Classification boundaries
This presentation is the property of its rightful owner.
Sponsored Links
1 / 40

CLASSIFICATION BOUNDARIES PowerPoint PPT Presentation


  • 62 Views
  • Uploaded on
  • Presentation posted in: General

CLASSIFICATION BOUNDARIES. 姓名 : 吳思葦 學號 :601630402 課堂教授 : 魏世杰 報告日期 :102/12/3 1. Weka’s Boundary Visualizer for OneR. Open iris.2D.arff , a 2D dataset Weka GUI Chooser : Visualization > BoundaryVisualizer Open iris.2D.arff Note: petallength on X , petalwidth on Y

Download Presentation

CLASSIFICATION BOUNDARIES

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Classification boundaries

CLASSIFICATION BOUNDARIES

姓名:吳思葦

學號:601630402

課堂教授:魏世杰

報告日期:102/12/31


Weka s boundary visualizer for oner

Weka’s Boundary Visualizer for OneR

  • Open iris.2D.arff , a 2D dataset

  • Weka GUI Chooser : Visualization >BoundaryVisualizer

    • Open iris.2D.arff

    • Note: petallength on X , petalwidth on Y

    • Choose rules > OneR

    • Check Plot training data

    • Click Start

    • In the Explorer , examine OneR’s rule


Visualize boundaries for other schemes

Visualize boundaries for other schemes

  • Choose lazy>IBK

    • Plot training data ; click Start

    • K=5,20;note mixed colors


Visualize boundaries for other schemes1

Visualize boundaries for other schemes

  • Choose bayes > NaiveBayes

    • Set useSupervisedDiscretization to true


Visualize boundaries for other schemes2

Visualize boundaries for other schemes

  • Choose trees > J48

    • Relate the plot to Explorer output


Classification boundaries1

CLASSIFICATION BOUNDARIES

  • Classifiers create boundaries in instance space

  • Different classifiers have different biases

  • Looked at OneR , IBK , NaiveBayes , J48

  • Visualization restricted to numeric attributes , and 2D plots


Preprocessing and parameter tuning

PREPROCESSING AND PARAMETER TUNING


Preprocessing

PREPROCESSING

  • Explorer可提供的資料預處理項目:

    • 離散化(Discretization)

    • 正規化(normalization)

    • 重新抽樣(resampling)

    • 屬性選擇(attribute selection)

    • 屬性轉換或合併(transforming and combining attributes)…


Discretization

Discretization

  • Unsupervised

    • weka.filters.unsupervised.attribute.Discretize

      • equal-width (the default)

      • equal-frequency

  • Supervised

    • weka.filters.supervised.attribute.Discretize


Attribute selection

Attribute Selection

  • 屬性評估器

    • 屬性子集評估器

    • 單一屬性評估器

  • 搜索方法

    • 搜索方法

    • 排序方法


Attribute selection1

Attribute Selection

  • 屬性評估器

    • 屬性子集評估器

    • 單一屬性評估器

  • 搜索方法

    • 搜索方法

    • 排序方法


Attribute selection2

Attribute Selection

  • 兩種屬性子集選取模式

    • 屬性子集評估器+搜索方法

    • 單一屬性評估器+排序方法


Classification boundaries

屬性子集評估器+搜索方法

搜索方法

BestFirst

ExhaustiveSearch

GeneticSearch

GreedyStepwise

RandomSearch

RankSearch

  • 屬性子集評估器

    • CfsSubsetEval

    • ClassifierSubsetEval

    • ConsistencySubsetEval

    • WrapperSubsetEval


Classification boundaries

單一屬性評估器+排序方法

  • 單一屬性評估器

    • ChiSquaredAttributeEval

    • GainRationAttributeEval

    • InfoGainAttributeEval

    • OneRAttributeEval

    • PrincipleComponents

    • ReliefAttributeEval

    • SymmetricalUncertAttributeEval

  • 排序方法

    • Ranker


  • Login