lindong28 commented on code in PR #157:
URL: https://github.com/apache/flink-ml/pull/157#discussion_r980594756
##########
flink-ml-python/pyflink/ml/lib/clustering/agglomerativeclustering.py:
##########
@@ -112,15 +113,20 @@ def compute_full_tree(self):
class AgglomerativeClustering(JavaClusteringAlgoOperator,
_AgglomerativeClusteringParams):
"""
An AlgoOperator that performs a hierarchical clustering using a bottom-up
approach. Each
- observation starts in its own cluster and the clusters are merged together
one by one.
- Users can choose different strategies to merge two clusters by setting
- {@link AgglomerativeClusteringParams#LINKAGE} and different distance
measures by setting
- {@link AgglomerativeClusteringParams#DISTANCE_MEASURE}.
+ observation starts in its own cluster and the clusters are merged together
one by one. Users can
+ choose different strategies to merge two clusters by setting
+ AgglomerativeClusteringParams#LINKAGE and different distance measures by
setting
+ AgglomerativeClusteringParams#DISTANCE_MEASURE.
<p>The output contains two tables. The first one assigns one cluster Id
for each data point.
The second one contains the information of merging two clusters at each
step. The data format
of the merging information is (clusterId1, clusterId2, distance,
sizeOfMergedCluster).
+ <p>This operator supports the HasWindows parameter, which creates
mini-batches(windows) from
Review Comment:
Update the doc to be consistent with the corresponding Javadoc.
##########
flink-ml-python/pyflink/ml/lib/clustering/tests/test_agglomerativeclustering.py:
##########
@@ -58,6 +63,18 @@ def setUp(self):
{Vectors.dense(4, 1.5), Vectors.dense(4, 0)}
]
+ self.eucliean_ward_count_five_window_as_two_result = [
Review Comment:
eucliean -> euclidean
Same for other lines in this file.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@flink.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
