Scribd Logo
Upload

Welcome to Scribd!

  • 177 views

    Tugas 2: Bayessian Method (Atribut Kontinyu) : Outlook Temperature Humidity Windy Play-Class

    Uploaded by

    Rifki Satyaw
    This document discusses using the Naive Bayes method with Laplace smoothing to classify a test sample for weather data. It provides sample weather data and calculates the probabilities of each attribute value given the class (YES or NO). It then calculates the probabilities P(X|Yes) and P(X|No) and determines that P(X|Yes) is greater, so the most likely class for the test sample is YES.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Tugas 2: Bayessian Method (Atribut Kontinyu) : Outlook Temperature Humidity Windy Play-Class

    Uploaded by

    Rifki Satyaw
    177 views3 pages
    This document discusses using the Naive Bayes method with Laplace smoothing to classify a test sample for weather data. It provides sample weather data and calculates the probabilities of each attribute value given the class (YES or NO). It then calculates the probabilities P(X|Yes) and P(X|No) and determines that P(X|Yes) is greater, so the most likely class for the test sample is YES.

    Original Title

    bahas alami

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses using the Naive Bayes method with Laplace smoothing to classify a test sample for weather data. It provides sample weather data and calculates the probabilities of each attribute value given the class (YES or NO). It then calculates the probabilities P(X|Yes) and P(X|No) and determines that P(X|Yes) is greater, so the most likely class for the test sample is YES.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    177 views3 pages

    Tugas 2: Bayessian Method (Atribut Kontinyu) : Outlook Temperature Humidity Windy Play-Class

    Uploaded by

    Rifki Satyaw
    This document discusses using the Naive Bayes method with Laplace smoothing to classify a test sample for weather data. It provides sample weather data and calculates the probabilities of each attribute value given the class (YES or NO). It then calculates the probabilities P(X|Yes) and P(X|No) and determines that P(X|Yes) is greater, so the most likely class for the test sample is YES.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 3

    TUGAS 2 : BAYESSIAN METHOD (ATRIBUT KONTINYU)

    1. Diketahui data set sebagai berikut :

    OUTLOOK TEMPERATURE HUMIDITY WINDY PLAY-


    CLASS
    OVERCAST 72 88 TRUE NO
    RAINY 50 69 FALSE YES
    RAINY 66 90 FALSE NO
    SUNNY 71 87 TRUE NO
    RAINY 63 68 TRUE YES
    RAINY 59 60 TRUE NO
    OVERCAST 91 89 FALSE YES
    RAINY 71 97 FALSE NO
    OVERCAST 94 66 TRUE YES
    SUNNY 69 83 FALSE YES
    DIMANA :
    UNTUK ATRIBUT OUTLOOK :
    1 : SUNNY
    2 : OVERCAST
    3 : RAINY
    UNTUK ATRIBUT WINDY : berangin
    1 : FALSE
    2 : TRUE
    UNTUK PLAY-CLASS :
    1 : NO
    2 : YES

    a) Tentukan kelas dari test sample : x=(Outl=Sunny, Temp=60, Hum=60, Wind=true)dengan


    metode naïve bayes dengan menggunakan pendekatan laplace.

     Temperature “No”
    𝜇 = (72 + 66 + 71 + 59 + 71)/5
    =𝟔𝟕. 𝟖

    𝑆 2 = ((72 − 67,8)2 + (66 − 67,8)2 + (71 − 67,8)2 + (59 − 67,8)2 + (71 − 67,8)2 )/4
    = (17.64+3.24+10.24+77.44+10.24)/4
    = 118.8/4
    = 𝟐𝟗, 𝟕
    𝑆 = √29,7 =𝟓. 𝟒𝟓

    1 (60−67.8)2
    −
    𝑃 (𝑇𝑒𝑚𝑝 = 60|𝑁𝑜) = 𝑒 2(29.7)
    √2𝜋(5.45)2
    1 60.84
    = 𝑒 − 59.4
    √2 ∗ 3.14(5.45)2

    1
    = 𝑒 −1.0242
    186.516

    = 0.005 ∗ 0.3591 = 0.001795

     Temperatur “Yes”
    𝜇 = (50 + 63 + 94 + 69)/4
    276
    = 4
    = 𝟔𝟗
    𝑆 2 = ((50 − 69)2 + (63 − 69)2 + (94 − 69)2 + (69 − 69)2 /3
    = (361+36+625+0)/3
    = 1022/3
    = 𝟑𝟒𝟎. 𝟔𝟔
    𝑆 = √340.66 = 𝟏𝟖. 𝟒𝟓
    1 (60−69)2
    −
    𝑃 (𝑇𝑒𝑚𝑝 = 60|𝑌𝑒𝑠) = 𝑒 2(340.66)
    √2𝜋(18.45)2

    1 81
    = 𝑒 −681.32
    √213771.2
    1
    = 𝑒 −0.119
    462.35

    = 0.0216 ∗ 0.8878= 0.0192

     Humidity “No”
    𝜇 = (88 + 90 + 87 + 60 + 97)/5
    =422/5
    = 𝟖𝟒. 𝟒

    𝑆 2 = ((88 − 84.4)2 + (90 − 84.4)2 + (87 − 84.4)2 + (60 − 84.4)2 + (97 − 84.4)2 )/4
    = (12.96+31.36 +6.76+595.36+158.76)/4
    = 805.2/4
    = 𝟐𝟎𝟏. 𝟑
    𝑆 = √201.3 = 𝟏𝟒. 𝟏𝟖𝟖

    1 (60−84.4)2
    −
    𝑃 (𝐻𝑢𝑚 = 60|𝑁𝑜) = 𝑒 2(201.3)
    √2𝜋(14.188)2
    1 595.36
    = 𝑒− 59.4
    √2 ∗ 3.14(14.188)2

    1
    = 𝑒 −1.0242
    126410.12

    = 0.00000791 ∗ 0.3591 = 0.00000284

     Humidity “Yes”
    𝜇 = (69 + 68 + 89 + 66 + 83)/5
    375
    =
    5
    = 𝟕𝟓
    𝑆 = ((69 − 75)2 + (68 − 75)2 + (89 − 75)2 + (66 − 75)2 + (83 − 75)2 /4
    2

    = (36+49+196+81+64)/4
    = 𝟏𝟎𝟔. 𝟓
    𝑆 = √106.5 = 𝟏𝟎. 𝟑𝟐
    1 (60−75)2
    −
    𝑃 (𝑇𝑒𝑚𝑝 = 60|𝑌𝑒𝑠) = 𝑒 2(106.5)
    √2𝜋(10.32)2

    1
    = 𝑒 −1.056
    √668.82
    1
    = ∗ 𝑒 −0.119
    25.86

    = 𝟎. 𝟎𝟏𝟑𝟓
    𝑃(𝑂𝑢𝑡𝑙 = 𝑆𝑢𝑛𝑛𝑦|𝑁𝑜) = 2/5= 0.4
    𝑃(𝑂𝑢𝑡𝑙 = 𝑆𝑢𝑛𝑛𝑦|𝑌𝑒𝑠) =1/5=0.2

    𝑃(𝑂𝑢𝑡𝑙 = 𝑜𝑣𝑒𝑟𝑐𝑎𝑠𝑡|𝑁𝑜) =1/5=0.2


    𝑃(𝑂𝑢𝑡𝑙 = 𝑜𝑣𝑒𝑟𝑐𝑎𝑠𝑡|𝑌𝑒𝑠) =2/5=0.4

    𝑃(𝑂𝑢𝑡𝑙 = 𝑅𝑎𝑖𝑛𝑦|𝑁𝑜) =3/5=0.6


    𝑃(𝑂𝑢𝑡𝑙 = 𝑅𝑎𝑖𝑛𝑦|𝑌𝑒𝑠) =2/5=0.4

    𝑃(𝑊𝑖𝑛𝑑 = 𝑇𝑟𝑢𝑒|𝑁𝑜) =3/5=0.6


    𝑃(𝑊𝑖𝑛𝑑 = 𝑇𝑟𝑢𝑒|𝑌𝑒𝑠) =2/5=0.4

    𝑃(𝑊𝑖𝑛𝑑 = 𝐹𝑎𝑙𝑠𝑒|𝑁𝑜) =2/5=0.4


    𝑃(𝑊𝑖𝑛𝑑 = 𝐹𝑎𝑙𝑠𝑒|𝑌𝑒𝑠) =3/5=0.6

    𝑃(𝑇𝑒𝑚𝑝 = 60|𝑁𝑜) = 0.001795


    𝑃(𝑇𝑒𝑚𝑝 = 60|𝑌𝑒𝑠) = 0.0192

    𝑃(𝐻𝑢𝑚 = 60|𝑁𝑜) = 0.00000284


    𝑃(𝐻𝑢𝑚 = 60|𝑌𝑒𝑠) = 0.0135

    𝑃(𝑋|𝑁𝑜) = 𝑃(𝑂𝑢𝑡𝑙 = 𝑆𝑢𝑛𝑛𝑦|𝑁𝑜) ∗ (𝑇𝑒𝑚𝑝 = 60|𝑁𝑜) ∗ (𝐻𝑢𝑚 = 60|𝑁𝑜) ∗ (𝑊𝑖𝑛𝑑 = 𝑇𝑟𝑢𝑒|𝑁𝑜)

    = 0.4 ∗ 0.001795 ∗ 0.00000284 ∗ 0.6

    = 0.0000000012235

    𝑃(𝑋|𝑌𝑒𝑠) = 𝑃(𝑂𝑢𝑡𝑙 = 𝑆𝑢𝑛𝑛𝑦|𝑌𝑒𝑠) ∗ (𝑇𝑒𝑚𝑝 = 60|𝑌𝑒𝑠) ∗ (𝐻𝑢𝑚 = 60|𝑌𝑒𝑠) ∗ (𝑊𝑖𝑛𝑑 = 𝑇𝑟𝑢𝑒|𝑌𝑒𝑠)

    = 0.2 ∗ 0.0192 ∗ 0.0135 ∗ 0.4

    = 0.000020736

    Karena P(X|No)P(No)<P(X|Yes)P(Yes)

    Maka P(No|X)<P(Yes|X)→Class = YES

    You might also like