线性回归 Codelab

1. 简介

在此 Codelab 中，您将学习如何使用线性回归来创建可预测每次点击费用的模型。

前提条件

要完成本 Codelab，您需要足够的高质量广告系列数据来建立模型。

2. 创建临时表

请运行以下查询

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. 创建和训练模型

最佳实践是将表创建步骤与模型创建步骤分开。

对您在上一步中创建的临时表运行以下查询。您不必费心提供开始日期和结束日期，因为系统会根据临时表中的数据推断出这些日期。

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`)

行	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