Histogram (v4beta1)

Cloud Talent Solution allows you to get a histogram representation of the number of jobs associated with a given search. A histogram search returns a count of all jobs that match a particular query, broken down by the requested SearchMode. For example, a histogram search could return the number of jobs per employment type (full-time, part-time, and so on) that exist in Mountain View, CA.

Histograms are generally run in parallel with a search call, using the same JobQuery and the same requestMetadata.

The histogram is defined by the histogramQuery field, a single string expression. For details on the functions available for histogram queries, see the histogramQuery documentation.

Retrieving a histogram

The following code sample returns histogram results:

Go

To learn how to install and use the client library for CTS, see CTS client libraries. For more information, see the CTS Go API reference documentation.

To authenticate to CTS, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import (
	"context"
	"fmt"
	"io"

	talent "cloud.google.com/go/talent/apiv4beta1"
	"google.golang.org/api/iterator"
	talentpb "google.golang.org/genproto/googleapis/cloud/talent/v4beta1"
)

// histogramSearch searches for jobs with histogram queries.
func histogramSearch(w io.Writer, projectID, companyID string) error {
	ctx := context.Background()

	// Initialize a jobService client.
	c, err := talent.NewJobClient(ctx)
	if err != nil {
		fmt.Printf("talent.NewJobClient: %v\n", err)
		return err
	}

	// Construct a searchJobs request.
	req := &talentpb.SearchJobsRequest{
		Parent: fmt.Sprintf("projects/%s", projectID),
		// Make sure to set the RequestMetadata the same as the associated
		// search request.
		RequestMetadata: &talentpb.RequestMetadata{
			// Make sure to hash your userId.
			UserId: "HashedUsrID",
			// Make sure to hash the sessionId.
			SessionId: "HashedSessionID",
			// Domain of the website where the search is conducted.
			Domain: "www.googlesample.com",
		},
		HistogramQueries: []*talentpb.HistogramQuery{
			{
				// More info on histogram facets, constants, and built-in functions:
				// https://godoc.org/google.golang.org/genproto/googleapis/cloud/talent/v4beta1#SearchJobsRequest
				HistogramQuery: "count(base_compensation, [bucket(12, 20)])",
			},
		},
	}
	if companyID != "" {
		req.JobQuery = &talentpb.JobQuery{
			CompanyNames: []string{fmt.Sprintf("projects/%s/companies/%s", projectID, companyID)},
		}
	}

	it := c.SearchJobs(ctx, req)

	for {
		resp, err := it.Next()
		if err == iterator.Done {
			return nil
		}
		if err != nil {
			fmt.Printf("it.Next: %v\n", err)
			return err
		}
		fmt.Fprintf(w, "Job: %q\n", resp.Job.GetName())
	}
}

Java

For more on installing and creating a Cloud Talent Solution client, see Cloud Talent Solution Client Libraries.

import com.google.cloud.talent.v4beta1.HistogramQuery;
import com.google.cloud.talent.v4beta1.Job;
import com.google.cloud.talent.v4beta1.JobServiceClient;
import com.google.cloud.talent.v4beta1.RequestMetadata;
import com.google.cloud.talent.v4beta1.SearchJobsRequest;
import com.google.cloud.talent.v4beta1.SearchJobsResponse;
import com.google.cloud.talent.v4beta1.TenantName;
import java.io.IOException;

public class HistogramSearchJobs {

  public static void searchJobs() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String tenantId = "your-tenant-id";
    String query = "count(base_compensation, [bucket(12, 20)])";
    searchJobs(projectId, tenantId, query);
  }

  // Search Jobs with histogram queries.
  public static void searchJobs(String projectId, String tenantId, String query)
      throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (JobServiceClient jobServiceClient = JobServiceClient.create()) {
      TenantName parent = TenantName.of(projectId, tenantId);

      String domain = "http://www.jobUrl.com";
      String sessionId = "Hashed session identifier";
      String userId = "Hashed user identifier";
      RequestMetadata requestMetadata =
          RequestMetadata.newBuilder()
              .setDomain(domain)
              .setSessionId(sessionId)
              .setUserId(userId)
              .build();
      HistogramQuery histogramQueriesElement =
          HistogramQuery.newBuilder().setHistogramQuery(query).build();
      SearchJobsRequest request =
          SearchJobsRequest.newBuilder()
              .setParent(parent.toString())
              .setRequestMetadata(requestMetadata)
              .addHistogramQueries(histogramQueriesElement)
              .build();

      for (SearchJobsResponse.MatchingJob responseItem :
          jobServiceClient.searchJobs(request).iterateAll()) {
        System.out.format("Job summary: %s%n", responseItem.getJobSummary());
        System.out.format("Job title snippet: %s%n", responseItem.getJobTitleSnippet());
        Job job = responseItem.getJob();
        System.out.format("Job name: %s%n", job.getName());
        System.out.format("Job title: %s%n", job.getTitle());
      }
    }
  }
}

Python

For more on installing and creating a Cloud Talent Solution client, see Cloud Talent Solution Client Libraries.

from google.cloud import talent


def search_jobs(project_id, tenant_id, query):
    """
    Search Jobs with histogram queries

    Args:
      query Histogram query
      More info on histogram facets, constants, and built-in functions:
      https://godoc.org/google.golang.org/genproto/googleapis/cloud/talent/v4beta1#SearchJobsRequest
    """

    client = talent.JobServiceClient()

    # project_id = 'Your Google Cloud Project ID'
    # tenant_id = 'Your Tenant ID (using tenancy is optional)'
    # query = 'count(base_compensation, [bucket(12, 20)])'

    if isinstance(project_id, bytes):
        project_id = project_id.decode("utf-8")
    if isinstance(tenant_id, bytes):
        tenant_id = tenant_id.decode("utf-8")
    if isinstance(query, bytes):
        query = query.decode("utf-8")
    parent = f"projects/{project_id}/tenants/{tenant_id}"
    domain = "www.example.com"
    session_id = "Hashed session identifier"
    user_id = "Hashed user identifier"
    request_metadata = {"domain": domain, "session_id": session_id, "user_id": user_id}
    histogram_queries_element = {"histogram_query": query}
    histogram_queries = [histogram_queries_element]

    # Iterate over all results
    results = []
    request = talent.SearchJobsRequest(
        parent=parent,
        request_metadata=request_metadata,
        histogram_queries=histogram_queries,
    )
    for response_item in client.search_jobs(request=request).matching_jobs:
        print("Job summary: {response_item.job_summary}")
        print("Job title snippet: {response_item.job_title_snippet}")
        job = response_item.job
        results.append(job)
        print("Job name: {job.name}")
        print("Job title: {job.title}")
    return results

Relevance thresholding

Histogram requests do not use relevance thresholding. To ensure that the counts are consistent between a histogram search and an identical job search, disableKeywordMatch in the job search must be false.