update scripts (#9)

* update scripts

* remove gitignore

* add output state to script

* add contrib guidelines

* get rid of the findStatesTemp workaround

* move methods and metrics one level higher

* fix commands

* bump version

* update workflow scripts

* fix script

.gitignore

@@ -1,10 +1,10 @@
-resources
-resources_test
-work
-.nextflow*
-target
+/resources
+/resources_test
+/work
+/.nextflow*
+/target
 .vscode
 .DS_Store
-output
+/output
 trace-*
-.ipynb_checkpoints
+.ipynb_checkpoints

CONTRIBUTING.md

@@ -0,0 +1,148 @@
+# Contribution guidelines
+
+We encourage contributions from the community. To contribute:
+
+* Star this repository: Click the star button in the top-right corner of the repository to show your support.
+* Fork the repository: Start by forking this repository to your account.
+* Develop your component: Create your Viash component, ensuring it aligns with our best practices (detailed below).
+* Submit a pull request: After testing your component, submit a pull request for review.
+
+## Installation
+
+You need to have Docker, Java, and Viash installed. Follow
+[these instructions](https://openproblems.bio/documentation/fundamentals/requirements)
+to install the required dependencies.
+
+## Getting started
+
+### Cloning the repository
+
+To get started, fork the repository and clone it to your local machine:
+
+```bash
+git clone <git url to fork> --recursive
+
+cd <name of the repository>
+```
+
+NOTE: If you forgot to clone the repository with the `--recursive` flag, you can run the following command to update the submodules:
+
+```bash
+git submodule update --init --recursive
+```
+
+### Downloading the test resources
+
+Next, you should download the test resources:
+
+```bash
+scripts/sync_resources.sh
+```
+
+You may need to run this script again if the resources are updated.
+
+## Good first steps
+
+### Creating a new method
+
+To create a new method, you can use the following command:
+
+```bash
+# in Python:
+common/scripts/create_component \
+  --name my_method \
+  --language python \
+  --type method
+
+# or in R:
+common/scripts/create_component \
+  --name my_method \
+  --language r \
+  --type method
+```
+
+This will create a new method in `src/methods/my_method`. Next, you should:
+
+* Fill in the component's metadata
+* Specify dependencies
+* Implement the method's code
+* Run the unit test
+
+Please review our documentation on [creating a new method](https://openproblems.bio/documentation/create_component/add_a_method) for more information on how to do this.
+
+
+### Creating a new metric
+
+Creating a new metric is similar to creating a new method. You can use the following command:
+
+```bash
+# in Python:
+common/scripts/create_component \
+  --name my_metric \
+  --language python \
+  --type metric
+
+# or in R:
+common/scripts/create_component \
+  --name my_metric \
+  --language r \
+  --type metric
+```
+
+This will create a new metric in `src/metrics/my_metric`. Next, you should:
+
+* Fill in the component's metadata
+* Specify dependencies
+* Implement the metric's code
+* Run the unit test
+
+Please review our documentation on [creating a new metric](https://openproblems.bio/documentation/create_component/add_a_metric) for more information.
+
+
+## Frequently used commands
+
+To get started, you can run the following commands:
+
+### Sync the test data
+
+To sync the test data, run the following command:
+
+```bash
+scripts/sync_resources.sh
+```
+
+### Building the components
+
+To run the benchmark, you first need to build the components.
+
+```bash
+viash ns build --parallel --setup cachedbuild
+```
+
+For each of the components, this will:
+
+* Build a Docker image
+* Build an executable at `target/executable/<component_name>`
+* Build a Nextflow module at `target/nextflow/<component_name>`
+
+### Running the unit tests
+
+To run the unit test of one component, you can use the following command:
+
+```bash
+viash test src/path/to/config.vsh.yaml
+```
+
+To run the unit tests for all components, you can use the following command:
+
+```bash
+viash ns test --parallel
+```
+
+### Running the benchmark
+
+To run the benchmark, you can use the following command:
+
+```bash
+scripts/run_benchmark/run.sh
+```

_viash.yaml

@@ -1,4 +1,4 @@
-viash_version: 0.9.0-RC7
+viash_version: 0.9.0
 
 # Step 1: Change the name of the task.
 # example: task_name_of_this_task

scripts/create_component/.gitignore

@@ -0,0 +1,2 @@
+# if users change the scripts, the changes should not be committed.
+/create_*_*.sh

scripts/create_component/create_python_method.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+set -e
+
+common/scripts/create_component \
+  --name my_python_method \
+  --language python \
+  --type method

scripts/create_component/create_python_metric.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+set -e
+
+common/scripts/create_component \
+  --name my_python_metric \
+  --language python \
+  --type metric

scripts/create_component/create_r_method.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+set -e
+
+common/scripts/create_component \
+  --name my_r_method \
+  --language r \
+  --type method

scripts/create_component/create_r_metric.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+set -e
+
+common/scripts/create_component \
+  --name my_r_metric \
+  --language r \
+  --type metric

scripts/create_datasets/resources.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+
+# get the root of the directory
+REPO_ROOT=$(git rev-parse --show-toplevel)
+
+# ensure that the command below is run from the root of the repository
+cd "$REPO_ROOT"
+
+# remove this when you have implemented the script
+echo "TODO: once the 'process_datasets' workflow is implemented, update this script to use it."
+echo "  Step 1: replace 'task_template' with the name of the task in the following command."
+echo "  Step 2: replace the rename keys parameters to fit your process_dataset inputs"
+echo "  Step 3: replace the settings parameter to fit your process_dataset outputs"
+echo "  Step 4: remove this message"
+exit 1
+
+cat > /tmp/params.yaml << 'HERE'
+input_states: s3://openproblems-data/resources/datasets/**/state.yaml
+rename_keys: 'input:output_dataset'
+output_state: '$id/state.yaml'
+settings: '{"output_train": "$id/train.h5ad", "output_test": "$id/test.h5ad"}'
+publish_dir: s3://openproblems-data/resources/task_template/datasets/
+HERE
+
+tw launch https://github.com/openproblems-bio/task_template.git \
+  --revision build/main \
+  --pull-latest \
+  --main-script target/nextflow/workflows/process_datasets/main.nf \
+  --workspace 53907369739130 \
+  --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
+  --params-file /tmp/params.yaml \
+  --entry-name auto \
+  --config common/nextflow_helpers/labels_tw.config \
+  --labels task_template,process_datasets

scripts/create_datasets/test_resources.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+
+# get the root of the directory
+REPO_ROOT=$(git rev-parse --show-toplevel)
+
+# ensure that the command below is run from the root of the repository
+cd "$REPO_ROOT"
+
+# remove this when you have implemented the script
+echo "TODO: replace the commands in this script with the sequence of components that you need to run to generate test_resources."
+echo "  Inside this script, you will need to place commands to generate example files for each of the 'src/api/file_*.yaml' files."
+exit 1
+
+set -e
+
+RAW_DATA=resources_test/common
+DATASET_DIR=resources_test/task_template
+
+mkdir -p $DATASET_DIR
+
+# process dataset
+echo Running process_dataset
+nextflow run . \
+  -main-script target/nextflow/workflows/process_datasets/main.nf \
+  -profile docker \
+  --publish_dir "$DATASET_DIR" \
+  --id "pancreas" \
+  --input "$RAW_DATA/pancreas/dataset.h5ad" \
+  --output_train '$id/train.h5ad' \
+  --output_test '$id/test.h5ad' \
+  --output_solution '$id/solution.h5ad' \
+  --output_state '$id/state.yaml'
+
+# run one method
+viash run src/methods/knn/config.vsh.yaml -- \
+    --input_train $DATASET_DIR/pancreas/train.h5ad \
+    --input_test $DATASET_DIR/pancreas/test.h5ad \
+    --output $DATASET_DIR/pancreas/prediction.h5ad
+
+# run one metric
+viash run src/metrics/accuracy/config.vsh.yaml -- \
+    --input_prediction $DATASET_DIR/pancreas/prediction.h5ad \
+    --input_solution $DATASET_DIR/pancreas/solution.h5ad \
+    --output $DATASET_DIR/pancreas/score.h5ad
+
+# only run this if you have access to the openproblems-data bucket
+aws s3 sync --profile op \
+  "$DATASET_DIR" s3://openproblems-data/resources_test/task_template \
+  --delete --dryrun

scripts/create_readme.sh

@@ -1,3 +1,5 @@
 #!/bin/bash
 
+set -e
+
 common/scripts/create_task_readme

scripts/project/build_all_components.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+set -e
+
+# Build all components in a namespace (refer https://viash.io/reference/cli/ns_build.html)
+viash ns build --parallel

scripts/project/build_all_docker_containers.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+set -e
+
+# Build all components in a namespace (refer https://viash.io/reference/cli/ns_build.html)
+# and set up the container via a cached build
+viash ns build --parallel --setup cachedbuild

scripts/test_all_components.sh → scripts/project/test_all_components.sh

@@ -1,4 +1,6 @@
 #!/bin/bash
 
+set -e
+
 # Test all components in a namespace (refer https://viash.io/reference/cli/ns_test.html)
 viash ns test --parallel