Le 11 juillet 2024 à 12:18:55 :
Le 11 juillet 2024 à 12:17:58 :
une petite tof du chaton peut-être??
Je peux pas la mais après si tu veux #standardSQL
SELECT
roc_auc,
CASE
WHEN roc_auc > .9 THEN 'good'
WHEN roc_auc > .8 THEN 'fair'
WHEN roc_auc > .7 THEN 'not great'
ELSE 'poor' END AS model_quality
FROM
ML.EVALUATE(MODEL ecommerce.classification_model_3, (
WITH all_visitor_stats AS (
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
)
- add in new features
SELECT * EXCEPT(unique_session_id) FROM (
SELECT
CONCAT(fullvisitorid, CAST(visitId AS STRING)) AS unique_session_id,
# labels
will_buy_on_return_visit,
MAX(CAST(h.eCommerceAction.action_type AS INT64)) AS latest_ecommerce_progress,
# behavior on the site
IFNULL(totals.bounces, 0) AS bounces,
IFNULL(totals.timeOnSite, 0) AS time_on_site,
totals.pageviews,
# where the visitor came from
trafficSource.source,
trafficSource.medium,
channelGrouping,
# mobile or desktop
device.deviceCategory,
# geographic
IFNULL(geoNetwork.country, "") AS country
FROM `data-to-insights.ecommerce.web_analytics`,
UNNEST(hits) AS h
JOIN all_visitor_stats USING(fullvisitorid)
WHERE 1=1
# only predict for new visits
AND totals.newVisits = 1
AND date BETWEEN '20170501' AND '20170630' # eval 2 months
GROUP BY
unique_session_id,
will_buy_on_return_visit,
bounces,
time_on_site,
totals.pageviews,
trafficSource.source,
trafficSource.medium,
channelGrouping,
device.deviceCategory,
country
)
));