👷 only test one method per package

.github/workflows/ci.yaml

@@ -59,8 +59,8 @@ jobs:
     - name: Run demo workflow
       run: | 
        cd project
-       snakemake -p -c1 -n
-       snakemake -p -c1
+       snakemake -p -c1 --configfile config/single_dev_dataset/example/config.yaml -n
+       snakemake -p -c1 --configfile config/single_dev_dataset/example/config.yaml
     - name: Archive results
       uses: actions/upload-artifact@v3
       with:

project/config/single_dev_dataset/example/config.yaml

@@ -0,0 +1,23 @@
+config_split: config/single_dev_dataset/proteinGroups_N50/split.yaml
+config_train: config/single_dev_dataset/proteinGroups_N50/train_{model}.yaml
+folder_experiment: runs/example
+# folder_experiment: runs/dev_dataset_small/proteinGroups_N50
+fn_rawfile_metadata: data/dev_datasets/HeLa_6070/files_selected_metadata_N50.csv
+file_format: csv
+models:
+  - Median # maps to median on file system?
+  - CF
+  - DAE
+  - VAE
+  - KNN
+NAGuideR_methods:
+  - ROWMEDIAN # e1071
+  - KNN_IMPUTE # impute
+  - SEQKNN # SeqKNN
+  - RF # missForest
+  - IMPSEQ # rrcovNA
+  - QRILC # imputeLCMD
+  - SVDMETHOD # pcaMethods
+  - MICE-NORM # mice
+  - MLE # norm
+  - IRM # VIM

project/config/single_dev_dataset/example/split.yaml

@@ -0,0 +1,8 @@
+FN_INTENSITIES: data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv
+fn_rawfile_metadata: data/dev_datasets/HeLa_6070/files_selected_metadata_N50.csv
+sample_completeness: 0.5
+min_RT_time: 120
+column_names:
+  - Gene Names
+index_col: 0
+meta_date_col: Content Creation Date

project/config/single_dev_dataset/example/train_CF.yaml

@@ -0,0 +1,8 @@
+folder_experiment:  runs/example
+file_format: csv
+latent_dim: 50
+batch_size: 4096
+epochs_max: 20
+sample_idx_position: 0
+cuda: False
+save_pred_real_na: True

project/config/single_dev_dataset/example/train_DAE.yaml

@@ -0,0 +1,8 @@
+file_format: csv
+latent_dim: 10
+batch_size: 10
+epochs_max: 100
+hidden_layers: "512"
+sample_idx_position: 0
+cuda: False
+save_pred_real_na: True

project/config/single_dev_dataset/example/train_KNN.yaml

@@ -0,0 +1,2 @@
+neighbors: 3
+file_format: csv

project/config/single_dev_dataset/example/train_Median.yaml

@@ -0,0 +1 @@
+file_format: csv

project/config/single_dev_dataset/example/train_RSN.yaml

@@ -0,0 +1 @@
+axis: 0 # per protein groups RSN

project/config/single_dev_dataset/example/train_VAE.yaml

@@ -0,0 +1,10 @@
+# models_training:
+folder_experiment:  runs/example
+file_format: csv
+latent_dim: 25
+batch_size: 10
+epochs_max: 50
+hidden_layers: "512_256"
+sample_idx_position: 0
+cuda: False
+save_pred_real_na: True