input data registered as data asset

classical/aml-cli-v2/data-science/environment/train-requirements.txt

@@ -1,7 +1,6 @@
 azureml-mlflow==1.38.0
-azureml-ai-ml==1.0.0
 pyarrow==10.0.0
 scikit-learn==0.24.1
 pandas==1.2.1
 joblib==1.2.0
-matplotlib==3.3.3
+matplotlib==3.3.3

classical/aml-cli-v2/data-science/src/prep/prep.py

@@ -75,7 +75,7 @@ def main(args):
     arr = os.listdir(args.raw_data)
     print(arr)
 
-    data = pd.read_csv((Path(args.raw_data) / 'taxi-data.csv'))
+    data = pd.read_csv((Path(args.raw_data)))
     data = data[NUMERIC_COLS + CAT_NOM_COLS + CAT_ORD_COLS + [TARGET_COL]]
 
     # ------------- Split Data ------------- #

classical/aml-cli-v2/data-science/src/prep/test_prep.py

@@ -82,7 +82,9 @@ def test_prep_data():
     df = pd.DataFrame(data)
     df.to_csv(os.path.join(raw_data, "taxi-data.csv"))
     
+    raw_data= os.path.join(raw_data, "taxi-data.csv")
     cmd = f"python data-science/src/prep/prep.py --raw_data={raw_data} --train_data={train_data} --val_data={val_data} --test_data={test_data}"
+
     p = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
     out, err = p.communicate() 
     result = str(out).split('\\n')

classical/aml-cli-v2/mlops/azureml/train/pipeline.yml

@@ -5,9 +5,9 @@ description: Training Pipeline to train a model that predicts taxi fare price
 
 # <inputs_and_outputs>
 inputs:
-  input: #using local data, will create an anonymous data asset
-    type: uri_folder
-    path: ../../../data/
+  input:
+    type: uri_file
+    path: azureml:taxi-data@latest
   enable_monitoring: "true"
   table_name: 'taximonitoring'
 

classical/aml-cli-v2/mlops/devops-pipelines/deploy-model-training-pipeline.yml

@@ -53,6 +53,11 @@ stages:
           environment_name: taxi-train-env
           environment_file: mlops/azureml/train/train-env.yml
           enable_monitoring: $(enable_monitoring)
+      - template: templates/${{ variables.version }}/register-data.yml@mlops-templates
+        parameters:
+          data_type: uri_file
+          data_name: taxi-data
+          data_file: mlops/azureml/train/data.yml
       - checkout: rai-vnext-preview
         path: s/
       - template: register-rai-components.yml