Feature Engineering python- In this video we will be feature encoding techniques and How to do frequency encoding also known as count or frequency encoding. we will discuss it with examples using python. Even if you use any other language such as Rstudio or scala , this video will be extremely helpful.
I this technique we simply replace our categories by the count or occurrence of that particular category.
I would encourage you to checkout my complete feature engineering playlist which will help you to learn and understand other feature engineering techniques also.
Feature Engineering playlist : https://youtube.com/playlist?list=PLyB8AGpv661FvHtb9jbNYSsnSANV4bkFG
pandas playlist : https://youtube.com/playlist?list=PLyB8AGpv661FAEgt1cNQKq_KeVpfFK21T
Source code for this video:
----------------------------------------------------------------------------
#!/usr/bin/env python
# coding: utf-8
import pandas as pd
from sklearn.model_selection import train_test_split
data = pd.read_csv('houseprice.csv', usecols=['MSZoning','Street','LotShape','Utilities','LandSlope','SalePrice'])
data.head()
data.isnull().mean()
X_train,X_test,y_train,y_test = train_test_split(data[['MSZoning','Street','LotShape','Utilities','LandSlope']],
data['SalePrice'], test_size =.3, random_state =111)
X_train.head()
X_train.shape
X_test.shape
y_train.shape
# In[32]:
y_train.head()
# In[33]:
Ms = X_train['MSZoning'].value_counts().to_dict()
Ms
cat_vars = ['MSZoning','Street','LotShape','Utilities','LandSlope']
encoder_dictionary ={}
for var in cat_vars:
encoder_dictionary[var] = (X_train[var].value_counts()/len(X_train)).to_dict()
encoder_dictionary
for var in cat_vars:
X_train[var] = X_train[var].map(encoder_dictionary[var])
X_train.head()
---------- End Source Code--------------------------------------------------
Related Tags:
How to deal with categorical data
Categorical encoding python
Machine learning tutorial
How to encode categorical variables
Count Encoding
One hot encoding
Feature engineering
Data Analytics