Icon

08_​Learning_​Asociation_​Rule_​for_​Next_​Restaurant_​Prediction

Recommending Restaurants Using Association Rules

In this workflow we demonstrate how to use the KNIME Spark nodes for giving locality recommendations. For this we are using the Yelp reviews as provided by the Kaggle challenge (https://www.kaggle.com/yelp-dataset/yelp-dataset). We wanted to find good next localities (e.g., restaurants) for everyone who to date only gave one review.

Recommending Restaurants using Association Rules In this workflow we demonstrate how to use the KNIME Spark nodes for giving locality recommendations. For this we are using the Yelp reviews as provided by the Kaggle challenge (https://www.kaggle.com/yelp-dataset/yelp-dataset). We wanted to find goodnext localities (e.g., restaurants) for everyone who to date only gave one review.For this we learnt association rules on the frequent reviewers and applied them to the newbies. Finally, we selected the best recommendation based on the distance to the first reviewed restaurant and the voting of the recommended restaurants. You can find thedata set here: https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting . After unzipping, you need to point the File Readers to the correct files on your local system. Exchange against "Create Spark Context"and a HDFS Connection Data Blending and Preprocessing Reading data Learning the model Select best fitting recommendation, based on rating and distance learn associationrulesapply associationrulesfind minimumdistancefind max ratingfind minimumdistance ratingcalculate distancebetween orig andpredictioncleaningGet the datainto a KNIME tableNode 159users who wrote morethan one reviewusers who wroteone reviewBusinesses /AttributesNode 261 Spark AssociationRule Learner Spark AssociationRule (Apply) Spark Joiner Spark GroupBy Spark GroupBy Spark SQL Query Spark Joiner Spark Column Filter Spark to Table Postprocess results totrue restaurant names Spark SQL Query Spark SQL Query CSV to Spark Data Blending Create Local BigData Environment Read-inyelp_users.csv Read inyelp_reviews.csv Read in yelp_businesseswith Oracle DB Recommending Restaurants using Association Rules In this workflow we demonstrate how to use the KNIME Spark nodes for giving locality recommendations. For this we are using the Yelp reviews as provided by the Kaggle challenge (https://www.kaggle.com/yelp-dataset/yelp-dataset). We wanted to find goodnext localities (e.g., restaurants) for everyone who to date only gave one review.For this we learnt association rules on the frequent reviewers and applied them to the newbies. Finally, we selected the best recommendation based on the distance to the first reviewed restaurant and the voting of the recommended restaurants. You can find thedata set here: https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting . After unzipping, you need to point the File Readers to the correct files on your local system. Exchange against "Create Spark Context"and a HDFS Connection Data Blending and Preprocessing Reading data Learning the model Select best fitting recommendation, based on rating and distance learn associationrulesapply associationrulesfind minimumdistancefind max ratingfind minimumdistance ratingcalculate distancebetween orig andpredictioncleaningGet the datainto a KNIME tableNode 159users who wrote morethan one reviewusers who wroteone reviewBusinesses /AttributesNode 261Spark AssociationRule Learner Spark AssociationRule (Apply) Spark Joiner Spark GroupBy Spark GroupBy Spark SQL Query Spark Joiner Spark Column Filter Spark to Table Postprocess results totrue restaurant names Spark SQL Query Spark SQL Query CSV to Spark Data Blending Create Local BigData Environment Read-inyelp_users.csv Read inyelp_reviews.csv Read in yelp_businesseswith Oracle DB

Nodes

Extensions

Links