#standardSQL
SELECT
*
FROM
ml.PREDICT(MODEL `ecommerce.classification_model_2`,
(
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
)
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
# only predict for new visits
totals.newVisits = 1
AND date BETWEEN '20170701' AND '20170801' # test 1 month
GROUP BY
unique_session_id,
will_buy_on_return_visit,
bounces,
time_on_site,
totals.pageviews,
trafficSource.source,
trafficSource.medium,
channelGrouping,
device.deviceCategory,
country
)
)
ORDER BY
predicted_will_buy_on_return_visit DESC;
#standardSQL
SELECT
*
FROM
ml.PREDICT(MODEL `taxi.taxifare_model`,
(
WITH params AS (
SELECT
1 AS TRAIN,
2 AS EVAL
),
daynames AS
(SELECT ['Sun', 'Mon', 'Tues', 'Wed', 'Thurs', 'Fri', 'Sat'] AS daysofweek),
taxitrips AS (
SELECT
(tolls_amount + fare_amount) AS total_fare,
daysofweek[ORDINAL(EXTRACT(DAYOFWEEK FROM pickup_datetime))] AS dayofweek,
EXTRACT(HOUR FROM pickup_datetime) AS hourofday,
pickup_longitude AS pickuplon,
pickup_latitude AS pickuplat,
dropoff_longitude AS dropofflon,
dropoff_latitude AS dropofflat,
passenger_count AS passengers
FROM
`nyc-tlc.yellow.trips`, daynames, params
WHERE
trip_distance > 0 AND fare_amount > 0
AND MOD(ABS(FARM_FINGERPRINT(CAST(pickup_datetime AS STRING))),1000) = params.EVAL
)
SELECT *
FROM taxitrips
));