Feature Encoding Techniques – Machine Learning

As we all know that better encoding leads to a better model and most of the algorithms cannot handle the categorical variables unless they are converted into a numerical value.

Categorical features are generally divided into 3 types:

  1. Binary: Either/or
    Examples:

    • Yes, No
    • True, False
  2. Ordinal: Specific ordered Groups.
    Examples:

    • low, medium, high
    • cold, hot, lava Hot
  3. Nominal: Unordered Groups.
    Examples



    • cat, dog, tiger
    • pizza, burger, coke
Dataset: To download the file click on the link.
encoding dataset

Code:

filter_none

edit
close

play_arrow

link
brightness_4
code

# data preprocessing
import pandas as pd  
# for linear calculations
import numpy as np    
# Plotting Graphs
import seaborn as sns 
df = pd.read_csv("Encoding Data.csv")
# displaying top 10 results
df.head(10)   

chevron_right


Output:


Dataset

Lets’ examine the columns of the dataset with different types of encoding techniques.
Code: Mapping binary features present in the dataset.

filter_none

edit
close

play_arrow

link
brightness_4
code

# you can always use simple mapping on binary features.
df['bin_1'] = df['bin_1'].apply(lambda x: 1 if x =='T' else (0 if x =='F' else None)) 
df['bin_2'] = df['bin_2'].apply(lambda x: 1 if x =='Y' else (0 if x =='N' else None))
sns.countplot(df['bin_1'])
sns.countplot(df['bin_2'])

chevron_right


Output:

Bin_1 after appying mapping

bin_2 after appying mapping

Label Encoding: Label encoding algorithm is quite simple and it considers an order for encoding, Hence can be used for encoding ordinal data.
Code:

filter_none

edit
close

play_arrow

link
brightness_4
code

# labelEncoder present in scikitlearn library
from sklearn.preprocessing import LabelEncoder  
le = LabelEncoder()
df['ord_2'] = le.fit_transform(df['ord_2'])
sns.set(style ="darkgrid")
sns.countplot(df['ord_2'])

chevron_right


Output:

Plot of ord_2 after label encoding

One-Hot Encoding: To overcome the Disadvantage of Label Encoding as it considers some hierarchy in the columns which can be misleading to nominal features present in the data. we can use One-Hot Encoding strategy.
One-hot encoding is processed in 2 steps:



  1. Spliting of categories to different columns.
  2. Put ‘0 for others and ‘1’ as an indicator for the appropriate column.

Code: One-Hot encoding with Sklearn libray

filter_none

edit
close

play_arrow

link
brightness_4
code

from sklearn.preprocessing import OneHotEncoder
enc = OneHotEncoder()
# tranforming the column after fitting
enc = enc.fit_transform(df[['nom_0']]).toarray()
# converting arrays to a dataframe
encoded_colm = pd.DataFrame(enc)
# concating dataframes 
df = pd.concat([df, encoded_colm], axis = 1
# removing the encoded column.
df = df.drop(['nom_0'], axis = 1
df.head(10)

chevron_right


Output:

Output

Code: One-Hot encoding with pandas

filter_none

edit
close

play_arrow

link
brightness_4
code

df = pd.get_dummies(df, prefix = ['nom_0'], columns = ['nom_0'])
df.head(10)

chevron_right


Output:

output


This method is more preferable since it gives good labels.
Note: One-hot encoding approach eliminates the order but it causes the number of columns to expand vastly. So for columns with more unique values try using other techniques.

Frequency Encoding: We can also encode considering the frequency distribution. This method can be effective at times for nominal features.

Code:

filter_none

edit
close

play_arrow

link
brightness_4
code

# grouping by frequency
fq = df.groupby('nom_0').size()/len(df)   
# mapping values to dataframe
df.loc[:, "{}_freq_encode".format('nom_0')] = df['nom_0'].map(fq)  
# drop original column.
df = df.drop(['nom_0'], axis = 1
fq.plot.bar(stacked = True)  
df.head(10)

chevron_right


Output:

Frequency distribution (fq)


Output


Ordinal Encoding: We can use Ordinal Encoding provided in Scikit learn class to encode Ordinal features. It ensures that ordinal nature of the variables is sustained.
Code: Using Scikit learn.

filter_none

edit
close

play_arrow

link
brightness_4
code

from sklearn.preprocessing import OrdinalEncoder
ord1 = OrdinalEncoder()
# fitting encoder
ord1.fit([df['ord_2']])
# tranforming the column after fitting
df["ord_2"]= ord1.fit_transform(df[["ord_2"]]) 
df.head(10)

chevron_right


Output:

Output

Code: Manually assigning ranking by using dictionary

filter_none

edit
close

play_arrow

link
brightness_4
code

# creating a dictionary
temp_dict ={'Cold':1, 'Warm':2, 'Hot':3
# mapping values in column from dictionary
df['Ord_2_encod']= df.ord_2.map(temp_dict)
df = df.drop(['ord_2'], axis = 1)
<strong>Output: </strong>

chevron_right


Output

Binary Encoding:
Initially categories are encoded as Integer and then converted into binary code, then the digits from that binary string are placed into separate columns.
for eg: for 7 : 1 1 1
This method is quite preferable when there are more number of categories. Imagine if you have 100 different categories. One hot encoding will create 100 different columns, But binary encoding only need 7 columns.
Code:

filter_none

edit
close

play_arrow

link
brightness_4
code

from category_encoders import BinaryEncoder 
encoder = BinaryEncoder(cols =['ord_2']) 
# tranforming the column after fitting
newdata = encoder.fit_transform(df['ord_2'])
# concating dataframe
df = pd.concat([df, newdata], axis = 1
# dropping old column 
df = df.drop(['ord_2'], axis = 1)
df.head(10)

chevron_right


Output:

Output

HashEncoding: Hashing is the process of converting of a string of characters into a unique hash value with applying a hash function. This process is quite useful as it can deal with a higher number of categorical data and its low memory usage.
Article regarding hashing
Code:

filter_none

edit
close

play_arrow

link
brightness_4
code

from sklearn.feature_extraction import FeatureHasher
# n_features contains the number of bits you want in your hash value.
h = FeatureHasher(n_features = 3, input_type ='string'
# tranforming the column after fitting
hashed_Feature = h.fit_transform(df['nom_0'])
hashed_Feature = hashed_Feature.toarray()
df = pd.concat([df, pd.DataFrame(hashed_Feature)], axis = 1)
df.head(10)

chevron_right


Output:

Output


You can further drop the converted feature from your Dataframe.
Mean/Target Encoding: Target encoding is good because it picks up values that can explain the target. It is used by most kagglers in their competitions. The basic idea to replace a categorical value with the mean of the target variable.
Code:

filter_none

edit
close

play_arrow

link
brightness_4
code

# inserting Target column in the dataset since it needs a target
df.insert(5, "Target", [0, 1, 1, 0, 0, 1, 0, 0, 0, 1], True
# importing TargetEncoder
from category_encoders import TargetEncoder
Targetenc = TargetEncoder()
# tranforming the column after fitting
values = Targetenc.fit_transform(X = df.nom_0, y = df.Target)
# concating values with dataframe
df = pd.concat([df, values], axis = 1)
df.head(10)

chevron_right


You can further drop the converted feature from your Dataframe.
Output:

output




My Personal Notes arrow_drop_up

Check out this Author's contributed articles.

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.


Article Tags :
Practice Tags :


8


Please write to us at contribute@geeksforgeeks.org to report any issue with the above content.