Machine learning workshop using Orange datamining framework
Download as PPTX, PDF1 like1,790 views
The document discusses a workshop on the Orange data mining framework, focusing on applications such as fault detection in photovoltaic systems and medical diagnosis for breast cancer using ultrasound images. It covers steps for defining problems, preparing data, and various data cleaning and feature engineering techniques. Additionally, it highlights essential processes like data preparation, model evaluation, and dimensionality reduction.
Machine learning workshop using Orange datamining framework
- 2. Workshop on Orange : Data mining framework, data visualization, and data analytics. Introduced by : Amr Rashed Lecturer, Department of Computer Engineering, College of Computers and Information Technology, Taif University M.Sc., Electronics & Communication Engineering Faculty of Engineering, Mansoura University
- 3. Agenda Topics: Introduction & overview Application 1: Fault Detection for Attaining Service Continuity of Photovoltaic Power System Application 2: Data Mining for Diagnosis of Breast Cancer in Medical Ultrasonic Images
- 4. Project 1
- 5. Project 2
- 6. Applied Machine Learning Process Improve Improve Results Present Present Results Spot Spot Check Algorithms Prepare Prepare Data Define Define the Problem
- 7. Define the Problem Step 1: What is the problem? Step 2: Why does the problem need to be solved? Step 3: How would I solve the problem?
- 8. Data Preparation Techniques 1.Common Data Preparation Tasks 1.Data Cleaning 1.Feature Selection 1.Data Transforms 1.Feature Engineering 1.Dimensionality Reduction
- 9. Common Data Preparation Tasks •Step 1: Define Problem. •Step 2: Prepare Data. •Step 3: Evaluate Models. •Step 4: Finalize Model.
- 10. Data Cleaning Data cleaning involves fixing systematic problems or errors in “messy” data. Using statistics to define normal data and identify outliers. Identifying columns that have the same value or no variance and removing them Identifying duplicate rows of data and removing them. Marking empty values as missing. Imputing missing values using statistics or a learned model.
- 11. Overview of data cleaning
- 14. Feature Engineering Feature engineering is the process of creating new input variables from the available data. Adding a Boolean flag variable for some state. Adding a group or global summary statistic, such as a mean. Adding new variables for each component of a compound variable, such as a date-time. Polynomial Transform: Create copies of numerical input variables that are raised to a power(raising them to a power or multiplied with other input variables).
- 16. Overview of data types
- 18. Cont.
- 19. Cont.
- 20. Cont.
- 25. Create Dataset for the First Project (250kw grid connected PV array)
- 28. Example
- 30. MATLAB Script
- 67. Project 2 • Data Mining for Diagnosis of Breast Cancer in Medical Ultrasonic Images
Editor's Notes
- #13: Feature Selection: Select a subset of input features from the dataset. Unsupervised: Do not use the target variable (e.g. remove redundant variables). e.g., Correlation Supervised: Use the target variable (e.g . remove irrelevant variables). Wrapper: Search for well-performing subsets of features. e.g., RFE Filter: Select subsets of features based on their relationship with the target. Statistical Methods Feature Importance Methods Intrinsic: Algorithms that perform automatic feature selection during training. Decision Trees Dimensionality Reduction: Project input data into a lower-dimensional feature space.
- #14: Discretization Transform: Encode a numeric variable as an ordinal variable. Ordinal Transform: Encode a categorical variable into an integer variable. One-Hot Transform: Encode a categorical variable into binary variables. Normalization Transform: Scale a variable to the range 0 and 1. Standardization Transform: Scale a variable to a standard Gaussian. Power Transform: Change the distribution of a variable to be more Gaussian. Quantile Transform: Impose a probability distribution such as uniform or Gaussian.
- #16: Principal Component Analysis (PCA) Singular Value Decomposition (SVD) Linear Discriminant Analysis (LDA) self-organizing maps(SOM)
- #17: Numeric Data Type: Number values. Integer: Integers with no fractional part. Real: Floating point values. Categorical Data Type: Label values. Ordinal: Labels with a rank ordering. Nominal: Labels with no rank ordering. Boolean: Values True and False.
- #18: https://orangedatamining.com/download/#windows