Criar modelos de ML com o BigQuery ML: laboratório com desafio avaliações

Pragya S. · Revisado há about 1 year

Swaritra S. · Revisado há about 1 year

nice

Hemant S. · Revisado há about 1 year

Shivam S. · Revisado há about 1 year

Good with help

Jose S. · Revisado há about 1 year

Akanksha P. · Revisado há about 1 year

Daniel M. · Revisado há about 1 year

Paulina A. · Revisado há about 1 year

Soumya M. · Revisado há about 1 year

David Israel P. · Revisado há about 1 year

Constantin S. · Revisado há about 1 year

Christian S. · Revisado há about 1 year

Manan S. · Revisado há about 1 year

Andrea C. · Revisado há about 1 year

Adrian A. · Revisado há about 1 year

PHANI G. · Revisado há about 1 year

Rohit 0. · Revisado há about 1 year

Andres Felipe P. · Revisado há about 1 year

cheikh b. · Revisado há about 1 year

Sagar J. · Revisado há about 1 year

Rathika R. · Revisado há about 1 year

Hemraj S. · Revisado há about 1 year

Soon Meng L. · Revisado há about 1 year

I do not understand what I am doing wrong in my query for the evaluation step. SELECT roc_auc FROM ML.EVALUATE( MODEL --`ecommerce.customer_classification_model` --`data-to-insights.ecommerce.classification_model` `qwiklabs-gcp-03-dd574b725332.ecommerce.customer_classification_model` , (( SELECT * EXCEPT(fullVisitorId) FROM # features (( SELECT fullVisitorId, IFNULL(totals.bounces, 0) AS bounces, IFNULL(totals.timeOnSite, 0) AS time_on_site FROM `data-to-insights.ecommerce.web_analytics` WHERE totals.newVisits = 1 AND date BETWEEN '20170430' AND '20170630') # train on first 9 months JOIN (SELECT fullvisitorid, IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit FROM `data-to-insights.ecommerce.web_analytics` GROUP BY fullvisitorid) USING (fullVisitorId) ) )) )

Lorenzo V. · Revisado há about 1 year

Joseph H. · Revisado há about 1 year