PlatoAiStream

PlatoAiStream

  • Discover
        • Bitcoin ATMs
          • Bit National
          • Bitcoin Depot
          • Bitcoin Well
          • Bitstop
          • Byte Federal
          • Coin Source
          • Coinflip
          • Digital Mint
          • Insta Coin
          • Kurant
          • Local Coin
          • National Bitcoin
          • Rocket Coin
          • Smart Kiosk
        • Insurance
          • Asure Network
          • BITRUST
          • CDx
          • Citizen Health
          • Cover Protocol
          • Etherisc
          • FidentiaX
          • Hurricaneguard.io
          • Nexus Mutual
          • Nsure
          • Opium Insurance
          • Teambrella
          • VouchForMe
        • Social
          • APPICS
          • Bounty Hub
          • D Tube
          • D.Buzz
          • Den
          • Distrubted Town
          • DLike
          • Ecency
          • GuildChat
          • Lumeos
          • Murmur
          • Native Money
          • PC Gamer
          • Sense Chat
          • Steem Leo
          • Stem Social
          • Wizz Network
        • Compliance
          • 3Box
          • Blockpass
          • BrightID
          • Ciphertrace
          • Codenotary
          • Coinfirm
          • Colendi
          • Comply Advantage
          • Elliptic
          • Gresham International
          • Hydro
          • Identity.com
          • Jolocom
          • KYC Chain
          • Maxcorp
          • Notabene
          • Solidus Labs
          • TRM Labs
        • Marketplaces
          • Atomic Market
          • Collect
          • Crypto Locally
          • Crypto Slam
          • Crypto Waifu
          • Cyber Time Finance
          • Decentraland
          • EOS Name Swaps
          • Fyooz
          • Hivelist
          • Jugger World
          • KnownOrigin
          • Miime
          • MintBase
          • Myth Market
          • Nagemon
          • NEAR
          • Near Names
          • NFT Farm Builder
          • NFT Key
          • NFT Mart
          • NFTB
          • Niftex
          • Open Kg
          • OpenSea
          • Paras
          • Pulse
          • Rarible
          • Scarcebits
          • Secret Auctions
          • Sign Art
          • Space Finance
          • Token Trove
          • Totle
          • Treasureland
          • Twinci
          • Unifty
          • Wax Stash
          • WaxArena
          • Waxplorer
          • Wyvren
          • Xanalia
        • Stablecoins
          • Augmint
          • DefiDollar
          • Empty Set Dollar
          • EOSDT
          • Frax
          • Gemini Dollar
          • Money on Chain
          • Paxos Standard
          • pTokens
          • USD Coin
          • WBTC
        • DAO's
          • 0x
          • 1Hive
          • Akropolis
          • Alien Worlds
          • Ar Weave
          • Boardroom
          • Daohaus
          • DAOStack
          • DXdao
          • Snapshot
        • Mining
          • BitFury
          • Blockware Solutions
          • BlokForge
          • Canaan Creative
          • CoinMiner
          • Costa Nord Mine
          • CryptoUniverse
          • Cudo Miner
          • Cyberian Mine
          • ECOS Cloud Mining
          • FlyHodler
          • FlyMining
          • FPGA Guide
          • Hash Core Mining
          • Hashfox
          • Iliium
          • Innosilicon
          • IQ Mining
          • Miner Bros
          • MinerGate
          • MineShop
          • Mining Dudes
          • Mining Store 5111
          • MiningStore
          • myMiner
          • New Mining
          • NuVoo Mining
          • Obelisk
          • PandaMiner
          • Pangolin Miner
          • RedBag Technologies
          • Quantech
          • Satoshi Miners
          • Sesterce Mining
          • WhatsMiner
          • Whats Miner
        • Staking / Farming
          • Akropolis
          • Alpha Homora
          • Autofarm
          • Balancer
          • Barnbridge
          • bEarn Fi
          • Beefy Finance
          • Certus One
          • Cream
          • Dokia Capital
          • HyperBlocks
          • Idle
          • Mythos
          • P2P Validator
          • PancakeBunny
          • Pickle
          • Rari Capital
          • Stake.Fish
          • Stake Capital
          • StakeWithUs
          • Stakin
          • Staking Facilities
          • xFai
        • Developers
          • 4irelabs
          • Antier
          • Applicature
          • Arstudioz
          • BairesDev
          • BCHD
          • BirthVenue
          • Bitcoin.com
          • Bitswift
          • Blaize
          • Block360
          • BlockBlox
          • Blockchain Center
          • Blockchain Foundry
          • Blockhunters
          • Blockwell
          • Cardinal Cryptography
          • Celer
          • Code for Startups
          • Code Zeros
          • Cubycode
          • Dapplica
          • Debut Infotech
          • DEIP
          • DevProvider
          • Ekoios
          • Emurgo
          • Espeo Software
          • Etheralabs
          • EthWorks
          • Geneva Software
          • Gnosis
          • Graph
          • Hashcash Consultants
          • HireNinja
          • Idealogic
          • Ideas By Nature
          • INC4
          • InMind Software
          • Inn4Science
          • Ionixx
          • IOST
          • Kaikas
          • Keep.Network
          • Lightning Network
          • LimeChain
          • Liquidity.Network
          • Merehead
          • Metronome
          • Minddeft Technologies
          • mStable
          • MVP Workshop
          • NEM
          • Nest
          • Nextrope
          • Node Factory
          • Nordwhale
          • OnGraph
          • Ontology
          • OpenLedger
          • Ouroboros
          • Owlab
          • PixelPlex
          • Provable Things
          • pTokens
          • Qualium Systems
          • R3
          • Ramlogics
          • Ren
          • RNS Solutions
          • SmartBox
          • SourceX
          • Stratus Cyber
          • Teamvoy
          • TechCreatix
          • TheGraph
          • Titanium Blockchain
          • TrendLine Global
          • Ubik Group
          • UMA
        • NFTs
          • Aavegotchi
          • Alien Worlds
          • Anr Key
          • ApeSwap
          • Art Blocks
          • Atari NFT
          • Auto Glyphs
          • Axie Infinity
          • Blockchain Heroes
          • BTC Origins
          • Crypto Punks
          • Crypto Voxels
          • DeadMau5
          • Decentraland
          • Euler Beats
          • F1 Delta Time
          • Foundation
          • Go Pepe
          • Market Decentraland
          • Meet Bits
          • Monsters of Rap
          • Nifty Dudes
          • Rarible
          • RPlanet
          • Somium Space
          • Sorare
          • The Hash Masks
          • The Horrors
          • Topps GPK
          • Topps MLB
          • Upland
          • Weezer
        • SupplyChain
          • 300 Cubits
          • Blockfreight
          • Blockhead Technologies
          • CargoCoin
          • CargoLedger
          • dexFreight
          • Fr8 Network
          • Hijro
          • IMMLA
          • Konexial
          • Koopman Logistics
          • Modum
          • MuleChain
          • NextPakk
          • OpenPort
          • Peer Ledger
          • SigmaLedger
          • ShipChain
          • Skuchain
          • SkyCell
          • SKYFchain
          • SyncFab
          • T-Mining
          • TangoTrade
          • Tradeline
          • Unicsoft
          • WaltonChain
          • WAVE
          • Zego
          • ZERO1 CAPITAL
        • DEX's
          • 1inch
          • AirSwap
          • Balancer
          • BitPortal
          • bSWAP
          • Curve
          • DeversiFI
          • Dex.AG
          • DexGuru
          • Dodo
          • Dolomite
          • DYDX
          • Eidoo
          • Ellipsis
          • Enzyme
          • IDEX
          • Jelly Swap
          • Loopring
          • Matcha
          • Mesa
          • Multichain.xyz
          • Newdex
          • PancakeSwap
          • ParaSwap
          • Quickswap
          • SHIBA TOKEN
          • Totle
          • TronTrade
          • Uniswap
          • WBTC.Cafe
          • YOLO
        • Payments
          • Bitt
          • Blockmove
          • Celer Network
          • Circle Invest
          • Connext
          • Lightning Network
          • OmiseGO
          • Paytomat
          • Request
          • Sablier
          • StablePay
          • xDai Stable Chain
          • zkSync
        • Trading
          • AAX
          • ACDX
          • Amber AI
          • BBX
          • Belfrics India
          • Betoken
          • Bitgo
          • Bitcoin IRA
          • Bitgo Wallet
          • BitWell
          • DefiPulse Index
          • Erisx
          • EXX
          • FinNexus Options
          • Furucombo
          • Hegic
          • Hetoro
          • Indexed Finance
          • Kirobo
          • Lien
          • NFT20
          • Opyn
          • PieDAO
          • Reflexer
        • Exchanges
          • 1inch
          • Aidosmarket
          • AliExchange
          • Alphaex
          • AOFEX
          • Aryana
          • Azbit
          • Beaxy
          • Bibox
          • Biconomy
          • Bidesk
          • BitAsset
          • Bitay
          • Bibox
          • Bingcoins
          • Bitci
          • BitGrail
          • BITEXBOOK
          • Bitinfi
          • Bitpanda Pro
          • BITPoint
          • Bitribe
          • Bluebelt
          • Braziliex
          • BTC38
          • BTC Markets
          • BTCBOX
          • BTC-exchange
          • BTSE
          • C2CX
          • CBX
          • CEX.IO
          • ChainX
          • Chilebit
          • Cobinhood
          • CoinCap
          • Coindeal
          • CoinEgg
          • CoinField
          • Coinlist
          • Coins Pro
          • Compound
          • Currency.com
          • dHEDGE
          • DigiFinex
          • Eidoo Hybrid Exchange
          • EQUOS
          • Everbloom
          • EXX
          • Gatecoin
          • Gemini
          • Gnosis
          • Huobi Global
          • iCoinbay
          • iDevex
          • IDEX
          • IncoreX
          • InstantBitex
          • Ironex
          • itBit
          • LIQNET
          • LMAX Digital
          • Lykke
          • MyCoinStory
          • NLexch
          • Onederx
          • OpenLedger
          • ORE
          • Poloni DEX
          • Raidofinance
          • RightBTC
          • SIGEN.pro
          • Sistemkoin
          • Slicex
          • SparkDEX
          • Surbitcoin
          • Switcheo
          • Thore
          • Tokens.net
          • TRUSTdex
          • Uniswap
          • Uniswap (V2)
          • Vaultoro
          • VBTC
          • WBB Exchange
          • Yacuna
          • Zloadr
        • Platform / Protocols
          • 88mph
          • AnySwap
          • Baanx
          • Badger Finance
          • Balancer
          • Band Protocol
          • Barnbridge
          • Beta Curve
          • Big Data Protocol
          • BitcoinCore
          • BlockStream
          • Bluzelle
          • Brave
          • Butterfly
          • bZx
          • CDx
          • Codex
          • Compound
          • Cover
          • Cream Finance
          • Curve
          • ELTWallet
          • Etherisc
          • Flexa
          • Fulcrum
          • Gnosis
          • Harbor
          • Homora
          • Just Liquidity
          • Keeper Dao
          • Linen App
          • Livepeer
          • Mirror Protocol
          • Mith Cash
          • Nayms
          • NEVERDIE
          • Omen.eth
          • OpenFinance
          • Opium Insurance
          • Parity
          • Parsiq
          • Paxos
          • Polymarket
          • Proof Suite
          • Protocol Labs
          • QUASA
          • Ren VM
          • RSK
          • RSK Infrastructure
          • Sablier
          • Shapeshit
          • Simplex
          • Stratis
          • Swerve Finance
          • Swirlds
          • Symbiont
          • Tinlake
          • Tokensoft
          • Tornado Cash
          • Torque
          • TrueFi
          • Uniswap
          • Vega
          • Venus
          • Voluto
          • WBTC
          • WeTrust
          • xDai Stable Chain
        • Wallets
          • Abra
          • Agama
          • AirGap
          • AlphaWallet
          • AnkerPay
          • ANX Vault Wallet
          • Armory Wallet
          • Atomic Wallet
          • BEPAL PRO S
          • BitcoinWallet
          • BitDaric Wallet
          • BitFi
          • Bither Wallet
          • BitKeep
          • Bitpanda
          • Bitpie
          • BitPortal
          • Blockmove
          • BTC Wallet
          • CAKE
          • Cobo
          • Coffee
          • Coin Wallet
          • CoinBank
          • Coinfy
          • Crypterium
          • Crypto.com
          • CryptX Wallet
          • Daedalus
          • DeFi Saver
          • Dharma
          • Dhedge
          • Digibyte
          • Dogecoin Core
          • Eidoo
          • Einc
          • ElectronCash
          • ElectrumLTC
          • Stratis
          • Electrum Wallet
          • Emerald
          • EO.Finance
          • Ethos
          • Evercoin
          • Ginco
          • Gnosis Safe
          • GreenAddress
          • HB Wallet
          • HelioWallet
          • Huobi Wallet
          • IndieSquare
          • Infinito Wallet
          • Joule
          • KCash
          • Keycard
          • Kimera
          • Kriptomat
          • Ledger
          • LiteVault
          • Litewallet
          • Lykke Wallet
          • Melon Terminal
          • Memory Box
          • MetaMask
          • Mobi
          • Monedero
          • Monerujo
          • MultiDoge
          • Multis
          • Mycelium Wallet
          • MyCrypto
          • MyMonero Wallet
          • Natrium Wallet
          • NEON Wallet
          • NEVERDIE
          • OpenLedger
          • OPOLO
          • Paytomat
          • Phoenix
          • Pirate Ocean
          • Prodoge
          • qPocket
          • Skull Island
          • Foxlet
          • TBCC Wallet
          • Token Pocket
          • Trust Wallet
          • Trust Wallet App
          • Trustology
          • UberPay
          • Vcash Client
          • WallETH
          • Zerion
  • Login
  • Register
PlatoAiStream

PlatoAiStream

  • Discover
  • Plato Search
  • Vertical Streams
    • Aerospace
    • Ai
    • AR/VR
    • Automotive
    • Aviation
    • Big Data
    • Blockchain
    • Bonds
    • Cannabis
    • Cleantech
    • Code
    • Crowdfunding
    • CyberSecurity
    • E sports
    • E-commerce
    • eCommerce
    • Edtech
    • ESports
    • Fintech
    • Forex
    • Gaming
    • IoT
    • M&A
    • Medical Devices
    • Nano Technology
    • Patents & IP
    • Payments
    • Private Equity
    • Quantum
    • Real Estate
    • SaaS
    • Semiconductor
    • SPACs
    • Startups
    • Supply Chain
    • Supply chain & Logistics
    • US Commodities
    • US Equities
    • Venture Capital
  • Publications
    • 99 Bitcoins
    • ACN Newswire
    • ADVFN
    • Ai TimeJornal
    • Aisa PEVC
    • AlexaBlockchain
    • AllCoins News
    • Alontrus
    • Alley Watch
    • AMB Crypto
    • Asia Crypto Today
    • Asian Spectator
    • Asic Miner Market
    • Baystreet
    • BeinCrypto
    • Bitcoin
    • Bitcoin Market Journal
    • Bitcoin PR Buzz
    • Bitcoinist
    • BitcoinNewsMiner
    • Bitcon Chaser
    • Bitpinas
    • Bitrazzi
    • Bitsonblocks
    • BlockNews Africa
    • Blockchain Health Review
    • Blockchain24
    • Blockchain Curated
    • Blokt
    • BTC Manager
    • BTC Upload
    • Bullish For Crypto
    • Business News Asia
    • Business News.ph
    • Business Press 24
    • Central Charts
    • ChainTimes
    • ChainDD
    • CoinBeat
    • Coinbureau
    • CoinCentral
    • Coinfloor
    • Coinigy
    • CoinJournal
    • Coinnounce
    • Coinpedia
    • Cointelegraph
    • Cointikka
    • Crunchbase
    • Crypto News
    • Crypto News Point
    • Crypto News Review
    • Crypto NewsZ
    • CryptoClarified
    • Cryptocoindude
    • Cryptocointrade
    • Cryptocoinzo
    • CryptoGlobe
    • Cryptomininq
    • ECrypto News
    • CryptoNinjas
    • CryptoPotato
    • Cryptoverza
    • Cryptozink
    • DC Forecasts
    • Decrypt
    • Digital Notice
    • Dragon
    • EthBLog
    • Ethical Markets
    • EventsNewsAsia
    • Finance Magnates
    • Finanzachricten
    • Finyear
    • Firmen Presse
    • Futures Trading Charts
    • Influencing
    • Inside Bitcoins
    • Intell Asia
    • Jump Start
    • Kanalcoin
    • Kraken Blog
    • Lioncity
    • LiveBitcoin News
    • MENAFN
    • Micro Small Cap
    • Multichain
    • News BTC
    • News Tag
    • Null TX
    • OpenZeppelin
    • PRWire
    • Press Malaysia
    • Primafelicitas
    • Quamnet
    • Quillhash
    • Sccop
    • Scietech Biz News
    • Sinchew Business
    • Street Insider
    • Street Signals
    • Techphile
    • Techstars
    • The Daily Hodl
    • The Merkle
    • TheBlock
    • The CoinsPost
    • Times Tech
    • TIMM
    • Twuko
    • Unhashed
    • Visual Capitalist
    • Weiss Crypto Ratings
    • WWB Global
    • Zaikei
  • Analytics
    • 0x Tracker
    • Amberdata
    • APY.Vision
    • Beam Explorer
    • Bitcoin BlockExplorer
    • BitcoinWiki
    • Bitcompare
    • BitRank
    • Bloxy
    • BTC Explorer
    • Croco Finance
    • CryptoChain
    • DappRadar
    • DeBank
    • Defi Tracker
    • DeepDAO
    • Defistation
    • DeFi Explore
    • DeFi Pulse
    • Dune Analytics
    • Etherchain
    • GlassNode
    • Helium
    • Kyber Network Tracker
    • Liquidtyfolio
    • LoanScan
    • Maker Governance Dashboard
    • Makervaults
    • Nansen
    • Pools.fyi
    • QLUE
    • Stablecoin Index
    • Token Terminal
    • TronScan
    • Uniswap
    • VeChain
    • VFat
    • Vite Explorer
    • Yield Farming Tools
  • Plato AudioStreams
  • Plato Newswire
  • Companies
  • Defi Gateway
    • Bitcoin ATMs
      • Bitcoin Depot
      • Bitstop
      • Byte Federal
      • Coin Source
      • Coinflip
      • Digital Mint
      • National Bitcoin
      • Rocket Coin
    • Compliance
      • 3Box
      • Blockpass
      • BrightID
      • Ciphertrace
      • Codenotary
      • Coinfirm
      • Colendi
      • Comply Advantage
      • Elliptic
      • Gresham International
      • Hydro
      • Identity.com
      • Jolocom
      • KYC Chain
      • Maxcorp
      • Notabene
      • Solidus Labs
      • TRM Labs
    • DAO’s
      • Boardroom
      • Daohaus
      • DAOStack
      • DXdao
      • Snapshot
    • Developers
      • 4irelabs
      • Antier
      • Applicature
      • Arstudioz
      • BairesDev
      • BCHD
      • BirthVenue
      • Bitcoin.com
      • Bitswift
      • Blaize
      • Block360
      • BlockBlox
      • Blockchain Center
      • Blockchain Foundry
      • Blockhunters
      • Blockwell
      • Cardinal Cryptography
      • Celer
      • Code for Startups
      • Code Zeros
      • Cubycode
      • Dapplica
      • Debut Infotech
      • DEIP
      • DevProvider
      • Ekoios
      • Emurgo
      • Espeo Software
      • Etheralabs
      • EthWorks
      • Geneva Software
      • Gnosis
      • Graph
      • Hashcash Consultants
      • HireNinja
      • Idealogic
      • Ideas By Nature
      • INC4
      • InMind Software
      • Inn4Science
      • Ionixx
      • IOST
      • Kaikas
      • Keep.Network
      • Lightning Network
      • LimeChain
      • Liquidity.Network
      • Merehead
      • Metronome
      • Minddeft Technologies
      • mStable
      • MVP Workshop
      • NEM
      • Nest
      • Nextrope
      • Node Factory
      • Nordwhale
      • OnGraph
      • Ontology
      • OpenLedger
      • Ouroboros
      • Owlab
      • PixelPlex
      • Provable Things
      • pTokens
      • Qualium Systems
      • R3
      • Ramlogics
      • Ren
      • RNS Solutions
      • SmartBox
      • SourceX
      • Stratus Cyber
      • Teamvoy
      • TechCreatix
      • TheGraph
      • Titanium Blockchain
      • TrendLine Global
      • Ubik Group
      • UMA
    • DEX’s
      • 1inch
      • AirSwap
      • Balancer
      • BitPortal
      • bSWAP
      • Curve
      • DeversiFI
      • Dex.AG
      • DexGuru
      • Dodo
      • Dolomite
      • DYDX
      • Eidoo
      • Ellipsis
      • Enzyme
      • IDEX
      • Jelly Swap
      • Loopring
      • Matcha
      • Mesa
      • Multichain.xyz
      • Newdex
      • PancakeSwap
      • ParaSwap
      • Quickswap
      • SHIBA TOKEN
      • Totle
      • TronTrade
      • Uniswap
      • WBTC.Cafe
      • YOLO
    • Exchanges
      • 1inch
      • Aidosmarket
      • AliExchange
      • Alphaex
      • AOFEX
      • Aryana
      • Azbit
      • Beaxy
      • Bibox
      • Biconomy
      • Bidesk
      • BitAsset
      • Bitay
      • Bibox
      • Bingcoins
      • Bitci
      • BitGrail
      • BITEXBOOK
      • Bitinfi
      • Bitpanda Pro
      • BITPoint
      • Bitribe
      • Bluebelt
      • Braziliex
      • BTC38
      • BTC Markets
      • BTCBOX
      • BTC-exchange
      • BTSE
      • C2CX
      • CBX
      • CEX.IO
      • ChainX
      • Chilebit
      • Cobinhood
      • CoinCap
      • Coindeal
      • CoinEgg
      • CoinField
      • Coinlist
      • Coins Pro
      • Compound
      • Currency.com
      • dHEDGE
      • DigiFinex
      • Eidoo Hybrid Exchange
      • EQUOS
      • Everbloom
      • EXX
      • Gatecoin
      • Gemini
      • Gnosis
      • Huobi Global
      • iCoinbay
      • iDevex
      • IDEX
      • IncoreX
      • InstantBitex
      • Ironex
      • itBit
      • LIQNET
      • LMAX Digital
      • Lykke
      • MyCoinStory
      • NLexch
      • Onederx
      • OpenLedger
      • ORE
      • Poloni DEX
      • Raidofinance
      • RightBTC
      • SIGEN.pro
      • Sistemkoin
      • Slicex
      • SparkDEX
      • Surbitcoin
      • Switcheo
      • Thore
      • Tokens.net
      • TRUSTdex
      • Uniswap
      • Uniswap (V2)
      • Vaultoro
      • VBTC
      • WBB Exchange
      • Yacuna
      • Zloadr
    • Insurance
      • Asure Network
      • BITRUST
      • CDx
      • Citizen Health
      • Cover Protocol
      • Etherisc
      • FidentiaX
      • Hurricaneguard.io
      • Nexus Mutual
      • Nsure
      • Opium Insurance
      • Teambrella
      • VouchForMe
    • Marketplaces
      • Atomic Market
      • Collect
      • Crypto Locally
      • Crypto Slam
      • Crypto Waifu
      • Cyber Time Finance
      • Decentraland
      • EOS Name Swaps
      • Fyooz
      • Hivelist
      • Jugger World
      • KnownOrigin
      • Miime
      • MintBase
      • Myth Market
      • Nagemon
      • NEAR
      • Near Names
      • NFT Farm Builder
      • NFT Key
      • NFT Mart
      • NFTB
      • Niftex
      • Open Kg
      • OpenSea
      • Paras
      • Pulse
      • Rarible
      • Scarcebits
      • Secret Auctions
      • Sign Art
      • Space Finance
      • Token Trove
      • Totle
      • Treasureland
      • Twinci
      • Unifty
      • Wax Stash
      • WaxArena
      • Waxplorer
      • Wyvren
      • Xanalia
    • Mining
      • BitFury
      • Blockware Solutions
      • BlokForge
      • Canaan Creative
      • CoinMiner
      • Costa Nord Mine
      • CryptoUniverse
      • Cudo Miner
      • Cyberian Mine
      • ECOS Cloud Mining
      • FlyHodler
      • FlyMining
      • FPGA Guide
      • Hash Core Mining
      • Hashfox
      • Iliium
      • Innosilicon
      • IQ Mining
      • Miner Bros
      • MinerGate
      • MineShop
      • Mining Dudes
      • Mining Store 5111
      • MiningStore
      • myMiner
      • New Mining
      • NuVoo Mining
      • Obelisk
      • PandaMiner
      • Pangolin Miner
      • RedBag Technologies
      • Quantech
      • Satoshi Miners
      • Sesterce Mining
      • WhatsMiner
      • Whats Miner
    • NFTs
      • Aavegotchi
      • Alien Worlds
      • Anr Key
      • ApeSwap
      • Art Blocks
      • Atari NFT
      • Auto Glyphs
      • Axie Infinity
      • Blockchain Heroes
      • BTC Origins
      • Crypto Punks
      • Crypto Voxels
      • DeadMau5
      • Decentraland
      • Euler Beats
      • F1 Delta Time
      • Foundation
      • Go Pepe
      • Market Decentraland
      • Meet Bits
      • Monsters of Rap
      • Nifty Dudes
      • Rarible
      • RPlanet
      • Somium Space
      • Sorare
      • The Hash Masks
      • The Horrors
      • Topps GPK
      • Topps MLB
      • Upland
      • Weezer
    • Payments
      • Bitt
      • Blockmove
      • Celer Network
      • Circle Invest
      • Connext
      • Lightning Network
      • OmiseGO
      • Paytomat
      • Request
      • Sablier
      • StablePay
      • xDai Stable Chain
      • zkSync
    • Platform / Protocols
      • 88mph
      • AnySwap
      • Baanx
      • Badger Finance
      • Balancer
      • Band Protocol
      • Barnbridge
      • Beta Curve
      • Big Data Protocol
      • BitcoinCore
      • BlockStream
      • Bluzelle
      • Brave
      • Butterfly
      • bZx
      • CDx
      • Codex
      • Compound
      • Cover
      • Cream Finance
      • Curve
      • ELTWallet
      • Etherisc
      • Flexa
      • Fulcrum
      • Gnosis
      • Harbor
      • Homora
      • Just Liquidity
      • Keeper Dao
      • Linen App
      • Livepeer
      • Mirror Protocol
      • Mith Cash
      • Nayms
      • NEVERDIE
      • Omen.eth
      • OpenFinance
      • Opium Insurance
      • Parity
      • Parsiq
      • Paxos
      • Polymarket
      • Proof Suite
      • Protocol Labs
      • QUASA
      • Ren VM
      • RSK
      • RSK Infrastructure
      • Sablier
      • Shapeshit
      • Simplex
      • Stratis
      • Swerve Finance
      • Swirlds
      • Symbiont
      • Tinlake
      • Tokensoft
      • Tornado Cash
      • Torque
      • TrueFi
      • Uniswap
      • Vega
      • Venus
      • Voluto
      • WBTC
      • WeTrust
      • xDai Stable Chain
    • Social
      • APPICS
      • Bounty Hub
      • D Tube
      • D.Buzz
      • Den
      • Distrubted Town
      • DLike
      • Ecency
      • GuildChat
      • Lumeos
      • Murmur
      • Native Money
      • PC Gamer
      • Sense Chat
      • Steem Leo
      • Stem Social
      • Wizz Network
    • Stablecoins
      • Augmint
      • DefiDollar
      • Empty Set Dollar
      • EOSDT
      • Frax
      • Gemini Dollar
      • Money on Chain
      • Paxos Standard
      • pTokens
      • USD Coin
      • WBTC
    • Staking / Farming
      • Akropolis
      • Alpha Homora
      • Autofarm
      • Balancer
      • Barnbridge
      • bEarn Fi
      • Beefy Finance
      • Certus One
      • Cream
      • Dokia Capital
      • HyperBlocks
      • Idle
      • Mythos
      • P2P Validator
      • PancakeBunny
      • Pickle
      • Rari Capital
      • Stake.Fish
      • Stake Capital
      • StakeWithUs
      • Stakin
      • Staking Facilities
      • xFai
    • SupplyChain
      • 300 Cubits
      • Blockfreight
      • Blockhead Technologies
      • CargoCoin
      • CargoLedger
      • dexFreight
      • Fr8 Network
      • Hijro
      • IMMLA
      • Konexial
      • Koopman Logistics
      • Modum
      • MuleChain
      • NextPakk
      • OpenPort
      • Peer Ledger
      • SigmaLedger
      • ShipChain
      • Skuchain
      • SkyCell
      • SKYFchain
      • SyncFab
      • T-Mining
      • TangoTrade
      • Tradeline
      • Unicsoft
      • WaltonChain
      • WAVE
      • Zego
      • ZERO1 CAPITAL
    • Trading
      • AAX
      • ACDX
      • Amber AI
      • BBX
      • Belfrics India
      • Betoken
      • Bitgo
      • Bitcoin IRA
      • Bitgo Wallet
      • BitWell
      • DefiPulse Index
      • Erisx
      • EXX
      • FinNexus Options
      • Furucombo
      • Hegic
      • Hetoro
      • Indexed Finance
      • Kirobo
      • Lien
      • NFT20
      • Opyn
      • PieDAO
      • Reflexer
    • Wallets
      • Abra
      • Agama
      • AirGap
      • AlphaWallet
      • AnkerPay
      • ANX Vault Wallet
      • Armory Wallet
      • Atomic Wallet
      • BEPAL PRO S
      • BitcoinWallet
      • BitDaric Wallet
      • BitFi
      • Bither Wallet
      • BitKeep
      • Bitpanda
      • Bitpie
      • BitPortal
      • Blockmove
      • BTC Wallet
      • CAKE
      • Cobo
      • Coffee
      • Coin Wallet
      • CoinBank
      • Coinfy
      • Crypterium
      • Crypto.com
      • CryptX Wallet
      • Daedalus
      • DeFi Saver
      • Dharma
      • Dhedge
      • Digibyte
      • Dogecoin Core
      • Eidoo
      • Einc
      • ElectronCash
      • ElectrumLTC
      • Stratis
      • Electrum Wallet
      • Emerald
      • EO.Finance
      • Ethos
      • Evercoin
      • Ginco
      • Gnosis Safe
      • GreenAddress
      • HB Wallet
      • HelioWallet
      • Huobi Wallet
      • IndieSquare
      • Infinito Wallet
      • Joule
      • KCash
      • Keycard
      • Kimera
      • Kriptomat
      • Ledger
      • LiteVault
      • Litewallet
      • Lykke Wallet
      • Melon Terminal
      • Memory Box
      • MetaMask
      • Mobi
      • Monedero
      • Monerujo
      • MultiDoge
      • Multis
      • Mycelium Wallet
      • MyCrypto
      • MyMonero Wallet
      • Natrium Wallet
      • NEON Wallet
      • NEVERDIE
      • OpenLedger
      • OPOLO
      • Paytomat
      • Phoenix
      • Pirate Ocean
      • Prodoge
      • qPocket
      • Skull Island
      • Foxlet
      • TBCC Wallet
      • Token Pocket
      • Trust Wallet
      • Trust Wallet App
      • Trustology
      • UberPay
      • Vcash Client
      • WallETH
      • Zerion
  • Market Data
    • BTCUSD
    • Digital Assets
    • Exchanges
    • GS vs Coin
    • Crypto Indices
      • PX25
      • PX40
      • PX100
    • US Equities
  • Ethereum Alliance
    • Adhara
    • Alastria
    • Alpha Wallet
    • API3
    • Atato
    • Aventus
    • BambooDefi
    • Barn Bridge
    • Bidao
    • Blockapps
    • Blockchain Capital
    • Blockchain For Social Impact
    • Blockchain Management
    • Blockchain Research
    • BPS Financial
    • Brain Bot
    • British Blockchain Association
    • BSOS
    • CABROS
    • Chain Link
    • ClearMatrics
    • CMT Digital
    • Couger
    • DIF
    • Envision Blockchain Services
    • Fasset
    • Findora
    • Finso
    • Inferno Red
    • Io builders
    • IOSG
    • Kaula
    • Kaulian
    • Lime Chain
    • Perkins
    • Polygon
    • Provable Things
    • Reedll
    • Runtime Verification
    • SDX
    • Sollensys
    • Sigma Ledger
    • Streamfast
    • Stably
    • Streami
    • Tauras Group
    • The Machine Consultancy
    • Token Factory
    • Trade Log
    • Tranomics
    • Unibright
    • Valid Network
    • Vitro
    • VM Ware
    • Web3 Labs
    • WIPRO
    • World Markets
  • Patents
  • People
  • Crowdfunding
    • Birchal
    • Catapoolt
    • Causes
    • Compansito
    • Crowdcube
    • DealBox
    • Fundly
    • Give Campus
    • Goteo
    • HoneyFund
    • Mighty Cause
    • Netcapital
    • One Planet Crowd
    • Patreon
    • RealtyMogul
    • Rocket Hub
    • Startup Explore
    • Vedaslabs
    • Venture Crowd
    • Vested
  • Resources
    • Act1
    • Ahura
    • Amazing Blocks
    • ARCISPHERE
    • Blockchain Council
    • Blockchain Councilus
    • Blockchain CS
    • Blockchain Industry Group
    • Blockchain Institute
    • Blockchain Research Institute
    • BWBC
    • Cloud Credential
    • Cogent Law
    • Crypto Valley
    • Digital Chamber
    • Digital Dollar Project
    • Dubai Future
    • Energy Blockchain
    • Enterprise Ethereum Alliance
    • EST Cap
    • Fantom Foundation
    • Fibree
    • GBB Council
    • GDF
    • Government Blockchain Association
    • Global Blockchain Summit
    • Global Tech Council
    • Gov Chain
    • GSDC
    • IDAXA
    • Intelli Network
    • Intercoin
    • Market Across
    • MediaShower
    • Visionary
  • Venture Capital
    • VC Registry
      • Abstract Ventures
      • Alpha Sigma
      • Arcanum Capital
      • Arrington XRP Capital
      • Blockchain Capital
      • BlockTower
      • BlockVC
      • BlueYard
      • Boost VC
      • Breyer Capital
      • Bridgit
      • BTC Inc
      • Cambrial Capital
      • Circle Fund
      • Coinbase Ventures
      • Collaborative Fund
      • Compound VC
      • ConsenSys Ventures
      • Continue Capital
      • Craft Ventures
      • Cyber Fund
      • Dekrypt Capital
      • DFG Capital
      • Digital Currency Group
      • Draper Associates
      • Electric Capital
      • Ethereum Community Fund
      • Fabric Ventures
      • FBG Capital
      • Fenbushi Capital
      • Founders Fund
      • FreeS Fund
      • Future Perfect Ventures
      • GBIC
      • General Catalyst
      • Gumi Cryptos
      • Hard Yaka
      • Hashed
      • HashKey Group
      • HCM Capital
      • IMO Ventures
      • INBlockchain
      • Initialized Capital
      • INN Mind
      • IOSG Ventures
      • JRR Crypto
      • June Fund
      • KR1
      • Krypital
      • L4 Ventures
      • LD Capital
      • Lemniscap
      • Lightspeed Venture Partners
      • LinkVC
      • Matrix Partners
      • MetaStable
      • Metaverse Ventures
      • NGC Ventures
      • Notation Capital
      • Outlier Ventures
      • PANTERA Capital
      • PARADIGM
      • Passport Capital
      • Placeholder VC
      • Polychain Capital
      • PreAngel
      • Protocol Ventures
      • RRE Ventures
      • Scalar Capital
      • Sequoia Capital
      • Signal Ventures
      • Signum Capital
      • Slow Ventures
      • Social Capital
      • SVK Crypto
      • Union Square Ventures
      • Version One
      • Vy Capital
      • Walden Bridge Capital
      • Winklevoss Capital
      • Yeoman’s Capital
      • Youbi Capital
      • zk Capital
    • VC Directory
  • Innovation Events
    • Blockchain Events
      • AI in Payments
      • AIBC
      • Asia Crypto Week Hong Kong
      • Bitcoin 2021
      • Black Arrow Cryptology
      • Blockchain Events
      • Blockchain Expo Global
      • Blockchain Expo NA
      • Blockchain Fest Asia
      • Blockchain Week Rome
      • Blockchance Europe
      • Blockchian Fest
      • Club Fest
      • Coin Fest UK
      • Construction Blockchain Consortium
      • Crypto Asset Conference
      • Digital Assets Realised
      • DX Daily
      • Finnovex
      • Finnovex South Africa
      • Future of Blockchain Summit
      • Futurist Conference
      • Global Defi Summit
      • Global Fintech Fest
      • GoldFinger
      • Government Blockchain Week
      • Hyperledger Global Forum
      • London Digital Assets Week
      • NFT.NYC
      • NFT Summit
      • Reg Tech Summit
      • Security Tokens Realised
      • Synopsis
      • The Blockchian Event
      • The Conference. NFT
      • The Virtual Martech Summit
      • Token 2049
  • W3 Registry
  • PR Syndication
  • Press Release
  • Plato Support
  • Terms of Use
  • Privacy Policy
  • Cookies Policy
  • DMCA Notice
  • GDPR
  • Contact
Uncategorized

A Beginner’s Guide to Feature Engineering – Everything You Need to Know!

Republished By Plato Republished By PlatoTime Stamp: October 3, 2021
A Beginner’s Guide to Feature Engineering – Everything You Need to Know! Uncategorized PlatoAiStream PlatoAiStream. Data Intelligence. Vertical Search. Ai.

This article was published as a part of the Data Science Blogathon

Overview

Say, you were setting up a gift shop and your supplier dumps all the toys that you asked for in a room. It’s going to look something like this. Total chaos! Now picture yourself standing in front of this huge pile of toys trying to find the right toy for a customer!

Feature Engineering image

(Source: https://tripswithtots.files.wordpress.com/2012/11/piles-of-plastic-toys.jpg)

You know it is in there, but you just don’t know where to look for it! Frustrating right?

In a second scenario, you first organize the toys before opening up the shop. You might want to group the toys into categories or you might even choose to replace some broken toys with newer ones. You might even realize some toys that you had asked for were missing and take the necessary actions.

That sounds like a more organized and sensible approach, right?

Well, when we build Machine Learning models, in most cases the data we deal with looks like this unorganized chaos of toys. This data needs to be cleaned up and pre-processed before it can be put to use and that is where Feature Engineering comes into play. It is a process that aims to bring order to chaos.

So let’s dive right in and have a look at the topics we are going to cover!

Table of Contents

  1. What is Feature Engineering?
  2. Why is Feature Engineering so important?
  3. Analyzing the Dataset Features
  4. Handling Missing Data
    • Delete the Columns
    • Impute missing values for Continuous variable
    • Impute missing values for Categorical variable
    • Predict the missing Values
  5. Encoding Categorical Data
    • Encoding Independent Variables
    • Encoding Dependent Variables
  6. Feature Scaling
  7. Conclusion

What is Feature Engineering?

Feature Engineering is the process of extracting and organizing the important features from raw data in such a way that it fits the purpose of the machine learning model. It can be thought of as the art of selecting the important features and transforming them into refined and meaningful features that suit the needs of the model.

FEATURE ENGINEERING

(Source: https://www.omnisci.com/technical-glossary/feature-engineering)

Feature Engineering encapsulates various data engineering techniques such as selecting relevant features, handling missing data, encoding the data, and normalizing it.

It is one of the most crucial tasks and plays a major role in determining the outcome of a model. In order to ensure that the chosen algorithm can perform to its optimum capability, it is important to engineer the features of the input data effectively.

Why is Feature Engineering so important?

Do you know what takes the maximum amount of time and effort in a Machine Learning workflow?

Well to analyze that, let us have a look at this diagram.

Why is Feature Engineering so important?

(Source: https://www.forbes.com/sites/gilpress/2016/03/23/data-preparation-most-time-consuming-least-enjoyable-data-science-task-survey-says/)

This pie-chart shows the results of a survey conducted by Forbes. It is abundantly clear from the numbers that one of the main jobs of a Data Scientist is to clean and process the raw data. This can take up to 80% of the time of a data scientist. This is where Feature Engineering comes into play. After the data is cleaned and processed it is then ready to be fed into the machine learning models to train and generate outputs.

So far we have established that Data Engineering is an extremely important part of a Machine Learning Pipeline, but why is it needed in the first place?

To understand that, let us understand how we collect the data in the first place. In most cases, Data Scientists deal with data extracted from massive open data sources such as the internet, surveys, or reviews. This data is crude and is known as raw data. It may contain missing values, unstructured data, incorrect inputs, and outliers. If we directly use this raw, un-processed data to train our models, we will land up with a model having a very poor efficiency.

Thus Feature Engineering plays an extremely pivotal role in determining the performance of any machine learning model

Benefits of Feature Engineering

An effective Feature Engineering implies:

  • Higher efficiency of the model
  • Easier Algorithms that fit the data
  • Easier for Algorithms to detect patterns in the data
  • Greater Flexibility of the features

Well, cleaning up bulks of raw, unstructured, and dirty data may seem like a daunting task, but that is exactly what this guide is all about.

So let’s get started and demystify Feature Engineering!

Analyzing The Dataset Features

Whenever you get a dataset, I would strongly advise you to first spend some time analyzing the dataset. This will help you get an understanding of the type of features and data you are dealing with. Analyzing the dataset will also help you create a mind map of the feature engineering techniques that you will need to process your data.

So let us import the libraries and have a look at our dataset.

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset= pd.read_csv("Data.csv")
dataset.head()

Output:

Feature Analysis

This is how our dataset looks. Once you have identified the input features and the values to be predicted (in our case ‘Purchased’ is the column to be predicted and the rest are the input features) let us analyze the data we have.

We also see that we have a column “Name” which plays no role in determining the output of our model. So we can safely exclude it from the training set. This can be done as follows.

x= dataset.iloc[:,1:-1].values
y= dataset.iloc[:,-1].values
print (x)

Output:

print output

Output:

output of print

The variable ‘x’ shall contain the inputs and the variable ‘y’ shall contain the outputs.

Handling Missing Data – An important Feature Engineering Step

Now let us check if we have any missing data.

A neat way to do that would be to display the sum of all the null values in each column of our dataset. The following line of code helps us do just that.

dataset.isnull().sum()

Output:

Handling Missing Data

This gives us a very clear representation of the total number of missing values present in each column. Now let us see how we can handle these missing values.

Deleting the Columns

Sometimes there may be certain features in our dataset which contain multiple empty entries or null values. These columns which have a very high number of null values often do not contribute much to the predicted output. In such cases, we may choose to completely delete the column.

We can fix a certain threshold value, say 70% or 80%, and if the number of null values exceeds the threshold we may want to delete that particular column from our training dataset.

threshold=0.7
dataset = dataset[dataset.columns[dataset.isnull().mean() < threshold]]
print(dataset)

OUTPUT:

Deleting the Columns | Feature Engineering

What this piece of code is doing is basically selecting only those columns which have null values less than the given threshold value. In our example, we see that the ‘Cars’ column has been removed. The number of null values is 14 and the total number of entries per column is 20. As the number of null values is not less than our desired threshold, we delete the column.

BENEFITS

  • Dimensionality Reduction
  • Reduces computation complexity

DRAWBACKS

  • Causes loss of information.

For easier understanding, we are dealing with a small dataset, however in reality this method is preferred only when the dataset is large and deleting a few columns will not affect it much, or when the column to be deleted is a relatively less important feature.

Impute Missing Values for Continuous Variable

Imputing Missing Values refers to the process of filling up the missing values with some values computed from the corresponding feature columns.

We can use a number of strategies for Imputing the values of Continuous variables. Some such strategies are imputing with Mean, Median or Mode.

Let us first display our original variable x.

x= dataset.iloc[:,1:-1].values y= dataset.iloc[:,-1].values

Output:

Impute Missing Values for Continuous Variable

IMPUTING WITH MEAN

Now, to do this, we will import SimpleImputer from sklearn.impute and pass our strategy as the parameter. We shall also specify the columns in which this strategy is to be applied using the slicing.

from sklearn.impute import SimpleImputer
imputer =SimpleImputer(missing_values=np.nan, strategy= "mean")
imputer.fit(x[:,1:3])
x[:,1:3]= imputer.transform(x[:,1:3])

Output

Feature Engineering | IMPUTING WITH MEAN

We see that the nan values have been replaced with the mean values of their corresponding columns.

IMPUTING WITH MEDIAN

Now, instead of mean if we wish to impute the missing values with median instead of mean, we simply have to change the parameter to ‘median’.

from sklearn.impute import SimpleImputer
imputer =SimpleImputer(missing_values=np.nan, strategy= "median")
imputer.fit(x[:,1:3])
x[:,1:3]= imputer.transform(x[:,1:3])

Output

IMPUTING WITH MEDIAN | Feature Engineering

IMPUTING WITH MODE

One of the most commonly used imputation methods to handle missing values is to substitute the missing values with the most frequent value in the column. In such cases, we impute the missing values with mode. To do this, we simply have to pass “most_frequent” as our strategy parameter.

from sklearn.impute import SimpleImputer
imputer =SimpleImputer(missing_values=np.nan, strategy= "most_frequent")
imputer.fit(x[:,1:3])
x[:,1:3]= imputer.transform(x[:,1:3])

Output

IMPUTING WITH MODE | Feature Engineering

Impute Missing Values for Categorical Variable

In our case, our dataset does not have any Categorical Variable with missing values. However, there may be cases when you come across a dataset where you might have to impute the missing values for some categorical variable.

To understand how to deal with such a scenario, let us modify our dataset a little and another new categorical ‘Gender’ which has a few missing entries. This will help us understand how to handle such cases. Our dataset now looks something like this:

dataset.isnull().sum()
Impute Missing Values for Categorical Variable | Feature Engineering
dataset.head(10)
data head

Now, look carefully at the ‘Gender’ column. It has ‘M’, ‘F’, and missing values (nan) as the entries.

There are three main ways to deal with missing Categorical values. We shall discuss each one of them.

DROPPING THE ROWS CONTAINING MISSING CATEGORICAL VALUES

dataset.dropna(axis=0, subset=['Gender'], inplace=True)
dataset.head(10)
DROPPING THE ROWS CONTAINING MISSING CATEGORICAL VALUES | Feature Engineering

Observe that all the rows in which the ‘Gender’ was NAN have been removed from the dataset. Here axis=0 specifies that the rows containing missing values must be removed and the ‘subset’ parameter contains the list of columns that should be checked for missing values.

ASSIGNING A NEW CATEGORY TO THE MISSING CATEGORICAL VALUES

Simply deleting the values which are missing, causes loss of information. To avoid that we can also replace the missing values with a new category. For example, we may assign ‘U’ to the missing genders where ‘U’ stands for Unknown.

dataset['Gender']= dataset['Gender'].fillna('U')
dataset.head(10)
ASSIGNING A NEW CATEGORY TO THE MISSING CATEGORICAL VALUES

Here all the missing values in the ‘Gender’ column have been replaced with ‘U’. This method adds information to the dataset instead of causing information loss.

IMPUTING CATEGORICAL VARIABLE WITH MOST FREQUENT VALUE

Finally, we may also impute the missing value with the most frequent value for that particular column. Yes, you guessed it right! We are going to substitute the mode value in the missing fields. Since in our dataset the category with the highest frequency is ‘M’, the missing values should be substituted with ‘M’.

dataset['Gender']= dataset['Gender'].fillna(dataset['Gender'].mode()[0])
dataset.head(10)
IMPUTING CATEGORICAL VARIABLE WITH MOST FREQUENT VALUE | feature Engineering

Predict the Missing Values

We are almost done with the various techniques to handle missing values. We are now down to the last method and that is Prediction Imputation.

The intuition behind this method is very simple yet effective. We are going to think of the column having missing values as the dependent variable ( or the y column). The rest of the columns can be the independent variable ( or the x column). Now, we take the completely filled rows as our training set and the missing value containing rows as our test set. Then we simply use a simple Linear regression model or a classification model to predict the missing values. Since this method takes into account the correlation between the missing value column and other columns to predict the missing values, it yields much better results than the previous methods. This is a great strategy to handle missing values.

Encoding Categorical Data

Congratulations! You’re done with all the missing data handling techniques. Now comes one of the most important Feature Engineering steps –  Encoding the categorical variables.

Let us first understand why this is needed.

Our dataset contains fields like ‘Country’ which have country names such as India, Spain and Belgium. The ‘Purchased’ column contains Yes or No. We cannot work with these Categorical variables as they are literals. All these non-numeric values must be encoded into a convenient numeric value that can be used to train our model. This is why we need Encoding of Categorical variables.

Encoding Independent Variables

Let us get back to our original dataset and have a look at our Independent variable x.

x= dataset.iloc[:,1:-1].values
y= dataset.iloc[:,-1].values
print (x)
Encoding Independent Variables

Our independent variable x contains a categorical variable “Country”. This field has 3 different values – India, Spain, and Belgium.

So should we encode India, Spain, and Belgium as 0, 1, and 2?

This apparently seems to be okay, right? But hold on. There is a catch!

The correct answer is NO. We cannot directly encode the 3 countries as 0,1 and 2. This is because, if we encode the countries in this manner then the machine learning model will wrongly assume that there is some sort of sequential relationship between the countries. This will make the model believe that India, Spain, and Belgium have a sequential order like the numbers 0, 1, and 2. This is not true. Hence, we must not feed in the model with such incorrect information.

So what is the solution?

The solution is to create separate columns for each category of the Categorical variable. Then we assign 1 to the column which is true and 0 to the others. The entire set of columns that represent the Categorical variable shall give us the result without creating any ordinal relationship

For our example, we may encode the countries as follows

solution

This can be done with the help of One Hot Encoding. The separate columns which are created to represent the categorical variables are known as the Dummy Variables. The fit_transform() method is called from the OneHotEncoder class which creates the dummy variables and assigns them with binary values. Let us have a look at the code.

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [0])], remainder='passthrough')
X = np.array(ct.fit_transform(x))
print(X)
dummy variables | feature Engineering

Voila! There we have our Categorical variables beautifully encoded into dummy variables without any ordinal relationship among the various categories.

Encoding Dependent Variables

Let us now have a look at our dependent variable y.

print(y)
Encoding Dependent Variables

Our dependent variable y is also a categorical variable. However in this case we can simply assign 0 and 1 to the two categories ‘No’ and ‘Yes’. In this case, we do not require dummy variables to encode the ‘Predicted’ variable as it is a dependent variable that will not be used to train the model.

To code this, we are going to need the LabelEncoder class.

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y = le.fit_transform(y)
LabelEncoder

Feature Scaling – The last step of Feature Engineering

Finally, we come to the last step of Feature Engineering – Feature Scaling.

Feature Scaling is the process of scaling or converting all the values in our dataset to a given scale. Some machine learning algorithms like linear regression, logistic regression, etc use gradient descent optimization. Such algorithms require the data to be scaled in order to perform optimally. K Nearest Neighbours, Support Vector Machine, and K-Means clustering also show a drastic rise in performance on scaling the data.

There are two main techniques of feature scaling:

  • Standardization
  • Normalization

NORMALIZATION

Normalization is the process of scaling the data values in such a way that that the value of all the features lies between 0 and 1.

NORMALIZATION

This method works well when the data is normally distributed.

STANDARDIZATION

Standardization is the process of scaling the data values in such a way that that they gain the properties of standard normal distribution. This means that the data is rescaled in such a way that the mean becomes zero and the data has unit standard deviation.

STANDARDIZATION

Standardized values do not have a fixed bounded range like Normalised values.

Let us have a look at the code. If you do not have separate training and test sets then you can split your dataset into two parts – one for training and the other for testing.

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 1)
print(X_train)
train_test split
print(X_test)
print test

Now we shall import the StandardScaler class to scale all the variables.

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train[:, 3:] = sc.fit_transform(X_train[:, 3:])
X_test[:, 3:] = sc.transform(X_test[:, 3:])
print(X_train)
StandardScaler
print(X_test)
x-test

We observe that all our values have been scaled. This is how Feature Scaling is performed.

NOTE: Keep in mind, that while scaling the features, we must only use the independent variables of the training set to compute mean(x) and standard deviation(x). Then these same values of  mean(x) and standard deviation(x) of the training set must be used to apply feature scaling to the test set.

Conclusion

Now our dataset is feature engineered and all ready to be fed into a Machine Learning model. This dataset can now be used to train the model to make the desired predictions. We have effectively engineered all our features. The missing values have been handled, the categorical variables have been effectively encoded and the features have been scaled to a uniform scale. Rest assured, now we can safely sit back and wait for our data to generate some amazing results!

Once you have effectively feature engineered all the variables in your dataset, you can be sure to generate models having the best possible efficiency as all the algorithms can now perform to their optimum capabilities.

That is the magic of Feature Engineering!

So next time you lay your hands on a dataset, bring out your inner Monica and start cleaning up those raw data! I’m sure you are going to ace it with the help of all the newly acquired Feature Engineering tools that you now have in your Machine Learning toolbox!

A Beginner’s Guide to Feature Engineering – Everything You Need to Know! Uncategorized PlatoAiStream PlatoAiStream. Data Intelligence. Vertical Search. Ai.

(Source: https://j-guard.com/wp-content/uploads/2021/05/notjustclean-1024×546.jpeg)

About Me:

Hey there, I’m Tithi Sreemany. Hope you liked reading this article and found it useful!

You can reach out to me on LinkedIn.

Do check out my other articles here: link.

Thanks for reading!

The media shown in this article are not owned by Analytics Vidhya and are used at the Author’s discretion.

Source: https://www.analyticsvidhya.com/blog/2021/10/a-beginners-guide-to-feature-engineering-everything-you-need-to-know/

" 7 9 Account algorithm algorithms All among Analysis analytics Art article articles Belgium BEST Build cases change classification Cleaning code Column Compute countries Creating data data scientist deal dealing Effective efficiency engineer Engineering ETC Feature Features fed Fields First fit Fix Flexibility Forbes Gender great Group guide Handling head here High hold How How To HTTPS huge image India information Internet intuition IT Jobs large learning Line LinkedIn List machine learning major map Media model names Neat numbers Okay open order organizing Other Others performance picture pivotal poor prediction Predictions present range Raw raw data Reading Reality regression REST Results Reviews Scale scaling Science scientists set setting Simple small So Spain spend split start started Strategy support Survey test Testing time Topics toy Training transforming US value wait What is WordPress Work workflow works X zero

Related Posts

The Future of Gaming has Arrived Everything You Need to Know About the Mirror Image One Console

Source Node:
Time Stamp: June 9, 2022 5:19 AM - Modified On: June 9, 2022 - Published By:
Source Cluster:
Republished By Plato

PRE-ORDER TODAY! www.mirrorimageone.xyz I hope you are as excited as we are for the release of the Mirror Image One Console. In the meantime, we wanted to provide details on what to expect from the console and our launch. What is the Mirror Image One? The Mirror Image One is the world's first Web 3.0 Gaming console powered by Nvidia GPUs and a Virtual Windows PC in the cloud. Our Console allows you to play your favorite games, securely browse the internet by using our secured browser, and development programs

Catalyst Blockchain Platform launches Blockchain Adoption Program

Source Node:
Time Stamp: April 7, 2022 1:16 PM - Modified On: April 7, 2022 - Published By:
Source Cluster:
Republished By Plato

Build enterprise-grade blockchain networks with high automation and guaranteed uptimes Wednesday 6th April 2022 — Catalyst Blockchain Platform has officially launched its Blockchain Adoption Program for innovation labs, research institutes, and accelerators. From today, organizations at the forefront of innovation can enroll to receive special commercial terms for the use of the platform. Collaborating innovators benefit from a 30% discount and an additional free month on the most complete blockchain management solution available. Catalyst Blockchain Platform is a comprehensive solution, allowing anyone to build, deploy, and maintain blockchain networks anapplications

About Us

  • Open Intelligence
  • Culture
  • Data Ecosystem
  • W3 Disruption
  • Team

Vertical Search & Ai

  • The Evolution of Search
  • What is Vertical Search
  • What is Vertical Intelligence
  • Ai Data Defragmentation
  • Data As A Service (DaaS)

Platform

  • Platform Features
  • Plato Analytics Reporting
  • PlatoAi NLP Engine
  • Sectors / Verticals
  • How Plato Works

Stay Connected

  • Governance
  • Register
  • Live Chat
  • Contact Us
  • Social

Account

  • Register
  • Packages
  • Enterprise
  • Listing
  • Partnerships
null
null

Copyright @ 2022 Plato Technologies Inc

Login

Lost your password?

Not a member yet? Register now.

[ethpress_login_button]