1  from sklearn.datasets import load_iris
 2  from sklearn.linear_model import LogisticRegression
 3  from sklearn.model_selection import train_test_split
 4  
 5  import mlflow
 6  from mlflow.models import infer_signature
 7  
 8  X, y = load_iris(return_X_y=True, as_frame=True)
 9  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
10  X_test_1, X_test_2, y_test_1, y_test_2 = train_test_split(
11      X_test, y_test, test_size=0.5, random_state=42
12  )
13  model = LogisticRegression().fit(X_train, y_train)
14  
15  predictions = model.predict(X_train)
16  signature = infer_signature(X_train, predictions)
17  
18  with mlflow.start_run() as run:
19      model_info = mlflow.sklearn.log_model(model, name="model", signature=signature)
20      print(model_info.name)
21  
22      # Evaluate the model URI
23      mlflow.evaluate(
24          model_info.model_uri,
25          X_test_1.assign(label=y_test_1),
26          targets="label",
27          model_type="classifier",
28          evaluators=["default"],
29      )
30      print(mlflow.get_logged_model(model_info.model_id))
31  
32      # Evaluate the pyfunc model object
33      model = mlflow.pyfunc.load_model(model_info.model_uri)
34      assert model.model_id is not None
35      mlflow.evaluate(
36          model,
37          X_test_2.assign(label=y_test_2),
38          targets="label",
39          model_type="classifier",
40          evaluators=["default"],
41      )
42      print(mlflow.get_logged_model(model_info.model_id))