Create ML Models with BigQuery ML: Challenge Lab avis

The lab doesn't work properly

Zuzanna M. · Examiné il y a plus d'un an

Kevin C. · Examiné il y a plus d'un an

I don't understand the task descriptions??? sometimes it says linear and sometimes logistic, I don't know what is the purpose of the task to be done

Zuzanna M. · Examiné il y a plus d'un an

Christian A. · Examiné il y a plus d'un an

Patrick L. · Examiné il y a plus d'un an

Halimathu S. · Examiné il y a plus d'un an

Bhagyashree P. · Examiné il y a plus d'un an

Aman N. · Examiné il y a plus d'un an

Camille H. · Examiné il y a plus d'un an

Zhenru C. · Examiné il y a plus d'un an

Zhenru C. · Examiné il y a plus d'un an

Жандос О. · Examiné il y a plus d'un an

Octavia R. · Examiné il y a plus d'un an

Task 3 doesn't work

Pierpaolo S. · Examiné il y a plus d'un an

Md I. · Examiné il y a plus d'un an

Ozana I. · Examiné il y a plus d'un an

I finished Task 3 by creating and evaluating the new model improved_customer_classification_model with the required additional features, but it would never mark it as complete. Here's the query I used to create the model: CREATE OR REPLACE MODEL `ecommerce.improved_customer_classification_model` OPTIONS ( model_type='logistic_reg', labels = ['will_buy_on_return_visit'] ) AS #standardSQL SELECT * EXCEPT(fullVisitorId) FROM # features (SELECT fullVisitorId, IFNULL(totals.bounces, 0) AS bounces, IFNULL(totals.timeOnSite, 0) AS time_on_site, IFNULL(totals.pageviews, 0) AS pageviews, trafficSource.source, trafficSource.medium, channelGrouping, # mobile or desktop device.deviceCategory, # geographic IFNULL(geoNetwork.country, "") AS country FROM `data-to-insights.ecommerce.web_analytics` WHERE totals.newVisits = 1 AND date BETWEEN '20160801' AND '20170430') # 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) ; And here's how I evaluated it: SELECT roc_auc, CASE WHEN roc_auc > .9 THEN 'good' WHEN roc_auc > .8 THEN 'fair' WHEN roc_auc > .7 THEN 'decent' WHEN roc_auc > .6 THEN 'not great' ELSE 'poor' END AS model_quality FROM ML.EVALUATE(MODEL ecommerce.improved_customer_classification_model, ( #standardSQL SELECT * EXCEPT(fullVisitorId) FROM # features (SELECT fullVisitorId, IFNULL(totals.bounces, 0) AS bounces, IFNULL(totals.timeOnSite, 0) AS time_on_site, IFNULL(totals.pageviews, 0) AS pageviews, trafficSource.source, trafficSource.medium, channelGrouping, # mobile or desktop device.deviceCategory, # geographic IFNULL(geoNetwork.country, "") AS country FROM `data-to-insights.ecommerce.web_analytics` WHERE totals.newVisits = 1 AND date BETWEEN '20160801' AND '20170430') # 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) ));

Adam W. · Examiné il y a plus d'un an

Kevin C. · Examiné il y a plus d'un an

Juan Carlos B. · Examiné il y a plus d'un an

Manish S. · Examiné il y a plus d'un an

Jesús Arnulfo C. · Examiné il y a plus d'un an

Ilyas N. · Examiné il y a plus d'un an

William B. · Examiné il y a plus d'un an

Shannon M. · Examiné il y a plus d'un an

Shannon M. · Examiné il y a plus d'un an