mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-12-11 08:52:06 +00:00
67c2e50331
* update presentations * CLICKHOUSE-2936: redirect from clickhouse.yandex.ru and clickhouse.yandex.com * update submodule * lost files * CLICKHOUSE-2981: prefer sphinx docs over original reference * CLICKHOUSE-2981: docs styles more similar to main website + add flags to switch language links * update presentations * Less confusing directory structure (docs -> doc/reference/) * Minify sphinx docs too * Website release script: fail fast + pass docker hash on deploy * Do not underline links in docs * shorter * cleanup docker images * tune nginx config * CLICKHOUSE-3043: get rid of habrastorage links * Lost translation * CLICKHOUSE-2936: temporary client-side redirect * behaves weird in test * put redirect back * CLICKHOUSE-3047: copy docs txts to public too * move to proper file * remove old pages to avoid confusion * Remove reference redirect warning for now * Refresh README.md * Yellow buttons in docs * Use svg flags instead of unicode ones in docs * fix test website instance * Put flags to separate files * wrong flag * Copy Yandex.Metrica introduction from main page to docs * Yet another home page structure change, couple new blocks (CLICKHOUSE-3045) * Update Contacts section * CLICKHOUSE-2849: more detailed legal information * CLICKHOUSE-2978 preparation - split by files * More changes in Contacts block * Tune texts on index page * update presentations * One more benchmark * Add usage sections to index page, adapted from slides * Get the roadmap started, based on slides from last ClickHouse Meetup * CLICKHOUSE-2977: some rendering tuning * Get rid of excessive section in the end of getting started * Make headers linkable * CLICKHOUSE-2981: links to editing reference - https://github.com/yandex/ClickHouse/issues/849 * CLICKHOUSE-2981: fix mobile styles in docs * Ban crawling of duplicating docs * Open some external links in new tab * Ban old docs too * Lots of trivial fixes in english docs * Lots of trivial fixes in russian docs * Remove getting started copies in markdown * Add Yandex.Webmaster * Fix some sphinx warnings * More warnings fixed in english docs * More sphinx warnings fixed * Add code-block:: text * More code-block:: text * These headers look not that well * Better switch between documentation languages * merge use_case.rst into ya_metrika_task.rst * Edit the agg_functions.rst texts * Add lost empty lines * Lost blank lines * Add new logo sizes * update presentations * Next step in migrating to new documentation * Fix all warnings in en reference * Fix all warnings in ru reference * Re-arrange existing reference * Move operation tips to main reference * Fix typos noticed by milovidov@ * Get rid of zookeeper.md * Looks like duplicate of tutorial.html * Fix some mess with html tags in tutorial * No idea why nobody noticed this before, but it was completely not clear whet to get the data * Match code block styling between main and tutorial pages (in favor of the latter) * Get rid of some copypaste in tutorial * Normalize header styles * Move example_datasets to sphinx * Move presentations submodule to website * Move and update README.md * No point in duplicating articles from habrahabr here * Move development-related docs as is for now * doc/reference/ -> docs/ (to match the URL on website) * Adapt links to match the previous commit * Adapt development docs to rst (still lacks translation and strikethrough support) * clean on release * blacklist presentations in gulp * strikethrough support in sphinx * just copy development folder for now * fix weird introduction in style article * Style guide translation (WIP) * Finish style guide translation to English * gulp clean separately * Update year in LICENSE * Initial CONTRIBUTING.md * Fix remaining links to old docs in tutorial * Some tutorial fixes * Typo * Another typo * Update list of authors from yandex-team accoding to git log
74 lines
3.4 KiB
ReStructuredText
74 lines
3.4 KiB
ReStructuredText
Criteo Terabyte Click Logs
|
|
--------------------------
|
|
|
|
Download all data from http://labs.criteo.com/downloads/download-terabyte-click-logs/
|
|
|
|
Create log table:
|
|
|
|
.. code-block:: sql
|
|
|
|
CREATE TABLE criteo_log (date Date, clicked UInt8, int1 Int32, int2 Int32, int3 Int32, int4 Int32, int5 Int32, int6 Int32, int7 Int32, int8 Int32, int9 Int32, int10 Int32, int11 Int32, int12 Int32, int13 Int32, cat1 String, cat2 String, cat3 String, cat4 String, cat5 String, cat6 String, cat7 String, cat8 String, cat9 String, cat10 String, cat11 String, cat12 String, cat13 String, cat14 String, cat15 String, cat16 String, cat17 String, cat18 String, cat19 String, cat20 String, cat21 String, cat22 String, cat23 String, cat24 String, cat25 String, cat26 String) ENGINE = Log
|
|
|
|
Load data:
|
|
|
|
.. code-block:: bash
|
|
|
|
for i in {00..23}; do echo $i; zcat datasets/criteo/day_${i#0}.gz | sed -r 's/^/2000-01-'${i/00/24}'\t/' | clickhouse-client --host=example-perftest01j --query="INSERT INTO criteo_log FORMAT TabSeparated"; done
|
|
|
|
Create table for converted data:
|
|
|
|
.. code-block:: sql
|
|
|
|
CREATE TABLE criteo
|
|
(
|
|
date Date,
|
|
clicked UInt8,
|
|
int1 Int32,
|
|
int2 Int32,
|
|
int3 Int32,
|
|
int4 Int32,
|
|
int5 Int32,
|
|
int6 Int32,
|
|
int7 Int32,
|
|
int8 Int32,
|
|
int9 Int32,
|
|
int10 Int32,
|
|
int11 Int32,
|
|
int12 Int32,
|
|
int13 Int32,
|
|
icat1 UInt32,
|
|
icat2 UInt32,
|
|
icat3 UInt32,
|
|
icat4 UInt32,
|
|
icat5 UInt32,
|
|
icat6 UInt32,
|
|
icat7 UInt32,
|
|
icat8 UInt32,
|
|
icat9 UInt32,
|
|
icat10 UInt32,
|
|
icat11 UInt32,
|
|
icat12 UInt32,
|
|
icat13 UInt32,
|
|
icat14 UInt32,
|
|
icat15 UInt32,
|
|
icat16 UInt32,
|
|
icat17 UInt32,
|
|
icat18 UInt32,
|
|
icat19 UInt32,
|
|
icat20 UInt32,
|
|
icat21 UInt32,
|
|
icat22 UInt32,
|
|
icat23 UInt32,
|
|
icat24 UInt32,
|
|
icat25 UInt32,
|
|
icat26 UInt32
|
|
) ENGINE = MergeTree(date, intHash32(icat1), (date, intHash32(icat1)), 8192)
|
|
|
|
Parse the data from raw log and put it into second table:
|
|
|
|
.. code-block:: sql
|
|
|
|
INSERT INTO criteo SELECT date, clicked, int1, int2, int3, int4, int5, int6, int7, int8, int9, int10, int11, int12, int13, reinterpretAsUInt32(unhex(cat1)) AS icat1, reinterpretAsUInt32(unhex(cat2)) AS icat2, reinterpretAsUInt32(unhex(cat3)) AS icat3, reinterpretAsUInt32(unhex(cat4)) AS icat4, reinterpretAsUInt32(unhex(cat5)) AS icat5, reinterpretAsUInt32(unhex(cat6)) AS icat6, reinterpretAsUInt32(unhex(cat7)) AS icat7, reinterpretAsUInt32(unhex(cat8)) AS icat8, reinterpretAsUInt32(unhex(cat9)) AS icat9, reinterpretAsUInt32(unhex(cat10)) AS icat10, reinterpretAsUInt32(unhex(cat11)) AS icat11, reinterpretAsUInt32(unhex(cat12)) AS icat12, reinterpretAsUInt32(unhex(cat13)) AS icat13, reinterpretAsUInt32(unhex(cat14)) AS icat14, reinterpretAsUInt32(unhex(cat15)) AS icat15, reinterpretAsUInt32(unhex(cat16)) AS icat16, reinterpretAsUInt32(unhex(cat17)) AS icat17, reinterpretAsUInt32(unhex(cat18)) AS icat18, reinterpretAsUInt32(unhex(cat19)) AS icat19, reinterpretAsUInt32(unhex(cat20)) AS icat20, reinterpretAsUInt32(unhex(cat21)) AS icat21, reinterpretAsUInt32(unhex(cat22)) AS icat22, reinterpretAsUInt32(unhex(cat23)) AS icat23, reinterpretAsUInt32(unhex(cat24)) AS icat24, reinterpretAsUInt32(unhex(cat25)) AS icat25, reinterpretAsUInt32(unhex(cat26)) AS icat26 FROM criteo_log;
|
|
|
|
DROP TABLE criteo_log;
|