hsclient HydroShare Python Client Resource Aggregation Operation Examples

!pip install hsclient

from hsclient import HydroShare

hs = HydroShare()
hs.sign_in()

# Create the new, empty resource
new_resource = hs.create()

# Get the HydroShare identifier for the new resource
res_identifier = new_resource.resource_id
print(f'The HydroShare Identifier for your new resource is: {res_identifier}')

# Construct a hyperlink for the new resource
print(f'Your new resource is available at: {new_resource.metadata.url}')

# Import the aggregation types
from hsmodels.schemas.enums import AggregationType

# Upload a single content file to the resource. This is a generic text file.
new_resource.file_upload('Example_Files/Data_File1.txt')

# Specify the file you want to add the aggregation to
file = new_resource.file(path='Data_File1.txt')

# Create a single file aggregation on the file and refresh the resource
agg = new_resource.file_aggregate(file, AggregationType.SingleFileAggregation)

# Print the title for the aggregation that was added to the resource
print(f'The following aggregation was added to the resource: {agg.metadata.title}')
print(f'Aggregation type: {agg.metadata.type}')

# Set the title and subject keywords for the aggregation
agg.metadata.title = 'A Single File Aggregation'
agg.metadata.subjects = ['Aggregation', 'Single File', 'Text']

# Print the title and keywords for the aggregation
print(f'Aggregation Title: {agg.metadata.title}')
print(f'Aggregation Keywords: {", ".join(agg.metadata.subjects)}')

# Save the aggregation to write the metadata to HydroShare
agg.save()

# Add an extended metadata element to the aggregation as a key-value pair
agg.metadata.additional_metadata['New Element Key'] = 'Text value of new element.'

# Remove an individual key-value pair from the aggregation using its key
del agg.metadata.additional_metadata['New Element Key']

# Or, you can clear out all extended metadata elements that might exist
agg.metadata.additional_metadata.clear()

# Add multiple key-value pairs to the aggregation at once using a Python dictionary
agg.metadata.additional_metadata = {
    'Observed Variable': 'Water use',
    'Site Location': 'Valley View Tower Dormitory on Utah State University\'s Campus in Logan, UT'
}

# Print the extended metadata elements
print('The extended metadata elements for the aggregation include:')
for key, value in agg.metadata.additional_metadata.items():
    print(key + ':', value)

# Save the aggregation to write the metadata to HydroShare
agg.save()

# Import the required metadata classes for coverage objects
from hsmodels.schemas.fields import BoxCoverage, PointCoverage, PeriodCoverage
from datetime import datetime

# Set the spatial coverage of the aggregation to a BoxCoverage object
agg.metadata.spatial_coverage = BoxCoverage(name='Logan, Utah',
                                            northlimit=41.7910,
                                            eastlimit=-111.7664,
                                            southlimit=41.6732,
                                            westlimit=-111.9079,
                                            projection='WGS 84 EPSG:4326',
                                            type='box',
                                            units='Decimal degrees')

# You can remove the spatial coverage element by setting it to None
agg.metadata.spatial_coverage = None

# If you want to set the spatial coverage to a PointCoverage instead
agg.metadata.spatial_coverage = PointCoverage(name='Logan, Utah',
                                              north=41.7371,
                                              east=-111.8351,
                                              projection='WGS 84 EPSG:4326',
                                              type='point',
                                              units='Decimal degrees')

# Create a beginning and ending date for a time period
beginDate = datetime.strptime('2020-12-01T00:00:00Z', '%Y-%m-%dT%H:%M:%S%fZ')
endDate = datetime.strptime('2020-12-31T00:00:00Z', '%Y-%m-%dT%H:%M:%S%fZ')

# Set the temporal coverage of the aggregation to a PeriodCoverage object
agg.metadata.period_coverage = PeriodCoverage(start=beginDate, end=endDate)

# Print the temporal coverage information
print('Temporal Coverage:')
print(agg.metadata.period_coverage)

# Print the spatial coverage information
print('\nSpatial Coverage:')
print(agg.metadata.spatial_coverage)

# Save the aggregation to write the metadata to HydroShare
agg.save()

# Create a list of the files that make up the shapefile to be uploaded
file_list = ['Example_Files/watersheds.cpg', 'Example_Files/watersheds.dbf',
             'Example_Files/watersheds.prj', 'Example_Files/watersheds.sbn',
             'Example_Files/watersheds.sbx', 'Example_Files/watersheds.shp',
             'Example_Files/watersheds.shx', 'Example_Files/watersheds.shp.xml']

# Upload the files to the resource all at the same time
new_resource.file_upload(*file_list)

print('Files uploaded!')

# Get the aggregation that was just created

# You can get the aggregation by searching for a file that is inside of it
agg = new_resource.aggregation(file__name='watersheds.shp')

# Or, you can get the aggregation by searching for its title, which is initially
# set to the name of the shapefile
agg = new_resource.aggregation(title='watersheds')

# Print the title for the aggregation that was added to the resource
print(f'The following aggregation was added to the resource: {agg.metadata.title}')
print(f'Aggregation type: {agg.metadata.type}')

# Upload the files making up the raster dataset to the resource
file_list = ['Example_Files/logan1.tif', 'Example_Files/logan2.tif', 'Example_Files/logan.vrt']
new_resource.file_upload(*file_list)

# Get the aggregation that was just created - initially the title will be "logan1"
# based on the name of the first .tif file that appears in the .vrt file
agg = new_resource.aggregation(title='logan1')

# Print the title for the aggregation that was added to the resource
print(f'The following aggregation was added to the resource: {agg.metadata.title}')
print(f'Aggregation type: {agg.metadata.type}')

# Upload the NetCDF file to the resource
new_resource.file_upload('Example_Files/SWE_time.nc')

# Get the aggregation by searching for the NetCDF file that is inside of it
agg = new_resource.aggregation(file__name='SWE_time.nc')

# Print the title for the aggregation that was added to the resource
print(f'The following aggregation was added to the resource: {agg.metadata.title}')
print(f'Aggregation type: {agg.metadata.type}')

# Upload the SQLite file to the resource
new_resource.file_upload('Example_Files/ODM2.sqlite')

# Get the aggregation by searching for the SQLite file that is inside of it
agg = new_resource.aggregation(file__name='ODM2.sqlite')

# Print the title for the aggregation that was added to the resource
print(f'The following aggregation was added to the resource: {agg.metadata.title}')
print(f'Aggregation type: {agg.metadata.type}')

# Create a new folder for the file set aggregation
new_resource.folder_create('Fileset_Aggregation')

# Add some files to the folder
new_resource.file_upload('Example_Files/Data_File1.txt', 'Example_Files/Data_File2.txt',
                         destination_path='Fileset_Aggregation')

# set the folder to fileset aggregation
new_resource.file_aggregate(path='Fileset_Aggregation', agg_type=AggregationType.FileSetAggregation)
fs_agg = new_resource.aggregation(type='FileSet')
print(f"Aggregation Type: {fs_agg.metadata.type}")

# Upload a CSV file to the resource
new_resource.file_upload('Example_Files/Data_File1.csv')

# Get the aggregation by searching for the CSV file
agg = new_resource.aggregation(file__name='Data_File1.csv')

# Print the title for the aggregation that was added to the resource
print(f"The following aggregation was added to the resource: {agg.metadata.title}")
print(f"Aggregation type: {agg.metadata.type}")

# Get the time series aggregation that was created above
agg = new_resource.aggregation(type='TimeSeries')

# Print the metadata associated with the aggregation
print(f'Aggregation Title: {agg.metadata.title}')
print(f'Aggregation Type: {agg.metadata.type}')
print(f'Aggregation Keywords: {", ".join(agg.metadata.subjects)}')
print(f'Aggregation Temporal Coverage: {agg.metadata.period_coverage}')
print(f'Aggregation Spatial Coverage: {agg.metadata.spatial_coverage}')

# Print the list of files in the aggregation
file_list = agg.files()
print('List of files contained within the aggregation:')
print(*file_list, sep='\n')

# Get the CSV aggregation you created above
agg = new_resource.aggregation(type="CSV")

# we can edit any extracted column properties (like 'title', 'description', 'datatype')
table = agg.metadata.tableSchema.table

# here is an example of editing the 'title' property of the 1st column
table.columns[0].title = "Date of Observation"

# here is an example of editing the 'description' of the 7th column
table.columns[6].description = "Total Volume over time"

# save the updated metadata
agg.save()

# Get the list of all aggregations in the resource
aggregations = new_resource.aggregations()

# Get a list of all aggregations of a particular type
aggregations = new_resource.aggregations(type="TimeSeries")

# Get a list of aggregations with extended metadata searching by key
aggregations = new_resource.aggregations(additional_metadata__key="Observed Variable")

# Get a list of aggregations with extended metadata searching by value
aggregations = new_resource.aggregations(additional_metadata__value="Water Use")

# Get a list of aggregations with a subject keyword searching by value
aggregations = new_resource.aggregations(subjects__contains="Temperature")

# Get a list of aggregations searching by title (or any metadata attribute)
aggregations = new_resource.aggregations(title="watersheds")

# Get a list of aggregations searching by a nested metadata attribute (__)
aggregations = new_resource.aggregations(period_coverage__name="period_coverage name")

# Get a list of aggregations by combining field searching, filtered with "AND"
aggregations = new_resource.aggregations(period_coverage__name="period_coverage name", title="watersheds")

# Search for an aggregation of type time series
aggregation = new_resource.aggregation(type="TimeSeries")

# Search for an aggregation with a specific title
aggregation = new_resource.aggregation(title="watersheds")

# Search for an aggregation that contains a particular file name
aggregation = new_resource.aggregation(file__name="ODM2.sqlite")

# Get the geographic feature aggregation that was created above
agg = new_resource.aggregation(title="watersheds")

# Download the aggregation
new_resource.aggregation_download(agg)

!rm 'watersheds.shp.zip'

# Get the geographic raster aggregation that was created above
agg = new_resource.aggregation(title="logan1")

# Remove the aggregation and delete its metadata, but leave the file(s)
new_resource.aggregation_remove(agg)

# Get the multidimensional NetCDF aggregation that was created above
agg = new_resource.aggregation(type="NetCDF")

# Delete the aggregation and metadata along with files within aggregation
new_resource.aggregation_delete(agg)