-
Notifications
You must be signed in to change notification settings - Fork 0
/
Task 6. Improve model performance with feature engineering.sql
48 lines (48 loc) · 1.52 KB
/
Task 6. Improve model performance with feature engineering.sql
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
CREATE OR REPLACE MODEL `ecommerce.classification_model_2`
OPTIONS
(model_type='logistic_reg', labels = ['will_buy_on_return_visit']) AS
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 '20160801' AND '20170430' # train 9 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
);