bootstrap diabetes cleanup (#189)

bootstrap/README.md

@@ -2,8 +2,10 @@
 
 To use this existing project structure and scripts for your new ML project, you can quickly get started from the existing repository,  bootstrap and create a template that works for your ML project. Bootstraping will prepare a similar directory structure for your project which includes renaming files and folders, deleting and cleaning up some directories and fixing imports and absolute path based on your project name. This will enable reusing various resources like pre-built pipelines and scripts for your new project.
 
-To bootstrap from the existing MLOpsPython repository clone this repository and run bootstrap.py script as below
+To bootstrap from the existing MLOpsPython repository clone this repository, ensure Python is installed locally, and run bootstrap.py script as below
 
->python bootstrap.py --d [dirpath] --n [projectname]
+`python bootstrap.py --d [dirpath] --n [projectname]`
 
-Where [dirpath] is the absolute path to the root of your directory where MLOps repo is cloned and [projectname] is the name of your ML project  
+Where `[dirpath]` is the absolute path to the root of your directory where MLOps repo is cloned and `[projectname]` is the name of your ML project.
+
+[This article](https://docs.microsoft.com/azure/machine-learning/tutorial-convert-ml-experiment-to-production#use-your-own-model-with-mlopspython-code-template) will also assist to use this code template for your own ML project.

bootstrap/bootstrap.py

@@ -57,38 +57,6 @@ def deletedir(self):
             os.system(
                 'rmdir /S /Q "{}"'.format(os.path.join(self._project_directory, dir)))  # NOQA: E501
 
-    def replaceprojectname(self):
-        # Replace instances of diabetes_regression within files
-        dirs = [r".env.example",
-                r".pipelines\azdo-base-pipeline.yml",
-                r".pipelines\azdo-pr-build-train.yml",
-                r".pipelines\diabetes_regression-ci-build-train.yml",
-                r".pipelines\diabetes_regression-ci-image.yml",
-                r".pipelines\diabetes_regression-template-get-model-version.yml",  # NOQA: E501
-                r".pipelines\diabetes_regression-variables.yml",
-                r"environment_setup\Dockerfile",
-                r"environment_setup\install_requirements.sh",
-                r"ml_service\pipelines\diabetes_regression_build_train_pipeline_with_r_on_dbricks.py",  # NOQA: E501
-                r"ml_service\pipelines\diabetes_regression_build_train_pipeline_with_r.py",  # NOQA: E501
-                r"ml_service\pipelines\diabetes_regression_build_train_pipeline.py",  # NOQA: E501
-                r"ml_service\pipelines\diabetes_regression_verify_train_pipeline.py",  # NOQA: E501
-                r"ml_service\util\create_scoring_image.py",
-                r"diabetes_regression\azureml_environment.json",
-                r"diabetes_regression\conda_dependencies.yml",
-                r"diabetes_regression\evaluate\evaluate_model.py",
-                r"diabetes_regression\training\test_train.py"]  # NOQA: E501
-
-        for file in dirs:
-            fin = open(os.path.join(self._project_directory, file),
-                       "rt", encoding="utf8")
-            data = fin.read()
-            data = data.replace("diabetes_regression", self.project_name)
-            fin.close()
-            fin = open(os.path.join(self._project_directory, file),
-                       "wt", encoding="utf8")
-            fin.write(data)
-            fin.close()
-
     def cleandir(self):
         # Clean up directories
         dirs = ["data", "experimentation"]
@@ -108,6 +76,40 @@ def validateargs(self):
             raise Exception("Project name should be 3 to 15 chars long")
 
 
+def replaceprojectname(project_dir, project_name, rename_name):
+    # Replace instances of rename_name within files with project_name
+    dirs = [r".env.example",
+            r".pipelines\azdo-base-pipeline.yml",
+            r".pipelines\azdo-pr-build-train.yml",
+            r".pipelines\diabetes_regression-ci-build-train.yml",
+            r".pipelines\diabetes_regression-ci-image.yml",
+            r".pipelines\diabetes_regression-template-get-model-version.yml",  # NOQA: E501
+            r".pipelines\diabetes_regression-variables.yml",
+            r"environment_setup\Dockerfile",
+            r"environment_setup\install_requirements.sh",
+            r"ml_service\pipelines\diabetes_regression_build_train_pipeline_with_r_on_dbricks.py",  # NOQA: E501
+            r"ml_service\pipelines\diabetes_regression_build_train_pipeline_with_r.py",  # NOQA: E501
+            r"ml_service\pipelines\diabetes_regression_build_train_pipeline.py",  # NOQA: E501
+            r"ml_service\pipelines\diabetes_regression_verify_train_pipeline.py",  # NOQA: E501
+            r"ml_service\util\create_scoring_image.py",
+            r"diabetes_regression\azureml_environment.json",
+            r"diabetes_regression\conda_dependencies.yml",
+            r"diabetes_regression\evaluate\evaluate_model.py",
+            r"diabetes_regression\register\register_model.py",
+            r"diabetes_regression\training\test_train.py"]  # NOQA: E501
+
+    for file in dirs:
+        fin = open(os.path.join(project_dir, file),
+                   "rt", encoding="utf8")
+        data = fin.read()
+        data = data.replace(rename_name, project_name)
+        fin.close()
+        fin = open(os.path.join(project_dir, file),
+                   "wt", encoding="utf8")
+        fin.write(data)
+        fin.close()
+
+
 def main(args):
     parser = argparse.ArgumentParser(description='New Template')
     parser.add_argument("--d", type=str,
@@ -122,7 +124,9 @@ def main(args):
         helper.validateargs()
         # helper.clonerepo()
         helper.cleandir()
-        helper.replaceprojectname()
+        replaceprojectname(project_directory, project_name,
+                           "diabetes_regression")
+        replaceprojectname(project_directory, project_name, "diabetes")
         helper.deletedir()
         helper.renamefiles()
         helper.renamedir()

diabetes_regression/register/register_model.py

@@ -119,15 +119,15 @@ def register_aml_model(
         if (build_id != 'none'):
             model_already_registered(model_name, exp, run_id)
             run = Run(experiment=exp, run_id=run_id)
-            tagsValue = {"area": "diabetes", "type": "regression",
+            tagsValue = {"area": "diabetes_regression",
                          "BuildId": build_id, "run_id": run_id,
                          "experiment_name": exp.name}
             if (build_uri is not None):
                 tagsValue["BuildUri"] = build_uri
         else:
             run = Run(experiment=exp, run_id=run_id)
             if (run is not None):
-                tagsValue = {"area": "diabetes", "type": "regression",
+                tagsValue = {"area": "diabetes_regression",
                              "run_id": run_id, "experiment_name": exp.name}
             else:
                 print("A model run for experiment", exp.name,

ml_service/util/create_scoring_image.py

@@ -39,7 +39,7 @@
     runtime="python",
     conda_file="conda_dependencies.yml",
     description="Image with ridge regression model",
-    tags={"area": "diabetes", "type": "regression"},
+    tags={"area": "diabetes_regression"},
 )
 
 image = Image.create(