11.14 init kedro

.github/workflows/test-kedro-new.yml

@@ -111,10 +111,12 @@ jobs:
           python -m pip install --upgrade pip
           python -m pip install --upgrade poetry
           poetry config virtualenvs.create false
-          poetry install
+          poetry install --with test
 
       - name: Run kedro
         working-directory: test-project
+        env:
+          COLUMNS: 200
         run: kedro run --env=test
 
       - name: Run tests (pytest)

mini-poetry/{{ cookiecutter.repo_name }}/conf/base/catalog.yml

@@ -41,3 +41,12 @@
 #
 # This is a data set used by the "Hello World" example pipeline provided with the project
 # template. Please feel free to remove it once you remove the example pipeline.
+
+test_data:
+  type: pandas.CSVDataset
+  filepath: data/01_raw/test-data.csv
+  load_args:
+      sep: ","
+      index_col: 0
+#      parse_dates:
+#        - date

mini-poetry/{{ cookiecutter.repo_name }}/data/01_raw/test-data.csv

@@ -0,0 +1,2 @@
+Column1,Column2
+1,2

mini-poetry/{{ cookiecutter.repo_name }}/pyproject.toml

@@ -19,7 +19,7 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = ">=3.8.1"
 kedro = "^{{ cookiecutter.kedro_version }}"
-kedro-datasets = "^1.0.0"
+kedro-datasets = {version="^1.0.0", extras=["pandas.CSVDataset"]}
 
 [tool.poetry.group.dev]
 optional = true

mini-poetry/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/data_processing/__init__.py

@@ -0,0 +1,5 @@
+from .pipeline import create_pipeline
+
+__all__ = ["create_pipeline"]
+
+__version__ = "0.1"

mini-poetry/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/data_processing/nodes.py

@@ -0,0 +1,3 @@
+import logging
+
+LOGGER = logging.getLogger(__name__)

mini-poetry/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/data_processing/pipeline.py

@@ -0,0 +1,18 @@
+from kedro.pipeline import Pipeline, pipeline, node
+
+def create_pipeline(**kwargs) -> Pipeline:
+    return pipeline(
+        [
+            node(
+                func=lambda x: x,
+                inputs="test_data",
+                outputs="processed_data",
+                name="data_processing",
+            )
+        ],
+        inputs=None,
+        outputs=None,
+        parameters=None,
+        namespace=None,
+        tags=None,
+    )