선형 회귀 Codelab

1. 소개

이 Codelab에서는 선형 회귀를 사용하여 클릭당비용을 예측하는 모델을 만드는 방법을 알아봅니다.

사전 준비 사항

이 Codelab을 완료하려면 모델을 구축하기에 충분한 고품질 캠페인 데이터가 필요합니다.

2. 임시 테이블 만들기

다음 쿼리를 실행합니다.

CREATE TABLE
 linear_regression_example_data
AS(
 WITH all_data AS (
   SELECT
     imp.user_id as user_id,
     ROW_NUMBER() OVER(PARTITION BY imp.user_id) AS rowIdx,
     imp.browser AS browser_name,
     gender_name AS gender_name,
     age_group_name AS age_group_name,
     DATETIME(TIMESTAMP_MICROS(
       imp.query_id.time_usec), "America/Los_Angeles") as impression_time,
     clk.advertiser_click_cost_usd AS label
   FROM adh.google_ads_impressions imp
     INNER JOIN adh.google_ads_clicks clk USING (impression_id)
     LEFT JOIN adh.gender ON demographics.gender = gender_id
     LEFT JOIN adh.age_group ON demographics.age_group = age_group_id
 )
 # Need just one user ID or regression won't work
 SELECT
   label,
   browser_name,
   gender_name,
   age_group_name,
   # Although BQML could divide impression_time into several useful variables on
   # its own, it may attempt to divide it into too many features. As a best
   # practice extract the variables that you think will be most helpful.
   # The output of impression_time is a number, but we care about it as a
   # category, so we cast it to a string.
   CAST(EXTRACT(DAYOFWEEK FROM impression_time) AS STRING) AS day_of_week,
   CAST(EXTRACT(HOUR FROM impression_time) AS STRING) AS hour,
 FROM
   all_data
 WHERE
   rowIdx = 1 # This ensures that there's only 1 row per user.
   AND
   label IS NOT NULL
   AND
   gender_name IS NOT NULL
   AND
   age_group_name IS NOT NULL
);

3. 모델 만들기 및 학습

테이블 만들기 단계를 모델 만들기 단계와 분리하는 것이 좋습니다.

이전 단계에서 만든 임시 테이블에 아래의 쿼리를 실행합니다. 시작일과 종료일은 임시 테이블의 데이터를 기반으로 추론되므로 걱정하지 마세요.

CREATE OR REPLACE
MODEL `example_linear`
OPTIONS(
   model_type = 'adh_linear_regression'
)
AS (
   SELECT *
   FROM
       tmp.linear_regression_example_data
);

SELECT * FROM ML.EVALUATE(MODEL `example_linear`)

행	mean_absolute_error	mean_squared_error	mean_squared_log_error	median_absolute_error	r2_score	explained_variance
1	0.11102380666874107	0.019938972461569476	0.019503393448234131	0.091792024503562136	-9.8205955364568478	-9.7975398794423025