DataFrame Patterns¶

function patternSelectAssignSort(ASTX) {
  const df = ASTX.DataFrame.fromRecords([
    { id: 1, amount: 10, status: 'open' },
    { id: 2, amount: 25, status: 'closed' }
  ]);

  return df
    .select(['id', 'amount'])
    .assign({
      amount_x2: frame => frame.amount.multiply(2)
    })
    .sort('amount', false);
}

function patternSelectExpr(ASTX) {
  const df = ASTX.DataFrame.fromRecords([
    { id: 1, amount: 10, score: 81 },
    { id: 2, amount: 20, score: 63 }
  ]);

  return df.selectExpr({
    id: 'id',
    amount_x2: row => row.amount * 2,
    score_bucket: (columns, idx) => columns.score.array[idx] >= 80 ? 'high' : 'standard'
  });
}

function patternFromColumns(ASTX) {
  return ASTX.DataFrame.fromColumns({
    id: [1, 2, 3, 4],
    region: ['east', 'west', 'east', 'west'],
    amount: [10, 15, 25, 30]
  });
}

function patternDedupe(ASTX) {
  const df = ASTX.DataFrame.fromRecords([
    { region: 'east', amount: 10 },
    { region: 'east', amount: 20 },
    { region: 'west', amount: 30 }
  ]);

  const byAllColumns = df.dropDuplicates();
  const byRegionOnly = df.dropDuplicates(['region']);

  return { byAllColumns, byRegionOnly };
}

function patternMerge(ASTX) {
  const users = ASTX.DataFrame.fromRecords([
    { user_id: 1, name: 'Alice' },
    { user_id: 2, name: 'Bob' }
  ]);

  const scores = ASTX.DataFrame.fromRecords([
    { uid: 1, score: 88 },
    { uid: 2, score: 91 }
  ]);

  return users.merge(scores, 'inner', {
    leftOn: 'user_id',
    rightOn: 'uid'
  });
}

function patternGroupMetrics(ASTX) {
  const df = ASTX.DataFrame.fromRecords([
    { region: 'east', amount: 10 },
    { region: 'east', amount: 20 },
    { region: 'west', amount: 30 }
  ]);

  return df.groupBy(['region']).agg({
    amount: ['sum', 'mean', values => Math.max(...values)]
  });
}

function patternWindow(ASTX) {
  const df = ASTX.DataFrame.fromRecords([
    { region: 'east', event_ts: 1, amount: 10 },
    { region: 'east', event_ts: 2, amount: 15 },
    { region: 'west', event_ts: 1, amount: 5 }
  ]);

  return df
    .window({
      partitionBy: ['region'],
      orderBy: [{ column: 'event_ts', ascending: true }]
    })
    .assign({
      row_number: w => w.rowNumber(),
      amount_lag_1: w => w.col('amount').lag(1),
      amount_running_sum: w => w.col('amount').running('sum')
    });
}

function patternOutput(ASTX) {
  const df = ASTX.DataFrame.fromRecords([
    { id: 1, amount: 10 },
    { id: 2, amount: 20 }
  ]);

  return {
    markdown: df.toMarkdown(),
    prettyJson: df.toJson({ indent: 2 }),
    newlineJson: df.toJson({ multiline: true })
  };
}