Init and have all packages required

azuremlpythonsdk-v2/diabetes_hyperdrive/diabetes_training.py

@@ -0,0 +1,123 @@
+# Import libraries
+import argparse
+import os
+
+import mlflow
+import mlflow.sklearn
+import numpy as np
+import pandas as pd
+from sklearn.ensemble import GradientBoostingClassifier
+from sklearn.metrics import roc_auc_score
+from sklearn.model_selection import train_test_split
+
+
+def main():
+    """Main function of the script."""
+
+    # Input and output arguments
+
+    # Get script arguments
+    parser = XXXX()
+
+    # Input dataset
+    parser.add_argument(
+        "XXXX",
+        type=str,
+        help="path to input data",
+    )
+
+    # Model name
+    parser.add_argument("XXXX", type=str, help="model name")
+
+    # Hyperparameters
+    parser.add_argument(
+        "XXXX",
+        type=float,
+        dest="learning_rate",
+        default=0.1,
+        help="learning rate",
+    )
+    parser.add_argument(
+        "XXXX",
+        type=int,
+        dest="n_estimators",
+        default=100,
+        help="number of estimators",
+    )
+
+    # Add arguments to args collection
+    args = parser.parse_args()
+    print(" ".join(f"{k}={v}" for k, v in vars(args).items()))
+
+    # Start Logging
+    mlflow.XXXX()
+
+    # enable autologging
+    mlflow.XXXX()
+
+    # load the diabetes data (passed as an input dataset)
+    print("input data:", args.data)
+
+    diabetes = pd.read_csv(args.data)
+
+    # Separate features and labels
+    X, y = (
+        diabetes[
+            [
+                "Pregnancies",
+                "PlasmaGlucose",
+                "DiastolicBloodPressure",
+                "TricepsThickness",
+                "SerumInsulin",
+                "BMI",
+                "DiabetesPedigree",
+                "Age",
+            ]
+        ].values,
+        diabetes["Diabetic"].values,
+    )
+
+    # Split data into training set and test set
+    X_train, X_test, y_train, y_test = XXXX(
+        X, y, test_size=0.30, random_state=0
+    )
+
+    # Train a Gradient Boosting classification model
+    # with the specified hyperparameters
+    print("Training a classification model")
+    model = XXXX(
+        learning_rate=XXXX, n_estimators=XXXX
+    ).fit(X_train, y_train)
+
+    # calculate accuracy
+    y_hat = model.XXXX(X_test)
+    accuracy = np.average(y_hat == y_test)
+    print("Accuracy:", accuracy)
+    mlflow.log_metric("Accuracy", float(accuracy))
+
+    # calculate AUC
+    y_scores = model.XXXX(X_test)
+    auc = roc_auc_score(y_test, y_scores[:, 1])
+    print("AUC: " + str(auc))
+    mlflow.log_metric("AUC", float(auc))
+
+    # Registering the model to the workspace
+    print("Registering the model via MLFlow")
+    mlflow.XXXX(
+        sk_model=model,
+        registered_model_name=args.registered_model_name,
+        artifact_path=args.registered_model_name,
+    )
+
+    # Saving the model to a file
+    mlflow.sklearn.save_model(
+        sk_model=model,
+        path=os.path.join(args.registered_model_name, "trained_model"),
+    )
+
+    # Stop Logging
+    mlflow.XXXX()
+
+
+if __name__ == "__main__":
+    main()