### **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’**.

        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

 *
 * 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

					<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.

    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.

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;
}

        "//tensorflow/core/grappler:grappler_item",
        "//tensorflow/core/grappler:grappler_item_builder",
        "//tensorflow/core/kernels:data_service_ops",
        "//tensorflow/core/kernels:dataset_ops",
        "//tensorflow/core/platform:logging",
        "//tensorflow/core/platform:path",
        "//tensorflow/core/platform:stacktrace_handler",
        "//tensorflow/core/platform:statusor",

			if err.Error() != test.ExpectedErr.Error() {
				t.Errorf("Test %d: got error '%v' - want error '%v'", i, err, test.ExpectedErr)
			}
		}
		if !bytes.Equal(dataKey, test.DataKey) {
			t.Errorf("Test %d: got data key '%v' - want data key '%v'", i, dataKey, test.DataKey)
		}
		if keyID != test.KeyID {
			t.Errorf("Test %d: got key-ID '%v' - want key-ID '%v'", i, keyID, test.KeyID)
		}

				notZero = notZero || !zero
			}

			if notZero {
				dataKey := utils.ToStringKey(fieldValues...)
				if _, ok := dataResults[dataKey]; !ok {
					results = append(results, fieldValues)
					dataResults[dataKey] = []reflect.Value{elem}
				} else {
					dataResults[dataKey] = append(dataResults[dataKey], elem)
				}
			}
		}
	}

	return dataResults, results
}