Dimensionality-Reduction-in-Python

• Problem of Multicollinearity, lead to Overfitting
• Dimesionality reduction reduces dimension and not loose any information

01 Curse of Dimensionality (Theory)

• Risk of Overfitting

02 Correlation (Theory)

• Strength and Relationship between two variables
  1. Spearman Correlation (Assume linear relation between variable)
  2. Pearson Correlation (Not assumne any kind of relationship)

03 Collinearity & Multi Collinearity (Theory)

• Definition, Why it is a problem ?
• Technique to check collinearity : VIF

04 Variation Inflation Factor (VIF) (Theory)

• Deteces Multicollinearity in the dataset

05 Dimensionality Reduction Overview (Theory)

• Problem of Multicollinearity, lead to Overfitting
• Dimesionality reduction reduces dimension and not loose any information
• Definition, Type of Dimensionality Reduction Technique
  1. PCA
  2. Factor Analysis
  3. LDA
  4. T-sne

06 LDA (Theory)

• Linear Discriminant Analysis
• Used for Supervised Classification problem

07 LDA (Python Code)

• Steps by steps to solve LDA

08 PCA (Theory)

• Principal Component Analysis
• Used for Unsupervised Learning problem

09 PCA Example (Theory)

• Example of PCA in depth

10 PCA Practical Tips (Theory)

• Different Practical Tips to solve before PCA
  1. Variable are on Same Scale
  2. How many principal component should be expect

11 Eigen Value and Eigen Vector (Theory)

• Definition and Example

12 PCA (Python Code)

• Steps by steps to solve PCA

13 Dimensionality Reduction Assumptions (Theory)

• Assumption of Each Dimensionality Reduction Algorithim

14 Factor Analysis (Theory)

• Definition, Steps and Example

15 Factor Analysis (Python Code)

• Steps by steps to solve Factor Analysis

16 Interview Question Dimensionality Reduction