gingerwizard

Download data

wget https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/nyc-taxi-vectors.csv.gz
gzip -d nyc-taxi-vectors.csv.gz

Install Dependencies

gingerwizard

-- data table
CREATE TABLE transactions
(
  id UInt32,
  vector Array(Float32),
  customer UInt32,
)
ENGINE = MergeTree -- this can be a Null engine
ORDER BY id

gingerwizard

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.

gingerwizard

-- 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,

gingerwizard

#!/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')

gingerwizard

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' ','

gingerwizard

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,

gingerwizard

gingerwizard

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)

gingerwizard

/*-----------------------------------------------------------------------*/
/* Program: STREAM                                                       */
/* Revision: $Id: stream.c,v 5.10 2013/01/17 16:01:06 mccalpin Exp mccalpin $ */
/* Original code developed by John D. McCalpin                           */
/* Programmers: John D. McCalpin                                         */
/*              Joe R. Zagar                                             */
/*                                                                       */
/* This program measures memory transfer rates in MB/s for simple        */
/* computational kernels coded in C.                                     */
/*-----------------------------------------------------------------------*/