Model monitor baseline processing job crashes on CSV file #1652

import pickle, gzip, urllib.request, json
import numpy as np

# Load the dataset
urllib.request.urlretrieve("http://deeplearning.net/data/mnist/mnist.pkl.gz", "mnist.pkl.gz")
with gzip.open('mnist.pkl.gz', 'rb') as f:
    train_set, valid_set, test_set = pickle.load(f, encoding='latin1')

import numpy as np
import boto3
from sagemaker import get_execution_role

role = get_execution_role()

region = boto3.Session().region_name

bucket='myBucket' # Replace with your s3 bucket name
prefix = 'sagemaker/xgboost-mnist' # Used as part of the path in the bucket where you store data

def convert_data():
    data_partitions = [('train', train_set), ('validation', valid_set), ('test', test_set)]
    for data_partition_name, data_partition in data_partitions:
        print('{}: {} {}'.format(data_partition_name, data_partition[0].shape, data_partition[1].shape))
        labels = [t.tolist() for t in data_partition[1]]
        features = [t.tolist() for t in data_partition[0]]
        
        if data_partition_name != 'test':
            examples = np.insert(features, 0, labels, axis=1)
        else:
            examples = features
        #print(examples[50000,:])
        
        
        np.savetxt('data.csv', examples, delimiter=',', format='%f')
        
        
        
        key = "{}/{}/examples.csv".format(prefix,data_partition_name)
        url = 's3://{}/{}'.format(bucket, key)
        boto3.Session().resource('s3').Bucket(bucket).Object(key).upload_file('data.csv')
        print('Done writing to {}'.format(url))
        
convert_data()

from sagemaker.model_monitor import DefaultModelMonitor
from sagemaker.model_monitor.dataset_format import DatasetFormat

my_default_monitor = DefaultModelMonitor(
    role=role,
    instance_count=1,
    instance_type='ml.m5.xlarge',
    volume_size_in_gb=20,
    max_runtime_in_seconds=3600,
)

my_default_monitor.suggest_baseline(
    baseline_dataset=baseline_data_uri+'examples.csv',            ## filename must have csv extension
    dataset_format=DatasetFormat.csv(header=False),            ## mnist has no header
    output_s3_uri=baseline_results_uri,
    wait=True
)