Merge pull request #19 from oduwsdl/configurable-time-slice

the number of clusters for time-slicing is now configurable

docs/source/conf.py

@@ -26,7 +26,7 @@
 # The short X.Y version
 version = u''
 # The full version, including alpha/beta/rc tags
-release = u'0.2020.07.13.224110'
+release = u'0.2020.07.14.023052'
 
 # -- General configuration ---------------------------------------------------
 

hypercane/actions/cluster.py

@@ -174,6 +174,11 @@ def time_slice(args):
         prog="hc cluster time-slice"
     )
 
+    parser.add_argument('-k', dest='k',
+        default=None, type=int,
+        help='The number of clusters to create.'
+    )
+
     args = process_input_args(args, parser)
     output_type = 'mementos'
 
@@ -187,15 +192,15 @@ def time_slice(args):
 
     session = get_web_session(cache_storage=args.cache_storage)
 
-
     urimdata = discover_resource_data_by_input_type(
         args.input_type, output_type, args.input_arguments, args.crawl_depth,
         session, discover_mementos_by_input_type
     )
 
     logger.info("There were {} mementos discovered in the input".format(len(urimdata)))
 
-    urimdata_with_slices = execute_time_slice(urimdata, args.cache_storage)
+    urimdata_with_slices = execute_time_slice(
+        urimdata, args.cache_storage, number_of_slices=args.k)
 
     # we use urimdata and urimdata_with_slices because they should match, if they don't we will detect an error
     save_resource_data(args.output_filename, urimdata_with_slices, 'mementos', list(urimdata.keys()))

hypercane/cluster/time_slice.py

@@ -3,7 +3,7 @@
 
 module_logger = logging.getLogger('hypercane.cluster.time_slice')
 
-def execute_time_slice(urimdata, cache_storage):
+def execute_time_slice(urimdata, cache_storage, number_of_slices=None):
 
     import concurrent.futures
     import math
@@ -30,8 +30,9 @@ def execute_time_slice(urimdata, cache_storage):
                 module_logger.exception('URI-M [{}] generated an exception: [{}], skipping...'.format(urim, exc))
                 hypercane.errors.errorstore.add(urim, traceback.format_exc())
 
-    # calculate the number of slices 28 + math.log(len(mementos))
-    number_of_slices = math.ceil(28 + math.log(len(mementos)))
+    if number_of_slices is None:
+        # calculate the number of slices 28 + math.log(len(mementos))
+        number_of_slices = math.ceil(28 + math.log(len(mementos)))
 
     module_logger.info("The collection will be divided into {} slices".format(number_of_slices))
 

hypercane/version.py

@@ -1,3 +1,3 @@
 __appname__ = "hypercane"
-__appversion__ = '0.2020.07.13.224110'
+__appversion__ = '0.2020.07.14.023052'
 __useragent__ = "{}/{}".format(__appname__, __appversion__)