Data Explore

by wellcomecollection

data

Explore Hive tables and datasets in the Wellcome Collection data warehouse. Use this skill to query tables, understand schemas, or analyze data distributions. Invoke with /data-explore.

Skill Details

Repository Files

1 file in this skill directory


name: data-explore description: Explore Hive tables and datasets in the Wellcome Collection data warehouse. Use this skill to query tables, understand schemas, or analyze data distributions. Invoke with /data-explore.

Data Exploration

This skill helps explore the Wellcome Collection data warehouse stored in Hive tables.

Available Tables

Core Tables

Table Records Description
works 738,073 Wellcome Collection works catalog
images 128,755 Image metadata from IIIF manifests
iiif_manifests ~340,000 IIIF manifest metadata
iiif_canvases ~42M Page-level canvas data

Text Tables

Table Records Description
alto_text ~226,000 OCR text from works (9.8B words total)
alto_sentence ~550M Sentence-level text
alto_text_chunks ~74M Text chunks for embedding

Embedding Tables

Table Description
vlm_embeddings VLM image embeddings (1536-dim)
text_embeddings Qwen3 text embeddings

Label Tables

Table Records Description
dn_labels 646,786 Combined genres/subjects/contributors

Quick Start

Connect to Spark

from wc_simd.utility import get_spark_session
spark = get_spark_session()

List Tables

spark.sql("SHOW TABLES").show()

Explore Schema

spark.table("works").printSchema()

Sample Data

spark.table("works").show(10, truncate=False)

Count Records

spark.table("works").count()

Common Queries

Works with OCR Text

SELECT COUNT(*) FROM works w
JOIN alto_text t ON w.id = t.id

Genre Distribution

SELECT genre.label, COUNT(*) as cnt
FROM works
LATERAL VIEW explode(genres) AS genre
GROUP BY genre.label
ORDER BY cnt DESC
LIMIT 20

Subject Distribution

SELECT subject.label, COUNT(*) as cnt
FROM works
LATERAL VIEW explode(subjects) AS subject
GROUP BY subject.label
ORDER BY cnt DESC
LIMIT 20

Concept Types

SELECT concept.type, COUNT(*) as cnt
FROM works
LATERAL VIEW explode(subjects) AS subject
LATERAL VIEW explode(subject.concepts) AS concept
GROUP BY concept.type

Key Statistics

  • Total words: 9.8 billion (~12,500 King James Bibles)
  • Text chunks: 74.3 million (1000 chars, 200 overlap)
  • Languages: 78.9% English
  • Genre labels: 1,523 unique
  • Subject labels: 204,322 unique
  • Concept labels: 126,714 unique

Related Skills

Xlsx

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

data

Clickhouse Io

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

datacli

Clickhouse Io

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

datacli

Analyzing Financial Statements

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

data

Data Storytelling

Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.

data

Kpi Dashboard Design

Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use when building business dashboards, selecting metrics, or designing data visualization layouts.

designdata

Dbt Transformation Patterns

Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.

testingdocumenttool

Sql Optimization Patterns

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

designdata

Anndata

This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling large-scale biological datasets. Use when tasks involve AnnData objects, h5ad files, single-cell RNA-seq data, or integration with scanpy/scverse tools.

arttooldata

Xlsx

Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.

tooldata

Skill Information

Category:Data
Last Updated:1/5/2026