文件Experience Platform查詢服務指南

機器學習的工程師功能

Last update: Tue Jul 16 2024 00:00:00 GMT+0000 (Coordinated Universal Time)
  • 主題：

建立對象：

  • undefined
  • undefined

本檔案示範如何將Adobe Experience Platform中的資料轉換為​ 功能 ​或變數，以供機器學習模型使用。 此程式稱為​ 功能工程。 使用Data Distiller大規模計算ML功能，並將這些功能與您的機器學習環境共用。 這涉及下列專案：

  1. 建立查詢範本，以定義您要為您的模型計算的目標標籤和特徵
  2. 執行查詢並將結果儲存在訓練資料集中

定義您的訓練資料 define-training-data

下列範例說明如何查詢從Experience Events資料集衍生培訓資料，讓模型預測使用者訂閱電子報的傾向。 訂閱事件由事件型別web.formFilledOut表示，資料集中的其他行為事件可用來衍生設定檔層級功能以預測訂閱。

查詢正面和負面標籤 query-positive-and-negative-labels

訓練（監督）機器學習模型的完整資料集包括目標變數或標籤，代表要預測的結果，以及一組功能或說明變數，用於描述用來訓練模型的範例設定檔。

在此案例中，標籤是名為subscriptionOccurred的變數，如果使用者設定檔具有型別為web.formFilledOut的事件，則等於1，否則為0。 下列查詢會從事件資料集中傳回一組50,000位使用者，包含所有具有正數標籤(subscriptionOccurred = 1)的使用者，加上隨機選取具有負數標籤的使用者，以完成50,000位使用者範例大小。 這可確保訓練資料包含正面和負面範例，以供模型學習。

from aepp import queryservice

dd_conn = queryservice.QueryService().connection()
dd_cursor = queryservice.InteractiveQuery2(dd_conn)

query_labels = f"""
SELECT *
FROM (
    SELECT
        eventType,
        _{tenant_id}.user_id as userId,
        SUM(CASE WHEN eventType='web.formFilledOut' THEN 1 ELSE 0 END)
            OVER (PARTITION BY _{tenant_id}.user_id)
            AS "subscriptionOccurred",
        row_number() OVER (PARTITION BY _{tenant_id}.user_id ORDER BY randn()) AS random_row_number_for_user
    FROM {table_name}
)
WHERE (subscriptionOccurred = 1 AND eventType = 'web.formFilledOut') OR (subscriptionOccurred = 0 AND random_row_number_for_user = 1)
"""

df_labels = dd_cursor.query(query_labels, output="dataframe")
print(f"Number of classes: {len(df_labels)}")
df_labels.head()

範例輸出

類別數目： 50000

eventType
userId
subscriptionOcked
random_row_number_for_user
0
directMarketing.emailClicked
01027994177972439148069092698714414382
0
1
1
directMarketing.emailOpened
01054714817856066632264746967668888198
0
1
2
web.formFilledOut
01117296890525140996735553609305695042
1
15
3
directMarketing.emailClicked
01149554820363915324573708359099551093
0
1
4
directMarketing.emailClicked
01172121447143590196349410086995740317
0
1

為機器學習定義功能的彙總事件 define-features

透過適當的查詢，您可以將資料集中的事件收集到有意義的、數值的功能中，以便用於訓練傾向模型。 範例事件顯示如下：

  • 使用者為了行銷目的而傳送和接收的 ​電子郵件數目。
  • 這些電子郵件中​ 已開啟 ​的部分。
  • 使用者​ 已選取 ​連結的電子郵件部分。
  • 已檢視的產品數目。
  • 與​ 互動的 ​主張數目。
  • 被解除的​ 主張數目。
  • 已選取的​ 個連結數目。
  • 收到兩封連續電子郵件的間隔分鐘數。
  • 連續開啟兩封電子郵件的間隔分鐘數。
  • 使用者實際選取連結的兩封連續電子郵件之間的分鐘數。
  • 兩次連續產品檢視之間的分鐘數。
  • 與兩個建議互動的分鐘數。
  • 兩個被駁回的建議之間的分鐘數。
  • 選取的兩個連結之間的分鐘數。

下列查詢會彙總這些事件：

選取以檢視範例查詢
code language-python 
query_features = f"""
SELECT
    _{tenant_id}.user_id as userId,
    SUM(CASE WHEN eventType='directMarketing.emailSent' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "emailsReceived",
    SUM(CASE WHEN eventType='directMarketing.emailOpened' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "emailsOpened",
    SUM(CASE WHEN eventType='directMarketing.emailClicked' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "emailsClicked",
    SUM(CASE WHEN eventType='commerce.productViews' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "productsViewed",
    SUM(CASE WHEN eventType='decisioning.propositionInteract' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "propositionInteracts",
    SUM(CASE WHEN eventType='decisioning.propositionDismiss' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "propositionDismissed",
    SUM(CASE WHEN eventType='web.webinteraction.linkClicks' THEN 1 ELSE 0 END)
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "webLinkClicks" ,
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailSent', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_emailSent",
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailOpened', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_emailOpened",
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailClicked', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_emailClick",
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'commerce.productViews', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_productView",
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'decisioning.propositionInteract', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_propositionInteract",
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'propositionDismiss', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_propositionDismiss",
    TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'web.webinteraction.linkClicks', 'minutes')
       OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
       AS "minutes_since_linkClick"
FROM {table_name}
"""

df_features = dd_cursor.query(query_features, output="dataframe")
df_features.head()

範例輸出

userId
電子郵件已接收
電子郵件已開啟
電子郵件已點按
已檢視的產品
propositionInteracts
propositionMissed
webLinkClicks
minutes_since_emailSent
minutes_since_emailOpen
minutes_since_emailClick
minutes_since_productView
minutes_since_propositionInteract
minutes_since_propositionDiscisse
minutes_since_linkClick
0
01102546977582484968046916668339306826
1
0
0
0
0
0
0
0.0
NaN
NaN
NaN
NaN
None
NaN
1
01102546977582484968046916668339306826
2
0
0
0
0
0
0
0.0
NaN
NaN
NaN
NaN
None
NaN
2
01102546977582484968046916668339306826
3
0
0
0
0
0
0
0.0
NaN
NaN
NaN
NaN
None
NaN
3
01102546977582484968046916668339306826
3
1
0
0
0
0
0
540.0
0.0
NaN
NaN
NaN
None
NaN
4
01102546977582484968046916668339306826
3
2
0
0
0
0
0
588.0
0.0
NaN
NaN
NaN
None
NaN

結合標籤和功能查詢 combine-queries

最後，標籤查詢和功能查詢可以合併到單一查詢中，以傳回標籤和功能的訓練資料集：

選取以檢視範例查詢
code language-python 
query_training_set = f"""
SELECT *
FROM (
    SELECT _{tenant_id}.user_id as userId,
       eventType,
       timestamp,
       SUM(CASE WHEN eventType='web.formFilledOut' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id)
           AS "subscriptionOccurred",
       SUM(CASE WHEN eventType='directMarketing.emailSent' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsReceived",
       SUM(CASE WHEN eventType='directMarketing.emailOpened' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsOpened",
       SUM(CASE WHEN eventType='directMarketing.emailClicked' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsClicked",
       SUM(CASE WHEN eventType='commerce.productViews' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "productsViewed",
       SUM(CASE WHEN eventType='decisioning.propositionInteract' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "propositionInteracts",
       SUM(CASE WHEN eventType='decisioning.propositionDismiss' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "propositionDismissed",
       SUM(CASE WHEN eventType='web.webinteraction.linkClicks' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "webLinkClicks" ,
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailSent', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailSent",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailOpened', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailOpened",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailClicked', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailClick",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'commerce.productViews', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_productView",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'decisioning.propositionInteract', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_propositionInteract",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'propositionDismiss', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_propositionDismiss",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'web.webinteraction.linkClicks', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_linkClick",
        row_number() OVER (PARTITION BY _{tenant_id}.user_id ORDER BY randn()) AS random_row_number_for_user
    FROM {table_name} LIMIT 1000
)
WHERE (subscriptionOccurred = 1 AND eventType = 'web.formFilledOut') OR (subscriptionOccurred = 0 AND random_row_number_for_user = 1)
ORDER BY timestamp
"""

df_training_set = dd_cursor.query(query_training_set, output="dataframe")
df_training_set.head()

範例輸出

userId
eventType
時間戳記
subscriptionOcked
電子郵件已接收
電子郵件已開啟
電子郵件已點按
已檢視的產品
propositionInteracts
propositionMissed
webLinkClicks
minutes_since_emailSent
minutes_since_emailOpen
minutes_since_emailClick
minutes_since_productView
minutes_since_propositionInteract
minutes_since_propositionDiscisse
minutes_since_linkClick
random_row_number_for_user
0
02554909162592418347780983091131567290
directMarketing.emailSent
2023-06-17 13:44:59.086
0
2
0
0
0
0
0
0
0.0
NaN
NaN
NaN
NaN
None
NaN
1
1
01130334080340815140184601481559659945
directMarketing.emailOpened
2023-06-19 06:01:55.366
0
1
3
0
1
0
0
0
1921.0
0.0
NaN
1703.0
NaN
None
NaN
1
2
01708961660028351393477273586554010192
web.formFilledOut
2023-06-19 18:36:49.083
1
1
2
2
0
0
0
0
2365.0
26.0
1.0
NaN
NaN
None
NaN
7
3
01809182902320674899156240602124740853
directMarketing.emailSent
2023-06-21 19:17:12.535
0
1
0
0
0
0
0
0
0.0
NaN
NaN
NaN
NaN
None
NaN
1
4
03441761949943678951106193028739001197
directMarketing.emailSent
2023-06-21 21:58:29.482
0
1
0
0
0
0
0
0
0.0
NaN
NaN
NaN
NaN
None
NaN
1

建立查詢範本以逐步計算培訓資料

通常使用更新的訓練資料定期重新訓練模型，以隨著時間保持模型的準確性。 為了有效更新您的訓練資料集，最佳實務是透過訓練集查詢建立範本，以增量方式計算新的訓練資料。 這可讓您僅從上次更新訓練資料以來新增至原始體驗事件資料集的資料計算標籤和功能，並將新標籤和功能插入現有訓練資料集。

若要這麼做，需要對訓練集查詢進行一些修改：

  • 新增邏輯以建立不存在的新訓練資料集，否則請將新標籤和功能插入現有訓練資料集中。 這需要訓練集查詢的一系列兩個版本：

    • 首先，使用CREATE TABLE IF NOT EXISTS {table_name} AS陳述式
    • 接著，針對訓練資料集已存在的情況使用INSERT INTO {table_name}陳述式

  • 新增SNAPSHOT BETWEEN $from_snapshot_id AND $to_snapshot_id陳述式，將查詢限制在指定間隔內新增的事件資料。 快照ID上的$首碼表示它們是在執行查詢範本時要傳入的變數。

套用這些變更會導致下列查詢：

選取以檢視範例查詢
code language-python 
ctas_table_name = "propensity_training_set"

query_training_set_template = f"""
$$ BEGIN

SET @my_table_exists = SELECT table_exists('{ctas_table_name}');

CREATE TABLE IF NOT EXISTS {ctas_table_name} AS
SELECT *
FROM (
    SELECT _{tenant_id}.user_id as userId,
       eventType,
       timestamp,
       SUM(CASE WHEN eventType='web.formFilledOut' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id)
           AS "subscriptionOccurred",
       SUM(CASE WHEN eventType='directMarketing.emailSent' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsReceived",
       SUM(CASE WHEN eventType='directMarketing.emailOpened' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsOpened",
       SUM(CASE WHEN eventType='directMarketing.emailClicked' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsClicked",
       SUM(CASE WHEN eventType='commerce.productViews' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "productsViewed",
       SUM(CASE WHEN eventType='decisioning.propositionInteract' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "propositionInteracts",
       SUM(CASE WHEN eventType='decisioning.propositionDismiss' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "propositionDismissed",
       SUM(CASE WHEN eventType='web.webinteraction.linkClicks' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "webLinkClicks" ,
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailSent', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailSent",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailOpened', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailOpened",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailClicked', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailClick",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'commerce.productViews', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_productView",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'decisioning.propositionInteract', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_propositionInteract",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'propositionDismiss', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_propositionDismiss",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'web.webinteraction.linkClicks', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_linkClick",
        row_number() OVER (PARTITION BY _{tenant_id}.user_id ORDER BY randn()) AS random_row_number_for_user
    FROM {table_name}
    SNAPSHOT BETWEEN $from_snapshot_id AND $to_snapshot_id
)
WHERE (subscriptionOccurred = 1 AND eventType = 'web.formFilledOut') OR (subscriptionOccurred = 0 AND random_row_number_for_user = 1)
ORDER BY timestamp;

INSERT INTO {ctas_table_name}
SELECT *
FROM (
    SELECT _{tenant_id}.user_id as userId,
       eventType,
       timestamp,
       SUM(CASE WHEN eventType='web.formFilledOut' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id)
           AS "subscriptionOccurred",
       SUM(CASE WHEN eventType='directMarketing.emailSent' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsReceived",
       SUM(CASE WHEN eventType='directMarketing.emailOpened' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsOpened",
       SUM(CASE WHEN eventType='directMarketing.emailClicked' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "emailsClicked",
       SUM(CASE WHEN eventType='commerce.productViews' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "productsViewed",
       SUM(CASE WHEN eventType='decisioning.propositionInteract' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "propositionInteracts",
       SUM(CASE WHEN eventType='decisioning.propositionDismiss' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "propositionDismissed",
       SUM(CASE WHEN eventType='web.webinteraction.linkClicks' THEN 1 ELSE 0 END)
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "webLinkClicks" ,
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailSent', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailSent",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailOpened', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailOpened",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'directMarketing.emailClicked', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_emailClick",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'commerce.productViews', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_productView",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'decisioning.propositionInteract', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_propositionInteract",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'propositionDismiss', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_propositionDismiss",
       TIME_BETWEEN_PREVIOUS_MATCH(timestamp, eventType = 'web.webinteraction.linkClicks', 'minutes')
           OVER (PARTITION BY _{tenant_id}.user_id ORDER BY timestamp ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)
           AS "minutes_since_linkClick",
        row_number() OVER (PARTITION BY _{tenant_id}.user_id ORDER BY randn()) AS random_row_number_for_user
    FROM {table_name}
    SNAPSHOT BETWEEN $from_snapshot_id AND $to_snapshot_id
)
WHERE
    @my_table_exists = 't' AND
    ((subscriptionOccurred = 1 AND eventType = 'web.formFilledOut') OR (subscriptionOccurred = 0 AND random_row_number_for_user = 1))
ORDER BY timestamp;

EXCEPTION
  WHEN OTHER THEN
    SELECT 'ERROR';

END $$;
"""

最後，下列程式碼會將查詢範本儲存在Data Distiller中：

template_res = dd.createQueryTemplate({
  "sql": query_training_set_template,
  "queryParameters": {},
  "name": "Template for propensity training data"
})
template_id = template_res["id"]

print(f"Template for propensity training data created as ID {template_id}")

範例輸出

Template for propensity training data created as ID f3d1ec6b-40c2-4d13-93b6-734c1b3c7235

在儲存範本後，您可以透過參考範本ID來隨時執行查詢，並指定應包含在查詢中的快照ID範圍。 下列查詢會擷取原始Experience Events資料集的快照：

query_snapshots = f"""
SELECT snapshot_id
FROM (
    SELECT history_meta('{table_name}')
)
WHERE is_current = true OR snapshot_generation = 0
ORDER BY snapshot_generation ASC
"""

df_snapshots = dd_cursor.query(query_snapshots, output="dataframe")

下列程式碼會示範如何使用第一個和最後一個快照來查詢整個資料集，進而執行查詢範本：

snapshot_start_id = str(df_snapshots["snapshot_id"].iloc[0])
snapshot_end_id = str(df_snapshots["snapshot_id"].iloc[1])

query_final_res = qs.postQueries(
    name=f"[CMLE][Week2] Query to generate training data created by {username}",
    templateId=template_id,
    queryParameters={
        "from_snapshot_id": snapshot_start_id,
        "to_snapshot_id": snapshot_end_id,
    },
    dbname=f"{cat_conn.sandbox}:all"
)
query_final_id = query_final_res["id"]
print(f"Query started successfully and got assigned ID {query_final_id} - it will take some time to execute")

範例輸出

Query started successfully and got assigned ID c6ea5009-1315-4839-b072-089ae01e74fd - it will take some time to execute

您可以定義以下函式以定期檢查查詢的狀態：

def wait_for_query_completion(query_id):
    while True:
        query_info = qs.getQuery(query_id)
        query_state = query_info["state"]
        if query_state in ["SUCCESS", "FAILED"]:
            break
        print("Query is still in progress, sleeping…")
        time.sleep(60)

    duration_secs = query_info["elapsedTime"] / 1000
    if query_state == "SUCCESS":
        print(f"Query completed successfully in {duration_secs} seconds")
    else:
        print(f"Query failed with the following errors:", file=sys.stderr)
        for error in query_info["errors"]:
            print(f"Error code {error['code']}: {error['message']}", file=sys.stderr)

wait_for_query_completion(query_final_id)

範例輸出

Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query is still in progress, sleeping…
Query completed successfully in 473.8 seconds

後續步驟：

閱讀本檔案後，您已瞭解如何將Adobe Experience Platform中的資料轉換為機器學習模型可以使用的功能或變數。 在機器學習環境中建立從Experience Platform到摘要自訂模型的功能管道的下一個步驟是匯出功能資料集。

recommendation-more-help
ccf2b369-4031-483f-af63-a93b5ae5e3fb