deequ_blog_example.cs

using deequ;
using deequ.Checks;
using deequ.Extensions;
using Microsoft.Spark.Sql;

namespace DeequExample
{
    class Program
    {
        static void Main(string[] args)
        {
            SparkSession spark = SparkSession.Builder().GetOrCreate();
            DataFrame data = spark.Read().Json("inventory.json");

            data.Show();

            VerificationResult verificationResult = new VerificationSuite()
                .OnData(data)
                .AddCheck(
                    new Check(CheckLevel.Error, "integrity checks")
                        .HasSize(value => value == 5)
                        .IsComplete("id")
                        .IsUnique("id")
                        .IsComplete("productName")
                        .IsContainedIn("priority", new[] { "high", "low" })
                        .IsNonNegative("numViews")
                )
                .AddCheck(
                    new Check(CheckLevel.Warning, "distribution checks")
                        .ContainsURL("description", value => value >= .5)
                )
                .Run();

            verificationResult.Debug();
        }
    }
}