Merge pull request #1 from OHNLP/database

DB setup & data quality checks

Author: JaerongA

.gitignore

@@ -178,3 +178,6 @@ data/
 
 # references
 references/
+
+# datajoint
+dj_local_c*.json

README.md

@@ -1,64 +1,6 @@
 # Activity tracker
 
-## Project Organization
-
-```
-├── LICENSE            <- Open-source license if one is chosen
-├── README.md          <- The top-level README for developers using this project.
-├── data
-│   ├── external       <- Data from third party sources.
-│   ├── interim        <- Intermediate data that has been transformed.
-│   ├── processed      <- The final, canonical data sets for modeling.
-│   └── raw            <- The original, immutable data dump.
-│
-├── docs               <- A default mkdocs project; see www.mkdocs.org for details
-│
-├── models             <- Trained and serialized models, model predictions, or model summaries
-│
-├── notebooks          <- Jupyter notebooks. Naming convention is a number (for ordering),
-│                         the creator's initials, and a short `-` delimited description, e.g.
-│                         `1.0-jqp-initial-data-exploration`.
-│
-├── pyproject.toml     <- Project configuration file with package metadata for
-│                         nlp_project_template and configuration for tools like black
-│
-├── references         <- Data dictionaries, manuals, and all other explanatory materials.
-│
-├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
-│   └── figures        <- Generated graphics and figures to be used in reporting
-│
-├── requirements.txt   <- The requirements file for reproducing the analysis environment, e.g.
-│                         generated with `pip freeze > requirements.txt`
-│
-├── .env               <- Store environment variables
-│
-├── setup.cfg          <- Configuration file for flake8
-│
-├── sql                <- Store sql queries
-│
-├── scratch            <- Temporary or experimental code or files
-│
-├── setup.cfg          <- Configuration file for flake8│
-│
-└── src/nlp_project_template   <- Source code for use in this project.
-    │
-    ├── __init__.py             <- Makes nlp_project_template a Python module
-    │
-    ├── config.py               <- Store useful variables and configuration
-    │
-    ├── dataset.py              <- Scripts to download or generate data
-    │
-    ├── features.py             <- Code to create features for modeling
-    │
-    ├── modeling
-    │   ├── __init__.py
-    │   ├── predict.py          <- Code to run model inference with trained models
-    │   └── train.py            <- Code to train models
-    │
-    └── plots.py                <- Code to create visualizations
-```
-
----
+![Database Schema](img/schema.svg)
 
 ### Create a virtual environment with:
 

docker/docker-compose.yml

@@ -0,0 +1,39 @@
+# This is for setting up an local testing environment.
+# Move to this folder and run the following commands:
+# docker-compose up -d
+# docker-compose down --volumes
+# docker exec -it datajoint-local mysql -uroot -psimple
+# docker exec -it datajoint-local bash
+# mysqld --verbose --help | grep bind-address
+
+# Some Errors with Docker?
+# Macbook M1 and M2 chips requires passing the platform environment.
+
+# In a case that youe encounter such errors do export this to your
+# environment before running the docker-compose commands above.
+
+# docker pull --platform linux/x86_64 mysql
+
+version: "3.3"
+
+services:
+  db:
+    container_name: datajoint-local
+    platform: linux/x86_64
+    image: mysql:5.7.40
+    restart: always
+    environment:
+      MYSQL_ROOT_PASSWORD: simple
+    command: --default-authentication-plugin=mysql_native_password --innodb-buffer-pool-size=512M --max-allowed-packet=64M
+    ports:
+      - "3306:3306"
+    volumes:
+      - mysql:/var/lib/mysql
+  adminer:
+    image: adminer
+    restart: always
+    ports:
+      - 8080:8080
+
+volumes:
+  mysql:

environment.yml

@@ -13,6 +13,7 @@ dependencies:
   - numpy
   - ipykernel
   - pip:
+      - datajoint
       - openpyxl
       - plotly
       - python-dotenv