Changeset 31263 for other-projects/hathitrust/wcsa/extracted-features-solr
- Timestamp:
- 2016-12-21T13:26:31+13:00 (7 years ago)
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
other-projects/hathitrust/wcsa/extracted-features-solr/trunk/solr-ingest/src/main/java/org/hathitrust/extractedfeatures/ProcessForPOSCount.java
r31260 r31263 98 98 */ 99 99 100 JavaPairRDD<String, Integer> pos_pairs = pos_list.mapToPair(s -> new Tuple2<String, Integer>(s,1));100 JavaPairRDD<String, Long> pos_pairs = pos_list.mapToPair(s -> new Tuple2<String, Long>(s, (long)1)); 101 101 pos_pairs.setName("single-pos-count"); 102 102 103 JavaPairRDD<String, Integer> pos_counts = pos_pairs.reduceByKey((a, b) -> a + b);103 JavaPairRDD<String, Long> pos_counts = pos_pairs.reduceByKey((a, b) -> a + b); 104 104 pos_counts.setName("pos-frequency"); 105 105 106 JavaPairRDD< Integer, String> pos_counts_swapped_pair106 JavaPairRDD<Long, String> pos_counts_swapped_pair 107 107 = pos_counts.mapToPair(item -> item.swap()); 108 108 pos_counts_swapped_pair.setName("frequency-pos-swap"); 109 109 110 JavaPairRDD< Integer, String> pos_counts_swapped_pair_sorted110 JavaPairRDD<Long, String> pos_counts_swapped_pair_sorted 111 111 = pos_counts_swapped_pair.sortByKey(false, num_partitions); 112 112 pos_counts_swapped_pair_sorted.setName("descending-sorted-frequency-pos"); 113 113 114 JavaPairRDD<String, Integer> pos_count_sorted114 JavaPairRDD<String, Long> pos_count_sorted 115 115 = pos_counts_swapped_pair_sorted.mapToPair(item -> item.swap()); 116 116 pos_count_sorted.setName("descending-pos-frequency");
Note:
See TracChangeset
for help on using the changeset viewer.