README.md

Data Filling and Cleaning Techniques

1. Dropping Row/Column -> Having more than 15% or 20% missing data
   
2. Measure Central Tendency -> Mean/Median
   
3. Measure Central Tendency for Each Class -> Mean & Median
   
4. Measure Central Tendency for Each Class -> Mode
   
5. SimpleImputer -> Scikit Learn Module
   
6. ColumnTransformer & Pipeline -> Scikit Learn Module
   
7. KNN imputer (resulted in more accuracy than simple imputer) -> Scikit Learn Module
   
8. One hot Encoding (Especially for categorical columns)
   
9. Random sample Imputation

Note : You can execute the KNN imputer and random sample imputation notebooks by using the train.csv files