[Python] #1 Python for Data Science: Intro

This is a self note while taking the online course from: LinkedIn Learning: Python for Data Science Essential Training Part 1 by Lillian Pierson

---

1. Introduction to the Data Professions

• Data science: systematic study of structure and behavior of data

  • past + current ==> predict future
  • interestd in why over how
  • uncover correlations and causations in data to support decision-making

• Data engineering: design, construction, and maintenance of data systems

  • prefer to design and build IT systems (rather than to analyze data)
  • interested in how over why
  • design systems to collect, handle, and store big datasets
  • build modular, scalable platforms for data processing

• Data analytics: data products that describe data and how it behaves by data analysis and visualization processes

  • use applications to analyze data (without coding)
  • deploys analytics technologies (analytics S/W applications)

2. Data Science

• Data Analysis: process for making sense of data
  • includes data cleaning, reformatting, and recombining data
  • discovers real-life phenomenon data
• Data Science:
• Artificial Intelligence: a machine or application with the capacity to autonomously execute upon predictions it makes from data
  1. Prediction: predictive modeling (from data science)
  2. Execution: autonomous response (from engineering)
• Deep learning: set of predictive methodologies that borrows its structure from the Neural Network structures of the brain
  • effective for making predictions from big data
  • can be used as a decision model with applications to produce deep learning AI

+) Main Python Libraries for Data Science

• Advanced Data Analysis: NumPy, SciPy, pandas
• Data Visualization: Matplotlib, Seaborn
• Machine Learning: scikit-learn, TensorFlow, Keras