All posts tagged elasticsearch

# in elasticsearch.yml
bootstrap.memory_lock: true
cluster.name: albedo
discovery.type: single-node
http.host: 0.0.0.0
node.name: ${HOSTNAME}
xpack.security.enabled: false

# in docker-compose.yml
version: "3"
services:
  django:
    build: .
    hostname: django
    working_dir: /app
    env_file: .docker-assets/django.env
    command: .docker-assets/django_start.sh
    ports:
      - 8000:8000
    volumes:
      - ".:/app"
      - "../albedo-vendors/bin:/usr/local/bin"
      - "../albedo-vendors/dist-packages:/usr/local/lib/python3.5/dist-packages"
    links:
      - mysql
      - elasticsearch
  mysql:
    image: vinta/mysql:5.7
    hostname: mysql
    env_file: .docker-assets/mysql.env
    command: mysqld --character-set-server=utf8 --collation-server=utf8_unicode_ci
    ports:
      - 3306:3306
  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:5.6.2
    ports:
      - 9200:9200
      - 9300:9300
    volumes:
      - "./.docker-assets/elasticsearch.yml:/usr/share/elasticsearch/config/elasticsearch.yml"
    environment:
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"

$ docker-compose up

from elasticsearch.helpers import bulk
from elasticsearch_dsl import analyzer
from elasticsearch_dsl import Date, Integer, Keyword, Text, Boolean
from elasticsearch_dsl import Index, DocType
from elasticsearch_dsl.connections import connections

client = connections.create_connection(hosts=['elasticsearch'])

repo_index = Index('repo')
repo_index.settings(
    number_of_shards=1,
    number_of_replicas=0
)

text_analyzer = analyzer(
    'text_analyzer',
    char_filter=["html_strip"],
    tokenizer="standard",
    filter=["asciifolding", "lowercase", "snowball", "stop"]
)
repo_index.analyzer(text_analyzer)

@repo_index.doc_type
class RepoInfoDoc(DocType):
    owner_id = Keyword()
    owner_username = Keyword()
    owner_type = Keyword()
    name = Text(text_analyzer, fields={'raw': Keyword()})
    full_name = Text(text_analyzer, fields={'raw': Keyword()})
    description = Text(text_analyzer)
    language = Keyword()
    created_at = Date()
    updated_at = Date()
    pushed_at = Date()
    homepage = Keyword()
    size = Integer()
    stargazers_count = Integer()
    forks_count = Integer()
    subscribers_count = Integer()
    fork = Boolean()
    has_issues = Boolean()
    has_projects = Boolean()
    has_downloads = Boolean()
    has_wiki = Boolean()
    has_pages = Boolean()
    open_issues_count = Integer()
    topics = Keyword(multi=True)

    class Meta:
        index = repo_index._name

    @classmethod
    def bulk_save(cls, documents):
        dicts = (d.to_dict(include_meta=True) for d in documents)
        return bulk(client, dicts)

    def save(self, **kwargs):
        return super(RepoInfoDoc, self).save(**kwargs)

RepoInfoDoc.init()

from django.core.management.base import BaseCommand

from app.mappings import RepoInfoDoc
from app.models import RepoInfo

class Command(BaseCommand):
    def handle(self, *args, **options):
        def batch_qs(qs, batch_size=500):
            total = qs.count()
            for start in range(0, total, batch_size):
                end = min(start + batch_size, total)
                yield (start, end, total, qs[start:end])

        large_qs = RepoInfo.objects.filter(stargazers_count__gte=10, stargazers_count__lte=290000, fork=False)
        for start, end, total, qs_chunk in batch_qs(large_qs):
            documents = []
            for repo_info in qs_chunk:
                repo_info_doc = RepoInfoDoc()
                repo_info_doc.meta.id = repo_info.id
                repo_info_doc.owner_id = repo_info.owner_id
                repo_info_doc.owner_username = repo_info.owner_username
                repo_info_doc.owner_type = repo_info.owner_type
                repo_info_doc.name = repo_info.name
                repo_info_doc.full_name = repo_info.full_name
                repo_info_doc.description = repo_info.description
                repo_info_doc.language = repo_info.language
                repo_info_doc.created_at = repo_info.created_at
                repo_info_doc.updated_at = repo_info.updated_at
                repo_info_doc.pushed_at = repo_info.pushed_at
                repo_info_doc.homepage = repo_info.homepage
                repo_info_doc.size = repo_info.size
                repo_info_doc.stargazers_count = repo_info.stargazers_count
                repo_info_doc.forks_count = repo_info.forks_count
                repo_info_doc.subscribers_count = repo_info.subscribers_count
                repo_info_doc.fork = repo_info.fork
                repo_info_doc.has_issues = repo_info.has_issues
                repo_info_doc.has_projects = repo_info.has_projects
                repo_info_doc.has_downloads = repo_info.has_downloads
                repo_info_doc.has_wiki = repo_info.has_wiki
                repo_info_doc.has_pages = repo_info.has_pages
                repo_info_doc.open_issues_count = repo_info.open_issues_count
                repo_info_doc.topics = repo_info.topics

                documents.append(repo_info_doc)

            RepoInfoDoc.bulk_save(documents)

import org.apache.http.HttpHost
import org.elasticsearch.client.{RestClient, RestHighLevelClient}

val lowClient = RestClient.builder(new HttpHost("127.0.0.1", 9200, "http")).build()
val highClient = new RestHighLevelClient(lowClient)

val userRecommendedItemDF = userDF
  .flatMap {
    case (userId: Int) => {
      val itemIds = selectUserStarredRepos(userId)

      val lowClient = RestClient.builder(new HttpHost("127.0.0.1", 9200, "http")).build()
      val highClient = new RestHighLevelClient(lowClient)

      val fields = Array("description", "full_name", "language", "topics")
      val texts = Array("")
      val items = itemIds.map((itemId: Int) => new Item("repo", "repo_info_doc", itemId.toString))
      val queryBuilder = moreLikeThisQuery(fields, texts, items)
        .minTermFreq(1)
        .maxQueryTerms(20)

      val searchSourceBuilder = new SearchSourceBuilder()
      searchSourceBuilder.query(queryBuilder)
      searchSourceBuilder.from(0)
      searchSourceBuilder.size($(topK))

      val searchRequest = new SearchRequest()
      searchRequest.indices("repo")
      searchRequest.types("repo_info_doc")
      searchRequest.source(searchSourceBuilder)

      val searchResponse = highClient.search(searchRequest)
      val hits = searchResponse.getHits
      val searchHits = hits.getHits

      val userItemScoreTuples = searchHits.map((searchHit: SearchHit) => {
        val itemId = searchHit.getId.toInt
        val score = searchHit.getScore
        (userId, itemId, score)
      })

      lowClient.close()

      userItemScoreTuples
    }
  }
  .toDF($(userCol), $(itemCol), $(scoreCol))
  .withColumn($(sourceCol), lit(source))

userRecommendedItemDF.show()
// +-------+--------+---------+-------+
// |user_id|repo_id |score    |source |
// +-------+--------+---------+-------+
// |652070 |26152923|44.360096|content|
// |652070 |28451314|38.752697|content|
// |652070 |16175350|35.676353|content|
// |652070 |10885469|30.280012|content|
// |652070 |24037308|28.488512|content|
// +-------+--------+---------+-------+