chore: import upstream snapshot with attribution

examples/tutorials/run-flow-with-pipeline/components/data-prep/conda.yaml

@@ -0,0 +1,15 @@
+name: my-env
+channels:
+  - conda-forge
+dependencies:
+  - python=3.9
+  - pip
+  - pip:
+      - mlflow
+      - azureml-core
+      - azure-ai-ml>=1.12.0
+      - azureml-dataset-runtime[pandas,fuse]
+      - azureml-telemetry
+      - mltable>=1.2.0
+      - pandas
+      - pillow

examples/tutorials/run-flow-with-pipeline/components/data-prep/data-prep.py

@@ -0,0 +1,21 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+import os
+import pandas as pd
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--input_data_file", type=str)
+parser.add_argument("--output_data_folder", type=str)
+
+args, _ = parser.parse_known_args()
+
+input_df = pd.read_json(args.input_data_file, lines=True)
+
+# data preparation, e.g. data sampling, data cleaning, etc.
+processed_data = input_df.sample(n=20, replace=True, random_state=1)
+
+# export data into output folder
+output_file_path = os.path.join(args.output_data_folder, "processed_data.csv")
+processed_data.to_csv(output_file_path, index=False, header=True)

examples/tutorials/run-flow-with-pipeline/components/data-prep/data-prep.yaml

@@ -0,0 +1,26 @@
+$schema: https://azuremlschemas.azureedge.net/latest/commandComponent.schema.json
+
+type: command
+
+name: data_prep
+display_name: data preparation
+version: 0.0.1
+
+inputs:
+  input_data_file:
+    type: uri_file
+
+outputs:
+  output_data_folder:
+    type: uri_folder
+
+code: ./
+
+environment: 
+  image: mcr.microsoft.com/azureml/inference-base-2004:latest
+  conda_file: ./conda.yaml
+
+command: >-
+  python data-prep.py
+  --input_data_file ${{inputs.input_data_file}}
+  --output_data_folder ${{outputs.output_data_folder}}