update away from numpy patterns removed in numpy 2.0, more deduplicat…

…ion and cleanup

pyproject.toml

@@ -10,6 +10,8 @@ select = [
     "F",
     # isort
     "I",
+    # numpy
+    "NPY",
     # pyupgrade
     "UP",
     # flake8-bugbear

source/cloud/azure/azureml.md

@@ -65,8 +65,6 @@ echo "kernel install completed"
 
 Select `local file`, then `Browse`, and upload that script.
 
-Optional to enable SSH access to your compute (if needed).
-
 ![Screenshot of the provision setup script screen](../../images/azureml-provision-setup-script.png)
 
 Refer to [Azure ML documentation](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-customize-compute-instance) for more details on how to create the setup script but it should resemble:
@@ -100,8 +98,7 @@ from azure.identity import DefaultAzureCredential
 # If it isn't found, open a shell and look in the
 # directory indicated by 'echo ${JUPYTER_SERVER_ROOT}'.
 ml_client = MLClient.from_config(
-    credential=DefaultAzureCredential(),
-    path="./config.json"
+    credential=DefaultAzureCredential(), path="./config.json"
 )
 ```
 
@@ -216,7 +213,7 @@ command_job = command(
         "max_depth": 10,
         "max_features": 1.0,
     },
-    compute="rapids-cluster",
+    compute=gpu_compute.name,
 )
 
 # submit training job
@@ -239,7 +236,7 @@ command_job_for_sweep = command_job(
 
 # apply hyperparameter sweep_job
 sweep_job = command_job_for_sweep.sweep(
-    compute="rapids-cluster",
+    compute=gpu_compute.name,
     sampling_algorithm="random",
     primary_metric="Accuracy",
     goal="Maximize",

source/examples/rapids-azureml-hpo/train_rapids.py

@@ -20,7 +20,6 @@
 import cudf
 import cuml
 import mlflow
-import numpy as np
 from rapids_csp_azure import PerfTimer, RapidsCloudML
 
 
@@ -62,13 +61,13 @@ def main():
     cv_folds = args.cv_folds
 
     n_estimators = args.n_estimators
-    mlflow.log_param("n_estimators", np.int(args.n_estimators))
+    mlflow.log_param("n_estimators", int(args.n_estimators))
     max_depth = args.max_depth
-    mlflow.log_param("max_depth", np.int(args.max_depth))
+    mlflow.log_param("max_depth", int(args.max_depth))
     n_bins = args.n_bins
-    mlflow.log_param("n_bins", np.int(args.n_bins))
+    mlflow.log_param("n_bins", int(args.n_bins))
     max_features = args.max_features
-    mlflow.log_param("max_features", np.str(args.max_features))
+    mlflow.log_param("max_features", str(args.max_features))
 
     print("\n---->>>> cuDF version <<<<----\n", cudf.__version__)
     print("\n---->>>> cuML version <<<<----\n", cuml.__version__)
@@ -156,9 +155,9 @@ def main():
             global_best_test_accuracy = test_accuracy
 
     mlflow.log_metric(
-        "Total training inference time", np.float(training_time + infer_time)
+        "Total training inference time", float(training_time + infer_time)
     )
-    mlflow.log_metric("Accuracy", np.float(global_best_test_accuracy))
+    mlflow.log_metric("Accuracy", float(global_best_test_accuracy))
     print("\n Accuracy             :", global_best_test_accuracy)
     print("\n accuracy per fold    :", accuracy_per_fold)
     print("\n train-time per fold  :", train_time_per_fold)
@@ -171,5 +170,5 @@ def main():
     with PerfTimer() as total_script_time:
         main()
     print(f"Total runtime: {total_script_time.duration:.2f}")
-    mlflow.log_metric("Total runtime", np.float(total_script_time.duration))
+    mlflow.log_metric("Total runtime", float(total_script_time.duration))
     print("\n Exiting script")