Merge pull request #22 from cbib/help-menu-byhydra

Help menu byhydra

Makefile

@@ -25,7 +25,7 @@ requirements: test_environment
 
 ## Make Dataset
 data: requirements
-	$(PYTHON_INTERPRETER) src/data/make_dataset.py data/raw data/processed
+	$(PYTHON_INTERPRETER) src/data/make_dataset.py data/
 
 ## Delete all compiled Python files
 clean:

src/dimet/__main__.py

@@ -9,12 +9,11 @@
 
 import hydra
 
-from dimet.method import Method
 from omegaconf import DictConfig, OmegaConf
 
 from dimet.data import Dataset
+from dimet.method import Method
 
-import click
 
 logger = logging.getLogger(__name__)
 
@@ -34,18 +33,17 @@ def main_run_analysis(cfg: DictConfig) -> None:
     method.run(cfg, dataset)
 
 
-@click.command(context_settings=dict(
-        help_option_names=['-h', '--help'])  # needed to recognize -h as well
+def fully_empty_args_custom_message() -> None:
+    custom_message: str = (
+        "\nDIMet is a tool for the Differential analysis of "
+        "targeted Isotope-labeled Metabolomics data. \n\n  Please type "
+        "'python -m dimet --help' or 'python -m dimet -h' for usage.\n"
     )
-@click.option('-cd', type=str, required=True,
-              help="Directory containing the general configuration "
-                   "(see -cn)")
-@click.option('-cn', type=str, required=True,
-              help="File name of the general configuration "
-                   "(only one .yaml file name)")
-def main_run_analysis__or_display_help(cd, cn) -> None:
-    main_run_analysis()  # run: hydra handles further arguments validation
+    print(custom_message)
 
 
 if __name__ == "__main__":
-    main_run_analysis__or_display_help()
+    if len(sys.argv) <= 1:
+        fully_empty_args_custom_message()
+    else:
+        main_run_analysis()

src/dimet/config/config.yaml

@@ -3,16 +3,16 @@ hydra:
     chdir: true
   run:
     dir: ../outputs/${now:%Y-%m-%d}/${now:%H-%M-%S}/${analysis.dataset.label}-${analysis.method.label}
-
-# Notes: 
-# This config.yaml file is never used by the code, but remains here as template.
-# All the method/*.yaml files YES THEY ARE USED by the code
+
+
+# This config.yaml file is used by the code when calling --help
 
 defaults:
-  - analysis: abundance_plot
   - _self_
+  - override hydra/help: dimet_help
+
 
 figure_path: figures
 table_path: tables
 
-# check https://hydra.cc/docs/patterns/specializing_config/ for more info about this
+# check https://hydra.cc/docs/patterns/specializing_config/ for more info about this

src/dimet/config/hydra/help/dimet_help.yaml

@@ -0,0 +1,38 @@
+# App name, override to match the name your app is known by
+app_name: DIMet
+
+# Help header, customize to describe your app to your users
+header: Welcome to ${hydra.help.app_name}!
+
+footer: |-
+  Powered by Hydra (https://hydra.cc)
+  Use --hydra-help to view Hydra specific help
+
+template: |-
+  ${hydra.help.header}
+
+  DIMet is a tool for the Differential analysis of targeted Isotope-labeled Metabolomics data
+  
+  Usage: python -m dimet [options]
+
+  optional arguments:
+    -cd, --config-dir     Directory name where the general configuration is located (see -cn)
+    -cn, --config-name    File name of the general configuration, only one .yaml file name
+    -h, --help            Show this help message and exit
+  
+  
+  == Available analyses ==
+  $APP_CONFIG_GROUPS
+ 
+  ${hydra.help.footer}
+  
+
+# Basic Hydra flags:
+#   $FLAGS_HELP
+#
+# Config groups, choose one of:
+#   $APP_CONFIG_GROUPS: All config groups that does not start with hydra/.
+#   $HYDRA_CONFIG_GROUPS: All the Hydra config groups (starts with hydra/)
+#
+# Configuration generated with overrides:
+#   $CONFIG : Generated config

src/dimet/data/__init__.py

@@ -46,7 +46,6 @@ def build(self) -> "Dataset":
 
 class Dataset(BaseModel):
     config: DatasetConfig
-    raw_data_folder: str = None
     sub_folder_absolute: str = None
     metadata_df: Optional[pd.DataFrame] = None
     abundances_df: Optional[pd.DataFrame] = None
@@ -75,22 +74,23 @@ def preload(self):
             logger.info("looking for data in %s", self.sub_folder_absolute)
         else:
             self.sub_folder_absolute = self.config.subfolder
-        self.raw_data_folder = os.path.join(self.sub_folder_absolute, "raw")
+
 
         # start loading the dataframes
         file_paths = [
-            ("metadata", os.path.join(self.raw_data_folder,
+            ("metadata", os.path.join(self.sub_folder_absolute,
                                       self.config.metadata + ".csv")),
-            ("abundances", os.path.join(self.raw_data_folder,
+            ("abundances", os.path.join(self.sub_folder_absolute,
                                         self.config.abundances + ".csv")),
             ("mean_enrichment", os.path.join(
-                self.raw_data_folder,
+                self.sub_folder_absolute,
                 self.config.mean_enrichment + ".csv")),
             ("isotopologue_proportions", os.path.join(
-                self.raw_data_folder,
+                self.sub_folder_absolute,
                 self.config.isotopologue_proportions + ".csv")),
             ("isotopologues", os.path.join(
-                self.raw_data_folder, self.config.isotopologues + ".csv")),
+                self.sub_folder_absolute,
+                self.config.isotopologues + ".csv")),
         ]
         dfs = []
         for label, file_path in file_paths:
@@ -130,7 +130,7 @@ def preload(self):
         # log the first 5 rows of the metadata
         logger.info("Loaded metadata: \n%s", self.metadata_df.head())
         logger.info(
-            "Finished loading raw dataset %s, available dataframes are : %s",
+            "Finished loading dataset %s, available dataframes are : %s",
             self.config.label, self.available_datasets
         )
         self.check_expectations()
@@ -191,17 +191,13 @@ class DataIntegrationConfig(DatasetConfig):
 
 class DataIntegration(Dataset):
     config: DataIntegrationConfig
-    integration_files_folder_absolute: str = None  # absolute path directory
     deg_dfs: Dict[int, pd.DataFrame] = {}
     pathways_dfs: Dict[str, pd.DataFrame] = {}
 
     def set_dataset_integration_config(self):
         self.preload()
         self.split_datafiles_by_compartment()
 
-        self.integration_files_folder_absolute = os.path.join(
-            self.sub_folder_absolute, "integration_files")
-
         self.check_expectations()  # of the Dataset class
         self.check_expectations_integration_data()  # of this child class
 
@@ -231,7 +227,7 @@ def load_deg_dfs(self):
         for i, file_name in enumerate(self.config.transcripts):
             try:
                 path_deg_file = os.path.join(
-                    self.integration_files_folder_absolute,
+                    self.sub_folder_absolute,
                     f"{file_name}.csv")
                 deg_df = pd.read_csv(path_deg_file, sep='\t', header=0)
                 self.deg_dfs[i] = deg_df
@@ -247,7 +243,7 @@ def load_pathways_dfs(self):
         for k in self.config.pathways.keys():
             try:
                 path_file = os.path.join(
-                    self.integration_files_folder_absolute,
+                    self.sub_folder_absolute,
                     f"{self.config.pathways[k]}.csv")
                 pathway_df = pd.read_csv(path_file, sep='\t', header=0)
                 self.pathways_dfs[k] = pathway_df