Updated regression log, fixed unit tests (#1562)

+ Updated regression docs to record overhaul of regressions for MS MARCO {passage, doc} and DL {19, 20}. + Turned back on assert in e2e unit test that was previously commented out accidentally.
castorini · Jun 15, 2021 · 5e8743f · 5e8743f
1 parent bc00a5c
commit 5e8743f
Show file tree

Hide file tree

Showing 5 changed files with 19 additions and 8 deletions.
diff --git a/docs/regressions-log.md b/docs/regressions-log.md
@@ -3,6 +3,16 @@
 The following change log details commits to regression tests that alter effectiveness and the addition of new regression tests.
 This documentation is useful for figuring why results may have changed over time.
 
+### June 14, 2021
+
++ commit [`b58c85`](https://github.com/castorini/anserini/commit/b58c8559b4fc473e857b9ce5ca73523d8d017b41) (06/14/2021)
+
+Overhauled regressions for MS MARCO {passage, doc} and DL {19, 20}:
++ MS MARCO passage + {doc2query, docTTTTTquery}
++ MS MARCO doc {per-doc, per-passage} x {doc2query, docTTTTTquery}
++ {DL19, DL20} passage + {doc2query, docTTTTTquery}
++ {DL19, DL20} doc {per-doc, per passage} x {doc2query, docTTTTTquery}
+
 ### April 13, 2021
 
 + commit [`868afe`](https://github.com/castorini/anserini/commit/868afe9ec07fa477ce817d7a43dd5723cb4c8a86) (04/13/2021)

diff --git a/docs/regressions.md b/docs/regressions.md
@@ -69,7 +69,7 @@ nohup python src/main/python/run_regression.py --collection dl19-doc-docTTTTTque
 nohup python src/main/python/run_regression.py --collection dl19-doc-docTTTTTquery-per-passage >& logs/log.dl19-doc-docTTTTTquery-per-passage &
 
 nohup python src/main/python/run_regression.py --collection dl20-passage >& logs/log.dl20-passage &
-nohup python src/main/python/run_regression.py --collection dl20-passage-docTTTTTquery >& logs/dl20-passage-docTTTTTquery &
+nohup python src/main/python/run_regression.py --collection dl20-passage-docTTTTTquery >& logs/log.dl20-passage-docTTTTTquery &
 nohup python src/main/python/run_regression.py --collection dl20-doc >& logs/log.dl20-doc &
 nohup python src/main/python/run_regression.py --collection dl20-doc-per-passage >& logs/log.dl20-doc-per-passage &
 nohup python src/main/python/run_regression.py --collection dl20-doc-docTTTTTquery-per-doc >& logs/log.dl20-doc-docTTTTTquery-per-doc &
@@ -128,7 +128,7 @@ nohup python src/main/python/run_regression.py --index --collection dl19-doc-doc
 nohup python src/main/python/run_regression.py --index --collection dl19-doc-docTTTTTquery-per-passage >& logs/log.dl19-doc-docTTTTTquery-per-passage &
 
 nohup python src/main/python/run_regression.py --index --collection dl20-passage >& logs/log.dl20-passage &
-nohup python src/main/python/run_regression.py --index --collection dl20-passage-docTTTTTquery >& logs/dl20-passage-docTTTTTquery &
+nohup python src/main/python/run_regression.py --index --collection dl20-passage-docTTTTTquery >& logs/log.dl20-passage-docTTTTTquery &
 nohup python src/main/python/run_regression.py --index --collection dl20-doc >& logs/log.dl20-doc &
 nohup python src/main/python/run_regression.py --index --collection dl20-doc-per-passage >& logs/log.dl20-doc-per-passage &
 nohup python src/main/python/run_regression.py --index --collection dl20-doc-docTTTTTquery-per-doc >& logs/log.dl20-doc-docTTTTTquery-per-doc &

diff --git a/src/main/java/io/anserini/collection/JsonCollection.java b/src/main/java/io/anserini/collection/JsonCollection.java
@@ -73,6 +73,7 @@ public JsonCollection(Path path){
     this.allowedFileSuffix = new HashSet<>(Arrays.asList(".json", ".jsonl"));
   }
 
+  @SuppressWarnings("unchecked")
   @Override
   public FileSegment<JsonCollection.Document> createFileSegment(Path p) throws IOException {
     return new Segment(p);
@@ -99,6 +100,7 @@ public Segment(Path path) throws IOException {
       }
     }
 
+    @SuppressWarnings("unchecked")
     @Override
     public void readNext() throws NoSuchElementException {
       if (node == null) {

diff --git a/src/test/java/io/anserini/integration/EndToEndTest.java b/src/test/java/io/anserini/integration/EndToEndTest.java
@@ -312,8 +312,7 @@ protected void checkRankingResults(String key, String output) throws IOException
     int cnt = 0;
     String s;
     while ((s = br.readLine()) != null) {
-      //assertEquals(ref[cnt], s);
-      System.out.println(s);
+      assertEquals(ref[cnt], s);
       cnt++;
     }
 

diff --git a/src/test/java/io/anserini/integration/JsonVectorEndToEndTest.java b/src/test/java/io/anserini/integration/JsonVectorEndToEndTest.java
@@ -68,10 +68,10 @@ protected void setSearchGroundTruth() {
     queryTokens.get("3").add("f4");
 
     referenceRunOutput.put("impact", new String[]{
-        "1 Q0 doc2 1 0.613600 Anserini",
-        "2 Q0 doc1 1 0.393100 Anserini",
-        "3 Q0 doc1 1 0.153100 Anserini",
-        "3 Q0 doc2 2 0.135500 Anserini"});
+        "1 Q0 doc2 1 8.000000 Anserini",
+        "2 Q0 doc1 1 1.000000 Anserini",
+        "3 Q0 doc1 1 4.000000 Anserini",
+        "3 Q0 doc2 2 3.000000 Anserini"});
   }
 
 }