Merge pull request #6 from cancervariants/staging

Staging

.coveragerc

@@ -0,0 +1,6 @@
+[run]
+source =
+    evidence/
+    tests/
+omit =
+    setup.py

.flake8

@@ -0,0 +1,19 @@
+[flake8]
+ignore = D205, D400, I101, ANN101, ANN002, ANN003
+max-line-length = 88
+exclude =
+  .git
+  venv
+  __pycache__
+  source
+  outputs
+  evidence/version.py
+inline-quotes = "
+import-order-style = pep8
+application-import-names =
+  evidence
+  tests
+per-file-ignores =
+  tests/*:ANN001, ANN2
+  setup.py:F821
+  *__init__.py:F401

.gitignore

@@ -89,7 +89,7 @@ ipython_config.py
 #   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
+Pipfile.lock
 
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow
 __pypackages__/
@@ -127,3 +127,8 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+pyproject.toml
+
+# data
+evidence/data/*

.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v1.4.0
+    hooks:
+    - id: flake8
+      additional_dependencies: [flake8-docstrings, flake8-quotes, flake8-import-order, flake8-annotations]
+    - id: check-added-large-files
+    - id: detect-private-key

Pipfile

@@ -0,0 +1,31 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+pydantic = "*"
+requests = "*"
+bravado = "*"
+matplotlib = "*"
+seaborn = "*"
+variation-normalizer = "*"
+pandas = "*"
+openpyxl = "*"
+xlrd = "*"
+xlwt = "*"
+fastapi = "*"
+boto3 = "*"
+
+[dev-packages]
+evidence = {editable = true, path = "."}
+pytest = "*"
+pre-commit = "*"
+flake8 = "*"
+flake8-docstrings = "*"
+flake8-quotes = "*"
+flake8-annotations = "*"
+flake8-import-order = "*"
+coverage = "*"
+pytest-cov = "*"
+ipykernel = "*"

README.md

@@ -1,2 +1,63 @@
-# evidence-normalization
+# Evidence Normalization
+
 Service for normalizing evidence
+
+## Developer instructions
+
+The following sections include instructions specifically for developers.
+
+### Installation
+For a development install, we recommend using Pipenv. See the 
+[pipenv docs](https://pipenv-fork.readthedocs.io/en/latest/#install-pipenv-today) 
+for direction on installing pipenv in your compute environment.
+
+Once installed, from the project root dir, just run:
+
+```commandline
+pipenv shell
+pipenv lock && pipenv sync
+```
+
+### Backend Services
+
+Evidence Normalization relies on [Variation Normalization](https://github.com/cancervariants/variation-normalization) for normalizing Cancer Hotspots data. You will need to setup backend services and set the appropriate environment variables. See the [README](https://github.com/cancervariants/variation-normalization#variation-normalization) for more information.
+
+
+### Starting the Evidence Normalization Service Locally
+
+To start the service, run the following:
+
+```commandline
+uvicorn evidence.main:app --reload
+```
+
+Next, view the OpenAPI docs on your local machine:
+http://127.0.0.1:8000/evidence
+
+### Init coding style tests
+
+Code style is managed by [flake8](https://github.com/PyCQA/flake8) and checked prior to commit.
+
+We use [pre-commit](https://pre-commit.com/#usage) to run conformance tests.
+
+This ensures:
+
+* Check code style
+* Check for added large files
+* Detect AWS Credentials
+* Detect Private Key
+
+Before first commit run:
+
+```commandline
+pre-commit install
+```
+
+
+### Running unit tests
+
+Running unit tests is as easy as pytest.
+
+```commandline
+pipenv run pytest
+```

evidence/__init__.py

@@ -0,0 +1,30 @@
+"""The VICC library for normalizing evidence"""
+from pathlib import Path
+from os import environ
+import logging
+
+APP_ROOT = Path(__file__).resolve().parents[0]
+DATA_DIR_PATH = APP_ROOT / "data"
+SEQREPO_DATA_PATH = environ.get("SEQREPO_DATA_PATH", "/usr/local/share/seqrepo/latest")
+
+if environ.get("EVIDENCE_PROD") == "True":
+    ENV_NAME = "PROD"
+    environ["VARIATION_NORM_EB_PROD"] = "True"
+    environ["GENE_NORM_EB_PROD"] = "True"
+else:
+    ENV_NAME = "DEV"
+
+logging.basicConfig(
+    filename="evidence-normalizer.log",
+    format="[%(asctime)s] - %(name)s - %(levelname)s : %(message)s"
+)
+logger = logging.getLogger("evidence")
+logger.setLevel(logging.DEBUG)
+
+logging.getLogger("bravado").setLevel(logging.INFO)
+logging.getLogger("bravado_core").setLevel(logging.INFO)
+logging.getLogger("boto3").setLevel(logging.INFO)
+logging.getLogger("botocore").setLevel(logging.INFO)
+logging.getLogger("python_jsonschema_objects").setLevel(logging.INFO)
+logging.getLogger("swagger_spec_validator").setLevel(logging.INFO)
+logging.getLogger("urllib3").setLevel(logging.INFO)

evidence/data_sources/__init__.py

@@ -0,0 +1,4 @@
+"""Import data sources"""
+from .gnomad import GnomAD
+from .cbioportal import CBioPortal
+from .cancer_hotspots import CancerHotspots