duckdb-query.yaml

id: duckdb-query
namespace: company.team
tasks:
  - id: download_csv
    type: io.kestra.plugin.core.http.Download
    description: salaries of data professionals from 2020 to 2023 (source ai-jobs.net)
    uri: https://huggingface.co/datasets/kestra/datasets/raw/main/csv/salaries.csv

  - id: avg_salary_by_job_title
    type: io.kestra.plugin.jdbc.duckdb.Query
    inputFiles:
      data.csv: "{{ outputs.download_csv.uri }}"
    sql: |
      SELECT 
        job_title,
        ROUND(AVG(salary),2) AS avg_salary
      FROM read_csv_auto('{{ workingDir }}/data.csv', header=True)
      GROUP BY job_title
      HAVING COUNT(job_title) > 10
      ORDER BY avg_salary DESC;
    fetchType: STORE

  - id: result
    type: io.kestra.plugin.serdes.csv.IonToCsv
    from: "{{ outputs.avg_salary_by_job_title.uri }}"

extend:
  title: Analyze salaries of data professionals using a SQL query in DuckDB,
    extract the results to a CSV file
  description: Download a CSV file and query data with DuckDB. Then, extract the
    results to a CSV file.
  tags:
    - DuckDB
    - SQL
    - Outputs
  ee: false
  demo: true
  meta_description: This flow will download a CSV file and query data with DuckDB.
    Then, extract the results to a CSV file.