}

    public void test_setEcsEventDataset() {
        activityHelper.setEcsEventDataset("test-dataset");
        activityHelper.useEcsFormat = true;
        activityHelper.login(OptionalThing.empty());
        assertTrue(localLogMsg.get().contains("\"event.dataset\":\"test-dataset\""));
    }

    public void test_setEnvMap() {
        Map<String, String> testEnv = new HashMap<>();

        setEncoding((String) src.get(ENCODING));
        final String dataStr = (String) src.get(DATA);
        if (dataStr != null) {
            try {
                setData(Base64Util.decode(dataStr));
            } catch (final Exception e) {
                throw new OpenSearchAccessException("data: " + dataStr, e);
            }
        }
    }

    /**

      for (int j = 0; j < datasetSize; j++) {
        datasets[i][j] = rng.nextDouble();
      }
    }
  }

  private double[] dataset(int i) {
    // We must test on a fresh clone of the dataset each time. Doing sorts and quickselects on a
    // dataset which is already sorted or partially sorted is cheating.
    return datasets[i & 0xFF].clone();
  }

  @Benchmark
  double median(int reps) {

   *
   * <p>This is guaranteed to return zero if the dataset contains only exactly one finite value. It
   * is not guaranteed to return zero when the dataset consists of the same value multiple times,
   * due to numerical errors. However, it is guaranteed never to return a negative result.
   *
   * <h3>Non-finite values</h3>
   *
   * <p>If the dataset contains any non-finite values ({@link Double#POSITIVE_INFINITY}, {@link

     */
    public void setEcsServiceName(final String ecsServiceName) {
        this.ecsServiceName = ecsServiceName;
    }

    /**
     * Set the ECS event dataset.
     * @param ecsEventDataset The ECS event dataset.
     */
    public void setEcsEventDataset(final String ecsEventDataset) {
        this.ecsEventDataset = ecsEventDataset;
    }

   *
   * <p>This is guaranteed to return zero if the dataset contains a single pair of finite values. It
   * is not guaranteed to return zero when the dataset consists of the same pair of values multiple
   * times, due to numerical errors.
   *
   * <h3>Non-finite values</h3>
   *
   * <p>If the dataset contains any non-finite values ({@link Double#POSITIVE_INFINITY}, {@link

*   `tf.data`

    *   `tf.data.Dataset.zip` now supports Python-style zipping, i.e. `Dataset.zip(a, b, c)`.

MinIO's Object Lambda implementation allows for transforming your data to serve unique data format requirements for each application. For example, a dataset created by an ecommerce application might include personally identifiable information (PII). When the same data is processed for analytics, PII should be redacted. However, if the same dataset is used for a marketing campaign, you might need to enrich the data with additional details, such as information from the customer loyalty database.

        print(statsDetails['BytesScanned'])
        print("Stats details bytesProcessed: ")
        print(statsDetails['BytesProcessed'])
```

## 4. Run the Program

Upload a sample dataset to MinIO using the following commands.

```sh
curl "https://population.un.org/wpp/Download/Files/1_Indicators%20(Standard)/CSV_FILES/WPP2019_TotalPopulationBySex.csv" > TotalPopulation.csv
mc mb myminio/mycsvbucket

### **4.2 WordCount**

WordCount is a simple program that counts how often a word occurs in a text file. The code builds a dataset of (String, Int) pairs called counts, and saves the dataset to a file.

The following example submits WordCount code to the Scala shell. Select an input file for the Spark WordCount example. We can use any text file as input.

- Login as user **‘spark’**.