A Practical Introduction to Data Science
summary
Explains building a data science capability from scratch, uses scikit-learn and pandas with Jupyter/Anaconda, and shows a practical Titanic demo where missing ages are imputed from honorifics and categorical sex and class are encoded; a decision tree yields ~75% accuracy then improves to 80% accuracy after limiting tree depth and pruning to avoid overfitting. Emphasizes that feature engineering and data cleaning take ~80% of effort, and models must be validated with held-out test sets.
AI-written summary · about
chapters (19)
- 0:00Start
- 5:27Data Science Process: Hypothesis Driven
- 9:27Data Science as an Evolution of BI
- 11:11Machine Learning: A Tool for Data Science
- 12:16What is Data Science: Key Takeaways
- 13:18Machine Learning: Models vs. Algorithms
- 16:04Machine Learning Algorithm Types
- 16:32Example Machine Learning Algorithms
- 18:47Linear Regression Notes
- 21:17Support Vector Machine Notes
- 22:28Building a Decision Tree: Recursive Partitioning
- 23:04Decision Tree Notes
- 24:20K-Means: Calculating the k value
- 26:20K-Means Clustering Notes
- 27:14Data Science Skills and Machine Learning
- 27:43Machine Learning Algorithms: Key Takeaways
- 28:30Use Case: Titanic Passenger Survival
- 39:20Building Machine Learning Models
- 43:43Practical Example: Key Takeaways
related talks
41mA Practical-ish Introduction to Data Science
47mA Practical(ish) Introduction to Data Science
44mA Practical-ish Introduction to Data Science
40mEveryone can Data! - A Practical Data Science Intro
27mUsing Machine Learning to solve a classification problem with scikit-learn
42mI'm Starting in DataScience – Where to Begin?
28mThe Coding Portion of Data Science
04h 03mTutorial - Intro to Data Science