Machine-Learning-with-Tree-Based-Models-in-Python

01 Decision Tree Regression (Theory)

• Non parametric algo
• find descriptive features contain most information about target
• split those feature to get pure subset
• learn simple decision rule of a target variable

02 Classification Tree (Theory)

• Decision tree used for Classification Problem

03 Entropy, Information Gain & Gini Index (Theory)

• Which feature to select first
• Entropy measure purity of split :
  • [-p(one class) * log(p(one class))] - [p(second class) * log(p(second class))]
• Information Gain is collection of all entropy from root node to leaf node
• Gini Index : Calculate purity of split also
  • 1- [P^2]
• Gini Impurity ranges from 0 - 0.5, Entropy ranges from 0 - 1

04 Decision Tree Classification (Theory)

• Decision tree used for Classification Problem

05 Decision Tree Classification (Python Code)

• Step by Step Python code to visualize Regression Tree

06 Decision Tree Classification (Python Code)

• Step by Step Python code to visualize Classification Tree

07 Random Forest and Ensemble Technique (Theory)

• Bagging Technique
• Collection of Decision Tree
• Variable Importance measure

08 Voting Classifier (Theory)

• Hard Voting : Predict output class with highest majority of Voting
• Soft Voting : Predict output class with average of probability given to the class

09 Random Forest (Python Code)

• Step by Step Python code for Random Forest Tree

10 Grid Search (Python Code)

• Hyperparameter Tuning
• Cross Validation
• Grid Search with Cross Validation

11 Interview Question Decision Tree & Random Forest