Predicting Titanic Survivors with Machine Learning
summary
891-row train.csv of Titanic passengers gets explored with pandas + matplotlib and then modeled with scikit-learn; a one-line heuristic “if female predict survive” scores ~78% (701 correct, 190 wrong), a LogisticRegression pushes to ~79%, and a DecisionTree hits ~98% on training but collapses under cross-validation (overfitting). visual export creates tree.dot/png showing top splits: sex, age < 6.5, Pclass; data finds 342 survivors total and that 77 of 78 first‑class women survive in this dataset.
AI-written summary · about
chapters (29)
- 0:00Introduction
- 2:05Desktop background
- 3:20Project overview
- 4:40Visualize the pipe
- 5:53Plot
- 6:50Normalize
- 7:20Subplots
- 8:10Copy Paste
- 8:39Survival Rate
- 9:47Passenger Class Distribution
- 10:55Python List Comprehension
- 12:38Titanic made 2 stops
- 14:33Men vs Women
- 19:30Women
- 22:54Check Accuracy
- 23:23Extract Results
- 24:46Linear Model
- 26:50Clean Data
- 27:46How Algorithms Work
- 28:24Classification
- 29:19Output
- 29:38Not linear
- 30:12Preprocessing
- 31:20Algorithm Improvements
- 32:09Decision Trees
- 33:01Classifier
- 33:19Overfitting
- 34:00Machine Learning
- 34:23Model Selection
related talks
44mA Practical-ish Introduction to Data Science
27mUsing Machine Learning to solve a classification problem with scikit-learn
01h 23mMachine learning in Action
54m"Would YOU Survive the Titanic?", with ML and .NET
39m"Would YOU Survive the Titanic?", with ML and .NET
57mHow To Evaluate and Improve Machine Learning Models
51mHow to Test Artificial Intelligence and Machine Learning Solutions?
44mPredict the Future with Watson Studio AutoAI