YAML based config (#14)

* fix ExternalArtifact behavior * update zenml-ref * fix ref name * YAML based template configuration * update docs * fix config * verbose tests output * verbose tests output * no fail fast * verbose tests output * bump timeouts for mlflow * try replace * testing inside python * restore test flow * update requirements * properly skip macos * revert ref
zenml-io · Oct 19, 2023 · 80aaa6c · cameronraysmith · Oct 22, 2023 · avishniakov
1 parent d4d52f9
commit 80aaa6c
Show file tree

Hide file tree

Showing 22 changed files with 328 additions and 347 deletions.
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -0,0 +1,16 @@
+## Describe changes
+I implemented/fixed _ to achieve _.
+
+## Pre-requisites
+Please ensure you have done the following:
+- [ ] If my change requires a change to docs, I have updated the documentation accordingly.
+- [ ] I have added tests to cover my changes.
+- [ ] I have updated `ref-zenml` in `.github/workflows/ci.yml` accordingly (if you don't know - `main` would be a solid choice)
+
+## Types of changes
+<!--- What types of changes does your code introduce? Put an `x` in all the boxes that apply: -->
+- [ ] Bug fix (non-breaking change which fixes an issue)
+- [ ] New feature (non-breaking change which adds functionality)
+- [ ] Breaking change (fix or feature that would cause existing functionality to change)
+- [ ] Other (add details above)
+
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -18,6 +18,7 @@ jobs:
   run-tests:
     runs-on: ${{ matrix.os }}
     strategy:
+      fail-fast: false
       matrix:
         stack-name: [local]
         os: [windows-latest, ubuntu-latest, macos-latest]

diff --git a/README.md b/README.md
@@ -209,7 +209,7 @@ df_inference, target = data_loader(is_inference=True)
 df_inference = inference_data_preprocessor(
     dataset_inf=df_inference,
     preprocess_pipeline=ExternalArtifact(
-        pipeline_name=MetaConfig.pipeline_name_training,
+        pipeline_name="your_product_name_training",
         artifact_name="preprocess_pipeline",
     ),
     target=target,

diff --git a/requirements.txt b/requirements.txt
@@ -1,2 +1 @@
-copier
-jinja2-time
+zenml[templates]
diff --git a/template/artifacts/__init__.py b/template/artifacts/__init__.py
diff --git a/template/artifacts/materializer.py b/template/artifacts/materializer.py
diff --git a/template/artifacts/model_metadata.py b/template/artifacts/model_metadata.py
diff --git a/template/config.py b/template/config.py
diff --git a/template/config.yaml b/template/config.yaml
@@ -0,0 +1,78 @@
+# {% include 'template/license_header' %}
+
+settings:
+  docker:
+    requirements:
+      - aws
+{%- if data_quality_checks %}
+      - evidently
+{%- endif %}
+      - kubeflow
+      - kubernetes
+      - mlflow
+      - sklearn
+      - slack
+extra:
+  mlflow_model_name: e2e_use_case_model
+{%- if target_environment == 'production' %}
+  target_env: Production
+{%- else %}
+  target_env: Staging
+{%- endif %}
+  notify_on_success: False
+  notify_on_failure: True
+{%- if hyperparameters_tuning %}
+  # This set contains all the models that you want to evaluate
+  # during hyperparameter tuning stage.
+  model_search_space:
+    random_forest:
+      model_package: sklearn.ensemble
+      model_class: RandomForestClassifier
+      search_grid:
+        criterion:
+          - gini
+          - entropy
+        max_depth:
+          - 2
+          - 4
+          - 6
+          - 8
+          - 10
+          - 12
+        min_samples_leaf:
+          range:
+            start: 1
+            end: 10
+        n_estimators:
+          range:
+            start: 50
+            end: 500
+            step: 25
+    decision_tree:
+      model_package: sklearn.tree
+      model_class: DecisionTreeClassifier
+      search_grid:
+        criterion:
+          - gini
+          - entropy
+        max_depth:
+          - 2
+          - 4
+          - 6
+          - 8
+          - 10
+          - 12
+        min_samples_leaf:
+          range:
+            start: 1
+            end: 10
+{%- else %}
+    # This model configuration will be used for the training stage.
+  model_configuration:
+    model_package: sklearn.tree
+    model_class: DecisionTreeClassifier
+    params:
+      criterion: gini
+      max_depth: 5
+      min_samples_leaf: 3
+{%- endif %}