DATA SCIENCE WITH WEKA GUI

Weka

Introduction

• Introduction
• Data Workflows

Pre-processing

• Creating and Loading Data
• Preprocessing
• Sparse Data
• Numeric Transform
• Outliers and Extreme Values
• Merge and Append ARFF files

Features

• Feature Scoring and Ranking 1 2 3
• Principal Component Analysis 1 2
• Feature Selection with Wrapper
• Feature Selection with Filter
• Generating Non-stratified Folds
• Attribute Selection with Knowledge Flow Environment

Data Visalization

• Visualizing data

Clustering

• K-Means 1 2 3
• Representing and Evaluating clusters 1 2 3

Data Modelling

• Predictive Models (33)

Classification

• Classification using Explorer
• Text Classification
• Logistic Regression
• SVM
• Cross-validation
• J48 Weka
• Systematic Oversampling (Class Imbalance Problem)
• Held-out Testing
• Stacking Multiple Classifiers
• Classification 101 with Knowledge Flow Environment
• Classification 101 using API

Model Evaluation

• Model Evaluation and Scoring
• Confusion Matrix
• Models 101
• Cross Validation Error Rates
• Detail Cross Validation Results using API
• Model Comparison
• Inverse k-fold Cross Validation
• ROC Curves and AUC

Image Analytics

• Clustering
• Classification
• Clustering of Monet and Manet
• Finding the Lost Monet

Text Preprocessing

• Text Preprocessing
• Classifying tweets
• Classification
• How to Import Text Documents

Java API

• The Java API with Eclipse
• Java API 101
• Saving Results in Weka

Advanced Data Mining with Weka

• Introduction
• Linear regression with lags
• Time Series Forecasting Package
• Looking at forecasts
• Lag creation, and overlay data
• Application: Infrared data from soil samples
• Incremental classifiers in Weka
• Weka’s MOA package
• The MOA interface
• MOA classifiers and streams
• Classifying tweets
• Application to Bioinformatics – Signal peptide prediction
• LibSVM and LibLINEAR
• Setting up R with Weka
• Using R to plot data
• Using R to run a classifier
• Using R to preprocess data
• Application: Functional MRI Neuroimaging dat
• Distributed Weka
• Installing with Apache Spark
• Using Naive Bayes and JRip
• Map tasks and Reduce tasks
• Miscellaneous capabilities
• Application: Image classification
• Invoking Python from Weka
• Building models
• Visualization
• Invoking Weka from Python

Highlights of the course

• Online, Classroom and On-Premise
• No prior programming experience required
• Suitable for professionals who have domain experience or starters who don’t want to be programmers

Course Duration

• Normal: One Month (online and classroom)
• Accelerated: One Week (online and classroom)
• On Premise: 3-5 days