FindSynonyms | Finds several Synonyms using the Unofficial Google API

Hello don't know much about Spark. Also can't post comments yet so an answer will have to do. Looking at the documention here.

.findSynonyms("string",num) "Find "num" number of words closest in similarity to the given word, not including the word itself."

So i can't help wondering is looking for the string "1" not maybe the problem. Off the top of my head i struggle to find 5 synonyms for "1", perhaps "one",maybe "uniary" or potentially "individual". From what I read Spark is a machine learning library so have you tried dumbing down the question? Maybe ask for a single synonym or give a simpler string to search for like "happy". This is just my two cents though, and mostly just curious about what is actually happening.

you can use the method w2v_model.transform(words=words)

(complete options are: w2v_model.transform(words =, aggregate_method =)

where words is an H2O Frame made of a single column containing source words (Note that you can specify to include a subset of this frame) and aggregate_method specifies how to aggregate sequences of words.

if you don't specify an aggregation method, then no aggregation is performed, and each input word is mapped to a single word-vector. If the method is AVERAGE, then the input is treated as sequences of words delimited by NA.

For example:

Seems like MLlib's currently only implements skip-gram.

Here is the open ticket/pull request for the skip-gram model: https://issues.apache.org/jira/browse/SPARK-20372

How exactly did you get vector.txt? If you read JavaDoc for Word2VecModel.save you may see that:

This saves: - human-readable (JSON) model metadata to path/metadata/ - Parquet formatted data to path/data/
The model may be loaded using Loader.load.

So what you need is model in Parquet format which is standard for Spark ML models.

Unfortunately load from Google's native format has not been implemented yet (see SPARK-9484).