commit 9d5e8b4bd9772cf607ecb7a7c5c44b1e4b37251a Author: Stefano Pigozzi Date: Sat Nov 5 22:42:38 2022 +0100 First commit! diff --git a/.gitmodules b/.gitmodules new file mode 100644 index 0000000..e69de29 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5256ec9 --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +# Ricerca in linguaggio naturale sul dataset Amazon + +Attività per **Big Data Analytics** al corso magistrale di Informatica a Unimore dell'anno accademico 2022/2023 diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 0000000..ecc5075 --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,28 @@ +version: "3.9" + + +services: + mongo: + image: "mongo:6.0.2-focal" + environment: + MONGO_INITDB_ROOT_USERNAME: "unimore" + MONGO_INITDB_ROOT_PASSWORD: "unimore" + MONGO_INITDB_DATABASE: "amazon" + + mongoimport: + image: "mongo:6.0.2-focal" + volumes: + - "./seed:/seed" + entrypoint: >- + mongoimport + --host mongo + --db amazon + --authenticationDatabase admin + --username unimore + --password unimore + --collection meta + --type json + --file /seed/metaexport.json + depends_on: + mongo: + condition: service_started diff --git a/seed/.gitignore b/seed/.gitignore new file mode 100644 index 0000000..e0208cb --- /dev/null +++ b/seed/.gitignore @@ -0,0 +1,4 @@ +# Data files should be provided externally +# I don't think I'm allowed to redistribute them + +*.json diff --git a/seed/README.md b/seed/README.md new file mode 100644 index 0000000..1477474 --- /dev/null +++ b/seed/README.md @@ -0,0 +1,5 @@ +# Data files + +This directory should contain an externally provided copy of: + +- `metaexport.json` (SHA256: `917fc2a44d03a68747fbe23389db9b178401d6cd1a869b63436bfa0eee526139`)