Mailing-List: contact dev-help@madlib.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@madlib.apache.org
From: iyerr3 <git@git.apache.org>
To: dev@madlib.apache.org
Reply-To: dev@madlib.apache.org
References: <git-pr-204-madlib@git.apache.org>
In-Reply-To: <git-pr-204-madlib@git.apache.org>
Subject: [GitHub] madlib pull request #204: Added additional distance metrics for k-NN: Jira-1...
Content-Type: text/plain
Message-Id: <20171120223049.D147DDFBC6@git1-us-west.apache.org>
Date: Mon, 20 Nov 2017 22:30:49 +0000 (UTC)
archived-at: Mon, 20 Nov 2017 22:30:52 -0000

Github user iyerr3 commented on a diff in the pull request:

    https://github.com/apache/madlib/pull/204#discussion_r152129858
  
    --- Diff: src/ports/postgres/modules/knn/test/knn.sql_in ---
    @@ -73,23 +73,23 @@ copy knn_test_data (id, data) from stdin delimiter '|';
     \.
     
     drop table if exists madlib_knn_result_classification;
    -select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False);
    +select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'madlib.squared_dist_norm2');
     select assert(array_agg(prediction order by id)='{1,1,0,1,0,0}', 'Wrong output in classification with k=3') from madlib_knn_result_classification;
     
     drop table if exists madlib_knn_result_classification;
    -select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,True);
    +select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,True,'madlib.squared_dist_norm2');
     select assert(array_agg(x)= '{1,2,3}','Wrong output in classification with k=3') from (select unnest(k_nearest_neighbours) as x from madlib_knn_result_classification where id = 1 order by x asc) y;
     
     drop table if exists madlib_knn_result_regression;
    -select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False);
    +select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'madlib.squared_dist_norm2');
     select assert(array_agg(prediction order by id)='{1,1,0.5,1,0.25,0.25}', 'Wrong output in regression') from madlib_knn_result_regression;
     
     drop table if exists madlib_knn_result_regression;
    -select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',3,True);
    +select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',3,True,'madlib.squared_dist_norm2');
     select assert(array_agg(x)= '{1,2,3}' , 'Wrong output in regression with k=3') from (select unnest(k_nearest_neighbours) as x from madlib_knn_result_regression where id = 1 order by x asc) y;
     
     drop table if exists madlib_knn_result_classification;
    -select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',False);
    +select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'madlib.squared_dist_norm2');
    --- End diff --
    
    How about we add other dist functions (including `NULL` input) in above functions? 


---