wget https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/nyc-taxi-vectors.csv.gz
gzip -d nyc-taxi-vectors.csv.gz
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
alexey-milovidov | |
tombouctou | |
mutantcornholio | |
rifler | |
rocco66 | |
serebrserg | |
NikitchenkoSergey | |
zakhar | |
sfod | |
blackwithwhite666 |
-- data table
CREATE TABLE transactions
(
id UInt32,
vector Array(Float32),
customer UInt32,
)
ENGINE = MergeTree -- this can be a Null engine
ORDER BY id
CREATE TABLE surveys
(
`response_id` Int64,
`development_activity` Enum8('I am a developer by profession' = 1, 'I am a student who is learning to code' = 2, 'I am not primarily a developer, but I write code sometimes as part of my work' = 3, 'I code primarily as a hobby' = 4, 'I used to be a developer by profession, but no longer am' = 5, 'None of these' = 6, 'NA' = 7),
`employment` Enum8('Independent contractor, freelancer, or self-employed' = 1, 'Student, full-time' = 2, 'Employed full-time' = 3, 'Student, part-time' = 4, 'I prefer not to say' = 5, 'Employed part-time' = 6, 'Not employed, but looking for work' = 7, 'Retired' = 8, 'Not employed, and not looking for work' = 9, 'NA' = 10),
`country` LowCardinality(String),
`us_state` LowCardinality(String),
`uk_county` LowCardinality(String),
`education_level` Enum8('Secondary school (e.g. American high school, German Realschule or Gymnasium, etc.)' = 1, 'Bachelor’s degree (B.A., B.S., B.Eng., etc.)' = 2, 'Master’s degree (M.
-- original table
CREATE TABLE hackernews_copy
(
`id` String,
`doc_id` String,
`comment` String,
`vector` Array(Float32),
`node_info` Tuple(start Nullable(UInt64), end Nullable(UInt64)),
`metadata` String,
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
if [[ -z "$CLOUD_ID" || -z "$CLOUD_SECRET" || -z "$AWS_ACCESS_KEY_ID" || -z "$AWS_SECRET_ACCESS_KEY" ]]; then | |
echo "Error: Required environment variables are not set." | |
exit 1 | |
fi | |
# identify the organization to create the service in | |
ORG_ID=$(curl --silent --user $CLOUD_ID:$CLOUD_SECRET https://api.clickhouse.cloud/v1/organizations | jq -r '.result[0].id') | |
ORG_NAME=$(curl --silent --user $CLOUD_ID:$CLOUD_SECRET https://api.clickhouse.cloud/v1/organizations | jq -r '.result[0].name') |
diff -u <(docker run --rm clickhouse/clickhouse-server:23.12 clickhouse-local --query "SELECT * FROM system.contributors ORDER BY name") <(docker run --rm clickhouse/clickhouse-server:24.1 clickhouse-local --query "SELECT * FROM system.contributors ORDER BY name") | grep -E "^\+" | tail -n +2 | sed 's/^\+//' | tr '\n' ','
CREATE EXTERNAL TABLE IF NOT EXISTS ookla (
quadkey string,
tile string,
avg_d_kbps int,
avg_u_kbps int,
avg_lat_ms int,
avg_lat_down_ms int,
avg_lat_up_ms int,
tests int,
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
resort_name | state | summit | base | vertical | lifts | runs | acres | green_percent | green_acres | blue_percent | blue_acres | black_percent | black_acres | lat | lon | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
49(degrees) North, WA | Washington | 5774 | 3923 | 1851 | 6 | 68 | 2325 | 0.3 | 697.5 | 0.4 | 930 | 0.3 | 697.5 | 49 | -115.84 | |
Afton Alps, MN | Minnesota | 700 | 350 | 350 | 21 | 48 | 300 | 0.2 | 60 | 0.6 | 180 | 0.2 | 60 | 44.85 | -92.79 | |
Alpine Meadows, CA | California | 8673 | 6385 | 2288 | 13 | 100 | 2400 | 0.25 | 600 | 0.4 | 960 | 0.35 | 840 | 39.17 | -120.22 | |
Alpine Mountain, PA | Pennsylvania | 1150 | 600 | 500 | 3 | 21 | 120 | 0.17 | 20.4 | 0.55 | 66 | 0.28 | 33.6 | 40.08 | -76.9 | |
Alpine Valley, MI | Michigan | 1210 | 910 | 300 | 14 | 25 | 118 | 0.39 | 46.02 | 0.26 | 30.68 | 0.35 | 41.3 | 44.96 | -84.87 | |
Alpine Valley, OH | Ohio | 1500 | 1260 | 230 | 6 | 11 | 72 | 0.33 | 23.76 | 0.34 | 24.48 | 0.33 | 23.76 | 40.31 | -83.68 | |
Alpine Valley, WI | Wisconsin | 388 | 16 | 20 | 90 | 0.4 | 36 | 0.4 | 36 | 0.2 | 18 | 42.45 | -88.25 | |||
Alta, UT | Utah | 10550 | 8530 | 2020 | 11 | 116 | 2200 | 0.25 | 550 | 0.4 | 880 | 0.35 | 770 | 40.6 | -111.64 | |
Alyeska, AK | Alaska | 3939 | 250 | 2500 | 9 | 73 | 1500 | 0.11 | 165 | 0.52 | 780 | 0.37 | 555 | 60.97 | -149.11 |
DESCRIBE TABLE gcs('https://storage.googleapis.com/clickhouse-website/ga-*.parquet', '<access key>', '<secret>')
FORMAT TSV
event_date Nullable(String)
event_timestamp Nullable(Int64)
event_name Nullable(String)
event_params Array(Tuple(key Nullable(String), value Tuple(string_value Nullable(String), int_value Nullable(Int64), float_value Nullable(Float64), double_value Nullable(Float64))))
event_previous_timestamp Nullable(Int64)
event_value_in_usd Nullable(Float64)
NewerOlder