Filling_Categories_Proportionally.py

def fill_proportionally(col, dataset):
    import random
    random.seed(0)
    
    # getting all unique values (without nan)
    values = dataset[col].dropna().unique()
    
    # getting weights for probability weighting
    weights = dataset[col].value_counts().values / dataset[col].value_counts().values.sum()
    print('Before Imputation Probablity Weights\n',weights)
    # filling
    dataset[col] = dataset[col].apply(lambda x: random.choices(values, weights=weights)[0] if pd.isnull(x) else x)
    
import pandas as pd
df = pd.read_csv('https://raw.githubusercontent.com/Abhayparashar31/datasets/master/titanic.csv')

### Imputing Missing Categories 
fill_proportionally('Embarked', df)