Find similar rows in a Spark dataframe, based on euclidian distance and business rules.
Budget: €8 – €30 EUR
Write code that does this :
- for each row : find 1 to 5 other rows that are most similar.
- similar rows need to have identical values for some features, and be in a certain interval for other features.
- for each row : find 1 to 5 other rows that are most similar.
- similar rows need to have identical values for some features, and be in a certain interval for other features.