Mapping main synced 24 feb #1061
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sonalgoyal
reviewed
Feb 25, 2025
| */ | ||
| PINCODE("PINCODE"), | ||
| private static final long serialVersionUID = 1L; | ||
| public String name; |
sonalgoyal
reviewed
Feb 25, 2025
| throws IOException, JsonProcessingException { | ||
| try { | ||
| jsonGen.writeObject(getStringFromMatchType(matchType)); | ||
| jsonGen.writeObject(getStringFromMatchType((List<IMatchType>) matchType)); |
sonalgoyal
requested changes
Feb 25, 2025
| C joinCondition = unmarkedRecords.and(joinCondition1, joinCondition2); | ||
|
|
||
| //we are selecting columns to bring back to original shape | ||
| return unmarkedRecords.join(zFieldsFromUpdatedLabelledRecords, joinCondition, "inner").select(unmarkedRecordColumns); |
There was a problem hiding this comment.
move to labeller or separate class. inner to be a constant
| @@ -21,20 +22,20 @@ public void testGetFieldDefinitionWithStopwords(){ | |||
| FieldDefinition def1 = new FieldDefinition(); | |||
| def1.setFieldName("field1"); | |||
| def1.setDataType("string"); | |||
| def1.setMatchTypeInternal(MatchType.FUZZY); | |||
| def1.setMatchTypeInternal((MatchType) MatchTypes.FUZZY); | |||
There was a problem hiding this comment.
fielddef setMatchTypeinternal to take IMatchType...
| try{ | ||
| for(IPreprocType preprocType: getPreprocOrder().getOrder()) { | ||
| if (ProcessingType.SINGLE.equals(preprocType.getProcessingType())) { | ||
| for(FieldDefinition def:((IArguments) getArgs()).getFieldDefinition()){ |
| if (ProcessingType.SINGLE.equals(preprocType.getProcessingType())) { | ||
| for(FieldDefinition def:((IArguments) getArgs()).getFieldDefinition()){ | ||
| //creating new instance of the class | ||
| ISingleFieldPreprocessor<S,D,R,C,T> ip = (ISingleFieldPreprocessor<S, D, R, C, T>) getPreprocMap().get(preprocType).getDeclaredConstructor().newInstance(); |
| } | ||
| } else { | ||
| //creating new instance of the class | ||
| IMultiFieldPreprocessor<S,D,R,C,T> ip = (IMultiFieldPreprocessor<S, D, R, C, T>) getPreprocMap().get(preprocType).getDeclaredConstructor().newInstance(); |
There was a problem hiding this comment.
move construction to separate method and call setContext, init, setFieldDef and preprocess commonly
|
|
||
| @Override | ||
| protected ZFrame<Dataset<Row>, Row, Column> applyCaseNormalizer(ZFrame<Dataset<Row>, Row, Column> incomingDataFrame, List<String> relevantFields) { | ||
| String[] incomingDFColumns = incomingDataFrame.columns(); |
There was a problem hiding this comment.
rethink this - zframe abstraction, function calling etc. try to not have platform specific code unless you have to
| this.udfName = registerUDF(); | ||
|
|
||
| public SparkStopWordsRemover(){ | ||
| super(); |
There was a problem hiding this comment.
see if this constructor is needed?
| @@ -49,7 +49,7 @@ public ZFrame<Dataset<Row>, Row, Column> getStopWordsDataset(ZFrame<Dataset<Row> | |||
|
|
|||
| @Override | |||
| public String getStopWordColName() { | |||
| return "z_word"; | |||
| return "z_stopword"; | |||
| @Override | ||
| protected List<String> getStopWordFileNames() { | ||
| String fileName1 = Objects.requireNonNull( | ||
| StopWordRemoverUtility.class.getResource("../../../../preProcess/stopwords/stopWords.csv")).getFile(); |
There was a problem hiding this comment.
see the logic of common resources
| @@ -0,0 +1,152 @@ | |||
| package zingg.spark.core.util; | |||
Fixes in PR1061
…4Feb # Conflicts: # common/core/src/test/java/zingg/common/core/executor/validate/BlockerValidator.java # spark/core/src/test/java/zingg/spark/core/recommender/TestSparkStopWordsRecommender.java
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.