plt.savefig(os.path.join(artifacts_dir, "example2.png"))
artifacts = {
"example_dict_2_from_obj_saved_as_csv":
example_dict,
"example_image_2_from_png_file":
os.path.join(artifacts_dir, "example2.png"),
}
return metrics, artifacts
with mlflow.start_run() as run:
mlflow.sklearn.log_model(lin_reg, "model")
model_uri = mlflow.get_artifact_uri("model")
result = mlflow.evaluate(
model=model_uri,
data=eval_data,
targets="target",
model_type="regressor",
dataset_name="cali_housing",
evaluators=["default"],
custom_metrics=[
metrics_only_fn,
file_artifacts_fn,
object_artifacts_fn,
mixed_example_fn,
],
)
print(f"metrics:\n{result.metrics}")
print(f"artifacts:\n{result.artifacts}")
# train XGBoost model
X, y = shap.datasets.adult()
num_examples = len(X)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=42)
model = xgboost.XGBClassifier().fit(X_train, y_train)
eval_data = X_test
eval_data["label"] = y_test
with mlflow.start_run() as run:
mlflow.sklearn.log_model(model, "model")
model_uri = mlflow.get_artifact_uri("model")
result = mlflow.evaluate(
model_uri,
eval_data,
targets="label",
model_type="classifier",
dataset_name="adult",
evaluators=["default"],
)
print(f"metrics:\n{result.metrics}")
print(f"artifacts:\n{result.artifacts}")
"squared_diff_plus_one":
np.sum(np.abs(eval_df["prediction"] - eval_df["target"] + 1)**2),
"sum_on_label_divided_by_two":
builtin_metrics["sum_on_label"] / 2,
}
plt.scatter(eval_df["prediction"], eval_df["target"])
plt.xlabel("Targets")
plt.ylabel("Predictions")
plt.title("Targets vs. Predictions")
plot_path = os.path.join(artifacts_dir, "example_scatter_plot.png")
plt.savefig(plot_path)
artifacts = {"example_scatter_plot_artifact": plot_path}
return metrics, artifacts
with mlflow.start_run() as run:
mlflow.sklearn.log_model(lin_reg, "model")
model_uri = mlflow.get_artifact_uri("model")
result = mlflow.evaluate(
model=model_uri,
data=eval_data,
targets="target",
model_type="regressor",
dataset_name="cali_housing",
evaluators=["default"],
custom_metrics=[example_custom_metric_fn],
)
print(f"metrics:\n{result.metrics}")
print(f"artifacts:\n{result.artifacts}")
import mlflow
from sklearn.datasets import fetch_california_housing
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
mlflow.sklearn.autolog()
california_housing_data = fetch_california_housing()
X_train, X_test, y_train, y_test = train_test_split(
california_housing_data.data, california_housing_data.target, test_size=0.33, random_state=42
)
with mlflow.start_run() as run:
model = LinearRegression().fit(X_train, y_train)
model_uri = mlflow.get_artifact_uri("model")
result = mlflow.evaluate(
model_uri,
X_test,
targets=y_test,
model_type="regressor",
dataset_name="california_housing",
evaluators="default",
feature_names=california_housing_data.feature_names,
evaluator_config={"explainability_nsamples": 1000},
)
print(f"metrics:\n{result.metrics}")
print(f"artifacts:\n{result.artifacts}")
X, y = make_classification(n_samples=10000,
n_classes=10,
n_informative=5,
random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=42)
with mlflow.start_run() as run:
model = LogisticRegression(solver="liblinear").fit(X_train, y_train)
model_uri = mlflow.get_artifact_uri("model")
result = mlflow.evaluate(
model_uri,
X_test,
targets=y_test,
model_type="classifier",
dataset_name="multiclass-classification-dataset",
evaluators="default",
evaluator_config={
"log_model_explainability": True,
"explainability_nsamples": 1000
},
)
print(f"run_id={run.info.run_id}")
print(f"metrics:\n{result.metrics}")
print(f"artifacts:\n{result.artifacts}")