update test resources

CHANGELOG.md

@@ -1,4 +1,4 @@
-# task_template x.y.z
+# task_predict_modality x.y.z
 
 ## BREAKING CHANGES
 

README.md

@@ -40,6 +40,8 @@ data shows that this is not trivial.
 | Kaiwen Deng        | contributor        |
 | Louise Deconinck   | author             |
 | Robrecht Cannoodt  | author, maintainer |
+| Xueer Chen         | contributor        |
+| Jiwei Liu          | contributor        |
 
 ## API
 
@@ -161,7 +163,7 @@ Arguments:
 The mod1 expression values of the test cells.
 
 Example file:
-`resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap/test_mod1.h5ad`
+`resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/test_mod1.h5ad`
 
 Format:
 
@@ -208,7 +210,7 @@ Data structure:
 The mod2 expression values of the test cells.
 
 Example file:
-`resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap/test_mod2.h5ad`
+`resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/test_mod2.h5ad`
 
 Format:
 
@@ -254,7 +256,7 @@ Data structure:
 The mod1 expression values of the train cells.
 
 Example file:
-`resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap/train_mod1.h5ad`
+`resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/train_mod1.h5ad`
 
 Format:
 
@@ -296,7 +298,7 @@ Data structure:
 The mod2 expression values of the train cells.
 
 Example file:
-`resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap/train_mod2.h5ad`
+`resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/train_mod2.h5ad`
 
 Format:
 
@@ -424,7 +426,7 @@ Arguments:
 A prediction of the mod2 expression values of the test cells
 
 Example file:
-`resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap/prediction.h5ad`
+`resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/prediction.h5ad`
 
 Format:
 
@@ -458,7 +460,7 @@ another.
 Metric score file
 
 Example file:
-`resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap/score.h5ad`
+`resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/score.h5ad`
 
 Format:
 

_viash.yaml

@@ -82,14 +82,20 @@ info:
       path: s3://openproblems-data/resources_test/common/
       dest: resources_test/common
     - type: s3
-      path: s3://openproblems-data/resources_test/predict_modality/
-      dest: resources_test/predict_modality
+      path: s3://openproblems-data/resources_test/task_predict_modality/
+      dest: resources_test/task_predict_modality
 
 repositories:
   - name: openproblems_v2
     type: github
     repo: openproblems-bio/openproblems-v2
     tag: main_build
+  - name: core
+    type: github
+    repo: openproblems-bio/core
+    # tag: build/main
+    tag: build/add_common_components
+    path: viash/core
 
 config_mods: |
   .runners[.type == "nextflow"].config.labels := { lowmem : "memory = 20.Gb", midmem : "memory = 50.Gb", highmem : "memory = 100.Gb", lowcpu : "cpus = 5", midcpu : "cpus = 15", highcpu : "cpus = 30", lowtime : "time = 1.h", midtime : "time = 4.h", hightime : "time = 8.h", veryhightime : "time = 24.h" }

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/resources_scripts/process_datasets.sh → scripts/create_datasets/resources.sh

@@ -1,22 +1,26 @@
 #!/bin/bash
 
-# only process the 'log_cp10k' datasets
+# 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"
+
 cat > /tmp/params.yaml << 'HERE'
-id: predict_modality_process_datasets
-input_states: s3://openproblems-data/resources/datasets/**/log_cp10k/state.yaml
-settings: '{"output_train_mod1": "$id/train_mod1.h5ad", "output_train_mod2": "$id/train_mod2.h5ad", "output_test_mod1": "$id/test_mod1.h5ad", "output_test_mod2": "$id/test_mod2.h5ad"}'
+input_states: s3://openproblems-data/resources/datasets/**/state.yaml
 rename_keys: 'input_mod1:output_mod1;input_mod2:output_mod2'
 output_state: "$id/state.yaml"
-publish_dir: s3://openproblems-data/resources/predict_modality/datasets
+settings: '{"output_train_mod1": "$id/train_mod1.h5ad", "output_train_mod2": "$id/train_mod2.h5ad", "output_test_mod1": "$id/test_mod1.h5ad", "output_test_mod2": "$id/test_mod2.h5ad"}'
+publish_dir: s3://openproblems-data/resources/task_predict_modality/datasets/
 HERE
 
 tw launch https://github.com/openproblems-bio/task_predict_modality.git \
-  --revision "build/main" \
+  --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 predict_modality,process_datasets
+  --labels task_predict_modality,process_datasets

scripts/resources_test_scripts/neurips2021_bmmc.sh → scripts/create_datasets/test_resources.sh

@@ -8,8 +8,10 @@ cd "$REPO_ROOT"
 
 set -e
 
-DATASETS_DIR="resources_test/common"
-OUTPUT_DIR="resources_test/predict_modality"
+RAW_DATA=resources_test/common
+OUTPUT_DIR=resources_test/task_predict_modality
+
+mkdir -p $OUTPUT_DIR
 
 export NXF_VER=22.04.5
 
@@ -49,4 +51,9 @@ viash run src/methods/knnr_py/config.vsh.yaml -- \
   --input_train_mod1 $OUTPUT_DIR/openproblems_neurips2021/bmmc_multiome/swap/train_mod1.h5ad \
   --input_train_mod2 $OUTPUT_DIR/openproblems_neurips2021/bmmc_multiome/swap/train_mod2.h5ad \
   --input_test_mod1 $OUTPUT_DIR/openproblems_neurips2021/bmmc_multiome/swap/test_mod1.h5ad \
-  --output $OUTPUT_DIR/openproblems_neurips2021/bmmc_multiome/swap/prediction.h5ad
+  --output $OUTPUT_DIR/openproblems_neurips2021/bmmc_multiome/swap/prediction.h5ad
+
+# only run this if you have access to the openproblems-data bucket
+aws s3 sync --profile op \
+  "$DATASET_DIR" s3://openproblems-data/resources_test/task_predict_modality \
+  --delete --dryrun

scripts/create_readme.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
 
-common/create_task_readme/create_task_readme \
-    --task_dir src \
-    --output README.md
+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 test --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 test --parallel --setup cachedbuild

scripts/project/test_all_components.sh

@@ -0,0 +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

scripts/run_benchmark/run.sh

@@ -0,0 +1,40 @@
+#!/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 'run_benchmark' workflow has been implemented, update this script to use it."
+echo "  Step 1: replace 'task_predict_modality' with the name of the task in the following command."
+echo "  Step 2: replace the rename keys parameters to fit your run_benchmark inputs"
+echo "  Step 3: replace the settings parameter to fit your run_benchmark outputs"
+echo "  Step 4: remove this message"
+exit 1
+
+set -e
+
+# generate a unique id
+RUN_ID="run_$(date +%Y-%m-%d_%H-%M-%S)"
+publish_dir="s3://openproblems-data/resources/task_predict_modality/results/${RUN_ID}"
+
+# make sure only log_cp10k is used
+cat > /tmp/params.yaml << HERE
+input_states: s3://openproblems-data/resources/task_predict_modality/datasets/**/state.yaml
+rename_keys: 'input_train:output_train;input_test:output_test'
+output_state: "state.yaml"
+publish_dir: "$publish_dir"
+HERE
+
+tw launch https://github.com/openproblems-bio/task_predict_modality.git \
+  --revision build/main \
+  --pull-latest \
+  --main-script target/nextflow/workflows/run_benchmark/main.nf \
+  --workspace 53907369739130 \
+  --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
+  --params-file /tmp/params.yaml \
+  --entry-name auto \
+  --config common/nextflow_helpers/labels_tw.config \
+  --labels task_predict_modality,full

scripts/run_benchmark/run_on_test_resources.sh

@@ -0,0 +1,35 @@
+#!/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 'run_benchmark' workflow has been implemented, update this script to use it."
+echo "  Step 1: replace 'task_predict_modality' with the name of the task in the following command."
+echo "  Step 2: replace the rename keys parameters to fit your run_benchmark inputs"
+echo "  Step 3: replace the settings parameter to fit your run_benchmark outputs"
+echo "  Step 4: remove this message"
+exit 1
+
+set -e
+
+cat > /tmp/params.yaml << 'HERE'
+input_states: s3://openproblems-data/resources_test/task_predict_modality/**/state.yaml
+rename_keys: 'input_train:output_train;input_test:output_test;input_solution:output_solution'
+output_state: "state.yaml"
+publish_dir: s3://openproblems-nextflow/temp/task_predict_modality/
+HERE
+
+tw launch https://github.com/openproblems-bio/task_predict_modality.git \
+  --revision build/main \
+  --pull-latest \
+  --main-script target/nextflow/workflows/run_benchmark/main.nf \
+  --workspace 53907369739130 \
+  --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
+  --params-file /tmp/params.yaml \
+  --entry-name auto \
+  --config common/nextflow_helpers/labels_tw.config \
+  --labels task_predict_modality,test

scripts/sync_resources.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+set -e
+
+common/scripts/sync_resources

src/api/comp_control_method.yaml

@@ -37,5 +37,5 @@ test_resources:
     path: /common/component_tests/check_config.py
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap
-    dest: resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap
+  - path: /resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap
+    dest: resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap

src/api/comp_method.yaml

@@ -24,9 +24,7 @@ arguments:
     direction: output
     required: true
 test_resources:
-  - type: python_script
-    path: /common/component_tests/check_config.py
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap
-    dest: resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap
+  - path: /resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap
+    dest: resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap

src/api/comp_method_predict.yaml

@@ -26,4 +26,9 @@ arguments:
   - name: "--output"
     __merge__: file_prediction.yaml
     direction: output
-    required: true
+    required: true
+test_resources:
+  - type: python_script
+    path: /common/component_tests/run_and_check_output.py
+  - path: /resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap
+    dest: resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap

src/api/comp_method_train.yaml

@@ -24,9 +24,7 @@ arguments:
     direction: output
     required: true
 test_resources:
-  - type: python_script
-    path: /common/component_tests/check_config.py
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap
-    dest: resources_test/predict_modality/openproblems_neurips2021/bmmc_cite/swap
+  - path: /resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap
+    dest: resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap