Substrate/get-california-wastewater-data

#!/usr/bin/env bun

/**
 * Get California Wastewater Data
 *
 * Analyzes trends and provides risk assessment for going out in public
 */

import { readFileSync } from 'fs';
import { join } from 'path';

const CSV_PATH = join(__dirname, 'Data/Bay-Area-COVID-Wastewater/California-Wastewater-Surveillance-Latest.csv');

interface WastewaterRecord {
  sample_collect_date: string;
  pcr_target: string;
  pcr_target_avg_conc: string;
  reporting_jurisdiction: string;
  county_names: string;
  pcr_target_units: string;
}

function parseCSV(csvContent: string): WastewaterRecord[] {
  const lines = csvContent.trim().split('\n');
  const headers = lines[0].split(',');

  const dateIdx = headers.indexOf('sample_collect_date');
  const targetIdx = headers.indexOf('pcr_target');
  const concIdx = headers.indexOf('pcr_target_avg_conc');
  const jurisdIdx = headers.indexOf('reporting_jurisdiction');
  const countyIdx = headers.indexOf('county_names');
  const unitsIdx = headers.indexOf('pcr_target_units');

  const records: WastewaterRecord[] = [];

  for (let i = 1; i < lines.length; i++) {
    const line = lines[i];
    if (!line.trim()) continue;

    const values = line.split(',');

    const record = {
      sample_collect_date: values[dateIdx] || '',
      pcr_target: values[targetIdx] || '',
      pcr_target_avg_conc: values[concIdx] || '',
      reporting_jurisdiction: values[jurisdIdx] || '',
      county_names: values[countyIdx] || '',
      pcr_target_units: values[unitsIdx] || ''
    };

    if (record.reporting_jurisdiction === 'CA' &&
        record.pcr_target &&
        record.pcr_target_avg_conc &&
        !isNaN(parseFloat(record.pcr_target_avg_conc))) {
      records.push(record);
    }
  }

  return records;
}

function formatDate(dateStr: string): string {
  const date = new Date(dateStr);
  return date.toLocaleDateString('en-US', {
    month: 'short',
    day: 'numeric',
    year: 'numeric'
  });
}

function analyzePathogenTrends(records: WastewaterRecord[], pathogenName: string) {
  const now = new Date();
  const oneYearAgo = new Date(now.getTime() - 365 * 24 * 60 * 60 * 1000);
  const threeMonthsAgo = new Date(now.getTime() - 90 * 24 * 60 * 60 * 1000);
  const oneMonthAgo = new Date(now.getTime() - 30 * 24 * 60 * 60 * 1000);
  const twoWeeksAgo = new Date(now.getTime() - 14 * 24 * 60 * 60 * 1000);

  const relevantRecords = records.filter(r =>
    r.pcr_target.toLowerCase() === pathogenName.toLowerCase()
  );

  const dataByPeriod = {
    recent: [] as number[],
    twoWeeks: [] as number[],
    oneMonth: [] as number[],
    threeMonths: [] as number[],
    year: [] as number[],
    latestDate: ''
  };

  for (const record of relevantRecords) {
    const date = new Date(record.sample_collect_date);
    const value = parseFloat(record.pcr_target_avg_conc);

    if (date >= oneYearAgo) {
      dataByPeriod.year.push(value);

      if (date >= threeMonthsAgo) {
        dataByPeriod.threeMonths.push(value);

        if (date >= oneMonthAgo) {
          dataByPeriod.oneMonth.push(value);

          if (date >= twoWeeksAgo) {
            dataByPeriod.twoWeeks.push(value);
            dataByPeriod.recent.push(value);
          }
        }
      }

      if (!dataByPeriod.latestDate || record.sample_collect_date > dataByPeriod.latestDate) {
        dataByPeriod.latestDate = record.sample_collect_date;
      }
    }
  }

  const avg = (arr: number[]) => arr.length ? arr.reduce((a, b) => a + b, 0) / arr.length : 0;
  const percentChange = (current: number, previous: number) =>
    previous ? ((current - previous) / previous * 100) : 0;

  return {
    current: avg(dataByPeriod.recent),
    twoWeeksAvg: avg(dataByPeriod.twoWeeks),
    oneMonthAvg: avg(dataByPeriod.oneMonth),
    threeMonthsAvg: avg(dataByPeriod.threeMonths),
    yearAvg: avg(dataByPeriod.year),
    yearMin: Math.min(...dataByPeriod.year),
    yearMax: Math.max(...dataByPeriod.year),
    latestDate: dataByPeriod.latestDate,
    trend2wk: percentChange(avg(dataByPeriod.recent), avg(dataByPeriod.twoWeeks)),
    trend1mo: percentChange(avg(dataByPeriod.recent), avg(dataByPeriod.oneMonth)),
    sampleCount: dataByPeriod.recent.length
  };
}

function generateYearGraph(records: WastewaterRecord[], pathogenName: string, title: string): string {
  const now = new Date();
  const oneYearAgo = new Date(now.getTime() - 365 * 24 * 60 * 60 * 1000);

  // Group data by month
  const monthlyData: { [key: string]: number[] } = {};

  for (const record of records) {
    if (record.pcr_target.toLowerCase() !== pathogenName.toLowerCase()) continue;

    const date = new Date(record.sample_collect_date);
    if (date < oneYearAgo) continue;

    const monthKey = `${date.getFullYear()}-${String(date.getMonth() + 1).padStart(2, '0')}`;
    const value = parseFloat(record.pcr_target_avg_conc);

    if (!monthlyData[monthKey]) {
      monthlyData[monthKey] = [];
    }
    monthlyData[monthKey].push(value);
  }

  // Calculate monthly averages
  const months: { label: string; value: number }[] = [];
  const sortedMonths = Object.keys(monthlyData).sort();

  for (const month of sortedMonths) {
    const avg = monthlyData[month].reduce((a, b) => a + b, 0) / monthlyData[month].length;
    const [year, monthNum] = month.split('-');
    const date = new Date(parseInt(year), parseInt(monthNum) - 1, 1);
    const label = date.toLocaleDateString('en-US', { month: 'short', year: '2-digit' });
    months.push({ label, value: avg });
  }

  if (months.length === 0) {
    return '   No data available for graphing\n';
  }

  // Find max value for scaling
  const maxValue = Math.max(...months.map(m => m.value));
  const graphWidth = 50;

  let graph = `\n   ${title}\n\n`;

  // Generate bars with trend arrows
  for (let i = 0; i < months.length; i++) {
    const month = months[i];
    const barLength = maxValue > 0 ? Math.round((month.value / maxValue) * graphWidth) : 0;
    const bar = '█'.repeat(barLength);
    const valueStr = month.value >= 1000 ? `${(month.value / 1000).toFixed(1)}k` : month.value.toFixed(0);

    // Calculate trend arrow
    let arrow = ' ';
    if (i > 0) {
      const prevValue = months[i - 1].value;
      const change = ((month.value - prevValue) / prevValue) * 100;
      if (change > 10) {
        arrow = '⬆️';
      } else if (change < -10) {
        arrow = '⬇️';
      } else {
        arrow = '➡️';
      }
    }

    graph += `   ${month.label} │${bar} ${valueStr} ${arrow}\n`;
  }

  return graph + '\n';
}

function getRiskLevel(covidData: any, rsvData: any, fluData: any) {
  // Risk scoring based on relative levels
  let riskScore = 0;
  let factors: string[] = [];

  // COVID risk
  if (covidData.current > 0) {
    const covidPercentile = (covidData.current - covidData.yearMin) / (covidData.yearMax - covidData.yearMin);
    if (covidPercentile > 0.7) {
      riskScore += 3;
      factors.push('COVID levels HIGH (top 30% of year)');
    } else if (covidPercentile > 0.4) {
      riskScore += 2;
      factors.push('COVID levels MODERATE');
    } else {
      riskScore += 1;
      factors.push('COVID levels LOW');
    }

    if (covidData.trend2wk > 20) {
      riskScore += 2;
      factors.push('COVID rapidly increasing');
    } else if (covidData.trend2wk > 0) {
      riskScore += 1;
      factors.push('COVID slowly increasing');
    }
  }

  // RSV risk
  if (rsvData.current > 0) {
    const rsvPercentile = (rsvData.current - rsvData.yearMin) / (rsvData.yearMax - rsvData.yearMin);
    if (rsvPercentile > 0.7) {
      riskScore += 2;
      factors.push('RSV levels HIGH');
    } else if (rsvPercentile > 0.4) {
      riskScore += 1;
      factors.push('RSV levels MODERATE');
    }
  }

  // Flu risk
  if (fluData.current > 0) {
    const fluPercentile = (fluData.current - fluData.yearMin) / (fluData.yearMax - fluData.yearMin);
    if (fluPercentile > 0.7) {
      riskScore += 2;
      factors.push('FLU levels HIGH');
    } else if (fluPercentile > 0.4) {
      riskScore += 1;
      factors.push('FLU levels MODERATE');
    }
  }

  let assessment = '';
  let emoji = '';
  let recommendation = '';

  if (riskScore <= 3) {
    assessment = 'LOW RISK';
    emoji = '🟢';
    recommendation = 'Generally safe to be in public. Standard precautions sufficient.';
  } else if (riskScore <= 6) {
    assessment = 'MODERATE RISK';
    emoji = '🟡';
    recommendation = 'Exercise caution in crowded indoor spaces. Consider masking in high-traffic areas.';
  } else if (riskScore <= 9) {
    assessment = 'HIGH RISK';
    emoji = '🟠';
    recommendation = 'Significant viral circulation. Recommend masking indoors and avoiding crowded spaces.';
  } else {
    assessment = 'VERY HIGH RISK';
    emoji = '🔴';
    recommendation = 'Multiple pathogens at elevated levels. Strong recommendation to mask and minimize public exposure.';
  }

  return { assessment, emoji, recommendation, factors, riskScore };
}

try {
  console.log('\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
  console.log('🦠 CALIFORNIA WASTEWATER SURVEILLANCE');
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  const csvContent = readFileSync(CSV_PATH, 'utf-8');
  const records = parseCSV(csvContent);

  const covidData = analyzePathogenTrends(records, 'sars-cov-2');
  const rsvData = analyzePathogenTrends(records, 'rsv');
  const fluData = analyzePathogenTrends(records, 'fluav'); // Influenza A

  console.log('📅 DATA STATUS\n');
  console.log(`📊 Latest data: ${formatDate(covidData.latestDate || rsvData.latestDate)}`);
  console.log(`📈 Analysis period: Past 12 months`);
  console.log(`🔬 Total samples: ${records.length.toLocaleString()}\n`);

  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  // COVID Analysis
  if (covidData.sampleCount > 0) {
    console.log('🦠 SARS-CoV-2 (COVID-19)\n');
    console.log(`   Current Level: ${covidData.current.toFixed(0)} copies/g`);
    console.log(`   12-Month Range: ${covidData.yearMin.toFixed(0)} - ${covidData.yearMax.toFixed(0)}`);
    console.log(`   12-Month Average: ${covidData.yearAvg.toFixed(0)}\n`);

    const trend2wk = covidData.trend2wk > 0 ? '⬆️' : covidData.trend2wk < 0 ? '⬇️' : '➡️';
    console.log(`   2-Week Trend: ${trend2wk} ${Math.abs(covidData.trend2wk).toFixed(1)}%`);

    const trend1mo = covidData.trend1mo > 0 ? '⬆️' : covidData.trend1mo < 0 ? '⬇️' : '➡️';
    console.log(`   1-Month Trend: ${trend1mo} ${Math.abs(covidData.trend1mo).toFixed(1)}%\n`);

    // COVID Graph
    console.log(generateYearGraph(records, 'sars-cov-2', '12-Month Trend (Monthly Averages)'));
  }

  // Flu Analysis
  if (fluData.sampleCount > 0) {
    console.log('🤧 INFLUENZA A\n');
    console.log(`   Current Level: ${fluData.current.toFixed(0)} copies/g`);
    console.log(`   12-Month Range: ${fluData.yearMin.toFixed(0)} - ${fluData.yearMax.toFixed(0)}`);
    console.log(`   12-Month Average: ${fluData.yearAvg.toFixed(0)}\n`);

    const trend2wk = fluData.trend2wk > 0 ? '⬆️' : fluData.trend2wk < 0 ? '⬇️' : '➡️';
    console.log(`   2-Week Trend: ${trend2wk} ${Math.abs(fluData.trend2wk).toFixed(1)}%`);

    const trend1mo = fluData.trend1mo > 0 ? '⬆️' : fluData.trend1mo < 0 ? '⬇️' : '➡️';
    console.log(`   1-Month Trend: ${trend1mo} ${Math.abs(fluData.trend1mo).toFixed(1)}%\n`);

    // Flu Graph
    console.log(generateYearGraph(records, 'fluav', '12-Month Trend (Monthly Averages)'));
  }

  // RSV Analysis
  if (rsvData.sampleCount > 0) {
    console.log('🤒 RSV (Respiratory Syncytial Virus)\n');
    console.log(`   Current Level: ${rsvData.current.toFixed(0)} copies/g`);
    console.log(`   12-Month Range: ${rsvData.yearMin.toFixed(0)} - ${rsvData.yearMax.toFixed(0)}`);
    console.log(`   12-Month Average: ${rsvData.yearAvg.toFixed(0)}\n`);

    const trend2wk = rsvData.trend2wk > 0 ? '⬆️' : rsvData.trend2wk < 0 ? '⬇️' : '➡️';
    console.log(`   2-Week Trend: ${trend2wk} ${Math.abs(rsvData.trend2wk).toFixed(1)}%`);

    const trend1mo = rsvData.trend1mo > 0 ? '⬆️' : rsvData.trend1mo < 0 ? '⬇️' : '➡️';
    console.log(`   1-Month Trend: ${trend1mo} ${Math.abs(rsvData.trend1mo).toFixed(1)}%\n`);

    // RSV Graph
    console.log(generateYearGraph(records, 'rsv', '12-Month Trend (Monthly Averages)'));
  }

  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  // Risk Assessment
  const risk = getRiskLevel(covidData, rsvData, fluData);

  console.log('🎯 RISK ASSESSMENT\n');
  console.log(`${risk.emoji} Overall Risk Level: ${risk.assessment}\n`);
  console.log('📋 Key Factors:');
  for (const factor of risk.factors) {
    console.log(`   • ${factor}`);
  }
  console.log();
  console.log('💡 RECOMMENDATION\n');
  console.log(`   ${risk.recommendation}\n`);

  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');
  console.log('ℹ️  Source: California Department of Public Health');
  console.log('ℹ️  Data: CHHS Open Data Portal (Updated Daily)');
  console.log('ℹ️  Analysis: 12-month trend comparison\n');

} catch (error) {
  if ((error as NodeJS.ErrnoException).code === 'ENOENT') {
    console.error('❌ Data file not found. Please run update first:\n');
    console.error('   ~/Library/Mobile\\ Documents/com~apple~CloudDocs/Projects/Substrate/Data/Bay-Area-COVID-Wastewater/update-wastewater-data\n');
  } else {
    console.error('❌ Error reading wastewater data:', error);
  }
  process.exit(1);
}