From 134a3246d5ec4825e53a5d3cc7f285393db1c7aa Mon Sep 17 00:00:00 2001 From: Kim Mennemann <2011879@stud.hs-mannheim.de> Date: Sat, 29 Jun 2024 12:00:19 +0200 Subject: [PATCH] README.md aktualisiert --- README.md | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index 73c40be..02b4dde 100644 --- a/README.md +++ b/README.md @@ -10,11 +10,11 @@ Die Befehle können in Cassandra Web mit der Adresse `localhost:3000` oder im Do sudo docker exec -it cass1 cqlsh -Hinweis: Die `MATERIALZIED VIEWS` und `CUSTOM INDEX` sind bereits im [Startup-Skript](https://github.com/Miracle-Fruit/kikeriki/blob/main/cassandra/startup/setup/setup_db.sh) erstellt und müssen nicht erneut ausgeführt werden. +Hinweis: Die `MATERIALZIED VIEWS` und `CUSTOM INDEX` sind bereits im [Startup-Skript](./startup/setup/setup_db.sh) erstellt und müssen nicht erneut ausgeführt werden. ## Queries -Alle Queries finden Sie auch [hier](https://github.com/Miracle-Fruit/kikeriki/tree/main/cassandra/startup/queries). +Alle Queries finden Sie auch [hier](./startup/queries). 1. Auflisten der Posts, die von einem Account gemacht wurden, bzw. ihm zugeordnet wurden @@ -52,33 +52,35 @@ print("100 accounts that follow the most of the accounts found in 2)",followed_t * 4.1 und 4.2 die Anzahl der Follower && die Anzahl der verfolgten Accounts - SELECT follower_len, follows_len FROM twitter.user_stats WHERE user_id = 233248636; //check user_id can be changed + ```SELECT follower_len, follows_len FROM twitter.user_stats WHERE user_id = 233248636; //check user_id can be changed``` ![result_ex4_1](img/ex4_1.png) * 4.3 wahlweise die 25 neusten (zeitbasiert) oder die 25 beliebtesten Posts (like-basiert) der verfolgten Accounts (per DB-Abfrage) - 25 neuste + 25 neuste - CREATE MATERIALIZED VIEW twitter.start_view_new AS - SELECT user_id_x,follower_id,number_of_likes,number_of_shares,date_time,name,author,content,id FROM twitter.user - WHERE user_id_x IS NOT NULL AND follower_id IS NOT NULL AND date_time IS NOT NULL AND id IS NOT NULL - PRIMARY KEY ((user_id_x),date_time,follower_id,id); + CREATE MATERIALIZED VIEW twitter.start_view_new AS + SELECT user_id_x,follower_id,number_of_likes,number_of_shares,date_time,name,author,content,id FROM twitter.user + WHERE user_id_x IS NOT NULL AND follower_id IS NOT NULL AND date_time IS NOT NULL AND id IS NOT NULL + PRIMARY KEY ((user_id_x),date_time,follower_id,id); - SELECT * FROM twitter.start_view_new WHERE user_id_x = 172883064 ORDER BY date_time DESC LIMIT 25; + SELECT * FROM twitter.start_view_new WHERE user_id_x = 172883064 ORDER BY date_time DESC LIMIT 25; ![result_ex4_2](img/ex4_2_date.png) - 25 beliebteste + 25 beliebteste - CREATE MATERIALIZED VIEW twitter.start_view_like AS - SELECT user_id_x,follower_id,number_of_likes,number_of_shares,date_time,author,name,content,id FROM twitter.user - WHERE user_id_x IS NOT NULL AND follower_id IS NOT NULL AND number_of_likes IS NOT NULL AND id IS NOT NULL - PRIMARY KEY ((user_id_x),number_of_likes,follower_id,id); + + // To order by the 25 most number_of_like is to our knowledge not possible with the current dataschema + CREATE MATERIALIZED VIEW twitter.start_view_like AS + SELECT user_id_x,follower_id,number_of_likes,number_of_shares,date_time,author,name,content,id FROM twitter.user + WHERE user_id_x IS NOT NULL AND follower_id IS NOT NULL AND number_of_likes IS NOT NULL AND id IS NOT NULL + PRIMARY KEY ((user_id_x),number_of_likes,follower_id,id); - SELECT * FROM twitter.start_view_like WHERE user_id_x = 172883064 ORDER BY number_of_likes DESC LIMIT 25; + SELECT * FROM twitter.start_view_like WHERE user_id_x = 172883064 ORDER BY number_of_likes DESC LIMIT 25; ![result_ex4_2](img/ex4_2_likes.png) @@ -105,7 +107,6 @@ print("100 accounts that follow the most of the accounts found in 2)",followed_t * 4.5 Auflisten der 25 beliebtesten Posts, die ein geg. Wort enthalten (falls möglich auch mit UND-Verknüpfung mehrerer Worte) - // To order by the 25 most number_of_like is at our knowledge not possible with the current dataschema CREATE CUSTOM INDEX search_in ON twitter.tweets (content) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH OPTIONS = { 'mode': 'CONTAINS', 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.NonTokenizingAnalyzer', 'case_sensitive': 'false' };