# Looks for the XGBoost image URI and builds an XGBoost container. Specify the repo_version depending on preference.
  container = get_image_uri(boto3.Session().region_name,
                            'xgboost', 
                            repo_version='1.0-1')

  hyperparameters = {
        "max_depth":"5",                ## Maximum depth of a tree. Higher means more complex models but risk of overfitting.
        "eta":"0.2",                    ## Learning rate. Lower values make the learning process slower but more precise.
        "gamma":"4",                    ## Minimum loss reduction required to make a further partition on a leaf node. Controls the model’s complexity.
        "min_child_weight":"6",         ## Minimum sum of instance weight (hessian) needed in a child. Higher values prevent overfitting.
        "subsample":"0.7",              ## Fraction of training data used. Reduces overfitting by sampling part of the data. 
        "objective":"binary:logistic",  ## Specifies the learning task and corresponding objective. binary:logistic is for binary classification.
        "num_round":50                  ## Number of boosting rounds, essentially how many times the model is trained.
        }
  # A SageMaker estimator that calls the xgboost-container
  estimator = sagemaker.estimator.Estimator(image_uri=container,                  # Points to the XGBoost container we previously set up. This tells SageMaker which algorithm container to use.
                                          hyperparameters=hyperparameters,      # Passes the defined hyperparameters to the estimator. These are the settings that guide the training process.
                                          role=sagemaker.get_execution_role(),  # Specifies the IAM role that SageMaker assumes during the training job. This role allows access to AWS resources like S3.
                                          train_instance_count=1,               # Sets the number of training instances. Here, it’s using a single instance.
                                          train_instance_type='ml.m5.large',    # Specifies the type of instance to use for training. ml.m5.2xlarge is a general-purpose instance with a balance of compute, memory, and network resources.
                                          train_volume_size=5, # 5GB            # Sets the size of the storage volume attached to the training instance, in GB. Here, it’s 5 GB.
                                          output_path=output_path,              # Defines where the model artifacts and output of the training job will be saved in S3.
                                          train_use_spot_instances=True,        # Utilizes spot instances for training, which can be significantly cheaper than on-demand instances. Spot instances are spare EC2 capacity offered at a lower price.
                                          train_max_run=300,                    # Specifies the maximum runtime for the training job in seconds. Here, it's 300 seconds (5 minutes).
                                          train_max_wait=600)                   # Sets the maximum time to wait for the job to complete, including the time waiting for spot instances, in seconds. Here, it's 600 seconds (10 minutes).

  estimator.fit({'train': s3_input_train,'validation': s3_input_test})

  xgb_predictor = estimator.deploy(initial_instance_count=1,instance_type='ml.m5.large')

  from sagemaker.serializers import CSVSerializer
  import numpy as np
  from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix

  # Drop the label column from the test data
  test_data_features = test_data_final.drop(columns=['Label']).values

  # Set the content type and serializer
  xgb_predictor.serializer = CSVSerializer()
  xgb_predictor.content_type = 'text/csv'

  # Perform prediction
  predictions = xgb_predictor.predict(test_data_features).decode('utf-8')

  y_test = test_data_final['Label'].values

  # Convert the predictions into a array
  predictions_array = np.fromstring(predictions, sep=',')
  print(predictions_array.shape)

  # Converting predictions them to binary (0 or 1)
  threshold = 0.5
  binary_predictions = (predictions_array >= threshold).astype(int)

  # Accuracy
  accuracy = accuracy_score(y_test, binary_predictions)

  # Precision
  precision = precision_score(y_test, binary_predictions)

  # Recall
  recall = recall_score(y_test, binary_predictions)

  # F1 Score
  f1 = f1_score(y_test, binary_predictions)

  # Confusion Matrix
  cm = confusion_matrix(y_test, binary_predictions)

  # False Positive Rate (FPR) using the confusion matrix
  tn, fp, fn, tp = cm.ravel()
  false_positive_rate = fp / (fp + tn)

  # Print the metrics
  print(f"Accuracy: {accuracy:.8f}")
  print(f"Precision: {precision:.8f}")
  print(f"Recall: {recall:.8f}")
  print(f"F1 Score: {f1:.8f}")
  print(f"False Positive Rate: {false_positive_rate:.8f}")

  # terraform.tfvars
  access_key = "<YOUR_ACCESS_KEY>"
  secret_key = "<YOUR_SECRET_KEY>"
  aws_account_id = "<YOUR_AWS_ACCOUNT_ID>"

  output = subprocess.check_output('terraform output -json', shell=True, cwd = r'<PATH_TO_THE_CLONED_FILE>' #C:\Users\Saahen\Desktop\ClassiSage

  # Try to upload the local CSV file to the S3 bucket
  try:
    print(f"try block executing")
    s3.upload_file(
        Filename=local_file_path, 
        Bucket=bucket_name,       
        Key=file_key               # S3 file key (filename in the bucket)
    )
    print(f"Successfully uploaded {file_key} to {bucket_name}")

    # Delete the local file after uploading to S3
    os.remove(local_file_path)
    print(f"Local file {local_file_path} deleted after upload.")

  except Exception as e:
    print(f"Failed to upload file: {e}")
    os.remove(local_file_path)

  aws s3 cp s3://<Bucket-Name>/pretrained_sm.ipynb /home/ec2-user/SageMaker/

  # S3 bucket, region, session
bucket_name = 'data-bucket-axhq3rp8'
my_region = boto3.session.Session().region_name
sess = boto3.session.Session()
print("Region is " + my_region + " and bucket is " + bucket_name)

# Print the metrics
print(f"Accuracy: {accuracy:.8f}")
print(f"Precision: {precision:.8f}")
print(f"Recall: {recall:.8f}")
print(f"F1 Score: {f1:.8f}")
print(f"False Positive Rate: {false_positive_rate:.8f}")

# Set an output path where the trained model will be saved
prefix = 'pretrained-algo'
output_path ='s3://{}/{}/output'.format(bucket_name, prefix)
print(output_path)

estimator.fit({'train': s3_input_train,'validation': s3_input_test})

xgb_predictor = estimator.deploy(initial_instance_count=1,instance_type='ml.m5.large')

  sagemaker.Session().delete_endpoint(xgb_predictor.endpoint)

  bucket_to_delete = boto3.resource('s3').Bucket(bucket_name)
  bucket_to_delete.objects.all().delete()