DS in Practice

Stages in Data Science Lifecycle

1. Data acquisition
2. Data cleaning and data warehousing
3. Data modeling and data summarization
4. Data analysis and data regression
5. Data visualization

Main Types of Data Analytics

• Predictive analytics: To make predictions about future trends or events and answers the question i.e. “What might happen in the future?”
• Descriptive analytics: To pull trends from raw data and succinctly describe what happened or is currently happening, i.e. “What happened?”
• Prescriptive analytics: To take into account all possible factors in a scenario and suggest actionable takeaways i.e. “What should we do next?”
• (Optional) Diagnostic analytics: To compare coexisting trends or movement, uncovering correlations between variables, and determining causal relationships where possible, i.e. “Why did this happen?”

Different Levels of Risks

Unacceptable Risks: (Prohibited)

• Voice-activated toys that encourage dangerous behaviour in children
• Biometric identification
• Social scoring
• Deceptive techniques
• Facial recognition databases

Exception: law enforcement purposes

High Risks: (Conformity Assessment)

Conformity Assessment「符合性评估」

• AI systems in cars, medical devices
• AI systems used in education, vocational training, employment
• AI system for record-keeping

Limited Risks: (Transparency)

• ChatGPT
• Deep Fakes
• Chat bots

Minimal Risks: (Code of Conducts)

• AI enabled video games
• Spam filters

Python Identifiers

Identifiers are names given by programmers to variables, functions, etc. in a program

An identifier must conform to the following rules:

• Contains only
  • Alphabets (A – Z, a – z)
  • Digits (0 – 9)
  • Underscore characters (_)
• First character cannot be a digit
• Case sensitive
• Cannot be one of the reserved words