id: wikipedia-top10-python-pandas
namespace: company.team
description: Analyze top 10 Wikipedia pages

tasks:
  - id: query
    type: io.kestra.plugin.gcp.bigquery.Query
    sql: |
      SELECT DATETIME(datehour) as date, title, views FROM
      `bigquery-public-data.wikipedia.pageviews_2024`
      WHERE DATE(datehour) = current_date() and wiki = 'en'
      ORDER BY datehour desc, views desc
      LIMIT 10
    store: true
    projectId: test-project
    serviceAccount: "{{ secret('GCP_SERVICE_ACCOUNT_JSON') }}"

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

  - id: pandas
    type: io.kestra.plugin.scripts.python.Script
    taskRunner:
      type: io.kestra.plugin.scripts.runner.docker.Docker
    containerImage: ghcr.io/kestra-io/pydata:latest
    inputFiles:
      data.csv: "{{ outputs.write_csv.uri }}"
    script: |
      import pandas as pd
      from kestra import Kestra

      df = pd.read_csv("data.csv")
      df.head(10)
      views = df['views'].max()
      Kestra.outputs({'views': int(views)})