Add initialization script, golden dataset mapper

pyproject.toml

@@ -15,7 +15,7 @@ license = "MIT"
 packages = [
     {include = "scope"},
 ]
-include = ["config.defaults.yaml"]
+include = ["config.defaults.yaml", "tools/golden_dataset_mapper.json"]
 
 [tool.poetry.dependencies]
 python = "^3.9, <3.12"
@@ -56,6 +56,7 @@ tables = ">=3.7,<3.9.2"
 pre-commit = ">=3.5.0"
 
 [tool.poetry.scripts]
+scope-initialize = "scope.scope_class:Scope.initialize"
 scope-develop = "scope._instantiate:develop"
 scope-lint = "scope.scope_class:Scope.lint"
 scope-doc = "scope._instantiate:doc"

scope/scope_class.py

@@ -26,6 +26,7 @@
 import json
 import shutil
 import argparse
+import site
 
 
 @contextmanager
@@ -563,6 +564,41 @@ def fetch_datasets(gcs_path: str = "gs://ztf-scope/datasets"):
         if p.returncode != 0:
             raise RuntimeError("Failed to fetch SCoPe datasets")
 
+    @staticmethod
+    def initialize():
+        main_dir = "scope-ml"
+        scope_dirs = ["tools"]
+        os.makedirs(main_dir, exist_ok=True)
+        for directory in scope_dirs:
+            os.makedirs(f"{main_dir}/{directory}", exist_ok=True)
+
+        site_packages_path = site.getsitepackages()[0]
+        default_config_name = "config.defaults.yaml"
+        copied_config_name = "config.yaml"
+        tools_dir = "tools"
+        mappers = ["golden_dataset_mapper.json"]
+
+        # Copy config defaults to new directory strucutre if needed
+        if not os.path.exists(f"{main_dir}/{copied_config_name}"):
+            shutil.copy(
+                f"{site_packages_path}/{default_config_name}",
+                f"{main_dir}/{copied_config_name}",
+            )
+            print(
+                f"Created new '{copied_config_name}' config file. Please customize/add tokens there before running scope."
+            )
+        else:
+            print(f"{copied_config_name} already exists in the '{main_dir}' directory.")
+
+        for mapper in mappers:
+            print(f"Copying dataset mapper '{mapper}'")
+            shutil.copy(
+                f"{site_packages_path}/{tools_dir}/{mapper}",
+                {main_dir} / {tools_dir} / {mapper},
+            )
+
+        print(f"scope-ml initialized. Run scripts from '{main_dir}' directory.")
+
     def parse_run_train(self):
         parser = argparse.ArgumentParser()
         parser.add_argument(