A Practical-ish Introduction to Data Science
summary
Uses the Titanic CSV (891 rows) to build a decision‑tree classifier predicting survival from age, gender, and ticket class; missing ages are imputed by extracting honorifics and filling with median ages (feature engineering). Data splits 75/25 train/test; initial tree scores ~75% accuracy, then pruning to max depth 3 raises accuracy to ~79.8% (about a 5% gain), implemented with scikit-learn in a Jupyter notebook (Anaconda).
AI-written summary · about
chapters (18)
- 0:00Start
- 3:27Data Science Process: Hypothesis Driven
- 9:53Machine Learning: A Tool for Data Science
- 10:57What is Data Science: Key Takeaways
- 12:51The Art of The Generalized Model
- 14:43Machine Learning Types
- 16:17Common Machine Learning Algorithm Types
- 19:27Fitting a trend line: Ordinary Least Squares
- 21:15Linear Regression Notes
- 21:37Decision Tree: Calculating the Best Split
- 24:01Decision Tree: Recursive Partitioning
- 25:21Decision Tree Notes
- 25:46Example Machine Learning Algorithms
- 26:54Sum of Squared Errors
- 29:08K-Means Clustering Notes
- 29:31Machine Learning Algorithms: Key Takeaways
- 30:16Use Case: Titanic Passenger Survival
- 33:42Feature Engineering 1: Impute missing Age values using name
related talks
45mA Practical Introduction to Data Science
39mPredicting Titanic Survivors with Machine Learning
27mUsing Machine Learning to solve a classification problem with scikit-learn
41mA Practical-ish Introduction to Data Science
47mA Practical(ish) Introduction to Data Science
01h 23mMachine learning in Action
51mExploring Decision Trees with Matryoshka
54m"Would YOU Survive the Titanic?", with ML and .NET