"Fp-Growth"

sylar_19
sylar_19 New Altair Community Member
edited November 2024 in Community Q&A
I used weather nominal base. Someone could help me to interpret this results or give a tutorial to do it?

Association Rules
[Temperatura = Frio] --> [Umidade] (confidence: 1.000)
[Vento, Temperatura = Frio] --> [Umidade] (confidence: 1.000)
[Probabilidade = Chuvoso, Temperatura = Frio] --> [Umidade] (confidence: 1.000)

T r e e
Probabilidade = Chuvoso
| Vento = Nao: Sim {Nao=0, Sim=3}
| Vento = Sim: Nao {Nao=2, Sim=0}
Probabilidade = Ensolarado
| Umidade = Alta: Nao {Nao=3, Sim=0}
| Umidade = Normal: Sim {Nao=0, Sim=2}
Probabilidade = Nublado: Sim {Nao=0, Sim=4}

Answers

  • DocMusher
    DocMusher New Altair Community Member
    Hi,
    A first step is to take a look at the following book:
    https://rapidminer.com/wp-content/uploads/2013/10/DataMiningForTheMasses.pdf
    If this does not provide you the answer you wanted, please come back.
    Cheers
    Sven
  • haddock
    haddock New Altair Community Member
    Hola sylar_19,

    I spend most of my time on association rules ( see my website ), and feel the need to jump in, so here goes.

    Association rules are a form of unsupervised learning, that means that their is no supervisor to tell the machine what to look for.  You use unsupervised learning to explore data. The machine first looks for things that happen together, and then makes rules from those patterns. In your case as follows:-

    Sets
    [Temperatura = Frio , Umidade]
    [Vento, Temperatura = Frio ,Umidade]
    [Probabilidade = Chuvoso, Temperatura = Frio ,Umidade]

    Association Rules
    [Temperatura = Frio] --> [Umidade] (confidence: 1.000)
    [Vento, Temperatura = Frio] --> [Umidade] (confidence: 1.000)
    [Probabilidade = Chuvoso, Temperatura = Frio,Umidade] (confidence: 1.000)
    By contrast with Decision trees you know what you are looking for, in this case whether it is sunny or cloudy, this is called supervised learning. You use supervised learning when you want to predict something.

    T r e e
    Probabilidade = Chuvoso
    | Vento = Nao: Sim {Nao=0, Sim=3}
    | Vento = Sim: Nao {Nao=2, Sim=0}
    Probabilidade = Ensolarado
    | Umidade = Alta: Nao {Nao=3, Sim=0}
    | Umidade = Normal: Sim {Nao=0, Sim=2}
    Probabilidade = Nublado: Sim {Nao=0, Sim=4}
    In my own case of text mining, if I have keywords already and type into Google that is supervised, whereas if I have the documents and want the key words that is unsupervised. It is the fundamental difference between " go find this in there" and "what is in there". Hope that helps,

    H