unzip datacircle-leads.zip -d datacircle-leads

pip install duckdb

import duckdb

con = duckdb.connect("datacircle.duckdb")

con.execute("""
    CREATE TABLE companies AS
    SELECT * FROM read_csv_auto('datacircle-leads/companies.csv')
""")

con.execute("""
    CREATE TABLE people AS
    SELECT * FROM read_csv_auto('datacircle-leads/people.csv')
""")

# Find all software companies in California
result = con.execute("""
    SELECT NAME, URL, EMPLOYEE_COUNT_RANGE
    FROM companies
    WHERE LINKEDIN_INDUSTRY = 'Computer Software' AND HQ_STATE_CODE = 'CA'
    ORDER BY LINKEDIN_FOLLOWERS DESC
    LIMIT 10
""").fetchdf()

print(result)

curl https://clickhouse.com/ | sh
./clickhouse server

CREATE TABLE companies
ENGINE = MergeTree()
ORDER BY NAME
AS SELECT * FROM file('datacircle-leads/companies.csv');

CREATE TABLE people
ENGINE = MergeTree()
ORDER BY LAST_NAME
AS SELECT * FROM file('datacircle-leads/people.csv');

-- Find VPs at mid-market companies
SELECT p.FIRST_NAME, p.LAST_NAME, p.CURRENT_JOB_TITLE, c.NAME AS company
FROM people p
JOIN companies c ON p.CURRENT_JOB_COMPANY_LINKEDIN_ID = c.LINKEDIN_ID
WHERE p.CURRENT_JOB_TITLE LIKE '%VP%'
  AND c.EMPLOYEE_COUNT_RANGE IN ('51-200', '201-500')
LIMIT 10;