)
+
+    log.info("Start downloading Lens.org patentdata dataset...")
+
+    for url in config.DATASET_SOURCE_URLS:
+        target_path_zip = os.path.join(config.DATASET_BASE_DIR, os.path.basename(url))
+        content_path = os.path.join(
+            config.DATASET_BASE_DIR, os.path.splitext(os.path.basename(url))[0]
+        )
+        if os.path.isdir(content_path) and not config.REDOWNLOAD_DATASET_IF_EXISTENT:
+            log.info(
+                "Skip downloading '{}'. Seems to be allready existing. Switch 'REDOWNLOAD_DATASET_IF_EXISTENT' in config.py to True to force redownload or delete '{}'".format(
+                    url, content_path
+                )
+            )
+            continue
+        r = requests.get(url)
+        with open(target_path_zip, "wb") as f:
+            f.write(r.content)
+        unzip(target_path_zip)
+        for root, dirs, files in os.walk(content_path):
+            for name in files:
+                unzip(os.path.join(root, name))
+
+    log.info("Finished downloading Lens.org patentdata dataset...")
+
+
+def unzip(zipfile_path):
+    target_path_content = os.path.dirname(zipfile_path)
+    with zipfile.ZipFile(zipfile_path, "r") as zip_ref:
+        zip_ref.extractall(target_path_content)
+    os.remove(zipfile_path)
+
+
+if __name__ == "__main__":
+    download()