// The included visits.csv fixture has six synthetic records, not patient data.
// Run from the directory that contains examples/fixtures/visits.csv.
import aner.data
import aner.tensor

var schema = data.schema()
schema = data.column(schema, "record_id", "String", false)
schema = data.column(schema, "age", "Int64", true)
schema = data.column(schema, "measurement", "Float64", true)
schema = data.column(schema, "site", "String", false)
schema = data.column(schema, "eligible", "Bool", false)
let source = data.scan_csv("examples/fixtures/visits.csv", schema, missing: "NA")
let adults = data.where_ge(source, "age", value: 18)
let selected = data.include(data.select(adults, "measurement"), "age")
let report = data.summarize(selected, max_bytes: 1048576, batch_rows: 2)
print("Validated, selected, present and missing measurement counts")
print(data.scanned_rows(report))
print(data.rows(report))
print(data.valid(report, "measurement"))
print(data.missing(report, "measurement"))
print("Mean of present measurements")
print(data.mean(report, "measurement"))
let table = data.collect(data.where_present(selected, "measurement"),
    max_rows: 100, max_bytes: 1048576, batch_rows: 2)
print("Collected schema")
print(data.column_name(table, 0))
print(data.column_type(table, 0))
print(data.column_nullable(table, 0))
let values = data.to_tensor(table, max_bytes: 1048576)
print("Complete numeric tensor shape and first measurement")
print(tensor.rows(values))
print(tensor.cols(values))
print(tensor.value(values, 0, 0))