#!/usr/bin/env python
# coding: utf-8

# [![Open in Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/justmarkham/scikit-learn-tips/master?filepath=notebooks%2F43_ordinal_encoding_for_trees.ipynb)
# 
# [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/justmarkham/scikit-learn-tips/blob/master/notebooks/43_ordinal_encoding_for_trees.ipynb)
# 
# # 🤖⚡ scikit-learn tip #43 ([video](https://www.youtube.com/watch?v=n_x40CdPZss&list=PL5-da3qGB5ID7YYAqireYEew2mWVvgmj6&index=43))
# 
# With a tree-based model, try OrdinalEncoder instead of OneHotEncoder even for nominal (unordered) features.
# 
# Accuracy will often be similar, but OrdinalEncoder will be much faster!
# 
# See example 👇

# In[1]:


import pandas as pd
df = pd.read_csv('https://www.openml.org/data/get_csv/1595261/adult-census.csv')


# In[2]:


from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import cross_val_score


# In[3]:


categorical_cols = ['workclass', 'education', 'marital-status',
                    'occupation', 'relationship', 'race', 'sex']


# In[4]:


X = df[categorical_cols]
y = df['class']


# In[5]:


# OneHotEncoder creates 60 columns
ohe = OneHotEncoder()
ohe.fit_transform(X).shape


# In[6]:


# OrdinalEncoder creates 7 columns
oe = OrdinalEncoder()
oe.fit_transform(X).shape


# In[7]:


# Random Forests is a tree-based model
rf = RandomForestClassifier(random_state=1, n_jobs=-1)


# In[8]:


# Pipeline containing OneHotEncoder
ohe_pipe = make_pipeline(ohe, rf)
get_ipython().run_line_magic('time', 'cross_val_score(ohe_pipe, X, y).mean()')


# In[9]:


# Pipeline containing OrdinalEncoder
oe_pipe = make_pipeline(oe, rf)
get_ipython().run_line_magic('time', 'cross_val_score(oe_pipe, X, y).mean()')


# ### Want more tips? [View all tips on GitHub](https://github.com/justmarkham/scikit-learn-tips) or [Sign up to receive 2 tips by email every week](https://scikit-learn.tips) 💌
# 
# © 2020 [Data School](https://www.dataschool.io). All rights reserved.