cloud-annotations | 🐝 A fast , easy and collaborative open source image | Data Labeling library

        datacolumn1
 row 1  knowledge; information; data
 row 2  digital;transmission; interoperability; data labeling
 row 3  library catalogs; libraries; mobile;libraries

       datacolumn1
row 1  knowledge; information; data
row 2  digital transmission; interoperability; data labeling
row 3  library catalogs; libraries; mobile libraries

import azureml.core
from azureml.core import Dataset, Datastore, Workspace

# Load in work space from saved config file
ws = Workspace.from_config()

# Define full dataset of interest and retrieve it
dataset_name = 'complete_2017'
data = Dataset.get_by_name(ws, dataset_name)

# Extract file references from dataset as relative paths
rel_filepaths = data.to_path()

# Stitch back in base directory path to get a list of absolute paths
src_folder = '/raw-data/2017'
abs_filepaths = [src_folder + path for path in rel_filepaths]

# Define regular expression pattern for extracting source section
import re
pattern = re.compile('\/(S.+)_image\d+.jpg')

# Create new list of all unique source sections
sections = sorted(set([m.group(1) for m in map(pattern.match, rel_filepaths) if m]))

# Randomly select sections
num_sections = 5
set_seed = 221020
random.seed(set_seed)   # for repeatibility
sample_sections = random.choices(sections, k = num_sections)

# Extract images related to the selected sections
matching_images = [filename for filename in abs_filepaths if any(section in filename for section in sample_sections)]

# Define datastore of interest
datastore = Datastore.get(ws, 'ml-datastore')

# Convert string paths to Azure Datapath objects and relate back to datastore
from azureml.data.datapath import DataPath
datastore_path = [DataPath(datastore, filepath) for filepath in matching_images]

# Generate new dataset using from_files() and filtered list of paths
sample = Dataset.File.from_files(datastore_path)

sample_name = 'random-section-sample'
sample_dataset = sample.register(workspace = ws, name = sample_name, description = 'Sampled sections from full dataset using set seed.')

Access denied: Failed to authenticate data access with Workspace system assigned identity. Make sure to add the identity as Reader of the data service.