FIT1043 | VINZ.UK

password

icon

TOC

Week 1 The data science process Standard Value Chain Week 5 Machine Learning Supervised ML Unsupervised ML

Week 1

The data science process

1, Pitching ideas 提出想法

for data science projects to investors / managers

2, Collecting data 收集数据

getting the data

eg. Researchers preparing to x-ray a patient.

3, Integration 整合

Data can come from many different sources.

4, Interpretation 解释

Data can be described using a database schema.

5, Governance 管理

(i) caring for the data and its subjects.

(ii) managing data standards and formats.

6, Engineering 工程

Data engineers make the back-end work

7, Wrangling 争论

Inspecting and cleaning the data

8, Modelling 建模

Proposing a conceptual / mathematical / functional model.

Analyst building models with his favorite tool.

Analysis, statistics and/or machine learning works on the data.

9, Visualisation 可视化

Visualizing data to interpret it and present results.

Choosing appropriate visualizations for the data. Many different options exist!

10, Operationalize 实施

Putting the results to work.

Standard Value Chain

Week 5

Machine Learning

Supervised ML

All data is labelled and the algorithms learn to predict (infer) the output from the input data.

The goal is to approximate the mapping function so well that when you have new input data (x), you can predict the output variable (y) for that data.

Examples

Classification: The output variable is a category (e.g. “Red” or “Blue” for the Fish Classification)

Regression: The output variable is a real value (e.g. “dollars” or “weight”)

Unsupervised ML

All data is unlabelled and the algorithms learn to inherent structure from the input data.

The goal is to model the underlying structure or distribution in the data in order to learn more about the data.

Examples

Example problems

Face similarity detection

Clustering: Discover the inherent groupings in the data (e.g. grouping customers by purchasing behavior)

Association: Discover rules that describe large portions of your data (e.g. people that buy X also tend to buy Y)

Example Algorithms

K-means for clustering problems.

Apriori algorithm for association rule learning problems.