Added two comprehensive datasets with full documentation: 1. Bay Area COVID-19 Wastewater Surveillance (2022-2025) - California statewide COVID-19 wastewater data - 161 weekly data points from CDPH - Leading health indicator for viral trends - Includes automated update scripts 2. Pulitzer Prize Winners - Arts & Letters (1918-2024) - 249 winners across 107 years - Poetry, Drama, and General/Special categories - High-quality curated data from Wikidata - CSV files for each category Added master Data directory documentation (Data/README.md) describing: - Data philosophy and quality standards - All four current datasets - Contribution guidelines - File naming conventions Includes utility commands: - get-bay-area-covid-status: Analyze current COVID wastewater levels - get-california-wastewater-data: Fetch latest surveillance data Updated .gitignore to exclude large raw data files (278MB+). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
50 lines
1.8 KiB
Plaintext
Executable File
50 lines
1.8 KiB
Plaintext
Executable File
#!/usr/bin/env bun
|
||
|
||
/**
|
||
* Update California Wastewater Data
|
||
*
|
||
* Fetches the latest wastewater surveillance data from CDPH
|
||
* for SARS-CoV-2, Influenza, and RSV
|
||
*/
|
||
|
||
import { writeFileSync } from 'fs';
|
||
import { join } from 'path';
|
||
|
||
const DATA_URL = 'https://data.chhs.ca.gov/dataset/a6ca879a-6014-4b72-9ea6-07ef8b87ae83/resource/2742b824-3736-4292-90a9-7fad98e94c06/download/wastewatersurveillancecalifornia.csv';
|
||
const CSV_PATH = join(__dirname, 'California-Wastewater-Surveillance-Latest.csv');
|
||
|
||
async function fetchLatestData(): Promise<string> {
|
||
console.log('📡 Fetching latest California wastewater data from CDPH Open Data Portal...\n');
|
||
|
||
const response = await fetch(DATA_URL);
|
||
if (!response.ok) {
|
||
throw new Error(`Failed to fetch data: ${response.statusText}`);
|
||
}
|
||
|
||
return await response.text();
|
||
}
|
||
|
||
try {
|
||
const csvData = await fetchLatestData();
|
||
|
||
// Save the raw CSV
|
||
writeFileSync(CSV_PATH, csvData);
|
||
|
||
const lines = csvData.trim().split('\n');
|
||
const recordCount = lines.length - 1; // minus header
|
||
|
||
console.log('✅ Data updated successfully\n');
|
||
console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
|
||
console.log('📊 CALIFORNIA WASTEWATER DATA UPDATE');
|
||
console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');
|
||
console.log(`📈 Total records: ${recordCount.toLocaleString()}`);
|
||
console.log(`📁 Saved to: California-Wastewater-Surveillance-Latest.csv\n`);
|
||
console.log('🦠 Pathogens tracked: SARS-CoV-2, Influenza, RSV, Mpox, Norovirus\n');
|
||
console.log('ℹ️ Source: California Health and Human Services Open Data Portal');
|
||
console.log('ℹ️ Updated: Daily\n');
|
||
|
||
} catch (error) {
|
||
console.error('❌ Error updating wastewater data:', error);
|
||
process.exit(1);
|
||
}
|