Introduction
- Introduction to Course
- How are we going to cover the content?
- Which tool are we going to use?
- What is unique about the course?
What is Data Science Project and our methodology
- Project Management Techniques : SEMMA and KDD
- Project Management : CRISP-DM
Knime Download and Installation
- Knime Web Page and Download
- Knime Environment and Screens
- First Workflow and Data Coloring / Visualization
Welcome to Data Science
- First end-to-end problem: Teaching to the machine
Understanding Problem
- Types of analytics: Descriptive, Predictive and Prescriptive Analytics
Understanding Data
- Data Types and Problem Types
Understanding Data and Data Preprocessing
- Introduction to Data Manipulation and Preprocessing
- Data Accessing (File Reader, Excel Reader and Table Creator)
- Data Discovery: Basic Visualization
- Data Discovery: Advanced Visualization Examples
- Row Filtering and Missing Values
- Advanced Filtering: Rule Based Row Filtering
- Column Filtering
- Concatenation
- Join (Inner Join, Left , Right or Full Outer Joins)
- Grouping and Aggregation
- Math Formula and String Replace
- Discrete / Quantized Data and Binning
- Normalization
- Pivot Operation
- EXTRA : Meta Node and Data Generation in Knime
- Splitting and Combining
- Type Conversion (String, Numeric)
Modeling
- Introduction to Machine Learning : Test and Train Datasets
- Introduction to Machine Learning: Problem Types
Classification
- Bayes Theorem and Naive Bayes Model
- Knime Application of Naive Bayes Algorithm
- Decision Tree, Information Gain and Gini index
- Decision Tree Practicum with Knime
- k-Nearest Neighbor Algorithm
- k-NN Practicum with Knime
- Distance Metrics
- Distance Metrics Practicum
- SVM: Support Vector Machines
- SVM Practicum
- End to End Practicum with all Algorithms
- Logistic Regression: Theory
- Comparing Classification Algorithms
Association Rule Mining / Learning
- An Introduction to ARM / ARL and A Priori Algorithm
- Apriori Algorithm in Action
Clustering / Segmentation
- Introduction to Clustering and Concepts
- K-Means Algorithm
- K-Means: Optimum number of clusters ( k value) and WCSS
- K-Means Practicum with Knime
- Optimizing number of clusters (k value) in Knime with Grid Search
- Hierarchical Clustering: Agglomerative and Divisive Approaches
- Hierarchical Clustering Practicum with Knime
- DBSCAN : Density Based Approach
- DBSCAN Practicum
- Comparison of Clustering Algorithms
Regression / Prediction Algorithms
- Linear Regression
- Linear Regression Practicum
- Introduction to Evaluation of Regression Models
- Practicum of Simple Evaluation of the Regression Models
- Multiple Linear Regression: Theory and Practicum
- Polynomial Regression
- Simple Regression Tree
- Simple Regression Tree Practicum
- Comparison of Regression Models
- Sample Problem / Solution : Stock Market Regression
Knime as a tool: Advanced Knime Features and Maintenance
- PMML Standard and Theory
- PMML Action with Knime
Evaluation
- Introduction to Evaluation
- Baseline, ZeroR and Imbalanced Data Sets
- Comparison of Imbalanced Data Solutions
- Evaluation Chart
