LTR feature rename + docs (#1496)

+ feature description list + rename features for consistency
castorini · Apr 4, 2021 · a2cfe15 · a2cfe15
1 parent f110d36
commit a2cfe15
Show file tree

Hide file tree

Showing 72 changed files with 414 additions and 436 deletions.
diff --git a/docs/ltr-features.md b/docs/ltr-features.md
@@ -0,0 +1,87 @@
+# LTR Features
+|Feature name                                    |
+|-------------------------------------------------|
+|[IBM Model1](../src/main/java/io/anserini/ltr/feature/IbmModel1.java)      
+|[Sum of BM25](../src/main/java/io/anserini/ltr/feature/BM25Stat.java)
+|Average of BM25
+|Median of BM25
+|Max of BM25 
+|Min of BM25 
+|MaxMinRatio of BM25 
+|[Sum of LMDir](../src/main/java/io/anserini/ltr/feature/LmDirStat.java)  
+|Average of LMDir 
+|Median of LMDir 
+|Max of LMDir 
+|Min of LMDir 
+|MaxMinRatio of LMDir
+| [Sum of DFR\_GL2](../src/main/java/io/anserini/ltr/feature/DfrGl2Stat.java)  
+| Average of DFR\_GL2 
+| Median of DFR\_GL2 
+| Max of DFR\_GL2 
+| Min of DFR\_GL2 
+| MaxMinRatio of DFR\_GL2 
+| [Sum of DFR\_in\_expB2](../src/main/java/io/anserini/ltr/feature/DfrInExpB2Stat.java)
+| Average of DFR\_in\_expB2 
+| Median of DFR\_in\_expB2 
+| Max of DFR\_in\_expB2 
+| Min of DFR\_in\_expB2 
+| MaxMinRatio of DFR\_in\_expB2 
+| [Sum of DPH](../src/main/java/io/anserini/ltr/feature/DphStat.java)
+| Average of DPH 
+| Median of DPH 
+| Max of DPH 
+| Min of DPH 
+| MaxMinRatio of DPH 
+| [Sum of TF](../src/main/java/io/anserini/ltr/feature/TfStat.java)  
+| Average of TF 
+| Median of TF 
+| Max of TF 
+| Min of TF 
+| MaxMinRatio of TF 
+| [Sum of TFIDF](../src/main/java/io/anserini/ltr/feature/TfIdfStat.java)  
+| Average of TFIDF 
+| Median of TFIDF 
+| Max of TFIDF 
+| Min of TFIDF 
+| MaxMinRatio of TFIDF 
+| [Sum of Normalized TF](../src/main/java/io/anserini/ltr/feature/NormalizedTfStat.java)  
+| Average of Normalized TF 
+| Median of Normalized TF 
+| Max of Normalized TF 
+| Min of Normalized TF 
+| MaxMinRatio of Normalized TF 
+| [Sum of IDF](../src/main/java/io/anserini/ltr/feature/IdfStat.java)  
+| Average of IDF 
+| Median of IDF 
+| Max of IDF 
+| Min of IDF 
+| MaxMinRatio of IDF 
+| [Sum of ICTF](../src/main/java/io/anserini/ltr/feature/IcTfStat.java)  
+| Average of ICTF 
+| Median of ICTF 
+| Max of ICTF 
+| Min of ICTF 
+| MaxMinRatio of ICTFs 
+| [UnorderedSequentialPairs with gap 3](../src/main/java/io/anserini/ltr/feature/UnorderedSequentialPairs.java) 
+| UnorderedSequentialPairs with gap 8
+| UnorderedSequentialPairs with gap 15
+| [OrderedSequentialPairs with gap 3](../src/main/java/io/anserini/ltr/feature/OrderedSequentialPairs.java)
+| OrderedSequentialPairs with gap 8
+| OrderedSequentialPairs with gap 15
+| [UnorderedQueryPairs with gap 3](../src/main/java/io/anserini/ltr/feature/UnorderedQueryPairs.java)
+| UnorderedQueryPairs with gap 8
+| UnorderedQueryPairs with gap 15
+| [OrderedQueryPairs with gap 3](../src/main/java/io/anserini/ltr/feature/OrderedQueryPairs.java)
+| OrderedQueryPairs with gap 8
+| OrderedQueryPairs with gap 15
+| [Normalized TFIDF](../src/main/java/io/anserini/ltr/feature/NormalizedTfIdf.java) 
+| [ProbabilitySum](../src/main/java/io/anserini/ltr/feature/ProbalitySum.java) 
+| [Proximity](../src/main/java/io/anserini/ltr/feature/Proximity.java) 
+| [BM25-TP score](../src/main/java/io/anserini/ltr/feature/TpScore.java)
+| [TP distance](../src/main/java/io/anserini/ltr/feature/TpDist.java)  
+| [Doc size](../src/main/java/io/anserini/ltr/feature/DocSize.java)
+| [Query Length](../src/main/java/io/anserini/ltr/feature/QueryLength.java)  
+| [Query Coverage Ratio](../src/main/java/io/anserini/ltr/feature/QueryCoverageRatio.java)  
+| [Unique Term Count in Query](../src/main/java/io/anserini/ltr/feature/UniqueTermCount.java) 
+| [Matching Term Count](../src/main/java/io/anserini/ltr/feature/MatchingTermCount.java) 
+| [SCS](../src/main/java/io/anserini/ltr/feature/SCS.java) 
diff --git a/...va/io/anserini/ltr/feature/AvgPooler.java → src/main/java/io/anserini/ltr/AvgPooler.java b/...va/io/anserini/ltr/feature/AvgPooler.java → src/main/java/io/anserini/ltr/AvgPooler.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import java.util.List;
 

diff --git a/...nserini/ltr/feature/ConfidencePooler.java → ...ava/io/anserini/ltr/ConfidencePooler.java b/...nserini/ltr/feature/ConfidencePooler.java → ...ava/io/anserini/ltr/ConfidencePooler.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import java.util.List;
 

diff --git a/...anserini/ltr/feature/DocumentContext.java → ...java/io/anserini/ltr/DocumentContext.java b/...anserini/ltr/feature/DocumentContext.java → ...java/io/anserini/ltr/DocumentContext.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import com.fasterxml.jackson.databind.JsonNode;
 import com.fasterxml.jackson.databind.ObjectMapper;

diff --git a/...ini/ltr/feature/DocumentFieldContext.java → ...io/anserini/ltr/DocumentFieldContext.java b/...ini/ltr/feature/DocumentFieldContext.java → ...io/anserini/ltr/DocumentFieldContext.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import io.anserini.index.IndexArgs;
 import io.anserini.index.IndexReaderUtils;

diff --git a/...nserini/ltr/feature/FeatureExtractor.java → ...ava/io/anserini/ltr/FeatureExtractor.java b/...nserini/ltr/feature/FeatureExtractor.java → ...ava/io/anserini/ltr/FeatureExtractor.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import java.io.FileNotFoundException;
 import java.io.IOException;

diff --git a/src/main/java/io/anserini/ltr/FeatureExtractorCli.java b/src/main/java/io/anserini/ltr/FeatureExtractorCli.java
@@ -18,7 +18,6 @@
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 import io.anserini.ltr.feature.*;
-import io.anserini.ltr.feature.base.*;
 import java.io.BufferedReader;
 import java.io.File;
 import java.io.FileInputStream;
@@ -31,7 +30,6 @@
 import org.kohsuke.args4j.CmdLineParser;
 import org.kohsuke.args4j.Option;
 
-//../indexes/lucene-index-msmarco-passage-doc-expanded-all
 public class FeatureExtractorCli {
   static class DebugArgs {
     @Option(name = "-index", metaVar = "[path]", required = true, usage = "Lucene index directory")
@@ -91,66 +89,64 @@ public static void addFeature(FeatureExtractorUtils utils, String queryField, St
      * utils.add(new Proximity(docField, queryField)); utils.add(new
      * TPscore(docField, queryField));
      */
-    utils.add(new tpDist(docField, queryField));
-    /*
-     * utils.add(new DocSize(docField)); if (queryField == "analyzed" && docField ==
-     * "contents") { utils.add(new QueryLength(queryField)); utils.add(new
-     * QueryCoverageRatio(docField, queryField)); utils.add(new
-     * UniqueTermCount(queryField)); }
-     * 
-     * utils.add(new MatchingTermCount(docField, queryField)); utils.add(new
-     * SCS(docField, queryField));
-     * 
-     * utils.add(new tfStat(new AvgPooler(), docField, queryField)); utils.add(new
-     * tfStat(new MedianPooler(), docField, queryField)); utils.add(new tfStat(new
-     * SumPooler(), docField, queryField)); utils.add(new tfStat(new MinPooler(),
-     * docField, queryField)); utils.add(new tfStat(new MaxPooler(), docField,
-     * queryField)); utils.add(new tfStat(new MaxMinRatioPooler(), docField,
-     * queryField));
-     * 
-     * utils.add(new tfIdfStat(true, new AvgPooler(), docField, queryField));
-     * utils.add(new tfIdfStat(true, new MedianPooler(), docField, queryField));
-     * utils.add(new tfIdfStat(true, new SumPooler(), docField, queryField));
-     * utils.add(new tfIdfStat(true, new MinPooler(), docField, queryField));
-     * utils.add(new tfIdfStat(true, new MaxPooler(), docField, queryField));
-     * utils.add(new tfIdfStat(true, new MaxMinRatioPooler(), docField,
-     * queryField));
-     * 
-     * utils.add(new normalizedTfStat(new AvgPooler(), docField, queryField));
-     * utils.add(new normalizedTfStat(new MedianPooler(), docField, queryField));
-     * utils.add(new normalizedTfStat(new SumPooler(), docField, queryField));
-     * utils.add(new normalizedTfStat(new MinPooler(), docField, queryField));
-     * utils.add(new normalizedTfStat(new MaxPooler(), docField, queryField));
-     * utils.add(new normalizedTfStat(new MaxMinRatioPooler(), docField,
-     * queryField));
-     * 
-     * utils.add(new idfStat(new AvgPooler(), docField, queryField)); utils.add(new
-     * idfStat(new MedianPooler(), docField, queryField)); utils.add(new idfStat(new
-     * SumPooler(), docField, queryField)); utils.add(new idfStat(new MinPooler(),
-     * docField, queryField)); utils.add(new idfStat(new MaxPooler(), docField,
-     * queryField)); utils.add(new idfStat(new MaxMinRatioPooler(), docField,
-     * queryField));
-     * 
-     * utils.add(new ictfStat(new AvgPooler(), docField, queryField)); utils.add(new
-     * ictfStat(new MedianPooler(), docField, queryField)); utils.add(new
-     * ictfStat(new SumPooler(), docField, queryField)); utils.add(new ictfStat(new
-     * MinPooler(), docField, queryField)); utils.add(new ictfStat(new MaxPooler(),
-     * docField, queryField)); utils.add(new ictfStat(new MaxMinRatioPooler(),
-     * docField, queryField));
-     * 
-     * utils.add(new UnorderedSequentialPairs(3, docField, queryField));
-     * utils.add(new UnorderedSequentialPairs(8, docField, queryField));
-     * utils.add(new UnorderedSequentialPairs(15, docField, queryField));
-     * utils.add(new OrderedSequentialPairs(3, docField, queryField)); utils.add(new
-     * OrderedSequentialPairs(8, docField, queryField)); utils.add(new
-     * OrderedSequentialPairs(15, docField, queryField)); utils.add(new
-     * UnorderedQueryPairs(3, docField, queryField)); utils.add(new
-     * UnorderedQueryPairs(8, docField, queryField)); utils.add(new
-     * UnorderedQueryPairs(15, docField, queryField)); utils.add(new
-     * OrderedQueryPairs(3, docField, queryField)); utils.add(new
-     * OrderedQueryPairs(8, docField, queryField)); utils.add(new
-     * OrderedQueryPairs(15, docField, queryField));
-     */
+    utils.add(new TpDist(docField, queryField));
+
+    utils.add(new DocSize(docField));
+    if (queryField == "analyzed" && docField == "contents"){
+       utils.add(new QueryLength(queryField));
+       utils.add(new QueryCoverageRatio(docField, queryField));
+       utils.add(new UniqueTermCount(queryField)); }
+
+    utils.add(new MatchingTermCount(docField, queryField));
+    utils.add(new SCS(docField, queryField));
+
+    utils.add(new TfStat(new AvgPooler(), docField, queryField));
+    utils.add(new TfStat(new MedianPooler(), docField, queryField));
+    utils.add(new TfStat(new SumPooler(), docField, queryField));
+    utils.add(new TfStat(new MinPooler(), docField, queryField));
+    utils.add(new TfStat(new MaxPooler(), docField, queryField));
+    utils.add(new TfStat(new MaxMinRatioPooler(), docField, queryField));
+
+    utils.add(new TfIdfStat(true, new AvgPooler(), docField, queryField));
+    utils.add(new TfIdfStat(true, new MedianPooler(), docField, queryField));
+    utils.add(new TfIdfStat(true, new SumPooler(), docField, queryField));
+    utils.add(new TfIdfStat(true, new MinPooler(), docField, queryField));
+    utils.add(new TfIdfStat(true, new MaxPooler(), docField, queryField));
+    utils.add(new TfIdfStat(true, new MaxMinRatioPooler(), docField, queryField));
+
+    utils.add(new NormalizedTfStat(new AvgPooler(), docField, queryField));
+    utils.add(new NormalizedTfStat(new MedianPooler(), docField, queryField));
+    utils.add(new NormalizedTfStat(new SumPooler(), docField, queryField));
+    utils.add(new NormalizedTfStat(new MinPooler(), docField, queryField));
+    utils.add(new NormalizedTfStat(new MaxPooler(), docField, queryField));
+    utils.add(new NormalizedTfStat(new MaxMinRatioPooler(), docField, queryField));
+
+    utils.add(new IdfStat(new AvgPooler(), docField, queryField));
+    utils.add(new IdfStat(new MedianPooler(), docField, queryField));
+    utils.add(new IdfStat(new SumPooler(), docField, queryField));
+    utils.add(new IdfStat(new MinPooler(), docField, queryField));
+    utils.add(new IdfStat(new MaxPooler(), docField, queryField));
+    utils.add(new IdfStat(new MaxMinRatioPooler(), docField, queryField));
+
+    utils.add(new IcTfStat(new AvgPooler(), docField, queryField));
+    utils.add(new IcTfStat(new MedianPooler(), docField, queryField));
+    utils.add(new IcTfStat(new SumPooler(), docField, queryField));
+    utils.add(new IcTfStat(new MinPooler(), docField, queryField));
+    utils.add(new IcTfStat(new MaxPooler(), docField, queryField));
+    utils.add(new IcTfStat(new MaxMinRatioPooler(), docField, queryField));
+
+    utils.add(new UnorderedSequentialPairs(3, docField, queryField));
+    utils.add(new UnorderedSequentialPairs(8, docField, queryField));
+    utils.add(new UnorderedSequentialPairs(15, docField, queryField));
+    utils.add(new OrderedSequentialPairs(3, docField, queryField));
+    utils.add(new OrderedSequentialPairs(8, docField, queryField));
+    utils.add(new OrderedSequentialPairs(15, docField, queryField));
+    utils.add(new UnorderedQueryPairs(3, docField, queryField));
+    utils.add(new UnorderedQueryPairs(8, docField, queryField));
+    utils.add(new UnorderedQueryPairs(15, docField, queryField));
+    utils.add(new OrderedQueryPairs(3, docField, queryField));
+    utils.add(new OrderedQueryPairs(8, docField, queryField));
+    utils.add(new OrderedQueryPairs(15, docField, queryField));
 
   }
 
@@ -168,16 +164,16 @@ public static void main(String[] args) throws IOException, ExecutionException, I
     }
 
     FeatureExtractorUtils utils = new FeatureExtractorUtils(cmdArgs.indexDir, cmdArgs.threads);
-    // addFeature(utils, "analyzed", "contents");
-    // addFeature(utils, "analyzed", "predict");
-    // addFeature(utils, "text_unlemm", "text_unlemm");
+    addFeature(utils, "analyzed", "contents");
+    addFeature(utils, "analyzed", "predict");
+    addFeature(utils, "text_unlemm", "text_unlemm");
     addFeature(utils, "text_bert_tok", "text_bert_tok");
 
-    // addFeature(utils,"text","text");
-    // addFeature(utils,"text_unlemm","text_unlemm");
-    // addFeature(utils,"text_bert_tok","text_bert_tok");
-    // System.out.println("Load IBM Models");
-    // utils.add(new
+    addFeature(utils,"text","text");
+    addFeature(utils,"text_unlemm","text_unlemm");
+    addFeature(utils,"text_bert_tok","text_bert_tok");
+    //System.out.println("Load IBM Models");
+    //utils.add(new
     // IBMModel1("../FlexNeuART/collections/msmarco_doc/derived_data/giza/title_unlemm",
     // "text_unlemm",
     // "title_unlemm", "text_unlemm"));
@@ -218,7 +214,6 @@ public static void main(String[] args) throws IOException, ExecutionException, I
           while (qids.size() > 0) {
             lastQid = qids.remove(0);
             List<debugOutput> outputArray = utils.getDebugResult(lastQid);
-            // System.out.println(String.format("Qid:%s\tLine:%d",lastQid,offset));
             for (debugOutput res : outputArray) {
               for (int i = 0; i < names.size(); i++) {
                 time[i] += res.time.get(i);
@@ -238,7 +233,6 @@ public static void main(String[] args) throws IOException, ExecutionException, I
         while (qids.size() > 0) {
           lastQid = qids.remove(0);
           List<debugOutput> outputArray = utils.getDebugResult(lastQid);
-          // System.out.println(String.format("Qid:%s\tLine:%d",lastQid,offset));
           for (debugOutput res : outputArray) {
             for (int i = 0; i < names.size(); i++) {
               time[i] += res.time.get(i);
@@ -251,24 +245,20 @@ public static void main(String[] args) throws IOException, ExecutionException, I
         throw e;
       }
     }
-    // long executionEnd = System.nanoTime();
-    // long sumtime = 0;
-    // for(int i = 0; i < names.size(); i++){
-    // sumtime += time[i];
-    // }
-    // for(int i = 0; i < names.size(); i++){
-    // System.out.println(names.get(i)+" takes
-    // "+String.format("%.2f",time[i]/1000000000.0) + "s, accounts for "+
-    // String.format("%.2f", time[i]*100.0/sumtime) + "%");
-    // }
+    long executionEnd = System.nanoTime();
+    long sumtime = 0;
+    for(int i = 0; i < names.size(); i++){
+      sumtime += time[i];
+    }
+    for(int i = 0; i < names.size(); i++){
+      System.out.println(names.get(i)+" takes "+String.format("%.2f",time[i]/1000000000.0) + "s, accounts for "+
+      String.format("%.2f", time[i]*100.0/sumtime) + "%");
+    }
     utils.close();
     reader.close();
-    //
-    // long end = System.nanoTime();
-    // long overallTime = end - start;
-    // long overhead = overallTime-(executionEnd - executionStart);
-    // System.out.println("The program takes
-    // "+String.format("%.2f",overallTime/1000000000.0) + "s, where the overhead
-    // takes " + String.format("%.2f",overhead/1000000000.0) +"s");
+    long end = System.nanoTime();
+    long overallTime = end - start;
+    long overhead = overallTime-(executionEnd - executionStart);
+    System.out.println("The program takes "+String.format("%.2f",overallTime/1000000000.0) + "s, where the overhead takes " + String.format("%.2f",overhead/1000000000.0) +"s");
   }
 }
diff --git a/src/main/java/io/anserini/ltr/FeatureExtractorUtils.java b/src/main/java/io/anserini/ltr/FeatureExtractorUtils.java
@@ -17,15 +17,9 @@
 package io.anserini.ltr;
 
 import com.fasterxml.jackson.core.JsonProcessingException;
-import com.fasterxml.jackson.core.type.TypeReference;
 import com.fasterxml.jackson.databind.JsonNode;
 import com.fasterxml.jackson.databind.ObjectMapper;
 import io.anserini.index.IndexArgs;
-import io.anserini.ltr.feature.*;
-import io.anserini.ltr.feature.base.*;
-import org.apache.logging.log4j.LogManager;
-import org.apache.logging.log4j.Logger;
-import org.apache.logging.log4j.core.tools.picocli.CommandLine;
 import org.apache.lucene.index.DirectoryReader;
 import org.apache.lucene.index.IndexReader;
 import org.apache.lucene.index.Term;

diff --git a/...serini/ltr/feature/MaxMinRatioPooler.java → ...va/io/anserini/ltr/MaxMinRatioPooler.java b/...serini/ltr/feature/MaxMinRatioPooler.java → ...va/io/anserini/ltr/MaxMinRatioPooler.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import java.util.List;
 

diff --git a/...va/io/anserini/ltr/feature/MaxPooler.java → src/main/java/io/anserini/ltr/MaxPooler.java b/...va/io/anserini/ltr/feature/MaxPooler.java → src/main/java/io/anserini/ltr/MaxPooler.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import java.util.List;
 

diff --git a/...io/anserini/ltr/feature/MedianPooler.java → ...in/java/io/anserini/ltr/MedianPooler.java b/...io/anserini/ltr/feature/MedianPooler.java → ...in/java/io/anserini/ltr/MedianPooler.java
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package io.anserini.ltr.feature;
+package io.anserini.ltr;
 
 import java.util.Collections;
 import java.util.List;