ATTACH 'md:_share/stackoverflow/6c318917-6888-425a-bea1-5860c29947e5' AS stackoverflow;
USE stackoverflow;
Copy code

SELECT Title, CommentCount
FROM posts
WHERE PostTypeId = 1
ORDER BY CommentCount DESC
LIMIT 5;
Copy code

SELECT name, reputation, 
       round(reputation/day(today()-createdAt)) as rate, 
       day(today()-createdAt) as days, 
       createdAt
FROM users WHERE reputation > 1000000 ORDER BY rate DESC;
Copy code

WITH top_users as (
  SELECT name, reputation, 
       round(reputation/day(today()-createdAt)) as rate, day(today()-createdAt) as days, 
       createdAt
       FROM users WHERE reputation > 1000000
)
SELECT name, reputation, rate, bar(rate,150,300,35) AS bar FROM top_users;
Copy code

SELECT  year(CreationDate) AS year, count(*), 
        round(avg(ViewCount)), max(AnswerCount)
FROM posts 
GROUP BY year 
ORDER BY year DESC LIMIT 10;
Copy code

SELECT count(*) as freq, dayname(CreationDate) AS day, 
       bar(freq, 0, 150000,20) AS plot
FROM posts WHERE posttypeid = 1 
AND tags LIKE '%<sql>%'
GROUP BY all 
ORDER BY freq DESC;
Copy code

SELECT count(*) as freq, dayname(CreationDate) AS day, 
       bar(freq, 0, 10000,20) AS plot
FROM posts WHERE posttypeid = 1 
AND tags LIKE '%<rust>%'
GROUP BY all 
ORDER BY freq DESC;
Copy code

COPY (FROM VALUES ('foo', 10/9), ('bar', 50/7), ('qux', 9/4) t(s, x))
TO 'example.csv';

CREATE OR REPLACE TABLE example AS
    FROM read_csv('example.csv', types = {'x': 'DECIMAL(15, 3)'});
Copy code

SELECT ([upper (x[1])||x[2:] 
for x in 
(
'the quick brown fox jumped over the lazy dog'
).string_split(' ')]).list_aggr('string_agg',' ') 
Copy code

CREATE OR REPLACE TABLE example_table AS
SELECT 
    CAST(substr(line, 1, 4) AS INTEGER) AS activity_year,
    CAST(substr(line, 5, 10) AS VARCHAR(10)) AS lei_or_respondent_id,
    CAST(substr(line, 15, 1) AS CHAR(1)) AS agency_code,
    CAST(substr(line, 16, 1) AS CHAR(1)) AS loan_type,
    CAST(substr(line, 17, 1) AS CHAR(1)) AS loan_purpose,
    CAST(substr(line, 18, 1) AS CHAR(1)) AS occupancy_type
FROM
    (SELECT column0 AS line FROM read_csv('data.txt', AUTO_DETECT=TRUE, skip=1));
Copy code

INSTALL httpfs;
LOAD httpfs;

CREATE SECRET http (
    TYPE HTTP,
    EXTRA_HTTP_HEADERS MAP {
        'Authorization': 'Bearer [Api Token]'
    }
); 

-- Replace strapi.mydomain.com with your Strapi URL and replace `pets` with your content type
COPY (SELECT unnest(data, recursive:= true) FROM read_json_auto('https://strapi.mydomain.com/api/pets')) TO 'pets.parquet';
Copy code

CREATE OR REPLACE MACRO KDE_EPANECH(data, varnum, bandwidth, bin_count := 30) AS TABLE 
WITH hist AS (
	FROM histogram_values(data, varnum, bin_count := bin_count)
)
SELECT hist.bin, k.kernel_value
FROM hist, LATERAL (
    SELECT 100 * AVG(
    IF(abs(hist.bin - varnum) / bandwidth  < 1,
    0.75 * (1 - POW(abs(hist.bin - varnum) / bandwidth, 2)) / bandwidth,
    0)) AS kernel_value
	FROM query_table(data)
) k
ORDER BY hist.bin ;

-- Following David Scott's rule, here is an estimate for bandwidth:
CREATE OR REPLACE MACRO KDE_BANDWIDTH(data, varnum) AS (
	FROM query_table(data)
	SELECT 1.06 * stddev(varnum) * pow(count(*), -1/5)
);

-- Usage
SET VARIABLE bandwidth = (SELECT KDE_BANDWIDTH(mydata, myvarnum)) ;

FROM KDE_EPANECH(mydata, myvarnum, getvariable('bandwidth')) ;

-- Inspiration and illustration: https://observablehq.com/@d3/kernel-density-estimation
Copy code

install psql from community;
load psql;

from 'https://sampledata.sidequery.ai/earthquakes.parquet' |>
limit 10000 |>
where status = 'Reviewed' |>
select
    data_type, 
    avg(depth), 
    avg(magnitudo)
group by all;
Copy code