Giter Club home page Giter Club logo

elasticsearch-workshop's Introduction

ElasticSearch Workshop

Hosted by Amine M. Boulouma, contact and questions: amine.boulouma.com

Installing python client

pip install elasticsearch

Importing packages

# Import packages

from elasticsearch import Elasticsearch

Configurating ElasticSearch

# Elastic search configuation

es = Elasticsearch(HOST="http://localhost", PORT=9200)
es = Elasticsearch()

Creating an index

# Creating index

es.indices.create(index="first_index")
{'acknowledged': True, 'shards_acknowledged': True, 'index': 'first_index'}

# Looking if the index exists

es.indices.exists(index="first_index")
True

Deleting an index

# Delete index

es.indices.delete(index="first_index")
{'acknowledged': True}

es.indices.exists(index="first_index")
False

Inserting and getting data

# Inserting data

doc_1 = {"city": "Paris", "country": "France"}
doc_2 = {"city": "Vienna", "country": "Austria"}
doc_3 = {"city": "London", "country": "England"}

es.index(index="cities", doc_type="places", id=1, body=doc_1)
{'_index': 'cities',
 '_type': 'places',
 '_id': '1',
 '_version': 2,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 6,
 '_primary_term': 1}

es.index(index="cities", doc_type="places", id=2, body=doc_2)
{'_index': 'cities',
 '_type': 'places',
 '_id': '2',
 '_version': 3,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 7,
 '_primary_term': 1}

es.index(index="cities", doc_type="places", id=3, body=doc_3)
{'_index': 'cities',
 '_type': 'places',
 '_id': '3',
 '_version': 4,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 8,
 '_primary_term': 1}

# Getting the data

res = es.get(index="cities", doc_type="places", id=1)

res
{'_index': 'cities',
 '_type': 'places',
 '_id': '1',
 '_version': 2,
 '_seq_no': 6,
 '_primary_term': 1,
 'found': True,
 '_source': {'city': 'Paris', 'country': 'France'}}

# Get the data which is present in the _source key

res["_source"]
{'city': 'Paris', 'country': 'France'}

Search query and matching documents

# Creating our data

doc_1 = {"sentence":"Hack COVID-19 is amazing!"}
doc_2 = {"sentence":"Hack-Quarantine is stunning!"}

es.index(index="english", doc_type="sentences", id=1, body=doc_1)
es.index(index="english", doc_type="sentences", id=2, body=doc_2)
{'_index': 'english',
 '_type': 'sentences',
 '_id': '2',
 '_version': 9,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 18,
 '_primary_term': 1}

# Creating our query

## Match query 

body = {
    "from":0,
    "size":0,
    "query": {
        "match": {
            "sentence":"Hack"
        }
    }
}

res = es.search(index="english", body=body)
res
{'took': 2,
 'timed_out': False,
 '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0},
 'hits': {'total': {'value': 3, 'relation': 'eq'},
  'max_score': None,
  'hits': []}}

body = {
    "from":0,
    "size":2,
    "query": {
        "match": {
            "sentence":"Hack"
        }
    }
}

res = es.search(index="english", body=body)
res
{'took': 2,
 'timed_out': False,
 '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0},
 'hits': {'total': {'value': 3, 'relation': 'eq'},
  'max_score': 0.13786995,
  'hits': [{'_index': 'english',
    '_type': 'sentences',
    '_id': '2',
    '_score': 0.13786995,
    '_source': {'sentence': 'Hack-Quarantine is stunning!'}},
   {'_index': 'english',
    '_type': 'sentences',
    '_id': '3',
    '_score': 0.13786995,
    '_source': {'sentence': 'Hack nCov is great!'}}]}}

body = {
    "from":0,
    "size":2,
    "query": {
        "match": {
            "sentence":"Hack Quarantine"
        }
    }
}

res = es.search(index="english", body=body)
res
{'took': 3,
 'timed_out': False,
 '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0},
 'hits': {'total': {'value': 3, 'relation': 'eq'},
  'max_score': 1.1505672,
  'hits': [{'_index': 'english',
    '_type': 'sentences',
    '_id': '2',
    '_score': 1.1505672,
    '_source': {'sentence': 'Hack-Quarantine is stunning!'}},
   {'_index': 'english',
    '_type': 'sentences',
    '_id': '3',
    '_score': 0.13786995,
    '_source': {'sentence': 'Hack nCov is great!'}}]}}

# match_phrase 

body = {
    "from":0,
    "size":1,
    "query": {
        "match_phrase": {
            "sentence":"Hack Quarantine"
        }
    }
}

res = es.search(index="english", body=body)
res
{'took': 2,
 'timed_out': False,
 '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0},
 'hits': {'total': {'value': 1, 'relation': 'eq'},
  'max_score': 1.1505672,
  'hits': [{'_index': 'english',
    '_type': 'sentences',
    '_id': '2',
    '_score': 1.1505672,
    '_source': {'sentence': 'Hack-Quarantine is stunning!'}}]}}

Combining queries

# must, must_not and should
 
body = {
    "from":0,
    "size":2,
    "query": {
        "bool": {
            "must_not": {
                "match": {
                    "sentence":"COVID-19"
                }
            },
            "should": {
                "match": {
                    "sentence": "Hack"
                }
            }
        }
    }
}

res = es.search(index="english", body=body)
res
{'took': 2,
 'timed_out': False,
 '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0},
 'hits': {'total': {'value': 2, 'relation': 'eq'},
  'max_score': 0.13786995,
  'hits': [{'_index': 'english',
    '_type': 'sentences',
    '_id': '2',
    '_score': 0.13786995,
    '_source': {'sentence': 'Hack-Quarantine is stunning!'}},
   {'_index': 'english',
    '_type': 'sentences',
    '_id': '3',
    '_score': 0.13786995,
    '_source': {'sentence': 'Hack nCov is great!'}}]}}

Regular Expressions Queries

# Updating our data

doc_1 = {"sentence":"Hack COVID-19 is amazing!"}
doc_2 = {"sentence":"Hack-Quarantine is stunning!"}
doc_3 = {"sentence":"Hack nCov is great!"}

es.index(index="english", doc_type="sentences", id=1, body=doc_1)
{'_index': 'english',
 '_type': 'sentences',
 '_id': '1',
 '_version': 9,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 19,
 '_primary_term': 1}

es.index(index="english", doc_type="sentences", id=2, body=doc_2)
{'_index': 'english',
 '_type': 'sentences',
 '_id': '2',
 '_version': 10,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 20,
 '_primary_term': 1}

es.index(index="english", doc_type="sentences", id=3, body=doc_3)
{'_index': 'english',
 '_type': 'sentences',
 '_id': '3',
 '_version': 3,
 'result': 'updated',
 '_shards': {'total': 2, 'successful': 1, 'failed': 0},
 '_seq_no': 21,
 '_primary_term': 1}

# regexp query

body = {
    "from":0,
    "size":3,
    "query": {
        "regexp": {
            "sentence":".*"
        }
    }
}

res = es.search(index="english", body=body)
res
{'took': 5,
 'timed_out': False,
 '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0},
 'hits': {'total': {'value': 3, 'relation': 'eq'},
  'max_score': 1.0,
  'hits': [{'_index': 'english',
    '_type': 'sentences',
    '_id': '1',
    '_score': 1.0,
    '_source': {'sentence': 'Hack COVID-19 is amazing!'}},
   {'_index': 'english',
    '_type': 'sentences',
    '_id': '2',
    '_score': 1.0,
    '_source': {'sentence': 'Hack-Quarantine is stunning!'}},
   {'_index': 'english',
    '_type': 'sentences',
    '_id': '3',
    '_score': 1.0,
    '_source': {'sentence': 'Hack nCov is great!'}}]}}

elasticsearch-workshop's People

Contributors

aminblm avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.