Ecommerce 2025 chapter

sql/2025/ecommerce/core_web_vitals_by_platform-yoy.sql

@@ -0,0 +1,78 @@
+#standardSQL
+# CrUX Core Web Vitals performance of Ecommerce vendors by device (fid was upated to inp, and is non optinal now)
+CREATE TEMP FUNCTION IS_GOOD(good FLOAT64, needs_improvement FLOAT64, poor FLOAT64) RETURNS BOOL AS (
+  good / (good + needs_improvement + poor) >= 0.75
+);
+
+CREATE TEMP FUNCTION IS_NON_ZERO(good FLOAT64, needs_improvement FLOAT64, poor FLOAT64) RETURNS BOOL AS (
+  good + needs_improvement + poor > 0
+);
+
+
+SELECT
+  date,
+  client,
+  ecomm,
+  COUNT(DISTINCT origin) AS origins,
+  # Origins with good LCP divided by origins with any LCP.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(fast_lcp, avg_lcp, slow_lcp), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(fast_lcp, avg_lcp, slow_lcp), origin, NULL))
+  ) AS pct_good_lcp,
+
+  # Origins with good INP divided by origins with any inp.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(fast_inp, avg_inp, slow_inp), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(fast_inp, avg_inp, slow_inp), origin, NULL))
+  ) AS pct_good_inp,
+
+  # Origins with good CLS divided by origins with any CLS.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(small_cls, medium_cls, large_cls), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(small_cls, medium_cls, large_cls), origin, NULL))
+  ) AS pct_good_cls,
+
+  # Origins with good LCP, inp, and CLS divided by origins with any LCP, inp, and CLS.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(
+      IS_GOOD(fast_lcp, avg_lcp, slow_lcp) AND
+      IS_GOOD(fast_inp, avg_inp, slow_inp) AND
+      IS_GOOD(small_cls, medium_cls, large_cls), origin, NULL
+    )),
+    COUNT(DISTINCT IF(
+      IS_NON_ZERO(fast_lcp, avg_lcp, slow_lcp) AND
+      IS_NON_ZERO(fast_inp, avg_inp, slow_inp) AND
+      IS_NON_ZERO(small_cls, medium_cls, large_cls), origin, NULL
+    ))
+  ) AS pct_good_cwv
+FROM
+  `chrome-ux-report.materialized.device_summary`
+JOIN (
+  SELECT DISTINCT
+    date,
+    client,
+    root_page,
+    tech.technology AS ecomm
+  FROM
+    `httparchive.crawl.pages`,
+    UNNEST(technologies) AS tech,
+    UNNEST(tech.categories) AS category
+  WHERE
+    date = '2025-07-01' AND
+    category = 'Ecommerce' AND
+    (
+      tech.technology != 'Cart Functionality' AND
+      tech.technology != 'Google Analytics Enhanced eCommerce'
+    )
+)
+ON
+  CONCAT(origin, '/') = root_page AND
+  IF(device = 'desktop', 'desktop', 'mobile') = client AND
+  date
+WHERE
+  date = '2025-07-01'
+GROUP BY
+  client,
+  ecomm
+ORDER BY
+  origins DESC

sql/2025/ecommerce/core_web_vitals_by_platform.sql

@@ -0,0 +1,75 @@
+#standardSQL
+# CrUX Core Web Vitals performance of Ecommerce vendors by device (fid was upated to inp, and is non optinal now)
+CREATE TEMP FUNCTION IS_GOOD(good FLOAT64, needs_improvement FLOAT64, poor FLOAT64) RETURNS BOOL AS (
+  good / (good + needs_improvement + poor) >= 0.75
+);
+
+CREATE TEMP FUNCTION IS_NON_ZERO(good FLOAT64, needs_improvement FLOAT64, poor FLOAT64) RETURNS BOOL AS (
+  good + needs_improvement + poor > 0
+);
+
+
+SELECT
+  client,
+  ecomm,
+  COUNT(DISTINCT origin) AS origins,
+  # Origins with good LCP divided by origins with any LCP.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(fast_lcp, avg_lcp, slow_lcp), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(fast_lcp, avg_lcp, slow_lcp), origin, NULL))
+  ) AS pct_good_lcp,
+
+  # Origins with good INP divided by origins with any inp.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(fast_inp, avg_inp, slow_inp), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(fast_inp, avg_inp, slow_inp), origin, NULL))
+  ) AS pct_good_inp,
+
+  # Origins with good CLS divided by origins with any CLS.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(small_cls, medium_cls, large_cls), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(small_cls, medium_cls, large_cls), origin, NULL))
+  ) AS pct_good_cls,
+
+  # Origins with good LCP, inp, and CLS divided by origins with any LCP, inp, and CLS.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(
+      IS_GOOD(fast_lcp, avg_lcp, slow_lcp) AND
+      IS_GOOD(fast_inp, avg_inp, slow_inp) AND
+      IS_GOOD(small_cls, medium_cls, large_cls), origin, NULL
+    )),
+    COUNT(DISTINCT IF(
+      IS_NON_ZERO(fast_lcp, avg_lcp, slow_lcp) AND
+      IS_NON_ZERO(fast_inp, avg_inp, slow_inp) AND
+      IS_NON_ZERO(small_cls, medium_cls, large_cls), origin, NULL
+    ))
+  ) AS pct_good_cwv
+FROM
+  `chrome-ux-report.materialized.device_summary`
+JOIN (
+  SELECT DISTINCT
+    client,
+    root_page,
+    tech.technology AS ecomm
+  FROM
+    `httparchive.crawl.pages`,
+    UNNEST(technologies) AS tech,
+    UNNEST(tech.categories) AS category
+  WHERE
+    date = '2025-07-01' AND
+    category = 'Ecommerce' AND
+    (
+      tech.technology != 'Cart Functionality' AND
+      tech.technology != 'Google Analytics Enhanced eCommerce'
+    )
+)
+ON
+  CONCAT(origin, '/') = root_page AND
+  IF(device = 'desktop', 'desktop', 'mobile') = client
+WHERE
+  date = '2025-07-01'
+GROUP BY
+  client,
+  ecomm
+ORDER BY
+  origins DESC

sql/2025/ecommerce/core_web_vitals_passingmetrics_byvendor_bydevice.sql

@@ -0,0 +1,75 @@
+#standardSQL
+# CrUX Core Web Vitals performance of Ecommerce vendors by device (fid was upated to inp, and is non optinal now)
+CREATE TEMP FUNCTION IS_GOOD(good FLOAT64, needs_improvement FLOAT64, poor FLOAT64) RETURNS BOOL AS (
+  good / (good + needs_improvement + poor) >= 0.75
+);
+
+CREATE TEMP FUNCTION IS_NON_ZERO(good FLOAT64, needs_improvement FLOAT64, poor FLOAT64) RETURNS BOOL AS (
+  good + needs_improvement + poor > 0
+);
+
+
+SELECT
+  client,
+  ecomm,
+  COUNT(DISTINCT origin) AS origins,
+  # Origins with good LCP divided by origins with any LCP.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(fast_lcp, avg_lcp, slow_lcp), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(fast_lcp, avg_lcp, slow_lcp), origin, NULL))
+  ) AS pct_good_lcp,
+
+  # Origins with good INP divided by origins with any inp.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(fast_inp, avg_inp, slow_inp), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(fast_inp, avg_inp, slow_inp), origin, NULL))
+  ) AS pct_good_inp,
+
+  # Origins with good CLS divided by origins with any CLS.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(IS_GOOD(small_cls, medium_cls, large_cls), origin, NULL)),
+    COUNT(DISTINCT IF(IS_NON_ZERO(small_cls, medium_cls, large_cls), origin, NULL))
+  ) AS pct_good_cls,
+
+  # Origins with good LCP, inp, and CLS divided by origins with any LCP, inp, and CLS.
+  SAFE_DIVIDE(
+    COUNT(DISTINCT IF(
+      IS_GOOD(fast_lcp, avg_lcp, slow_lcp) AND
+      IS_GOOD(fast_inp, avg_inp, slow_inp) AND
+      IS_GOOD(small_cls, medium_cls, large_cls), origin, NULL
+    )),
+    COUNT(DISTINCT IF(
+      IS_NON_ZERO(fast_lcp, avg_lcp, slow_lcp) AND
+      IS_NON_ZERO(fast_inp, avg_inp, slow_inp) AND
+      IS_NON_ZERO(small_cls, medium_cls, large_cls), origin, NULL
+    ))
+  ) AS pct_good_cwv
+FROM
+  `chrome-ux-report.materialized.device_summary`
+JOIN (
+  SELECT DISTINCT
+    client,
+    root_page,
+    app AS ecomm
+  FROM
+    `httparchive.crawl.pages`,
+    UNNEST(technologies) AS tech,
+    UNNEST(categories) AS category
+  WHERE
+    date = '2025-07-01' AND
+    category = 'Ecommerce' AND
+    (
+      technology != 'Cart Functionality' AND
+      technology != 'Google Analytics Enhanced eCommerce'
+    )
+)
+ON
+  CONCAT(origin, '/') = root_page AND
+  IF(device = 'desktop', 'desktop', 'mobile') = client
+WHERE
+  date = '2025-07-01'
+GROUP BY
+  client,
+  ecomm
+ORDER BY
+  origins DESC

sql/2025/ecommerce/counts.sql

@@ -0,0 +1,49 @@
+SELECT
+  client,
+  date,
+  EXTRACT(YEAR FROM date) AS year,
+  rank_grouping,
+  CASE
+    WHEN rank_grouping = 100000000 THEN 'all'
+    ELSE FORMAT("%'d", rank_grouping)
+  END AS ranking,
+  COUNT(DISTINCT root_page) AS ecommerce_sites,
+  total,
+  COUNT(DISTINCT root_page) / total AS pct_ecommerce
+FROM
+  `httparchive.crawl.pages`,
+  UNNEST(technologies) AS technologies,
+  UNNEST(technologies.categories) AS cats,
+  UNNEST([1000, 10000, 100000, 1000000, 10000000, 100000000]) AS rank_grouping
+JOIN (
+  SELECT
+    date,
+    client,
+    rank_grouping,
+    COUNT(DISTINCT root_page) AS total
+  FROM
+    `httparchive.crawl.pages`,
+    UNNEST([1000, 10000, 100000, 1000000, 10000000, 100000000]) AS rank_grouping
+  WHERE
+    date IN ('2025-07-01', '2024-06-01', '2023-07-01', '2022-06-01', '2025-07-01') AND
+    rank <= rank_grouping
+  GROUP BY
+    date,
+    client,
+    rank_grouping
+)
+USING (date, client, rank_grouping)
+WHERE
+  date IN ('2025-07-01', '2024-06-01', '2023-07-01', '2022-06-01', '2025-07-01') AND
+  rank <= rank_grouping AND
+  cats = 'Ecommerce' AND
+  technologies.technology NOT IN ('Cart Functionality', 'Google Analytics Enhanced eCommerce')
+GROUP BY
+  date,
+  client,
+  rank_grouping,
+  total
+ORDER BY
+  date DESC,
+  client,
+  rank_grouping

sql/2025/ecommerce/median_lighthouse_score_ecommsites.sql

@@ -0,0 +1,44 @@
+WITH totals AS (
+  SELECT
+    client,
+    COUNT(DISTINCT page) AS total_webpages,
+    COUNT(DISTINCT root_page) AS total_websites
+  FROM
+    `httparchive.crawl.pages`
+  WHERE
+    date = '2025-07-01'
+  GROUP BY
+    client
+)
+
+SELECT
+  client,
+  technology,
+  ARRAY_AGG(DISTINCT category) AS categories,
+  APPROX_QUANTILES(CAST(JSON_VALUE(lighthouse.categories.performance.score) AS NUMERIC) * 100, 1000)[OFFSET(500)] AS median_performance,
+  APPROX_QUANTILES(CAST(JSON_VALUE(lighthouse.categories.accessibility.score) AS NUMERIC) * 100, 1000)[OFFSET(500)] AS median_accessibility,
+  APPROX_QUANTILES(CAST(JSON_VALUE(lighthouse.categories.seo.score) AS NUMERIC) * 100, 1000)[OFFSET(500)] AS median_seo,
+  APPROX_QUANTILES(CAST(JSON_VALUE(lighthouse.categories.`best-practices`.score) AS NUMERIC) * 100, 1000)[OFFSET(500)] AS median_best_practices,
+  ANY_VALUE(total_websites) AS total_websites,
+  COUNT(DISTINCT root_page) AS number_of_websites,
+  COUNT(DISTINCT root_page) / ANY_VALUE(total_websites) AS percent_of_websites
+FROM
+  `httparchive.crawl.pages`,
+  UNNEST(technologies) AS tech,
+  UNNEST(categories) AS category
+INNER JOIN
+  totals
+USING (client)
+WHERE
+  date = '2025-07-01' AND
+  category = 'Ecommerce' AND
+  (
+    technology != 'Cart Functionality' AND
+    technology != 'Google Analytics Enhanced eCommerce'
+  )
+GROUP BY
+  client,
+  technology
+ORDER BY
+  client,
+  number_of_websites DESC