examples/3_integrations.deepnote

Rama main · réplica de lectura del repositorio original.

metadata:
  createdAt: '2025-11-04T05:25:00.936Z'
  modifiedAt: '2026-01-14T14:09:13.693Z'
  snapshotHash: sha256:7a3db0f474fa2fc56855a45456c85ec5214a57c271938b9bb4fd72eb29cd5e2b
project:
  id: 1c0d890d-b9b3-492b-bc41-6dd4047cc2ff
  name: Integrations example
  integrations:
    - id: 100eef5b-8ad8-4d35-8e5e-3dfeeb387d4d
      name: ClickHouse playground OSS
      type: clickhouse
  notebooks:
    - blocks:
        - blockGroup: c55d86401aca4829a7ad351dbfbbf38d
          content: |-
            SELECT
              *
            FROM
              default.hackernews
            WHERE
              type = 'story'
              AND url IS NOT NULL
              AND url != ''
            ORDER BY
              time DESC
            LIMIT 100000;
          id: 13db6a85530043f5aad25fdcc34f6329
          metadata:
            sql_integration_id: 100eef5b-8ad8-4d35-8e5e-3dfeeb387d4d
            deepnote_variable_name: stories
          sortingKey: x
          type: sql
          contentHash: sha256:80d4bb4ee11b1fb22b95004c2e01827e920a8cd07783ad1565330d75e3773978
        - blockGroup: 0b85a9f7-5a1b-4025-bd37-0f34cc616e9d
          content: |-
            import pandas as pd
            from urllib.parse import urlparse

            def extract_domain(url):
                if pd.isna(url):
                    return None
                domain = urlparse(url).netloc.lower()
                return domain.replace("www.", "")

            stories["domain"] = stories["url"].apply(extract_domain)
          id: 3d9000d7403f08ed8c829e0f1d13f09e
          metadata: {}
          sortingKey: a1
          type: code
          contentHash: sha256:ee6a08013f7a94f1645f512ea376aa705b9596be8128954e11a3d8203653d1ba
        - blockGroup: b81f1b2e-0798-4947-a8cf-48b04be3e5c4
          content: |-
            domain_counts = (
                stories["domain"]
                .dropna()
                .value_counts()
            )

            domain_counts.head(10)
          id: bb630c895022ac3b01e2080364e50a20
          metadata: {}
          sortingKey: a2
          type: code
          contentHash: sha256:07094d2c2452afb054ae3512ac6c3398a2e5e4eafac6dfee230437e2e9633bc4
        - blockGroup: e10542d3-3321-47b1-b449-96303d75c548
          content: |-
            import matplotlib.pyplot as plt

            TOP_N = 20

            top_domains = domain_counts.head(TOP_N)

            plt.figure(figsize=(10, 6))
            top_domains.plot(kind="bar", logy=True)
            plt.title(f"Top {TOP_N} Hacker News Domains (Log Scale)")
            plt.xlabel("Domain")
            plt.ylabel("Number of Posts (log)")
            plt.xticks(rotation=45, ha="right")
            plt.tight_layout()
            plt.show()
          id: 3544ef8a9113595f1e3c6f1d1b4d700f
          metadata: {}
          sortingKey: a3
          type: code
          contentHash: sha256:5e84f4b3ee6fb49c639a0f3c8f394882ea1c5f9843c104a4971665e7cfda59bc
      executionMode: block
      id: b641c8773e3b45759278d1b537ba1939
      isModule: false
      name: Integrations
  settings: {}
version: 1.0.0