### **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’**.

 *
 * Mappings Data (4,719 bytes)
 * ===========================
 *
 * This is UTF-8 character data. It is indexed into by b2b3 in the ranges dataset.
 *
 * Mappings may overlap.
 *
 * ASCII-Only
 * ==========
 *
 * Neither the section index nor the ranges data use bit 0x80 anywhere. That means the data is

    return {};
  }
  const auto& fdef_lib = gdef.library();
  if (fdef_lib.gradient_size() > 0) {
    status->status = tensorflow::errors::Internal(
        "GradientDef is not supported in reading Dataset related functions: ",
        text_proto);
    return {};
  }
  std::vector<UniqueFuncPtr> ret;
  for (const FunctionDef& fdef : fdef_lib.function()) {
    // Make a copy so that we can mutate it.

					<keyring>${gpg.keyring}</keyring>
					key>${gpg.key}</key>
					<passphrase>${gpg.passphrase}</passphrase>
					<signMethod>${deb.sign.method}</signMethod>
					-->
					<dataSet>
						<!-- Add app directory -->
						<data>
							<type>directory</type>
							<src>${project.build.directory}/fess</src>
							<excludes>**/fess_config.properties,**/fess_env*.properties,**/tika.xml</excludes>

 *  Fix: Recover gracefully when a cache entry's certificate is corrupted.

 *  Fix: Fail permanently when there's a failure loading the bundled public suffix database.
    This is the dataset that powers `HttpUrl.topPrivateDomain()`.

 *  Fix: Immediately update the connection's flow control window instead of waiting for the
    receiving stream to process it.

message FlockerVolumeSource {
  // datasetName is Name of the dataset stored as metadata -> name on the dataset for Flocker
  // should be considered as deprecated
  // +optional
  optional string datasetName = 1;

  // datasetUUID is the UUID of the dataset. This is unique identifier of a Flocker dataset
  // +optional
  optional string datasetUUID = 2;
}

    assertThat(TWO_VALUES_PAIRED_STATS.populationCovariance())
        .isWithin(ALLOWED_ERROR)
        .of(TWO_VALUES_SUM_OF_PRODUCTS_OF_DELTAS / 2);
    // For datasets of many double values, we test many combinations of finite and non-finite
    // x-values:
    for (ManyValues values : ALL_MANY_VALUES) {
      PairedStats stats = createPairedStatsOf(values.asIterable(), OTHER_MANY_VALUES);

    assertThat(Stats.of(NEGATIVE_INFINITY).mean()).isNegativeInfinity();
    assertThat(Stats.of(NaN).mean()).isNaN();
    assertThat(TWO_VALUES_STATS.mean()).isWithin(ALLOWED_ERROR).of(TWO_VALUES_MEAN);
    // For datasets of many double values created from an array, we test many combinations of finite
    // and non-finite values:
    for (ManyValues values : ALL_MANY_VALUES) {
      double mean = Stats.of(values.asArray()).mean();

    assertThat(manyValuesAccumulatorByAddAllPartitionedPairedStats.populationCovariance())
        .isWithin(ALLOWED_ERROR)
        .of(MANY_VALUES_SUM_OF_PRODUCTS_OF_DELTAS / MANY_VALUES_COUNT);
    // For datasets of many double values, we test many combinations of finite and non-finite
    // x-values:
    for (ManyValues values : ALL_MANY_VALUES) {
      PairedStatsAccumulator accumulator =

    assertThat(manyValuesAccumulatorByAddAllPartitionedPairedStats.populationCovariance())
        .isWithin(ALLOWED_ERROR)
        .of(MANY_VALUES_SUM_OF_PRODUCTS_OF_DELTAS / MANY_VALUES_COUNT);
    // For datasets of many double values, we test many combinations of finite and non-finite
    // x-values:
    for (ManyValues values : ALL_MANY_VALUES) {
      PairedStatsAccumulator accumulator =